From 51c2ec0ad41722f34d6cb8a5d111ceac021c4464 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 22 Apr 2026 13:25:16 +0300 Subject: [PATCH 01/35] feat(hami): add HAMi GPU virtualization system chart Add HAMi v2.8.1 (CNCF Sandbox) as a new system package for fractional GPU sharing in tenant Kubernetes clusters. The chart enables workloads to request specific amounts of GPU memory and compute cores instead of claiming entire GPUs. Vendored upstream chart includes device plugin, scheduler extender, mutating webhook, and DRA subchart. Wrapper values configure nvidia RuntimeClass and clear hardcoded node config from upstream defaults. Assisted-By: Claude Signed-off-by: Arsolitt --- packages/system/hami/Chart.yaml | 3 + packages/system/hami/Makefile | 11 + packages/system/hami/charts/hami/Chart.lock | 6 + packages/system/hami/charts/hami/Chart.yaml | 22 + packages/system/hami/charts/hami/README.md | 237 +++++++++ .../charts/hami/charts/hami-dra/.helmignore | 24 + .../charts/hami/charts/hami-dra/Chart.yaml | 18 + .../charts/hami-dra/templates/_commons.tpl | 84 ++++ .../charts/hami-dra/templates/_helpers.tpl | 73 +++ .../hami-dra-driver/deviceclass.yaml | 11 + .../nvidia-dra-driver-daemonset.yaml | 145 ++++++ .../templates/hami-dra-driver/rbac.yaml | 110 ++++ .../monitor/monitor-clusterrole.yaml | 11 + .../monitor/monitor-clusterrolebinding.yaml | 15 + .../templates/monitor/monitor-deployment.yaml | 62 +++ .../templates/monitor/monitor-service.yaml | 26 + .../monitor/monitor-serviceaccount.yaml | 8 + .../templates/webhook/cert-manager.yaml | 29 ++ .../templates/webhook/cert-secret.yaml | 13 + .../templates/webhook/device-config.yaml | 394 +++++++++++++++ .../webhook/mutatingwebhookconfiguration.yaml | 28 ++ .../validatingwebhookconfiguration.yaml | 29 ++ .../webhook/webhook-clusterrole.yaml | 14 + .../webhook/webhook-clusterrolebinding.yaml | 12 + .../templates/webhook/webhook-deployment.yaml | 59 +++ .../templates/webhook/webhook-service.yaml | 15 + .../webhook/webhook-serviceaccount.yaml | 5 + .../charts/hami/charts/hami-dra/values.yaml | 166 ++++++ .../hami/charts/hami/templates/NOTES.txt | 3 + .../hami/charts/hami/templates/_commons.tpl | 49 ++ .../hami/charts/hami/templates/_helpers.tpl | 163 ++++++ .../templates/device-plugin/configmap.yaml | 13 + .../device-plugin/daemonsetmock.yaml | 55 ++ .../device-plugin/daemonsetnvidia.yaml | 262 ++++++++++ .../templates/device-plugin/monitorrole.yaml | 29 ++ .../device-plugin/monitorrolebinding.yaml | 17 + .../device-plugin/monitorservice.yaml | 29 ++ .../device-plugin/monitorserviceaccount.yaml | 10 + .../device-plugin/runtime-class.yaml | 11 + .../hami/templates/scheduler/certmanager.yaml | 31 ++ .../hami/templates/scheduler/clusterrole.yaml | 36 ++ .../scheduler/clusterrolebinding.yaml | 49 ++ .../hami/templates/scheduler/configmap.yaml | 142 ++++++ .../templates/scheduler/configmapnew.yaml | 102 ++++ .../hami/templates/scheduler/deployment.yaml | 227 +++++++++ .../templates/scheduler/device-configmap.yaml | 410 +++++++++++++++ .../scheduler/job-patch/clusterrole.yaml | 30 ++ .../job-patch/clusterrolebinding.yaml | 22 + .../scheduler/job-patch/job-createSecret.yaml | 70 +++ .../scheduler/job-patch/job-patchWebhook.yaml | 65 +++ .../templates/scheduler/job-patch/psp.yaml | 40 ++ .../templates/scheduler/job-patch/role.yaml | 23 + .../scheduler/job-patch/rolebinding.yaml | 23 + .../scheduler/job-patch/serviceaccount.yaml | 15 + .../charts/hami/templates/scheduler/role.yaml | 14 + .../hami/templates/scheduler/rolebinding.yaml | 33 ++ .../hami/templates/scheduler/service.yaml | 36 ++ .../templates/scheduler/serviceaccount.yaml | 18 + .../hami/templates/scheduler/webhook.yaml | 57 +++ packages/system/hami/charts/hami/values.yaml | 476 ++++++++++++++++++ packages/system/hami/values.yaml | 8 + 61 files changed, 4198 insertions(+) create mode 100644 packages/system/hami/Chart.yaml create mode 100644 packages/system/hami/Makefile create mode 100644 packages/system/hami/charts/hami/Chart.lock create mode 100644 packages/system/hami/charts/hami/Chart.yaml create mode 100644 packages/system/hami/charts/hami/README.md create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/.helmignore create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml create mode 100644 packages/system/hami/charts/hami/charts/hami-dra/values.yaml create mode 100644 packages/system/hami/charts/hami/templates/NOTES.txt create mode 100644 packages/system/hami/charts/hami/templates/_commons.tpl create mode 100644 packages/system/hami/charts/hami/templates/_helpers.tpl create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/daemonsetmock.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml create mode 100644 packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/configmap.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/deployment.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/role.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/service.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml create mode 100644 packages/system/hami/charts/hami/templates/scheduler/webhook.yaml create mode 100644 packages/system/hami/charts/hami/values.yaml create mode 100644 packages/system/hami/values.yaml diff --git a/packages/system/hami/Chart.yaml b/packages/system/hami/Chart.yaml new file mode 100644 index 00000000..3fcf4c5d --- /dev/null +++ b/packages/system/hami/Chart.yaml @@ -0,0 +1,3 @@ +apiVersion: v2 +name: cozy-hami +version: 0.0.0 # Placeholder, the actual version will be automatically set during the build process diff --git a/packages/system/hami/Makefile b/packages/system/hami/Makefile new file mode 100644 index 00000000..b7a169c2 --- /dev/null +++ b/packages/system/hami/Makefile @@ -0,0 +1,11 @@ +export NAME=hami +export NAMESPACE=cozy-$(NAME) + +include ../../../hack/common-envs.mk +include ../../../hack/package.mk + +update: + rm -rf charts + helm repo add hami-charts https://project-hami.github.io/HAMi/ + helm repo update hami-charts + helm pull hami-charts/hami --untar --untardir charts diff --git a/packages/system/hami/charts/hami/Chart.lock b/packages/system/hami/charts/hami/Chart.lock new file mode 100644 index 00000000..25856c07 --- /dev/null +++ b/packages/system/hami/charts/hami/Chart.lock @@ -0,0 +1,6 @@ +dependencies: +- name: hami-dra + repository: https://project-hami.github.io/HAMi-DRA/ + version: 0.1.0 +digest: sha256:374551539570bcee82c1c4dea93eac59e6f410b6d5967d188efd630e203d43bb +generated: "2026-04-17T04:06:47.689117678Z" diff --git a/packages/system/hami/charts/hami/Chart.yaml b/packages/system/hami/charts/hami/Chart.yaml new file mode 100644 index 00000000..aba7e95c --- /dev/null +++ b/packages/system/hami/charts/hami/Chart.yaml @@ -0,0 +1,22 @@ +apiVersion: v2 +appVersion: 2.8.1 +dependencies: +- condition: dra.enabled + name: hami-dra + repository: https://project-hami.github.io/HAMi-DRA/ + version: 0.1.0 +description: Heterogeneous AI Computing Virtualization Middleware +keywords: +- vgpu +- gpu +kubeVersion: '>= 1.18.0-0' +maintainers: +- email: archlitchi@gmail.com + name: limengxuan +- email: xiaozhang0210@hotmail.com + name: zhangxiao +name: hami +sources: +- https://github.com/Project-HAMi/HAMi +type: application +version: 2.8.1 diff --git a/packages/system/hami/charts/hami/README.md b/packages/system/hami/charts/hami/README.md new file mode 100644 index 00000000..e8217290 --- /dev/null +++ b/packages/system/hami/charts/hami/README.md @@ -0,0 +1,237 @@ +# HAMi Helm Chart Values Documentation + +This document provides detailed descriptions of all configurable values parameters for the HAMi Helm Chart. + +## Global Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `global.imageRegistry` | Global Docker image registry | `""` | +| `global.imagePullSecrets` | Global Docker image pull secrets | `[]` | +| `global.imageTag` | Image tag | `"v2.8.1"` | +| `global.gpuHookPath` | GPU Hook path | `/usr/local` | +| `global.labels` | Global labels | `{}` | +| `global.annotations` | Global annotations | `{}` | +| `global.managedNodeSelectorEnable` | Whether to enable managed node selector | `false` | +| `global.managedNodeSelector.usage` | Managed node selector usage | `"gpu"` | +| `nameOverride` | Name override | `""` | +| `fullnameOverride` | Full name override | `""` | +| `namespaceOverride` | Namespace override | `""` | + +## Resource Name Configuration + +### NVIDIA GPU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `resourceName` | GPU resource name | `"nvidia.com/gpu"` | +| `resourceMem` | GPU memory resource name | `"nvidia.com/gpumem"` | +| `resourceMemPercentage` | GPU memory percentage resource name | `"nvidia.com/gpumem-percentage"` | +| `resourceCores` | GPU core resource name | `"nvidia.com/gpucores"` | +| `resourcePriority` | GPU priority resource name | `"nvidia.com/priority"` | + +### Cambricon MLU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `mluResourceName` | MLU resource name | `"cambricon.com/vmlu"` | +| `mluResourceMem` | MLU memory resource name | `"cambricon.com/mlu.smlu.vmemory"` | +| `mluResourceCores` | MLU core resource name | `"cambricon.com/mlu.smlu.vcore"` | + +### Hygon DCU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `dcuResourceName` | DCU resource name | `"hygon.com/dcunum"` | +| `dcuResourceMem` | DCU memory resource name | `"hygon.com/dcumem"` | +| `dcuResourceCores` | DCU core resource name | `"hygon.com/dcucores"` | + +### Metax GPU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `metaxResourceName` | GPU resource name | `"metax-tech.com/sgpu"` | +| `metaxResourceCore` | GPU core resource name | `"metax-tech.com/vcore"` | +| `metaxResourceMem` | GPU memory resource name | `"metax-tech.com/vmemory"` | +| `metaxsGPUTopologyAware` | GPU topology awareness | `"false"` | + +### Enflame GCU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `enflameResourceNameVGCU` | vGCU resource name | `"enflame.com/vgcu"` | +| `enflameResourceNameVGCUPercentage` | vGCU percentage resource name | `"enflame.com/vgcu-percentage"` | + +### Kunlunxin XPU Resources +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `kunlunResourceName` | XPU resource name | `"kunlunxin.com/xpu"` | + +## Scheduler Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `schedulerName` | Scheduler name | `"hami-scheduler"` | +| `scheduler.nodeName` | Define node name, scheduler will schedule to this node | `""` | +| `scheduler.overwriteEnv` | Whether to overwrite environment variables | `"false"` | +| `scheduler.defaultSchedulerPolicy.nodeSchedulerPolicy` | Node scheduler policy | `binpack` | +| `scheduler.defaultSchedulerPolicy.gpuSchedulerPolicy` | GPU scheduler policy | `spread` | +| `scheduler.metricsBindAddress` | Metrics bind address | `":9395"` | +| `scheduler.forceOverwriteDefaultScheduler` | Whether to force overwrite default scheduler | `true` | +| `scheduler.livenessProbe` | Whether to enable liveness probe | `false` | +| `scheduler.leaderElect` | Whether to enable leader election | `true` | +| `scheduler.replicas` | Number of replicas | `1` | + +### Kube Scheduler Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `scheduler.kubeScheduler.enabled` | Whether to run kube-scheduler container in scheduler pod | `true` | +| `scheduler.kubeScheduler.image.registry` | Kube scheduler image registry | `"registry.cn-hangzhou.aliyuncs.com"` | +| `scheduler.kubeScheduler.image.repository` | Kube scheduler image repository | `"google_containers/kube-scheduler"` | +| `scheduler.kubeScheduler.image.tag` | Kube scheduler image tag | `""` | +| `scheduler.kubeScheduler.image.pullPolicy` | Kube scheduler image pull policy | `IfNotPresent` | +| `scheduler.kubeScheduler.image.pullSecrets` | Kube scheduler image pull secrets | `[]` | +| `scheduler.kubeScheduler.extraNewArgs` | Extra new arguments | `["--config=/config/config.yaml", "-v=4"]` | +| `scheduler.kubeScheduler.extraArgs` | Extra arguments | `["--policy-config-file=/config/config.json", "-v=4"]` | + +### Extender Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `scheduler.extender.image.registry` | Scheduler extender image registry | `"docker.io"` | +| `scheduler.extender.image.repository` | Scheduler extender image repository | `"projecthami/hami"` | +| `scheduler.extender.image.tag` | Scheduler extender image tag | `""` | +| `scheduler.extender.image.pullPolicy` | Scheduler extender image pull policy | `IfNotPresent` | +| `scheduler.extender.image.pullSecrets` | Scheduler extender image pull secrets | `[]` | +| `scheduler.extender.extraArgs` | Scheduler extender extra arguments | `["--debug", "-v=4"]` | + +### Admission Webhook Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `scheduler.admissionWebhook.enabled` | Whether to enable admission webhook | `true` | +| `scheduler.admissionWebhook.customURL.enabled` | Whether to enable custom URL | `false` | +| `scheduler.admissionWebhook.customURL.host` | Custom URL host | `127.0.0.1` | +| `scheduler.admissionWebhook.customURL.port` | Custom URL port | `31998` | +| `scheduler.admissionWebhook.customURL.path` | Custom URL path | `/webhook` | +| `scheduler.admissionWebhook.reinvocationPolicy` | Reinvocation policy | `Never` | +| `scheduler.admissionWebhook.failurePolicy` | Failure policy | `Ignore` | + +### TLS Certificate Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `scheduler.certManager.enabled` | Whether to use cert-manager to generate self-signed certificates | `false` | +| `scheduler.patch.enabled` | Whether to use kube-webhook-certgen to generate self-signed certificates | `true` | +| `scheduler.patch.image.registry` | Certgen image registry | `"docker.io"` | +| `scheduler.patch.image.repository` | Certgen image repository | `"jettech/kube-webhook-certgen"` | +| `scheduler.patch.image.tag` | Certgen image tag | `"v1.5.2"` | +| `scheduler.patch.image.pullPolicy` | Certgen image pull policy | `IfNotPresent` | +| `scheduler.patch.imageNew.registry` | New certgen image registry | `"docker.io"` | +| `scheduler.patch.imageNew.repository` | New certgen image repository | `"liangjw/kube-webhook-certgen"` | +| `scheduler.patch.imageNew.tag` | New certgen image tag | `"v1.1.1"` | + +### Scheduler Service Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `scheduler.service.type` | Service type | `NodePort` | +| `scheduler.service.httpPort` | HTTP port | `443` | +| `scheduler.service.schedulerPort` | Scheduler NodePort | `31998` | +| `scheduler.service.monitorPort` | Monitor port | `31993` | +| `scheduler.service.monitorTargetPort` | Monitor target port | `9395` | + +## Device Plugin Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devicePlugin.image.registry` | Device plugin image registry | `"docker.io"` | +| `devicePlugin.image.repository` | Device plugin image repository | `"projecthami/hami"` | +| `devicePlugin.image.tag` | Device plugin image tag | `""` | +| `devicePlugin.image.pullPolicy` | Device plugin image pull policy | `IfNotPresent` | +| `devicePlugin.image.pullSecrets` | Device plugin image pull secrets | `[]` | + +### Monitor Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devicePlugin.monitor.image.registry` | Monitor image registry | `"docker.io"` | +| `devicePlugin.monitor.image.repository` | Monitor image repository | `"projecthami/hami"` | +| `devicePlugin.monitor.image.tag` | Monitor image tag | `""` | +| `devicePlugin.monitor.image.pullPolicy` | Monitor image pull policy | `IfNotPresent` | +| `devicePlugin.monitor.image.pullSecrets` | Monitor image pull secrets | `[]` | +| `devicePlugin.monitor.ctrPath` | Container path | `/usr/local/vgpu/containers` | +| `devicePlugin.monitor.extraArgs` | Monitor extra arguments | `["-v=4"]` | +| `devicePlugin.monitor.extraEnvs` | Monitor extra environments | `{}` | + +### Device Plugin Other Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devicePlugin.deviceSplitCount` | Integer type, default value: 10. Maximum number of tasks assigned to a single GPU device | `10` | +| `devicePlugin.deviceMemoryScaling` | Device memory scaling ratio | `1` | +| `devicePlugin.deviceCoreScaling` | Device core scaling ratio | `1` | +| `devicePlugin.runtimeClassName` | Runtime class name | `""` | +| `devicePlugin.createRuntimeClass` | Whether to create runtime class | `false` | +| `devicePlugin.migStrategy` | String type, "none" means ignore MIG functionality, "mixed" means allocate MIG devices through independent resources | `"none"` | +| `devicePlugin.disablecorelimit` | String type, "true" means disable core limit, "false" means enable core limit | `"false"` | +| `devicePlugin.passDeviceSpecsEnabled` | Whether to enable passing device specs | `false` | +| `devicePlugin.extraArgs` | Device plugin extra arguments | `["-v=4"]` | +| `devicePlugin.nodeConfiguration.config` | Node configuration for device plugin by json | An example of default configuration. | +| `devicePlugin.nodeConfiguration.externalConfigName` | Node configuration for device plugin by external congimap | `""` | +| `devicePlugin.extraEnvs` | Device plugin extra environments | `{}` | + +### Device Plugin Service Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devicePlugin.service.type` | Service type | `NodePort` | +| `devicePlugin.service.httpPort` | HTTP port | `31992` | + +### Device Plugin Deployment Configuration + +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devicePlugin.pluginPath` | Plugin path | `/var/lib/kubelet/device-plugins` | +| `devicePlugin.libPath` | Library path | `/usr/local/vgpu` | +| `devicePlugin.nvidiaNodeSelector` | NVIDIA node selector | `{"gpu": "on"}` | +| `devicePlugin.updateStrategy.type` | Update strategy type | `RollingUpdate` | +| `devicePlugin.updateStrategy.rollingUpdate.maxUnavailable` | Maximum unavailable count | `1` | + +## Device Configuration + +### AWS Neuron +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.awsneuron.customresources` | Custom resources | `["aws.amazon.com/neuron", "aws.amazon.com/neuroncore"]` | + +### Kunlunxin +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.kunlun.enabled` | Whether to enable | `true` | +| `devices.kunlun.customresources` | Custom resources | `["kunlunxin.com/xpu"]` | + +### Mthreads +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.mthreads.enabled` | Whether to enable | `true` | +| `devices.mthreads.customresources` | Custom resources | `["mthreads.com/vgpu"]` | + +### NVIDIA +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.nvidia.gpuCorePolicy` | GPU core policy | `default` | +| `devices.nvidia.libCudaLogLevel` | CUDA library log level | `1` | + +### Huawei Ascend +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.ascend.enabled` | Whether to enable | `false` | +| `devices.ascend.image` | Image | `""` | +| `devices.ascend.imagePullPolicy` | Image pull policy | `IfNotPresent` | +| `devices.ascend.extraArgs` | Extra arguments | `[]` | +| `devices.ascend.nodeSelector` | Node selector | `{"ascend": "on"}` | +| `devices.ascend.tolerations` | Tolerations | `[]` | +| `devices.ascend.customresources` | Custom resources | `["huawei.com/Ascend910A", "huawei.com/Ascend910A-memory", ...]` | + +### Iluvatar +| Parameter | Description | Default Value | +|-----------|-------------|---------------| +| `devices.iluvatar.enabled` | Whether to enable | `false` | +| `devices.iluvatar.customresources` | Custom resources | `["iluvatar.ai/BI-V150-vgpu", "iluvatar.ai/BI-V150.vMem","iluvatar.ai/BI-V150.vCore", ...]` | diff --git a/packages/system/hami/charts/hami/charts/hami-dra/.helmignore b/packages/system/hami/charts/hami/charts/hami-dra/.helmignore new file mode 100644 index 00000000..898df488 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/.helmignore @@ -0,0 +1,24 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml b/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml new file mode 100644 index 00000000..d01f678f --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml @@ -0,0 +1,18 @@ +apiVersion: v2 +appVersion: 0.1.0 +description: A Helm chart for HAMi DRA +home: https://github.com/Project-HAMi/HAMi-DRA +keywords: +- webhook +- kubernetes +- admission-controller +- hami +- dra +maintainers: +- name: hami-dra + url: https://github.com/Project-HAMi/HAMi-DRA +name: hami-dra +sources: +- https://github.com/Project-HAMi/HAMi-DRA +type: application +version: 0.1.0 diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl b/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl new file mode 100644 index 00000000..02fbed20 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl @@ -0,0 +1,84 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" $) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $tag := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if .tag }} + {{- if .tag.imageTag }} + {{- $tag = .tag.imageTag -}} + {{- end -}} +{{- end -}} +{{- if $registryName }} +{{- printf "%s/%s:%s" $registryName $repositoryName $tag -}} +{{- else -}} +{{- printf "%s:%s" $repositoryName $tag -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} + +{{/* +Renders a value that contains template. +Usage: +{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} +*/}} +{{- define "common.tplvalues.render" -}} + {{- if typeIs "string" .value }} + {{- tpl .value .context }} + {{- else }} + {{- tpl (.value | toYaml) .context }} + {{- end }} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "common.names.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl b/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl new file mode 100644 index 00000000..99beec77 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl @@ -0,0 +1,73 @@ +{{- define "hami.dra.webhook.fullname" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) "webhook" | trunc 63 | trimSuffix "-" -}} +{{- end }} + +{{- define "hami.dra.webhook.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.webhook.image "global" .Values.global) }} +{{- end -}} + +{{- define "hami.dra.webhook.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.webhook.image) "global" .Values.global) }} +{{- end -}} + +{{- define "hami.dra.driver.nvidia.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.drivers.nvidia.image "global" .Values.global) }} +{{- end -}} + +{{- define "hami.dra.driver.nvidia.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.drivers.nvidia.image) "global" .Values.global) }} +{{- end -}} + +{{/* +Common labels +*/}} +{{- define "hami-dra-webhook.labels" -}} +helm.sh/chart: {{ .Chart.Name }} +{{ include "hami-dra-webhook.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "hami-dra-webhook.selectorLabels" -}} +app.kubernetes.io/name: {{ .Release.Name }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/component: webhook +{{- end }} + +{{- define "hami.dra.monitor.fullname" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) "monitor" | trunc 63 | trimSuffix "-" -}} +{{- end }} + +{{- define "hami.dra.monitor.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.monitor.image "global" .Values.global) }} +{{- end -}} + +{{- define "hami.dra.monitor.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.monitor.image) "global" .Values.global) }} +{{- end -}} + +{{/* +Common labels for monitor +*/}} +{{- define "hami-dra-monitor.labels" -}} +helm.sh/chart: {{ .Chart.Name }} +{{ include "hami-dra-monitor.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels for monitor +*/}} +{{- define "hami-dra-monitor.selectorLabels" -}} +app.kubernetes.io/name: {{ .Release.Name }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/component: monitor +{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml new file mode 100644 index 00000000..bcb6d2c5 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml @@ -0,0 +1,11 @@ +{{- if .Values.drivers.nvidia.enabled }} +apiVersion: resource.k8s.io/v1 +kind: DeviceClass +metadata: + name: hami-core-gpu.project-hami.io +spec: + selectors: + - cel: + expression: |- + device.driver == "hami-core-gpu.project-hami.io" && device.attributes["hami-core-gpu.project-hami.io"].type == "hami-gpu" +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml new file mode 100644 index 00000000..a3fb0d01 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml @@ -0,0 +1,145 @@ +{{- if .Values.drivers.nvidia.enabled }} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: hami-dra-driver-kubelet-plugin + namespace: {{ .Release.Namespace }} +spec: + revisionHistoryLimit: 10 + selector: + matchLabels: + hami-dra-driver-component: kubelet-plugin + template: + metadata: + labels: + app.kubernetes.io/instance: hami-dra-driver + app.kubernetes.io/name: hami-dra-driver + hami-dra-driver-component: kubelet-plugin + spec: + {{- include "hami.dra.driver.nvidia.imagePullSecrets" . | nindent 6 }} + initContainers: + - name: init-container + image: {{ include "hami.dra.driver.nvidia.image" . }} + securityContext: + privileged: true + command: [bash, /usr/bin/kubelet-plugin-prestart.sh] + env: + - name: NVIDIA_DRIVER_ROOT + value: {{ if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} + - name: NVIDIA_VISIBLE_DEVICES + value: void + - name: KUBELET_REGISTRAR_DIRECTORY_PATH + value: /var/lib/kubelet/plugins_registry + - name: KUBELET_PLUGINS_DIRECTORY_PATH + value: /var/lib/kubelet/plugins + volumeMounts: + - name: driver-root-parent + mountPath: /driver-root-parent + readOnly: true + containers: + - args: + - |- + # Conditionally mask the params file to prevent this container from + # recreating any missing GPU device nodes. This is necessary, for + # example, when running under nvkind to limit the set GPUs governed + # by the plugin even though it has cgroup access to all of them. + if [ "${MASK_NVIDIA_DRIVER_PARAMS}" = "true" ]; then + cp /proc/driver/nvidia/params root/gpu-params + sed -i 's/^ModifyDeviceFiles: 1$/ModifyDeviceFiles: 0/' root/gpu-params + mount --bind root/gpu-params /proc/driver/nvidia/params + fi + hami-kubelet-plugin -v 6 + command: + - bash + - -c + env: + - name: MASK_NVIDIA_DRIVER_PARAMS + value: "" + - name: NVIDIA_DRIVER_ROOT + value: {{ if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} + - name: NVIDIA_VISIBLE_DEVICES + value: void + - name: CDI_ROOT + value: /var/run/cdi + - name: NVIDIA_MIG_CONFIG_DEVICES + value: all + - name: NODE_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: spec.nodeName + - name: NAMESPACE + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: metadata.namespace + - name: KUBELET_REGISTRAR_DIRECTORY_PATH + value: /var/lib/kubelet/plugins_registry + - name: KUBELET_PLUGINS_DIRECTORY_PATH + value: /var/lib/kubelet/plugins + - name: IMAGE_NAME + value: {{ include "hami.dra.driver.nvidia.image" . }} + lifecycle: + postStart: + exec: + command: ["/bin/bash", "-c", "/usr/bin/vgpu-init.sh /usr/local/vgpu/"] + image: {{ include "hami.dra.driver.nvidia.image" . }} + imagePullPolicy: {{ .Values.drivers.nvidia.image.pullPolicy | default "IfNotPresent" }} + name: gpus + securityContext: + privileged: true + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: File + volumeMounts: + - mountPath: /var/lib/kubelet/plugins_registry + name: plugins-registry + - mountPath: /var/lib/kubelet/plugins + mountPropagation: Bidirectional + name: plugins + - mountPath: /var/run/cdi + name: cdi + - mountPath: /driver-root + mountPropagation: HostToContainer + name: driver-root + readOnly: true + - mountPath: /usr/local/vgpu + name: host-vgpu + - mountPath: /tmp + name: host-tmp + dnsPolicy: ClusterFirst + serviceAccount: hami-dra-driver-service-account + serviceAccountName: hami-dra-driver-service-account + volumes: + - hostPath: + path: /var/lib/kubelet/plugins_registry + type: "" + name: plugins-registry + - hostPath: + path: /var/lib/kubelet/plugins + type: "" + name: plugins + - hostPath: + path: /var/run/cdi + type: "" + name: cdi + - hostPath: + path: {{if .Values.drivers.nvidia.containerDriver }}/run/nvidia{{ else }}/{{ end }} + type: DirectoryOrCreate + name: driver-root-parent + - hostPath: + path: {{if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} + type: DirectoryOrCreate + name: driver-root + - hostPath: + path: /dev + type: "" + name: host-dev + - hostPath: + path: /usr/local/vgpu + type: DirectoryOrCreate + name: host-vgpu + - hostPath: + path: /tmp + type: "" + name: host-tmp +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml new file mode 100644 index 00000000..435c37cc --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml @@ -0,0 +1,110 @@ +{{- if .Values.drivers.nvidia.enabled }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: hami-dra-driver-service-account + namespace: {{ .Release.Namespace }} +--- +apiVersion: v1 +items: +- apiVersion: rbac.authorization.k8s.io/v1 + kind: Role + metadata: + name: hami-dra-driver-role + namespace: {{ .Release.Namespace }} + rules: + - apiGroups: + - apps + resources: + - daemonsets + - deployments + verbs: + - get + - list + - watch + - create + - update + - patch + - delete +kind: List +metadata: + resourceVersion: "" +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: hami-dra-driver-role-binding + namespace: {{ .Release.Namespace }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: hami-dra-driver-role +subjects: +- kind: ServiceAccount + name: hami-dra-driver-service-account + namespace: {{ .Release.Namespace }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: hami-dra-driver-clusterrole +rules: +- apiGroups: + - resource.k8s.io + resources: + - resourceclaims + verbs: + - get + - list + - watch +- apiGroups: + - resource.k8s.io + resources: + - resourceclaimtemplates + verbs: + - get + - list + - watch + - create + - update + - delete +- apiGroups: + - resource.k8s.io + resources: + - resourceslices + verbs: + - get + - list + - watch + - create + - update + - delete +- apiGroups: + - resource.k8s.io + resources: + - resourceclaims/status + verbs: + - update +- apiGroups: + - "" + resources: + - nodes + verbs: + - get + - list + - watch + - update +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: hami-dra-driver-clusterrole-binding-hami-dra-driver +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: hami-dra-driver-clusterrole +subjects: +- kind: ServiceAccount + name: hami-dra-driver-service-account + namespace: {{ .Release.Namespace }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml new file mode 100644 index 00000000..45c24863 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml @@ -0,0 +1,11 @@ +{{- if .Values.monitor.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami.dra.monitor.fullname" . }} +rules: +- apiGroups: ["resource.k8s.io"] + resources: ["resourceslices", "resourceclaims"] + verbs: ["get", "list", "watch"] +{{- end }} + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml new file mode 100644 index 00000000..766d3098 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml @@ -0,0 +1,15 @@ +{{- if .Values.monitor.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami.dra.monitor.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami.dra.monitor.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ include "hami.dra.monitor.fullname" . }} + namespace: {{ .Release.Namespace }} +{{- end }} + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml new file mode 100644 index 00000000..b544b376 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml @@ -0,0 +1,62 @@ +{{- if .Values.monitor.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "hami.dra.monitor.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + app.kubernetes.io/name: {{ include "hami.dra.monitor.fullname" . }} + {{- include "hami-dra-monitor.labels" . | nindent 4 }} +spec: + replicas: {{ .Values.monitor.replicas | default 1 }} + selector: + matchLabels: + {{- include "hami-dra-monitor.selectorLabels" . | nindent 6 }} + template: + metadata: + labels: + {{- include "hami-dra-monitor.selectorLabels" . | nindent 8 }} + spec: + {{- include "hami.dra.monitor.imagePullSecrets" . | nindent 6 }} + serviceAccountName: {{ include "hami.dra.monitor.fullname" . }} + containers: + - name: monitor + image: {{ include "hami.dra.monitor.image" . }} + imagePullPolicy: {{ .Values.monitor.image.pullPolicy | default "IfNotPresent" }} + command: + - /bin/monitor + - --v={{ .Values.monitor.logLevel | default 2 }} + - --metrics-bind-address={{ .Values.monitor.metricsBindAddress | default ":8080" }} + - --health-probe-bind-address={{ .Values.monitor.healthProbeBindAddress | default ":8000" }} + - --kube-api-qps={{ .Values.monitor.kubeAPIQPS | default 40.0 }} + - --kube-api-burst={{ .Values.monitor.kubeAPIBurst | default 60 }} + - --collect-interval={{ .Values.monitor.collectInterval | default "30s" }} + ports: + - containerPort: 8080 + name: metrics + protocol: TCP + - containerPort: 8000 + name: health + protocol: TCP + {{- if .Values.monitor.resources }} + resources: + {{- toYaml .Values.monitor.resources | nindent 12 }} + {{- end }} + livenessProbe: + httpGet: + path: /healthz + port: 8000 + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 3 + readinessProbe: + httpGet: + path: /readyz + port: 8000 + initialDelaySeconds: 5 + periodSeconds: 5 + timeoutSeconds: 3 + failureThreshold: 3 +{{- end }} + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml new file mode 100644 index 00000000..d740cc38 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml @@ -0,0 +1,26 @@ +{{- if .Values.monitor.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "hami.dra.monitor.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "hami-dra-monitor.selectorLabels" . | nindent 4 }} +spec: + type: {{ .Values.monitor.service.type | default "ClusterIP" }} + selector: + {{- include "hami-dra-monitor.selectorLabels" . | nindent 4 }} + ports: + - port: 8080 + targetPort: 8080 + name: metrics + protocol: TCP + {{- if and (eq (.Values.monitor.service.type | default "ClusterIP") "NodePort") .Values.monitor.service.nodePort.metrics }} + nodePort: {{ .Values.monitor.service.nodePort.metrics }} + {{- end }} + - port: 8000 + targetPort: 8000 + name: health + protocol: TCP +{{- end }} + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml new file mode 100644 index 00000000..c61ad454 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml @@ -0,0 +1,8 @@ +{{- if .Values.monitor.enabled }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami.dra.monitor.fullname" . }} + namespace: {{ .Release.Namespace }} +{{- end }} + diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml new file mode 100644 index 00000000..dd31c71d --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml @@ -0,0 +1,29 @@ +{{- if .Values.certs.certManager.enabled }} +apiVersion: cert-manager.io/v1 +kind: Certificate +metadata: + name: {{ .Release.Name }}-dra-webhook-serving-cert + namespace: {{ .Release.Namespace }} + labels: + {{- include "hami-dra-webhook.labels" . | nindent 4 }} +spec: + dnsNames: + - {{ .Release.Name }}-dra-webhook.{{ .Release.Namespace }}.svc + - {{ .Release.Name }}-dra-webhook.{{ .Release.Namespace }}.svc.cluster.local + issuerRef: + kind: Issuer + name: {{ .Release.Name }}-dra-webhook-selfsigned-issuer + secretName: {{ .Release.Name }}-dra-webhook-tls + privateKey: + rotationPolicy: {{ .Values.certs.certManager.privateKeyRotationPolicy | default "Never" }} +--- +apiVersion: cert-manager.io/v1 +kind: Issuer +metadata: + name: {{ .Release.Name }}-dra-webhook-selfsigned-issuer + namespace: {{ .Release.Namespace }} + labels: + app.kubernetes.io/component: hami-dra-webhook +spec: + selfSigned: {} +{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml new file mode 100644 index 00000000..eadbb517 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml @@ -0,0 +1,13 @@ +{{- if eq .Values.certs.mode "custom" }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "hami-dra-webhook.tlsSecretName" . }} + namespace: {{ .Release.Namespace }} +type: kubernetes.io/tls +data: + tls.crt: | + {{- .Values.certs.custom.crt | b64enc | indent 4 }} + tls.key: | + {{- .Values.certs.custom.key | b64enc | indent 4 }} +{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml new file mode 100644 index 00000000..97283f3e --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml @@ -0,0 +1,394 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "hami.dra.webhook.fullname" . }}-device-config + namespace: {{ .Release.Namespace }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} +data: + device-config.yaml: |- + {{- if .Files.Glob "files/device-config.yaml" }} + {{- .Files.Get "files/device-config.yaml" | nindent 4}} + {{- else }} + nvidia: + resourceCountName: {{ .Values.resourceName }} + resourceMemoryName: {{ .Values.resourceMem }} + resourceMemoryPercentageName: {{ .Values.resourceMemPercentage }} + resourceCoreName: {{ .Values.resourceCores }} + resourcePriorityName: {{ .Values.resourcePriority }} + overwriteEnv: false + defaultMemory: 0 + defaultCores: 0 + defaultGPUNum: 1 + knownMigGeometries: + - models: [ "A30" ] + allowedGeometries: + - + - name: 1g.6gb + core: 25 + memory: 6144 + count: 4 + - + - name: 2g.12gb + core: 50 + memory: 12288 + count: 2 + - + - name: 4g.24gb + core: 100 + memory: 24576 + count: 1 + - models: [ "A100-SXM4-40GB", "A100-40GB-PCIe", "A100-PCIE-40GB"] + allowedGeometries: + - + - name: 1g.5gb + core: 14 + memory: 5120 + count: 7 + - + - name: 1g.5gb + core: 14 + memory: 5120 + count: 1 + - name: 2g.10gb + core: 28 + memory: 10240 + count: 3 + - + - name: 3g.20gb + core: 42 + memory: 20480 + count: 2 + - + - name: 7g.40gb + core: 100 + memory: 40960 + count: 1 + - models: [ "A100-SXM4-80GB", "A100-80GB-PCIe", "A100-PCIE-80GB"] + allowedGeometries: + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 7 + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 1 + - name: 2g.20gb + core: 28 + memory: 20480 + count: 3 + - + - name: 3g.40gb + core: 42 + memory: 40960 + count: 2 + - + - name: 7g.79gb + core: 100 + memory: 80896 + count: 1 + - models: [ "H100-PCIE-80GB", "H100-SXM5-80GB"] + allowedGeometries: + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 7 + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 1 + - name: 2g.20gb + core: 28 + memory: 20480 + count: 3 + - + - name: 3g.40gb + core: 42 + memory: 40960 + count: 2 + - + - name: 7g.80gb + core: 100 + memory: 81920 + count: 1 + - models: [ "H100-PCIE-94GB", "H100-SXM5-94GB"] + allowedGeometries: + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 7 + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 1 + - name: 2g.24gb + core: 28 + memory: 24576 + count: 3 + - + - name: 3g.47gb + core: 42 + memory: 48128 + count: 2 + - + - name: 7g.94gb + core: 100 + memory: 96256 + count: 1 + - models: [ "H20", "H100 on GH200"] + allowedGeometries: + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 7 + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 1 + - name: 2g.24gb + core: 28 + memory: 24576 + count: 3 + - + - name: 3g.48gb + core: 42 + memory: 49152 + count: 2 + - + - name: 7g.96gb + core: 100 + memory: 98304 + count: 1 + - models: [ "H200 NVL", "H200-SXM5"] + allowedGeometries: + - + - name: 1g.18gb + core: 14 + memory: 18432 + count: 7 + - + - name: 1g.18gb + core: 14 + memory: 18432 + count: 1 + - name: 2g.35gb + core: 28 + memory: 35840 + count: 3 + - + - name: 3g.71gb + core: 42 + memory: 72704 + count: 2 + - + - name: 7g.141gb + core: 100 + memory: 144384 + count: 1 + - models: [ "B200" ] + allowedGeometries: + - + - name: 1g.23gb + core: 14 + memory: 23552 + count: 7 + - + - name: 1g.23gb + core: 14 + memory: 23552 + count: 1 + - name: 2g.45gb + core: 28 + memory: 46080 + count: 3 + - + - name: 3g.90gb + core: 42 + memory: 92160 + count: 2 + - + - name: 7g.180gb + core: 100 + memory: 184320 + count: 1 + cambricon: + resourceCountName: {{ .Values.mluResourceName }} + resourceMemoryName: {{ .Values.mluResourceMem }} + resourceCoreName: {{ .Values.mluResourceCores }} + hygon: + resourceCountName: {{ .Values.dcuResourceName }} + resourceMemoryName: {{ .Values.dcuResourceMem }} + resourceCoreName: {{ .Values.dcuResourceCores }} + metax: + resourceCountName: "metax-tech.com/gpu" + resourceVCountName: {{ .Values.metaxResourceName }} + resourceVMemoryName: {{ .Values.metaxResourceMem }} + resourceVCoreName: {{ .Values.metaxResourceCore }} + sgpuTopologyAware: {{ .Values.metaxsGPUTopologyAware }} + enflame: + resourceNameGCU: "enflame.com/gcu" + resourceNameVGCU: {{ .Values.enflameResourceNameVGCU }} + resourceNameVGCUPercentage: {{ .Values.enflameResourceNameVGCUPercentage }} + mthreads: + resourceCountName: "mthreads.com/vgpu" + resourceMemoryName: "mthreads.com/sgpu-memory" + resourceCoreName: "mthreads.com/sgpu-core" + iluvatars: + - chipName: MR-V100 + commonWord: MR-V100 + resourceCountName: iluvatar.ai/MR-V100-vgpu + resourceMemoryName: iluvatar.ai/MR-V100.vMem + resourceCoreName: iluvatar.ai/MR-V100.vCore + - chipName: MR-V50 + commonWord: MR-V50 + resourceCountName: iluvatar.ai/MR-V50-vgpu + resourceMemoryName: iluvatar.ai/MR-V50.vMem + resourceCoreName: iluvatar.ai/MR-V50.vCore + - chipName: BI-V150 + commonWord: BI-V150 + resourceCountName: iluvatar.ai/BI-V150-vgpu + resourceMemoryName: iluvatar.ai/BI-V150.vMem + resourceCoreName: iluvatar.ai/BI-V150.vCore + - chipName: BI-V100 + commonWord: BI-V100 + resourceCountName: iluvatar.ai/BI-V100-vgpu + resourceMemoryName: iluvatar.ai/BI-V100.vMem + resourceCoreName: iluvatar.ai/BI-V100.vCore + kunlun: + resourceCountName: {{ .Values.kunlunResourceName }} + resourceVCountName: {{ .Values.kunlunResourceVCountName }} + resourceVMemoryName: {{ .Values.kunlunResourceVMemoryName }} + awsneuron: + resourceCountName: "aws.amazon.com/neuron" + resourceCoreName: "aws.amazon.com/neuroncore" + amd: + resourceCountName: "amd.com/gpu" + vnpus: + - chipName: 910A + commonWord: Ascend910A + resourceName: huawei.com/Ascend910A + resourceMemoryName: huawei.com/Ascend910A-memory + memoryAllocatable: 32768 + memoryCapacity: 32768 + aiCore: 30 + templates: + - name: vir02 + memory: 2184 + aiCore: 2 + - name: vir04 + memory: 4369 + aiCore: 4 + - name: vir08 + memory: 8738 + aiCore: 8 + - name: vir16 + memory: 17476 + aiCore: 16 + - chipName: 910B2 + commonWord: Ascend910B2 + resourceName: huawei.com/Ascend910B2 + resourceMemoryName: huawei.com/Ascend910B2-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + aiCore: 24 + aiCPU: 6 + templates: + - name: vir03_1c_8g + memory: 8192 + aiCore: 3 + aiCPU: 1 + - name: vir06_1c_16g + memory: 16384 + aiCore: 6 + aiCPU: 1 + - name: vir12_3c_32g + memory: 32768 + aiCore: 12 + aiCPU: 3 + - chipName: 910B3 + commonWord: Ascend910B3 + resourceName: huawei.com/Ascend910B3 + resourceMemoryName: huawei.com/Ascend910B3-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + aiCore: 20 + aiCPU: 7 + templates: + - name: vir05_1c_16g + memory: 16384 + aiCore: 5 + aiCPU: 1 + - name: vir10_3c_32g + memory: 32768 + aiCore: 10 + aiCPU: 3 + - chipName: 910B4-1 + commonWord: Ascend910B4-1 + resourceName: huawei.com/Ascend910B4-1 + resourceMemoryName: huawei.com/Ascend910B4-1-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + aiCore: 20 + aiCPU: 7 + templates: + # NOTE: Names of vnpu template for 910B4-1 are fixed by Ascend runtime and must not be changed. + # The memory is used for scheduling so the correct values must be set. + # Template vir05_1c_8g actually provides 16GB memory, + - name: vir05_1c_8g + memory: 16384 + aiCore: 5 + aiCPU: 1 + # Template vir10_3c_16g actually provides 32GB memory + - name: vir10_3c_16g + memory: 32768 + aiCore: 10 + aiCPU: 3 + - chipName: 910B4 + commonWord: Ascend910B4 + resourceName: huawei.com/Ascend910B4 + resourceMemoryName: huawei.com/Ascend910B4-memory + memoryAllocatable: 32768 + memoryCapacity: 32768 + aiCore: 20 + aiCPU: 7 + templates: + - name: vir05_1c_8g + memory: 8192 + aiCore: 5 + aiCPU: 1 + - name: vir10_3c_16g + memory: 16384 + aiCore: 10 + aiCPU: 3 + - chipName: 310P3 + commonWord: Ascend310P + resourceName: huawei.com/Ascend310P + resourceMemoryName: huawei.com/Ascend310P-memory + memoryAllocatable: 21527 + memoryCapacity: 24576 + aiCore: 8 + aiCPU: 7 + templates: + - name: vir01 + memory: 3072 + aiCore: 1 + aiCPU: 1 + - name: vir02 + memory: 6144 + aiCore: 2 + aiCPU: 2 + - name: vir04 + memory: 12288 + aiCore: 4 + aiCPU: 4 + {{ end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml new file mode 100644 index 00000000..c763b6aa --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml @@ -0,0 +1,28 @@ +{{- if .Values.webhook.config.mutating.enabled }} +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + name: {{ .Release.Name }}-mutatingwebhookconfiguration + annotations: + cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ .Release.Name }}-dra-webhook-serving-cert +webhooks: + - name: mutate.hami.io + admissionReviewVersions: ["v1"] + clientConfig: + service: + name: {{ .Release.Name }}-dra-webhook + namespace: {{ .Release.Namespace }} + path: /mutate + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + resources: + - pods + scope: '*' + sideEffects: None + timeoutSeconds: 10 +{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml new file mode 100644 index 00000000..acdcbb96 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml @@ -0,0 +1,29 @@ +{{- if .Values.webhook.config.validating.enabled }} +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + name: {{ .Release.Name }}-validatingwebhookconfiguration + annotations: + cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ .Release.Name }}-dra-webhook-serving-cert +webhooks: + - name: validate.hami.io + admissionReviewVersions: ["v1"] + clientConfig: + service: + name: {{ .Release.Name }}-dra-webhook + namespace: {{ .Release.Namespace }} + path: /validate + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - DELETE + resources: + - pods + scope: '*' + sideEffects: None + timeoutSeconds: 10 + failurePolicy: Ignore +{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml new file mode 100644 index 00000000..28916a36 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml @@ -0,0 +1,14 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami.dra.webhook.fullname" . }} +rules: +- apiGroups: [""] + resources: ["pods"] + verbs: ["get", "list", "watch"] +- apiGroups: ["admissionregistration.k8s.io"] + resources: ["mutatingwebhookconfigurations", "validatingwebhookconfigurations"] + verbs: ["get", "list", "watch"] +- apiGroups: ["resource.k8s.io"] + resources: ["resourceclaims"] + verbs: ["*"] diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml new file mode 100644 index 00000000..daad52f2 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml @@ -0,0 +1,12 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami.dra.webhook.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami.dra.webhook.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ include "hami.dra.webhook.fullname" . }} + namespace: {{ .Release.Namespace }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml new file mode 100644 index 00000000..8e3cf90c --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml @@ -0,0 +1,59 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "hami.dra.webhook.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + app.kubernetes.io/name: {{ include "hami.dra.webhook.fullname" . }} + {{- include "hami-dra-webhook.labels" . | nindent 4 }} +spec: + replicas: 1 + selector: + matchLabels: + {{- include "hami-dra-webhook.selectorLabels" . | nindent 6 }} + template: + metadata: + labels: + {{- include "hami-dra-webhook.selectorLabels" . | nindent 8 }} + spec: + {{- include "hami.dra.webhook.imagePullSecrets" . | nindent 6 }} + serviceAccountName: {{ include "hami.dra.webhook.fullname" . }} + containers: + - name: webhook + image: {{ include "hami.dra.webhook.image" . }} + imagePullPolicy: {{ .Values.webhook.image.pullPolicy | default "IfNotPresent" }} + command: + - /bin/webhook + - --v=5 + - --bind-address=0.0.0.0 + - --secure-port=8443 + - --cert-dir=/tls + - --tls-cert-file-name=tls.crt + - --tls-private-key-file-name=tls.key + - --metrics-bind-address=:8080 + - --health-probe-bind-address=:8000 + - --device-config-file=/device-config.yaml + ports: + - containerPort: 8443 + name: webhook + protocol: TCP + - containerPort: 8080 + name: metrics + protocol: TCP + - containerPort: 8000 + name: health + protocol: TCP + volumeMounts: + - name: device-config + mountPath: /device-config.yaml + subPath: device-config.yaml + - name: tls-config + mountPath: /tls + readOnly: true + volumes: + - name: device-config + configMap: + name: {{ include "hami.dra.webhook.fullname" . }}-device-config + - name: tls-config + secret: + secretName: {{ if .Values.certs.certManager.enabled }}{{ .Release.Name }}-dra-webhook-tls{{ else }}{{ .Release.Name }}-tls{{ end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml new file mode 100644 index 00000000..290174ec --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml @@ -0,0 +1,15 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ .Release.Name }}-dra-webhook + namespace: {{ .Release.Namespace }} + labels: + {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} +spec: + type: "ClusterIP" + selector: + {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} + ports: + - port: 443 + targetPort: 8443 + name: webhook diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml new file mode 100644 index 00000000..b0dc2fb2 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml @@ -0,0 +1,5 @@ +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami.dra.webhook.fullname" . }} + namespace: {{ .Release.Namespace }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/values.yaml b/packages/system/hami/charts/hami/charts/hami-dra/values.yaml new file mode 100644 index 00000000..ebbbfed7 --- /dev/null +++ b/packages/system/hami/charts/hami/charts/hami-dra/values.yaml @@ -0,0 +1,166 @@ +## @section Global configuration +## @param global.imageRegistry Global Docker image registry +## @param global.imagePullSecrets Global Docker image pull secrets +global: + ## @param global.imageRegistry Global Docker image registry + imageRegistry: "" + ## E.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## @param global.imagePullSecrets Global Docker image pull secrets + imagePullSecrets: [] + +#Nvidia GPU Parameters +resourceName: "nvidia.com/gpu" +resourceMem: "nvidia.com/gpumem" +resourceMemPercentage: "nvidia.com/gpumem-percentage" +resourceCores: "nvidia.com/gpucores" +resourcePriority: "nvidia.com/priority" + +#MLU Parameters +mluResourceName: "cambricon.com/vmlu" +mluResourceMem: "cambricon.com/mlu.smlu.vmemory" +mluResourceCores: "cambricon.com/mlu.smlu.vcore" + +#Hygon DCU Parameters +dcuResourceName: "hygon.com/dcunum" +dcuResourceMem: "hygon.com/dcumem" +dcuResourceCores: "hygon.com/dcucores" + +#Metax sGPU Parameters +metaxResourceName: "metax-tech.com/sgpu" +metaxResourceCore: "metax-tech.com/vcore" +metaxResourceMem: "metax-tech.com/vmemory" +metaxsGPUTopologyAware: "false" + +#Enflame VGCU Parameters +enflameResourceNameVGCU: "enflame.com/vgcu" +enflameResourceNameVGCUPercentage: "enflame.com/vgcu-percentage" + +#Kunlun XPU Parameters +kunlunResourceName: "kunlunxin.com/xpu" +kunlunResourceVCountName: "kunlunxin.com/vxpu" +kunlunResourceVMemoryName: "kunlunxin.com/vxpu-memory" + +# Webhook deployment configuration +webhook: + image: + registry: ghcr.io + repository: project-hami/hami-dra-webhook + tag: "v0.1.0" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: Always + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param resources controllerManager resource requests and limits + resources: + # If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + limits: + cpu: 500m + memory: 512Mi + requests: + cpu: 100m + memory: 128Mi + ## @param nodeSelector controllerManager node labels for pod assignment + args: + webhookName: "" # Default: {{ .Release.Name }}-hami-dra-webhook + secretName: "" # Default: {{ .Release.Name }}-hami-dra-webhook-tls + # Webhook configuration + config: + mutating: + enabled: true + validating: + enabled: true + +# Monitor deployment configuration +monitor: + enabled: true + replicas: 1 + image: + registry: ghcr.io + repository: project-hami/hami-dra-monitor + tag: "v0.1.0" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: Always + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param resources monitor resource requests and limits + resources: + limits: + cpu: 500m + memory: 512Mi + requests: + cpu: 100m + memory: 128Mi + ## Monitor configuration + logLevel: 2 + metricsBindAddress: ":8080" + healthProbeBindAddress: ":8000" + kubeAPIQPS: 40.0 + kubeAPIBurst: 60 + collectInterval: "30s" + ## Monitor service configuration + service: + ## Service type: ClusterIP, NodePort, or LoadBalancer + ## Defaults to ClusterIP + type: ClusterIP + ## NodePort configuration (only used when type is NodePort) + nodePort: + ## Metrics port (NodePort). If not specified, Kubernetes will assign a random port + metrics: "" + +# Certificate configuration +certs: + # Custom certificate (used when mode is "custom") + custom: + crt: "" + key: "" + # Cert-manager configuration (used when mode is "cert-manager") + certManager: + enabled: true + # Private key rotation policy: "Never" or "Always" + # In cert-manager >= v1.18.0, the default changed from "Never" to "Always" + # Setting to "Never" avoids frequent certificate rotation for webhooks + privateKeyRotationPolicy: "Never" + issuer: + clusterIssuerName: "" # Required when type is "clusterIssuer" + +# DRA Drivers configuration +drivers: + nvidia: + enabled: true + # If you are using gpu driver on host, you need to set this to false + containerDriver: true + image: + registry: ghcr.io + repository: projecthami/k8s-dra-driver + tag: "v0.0.1-dev" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] diff --git a/packages/system/hami/charts/hami/templates/NOTES.txt b/packages/system/hami/charts/hami/templates/NOTES.txt new file mode 100644 index 00000000..15bb1218 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/NOTES.txt @@ -0,0 +1,3 @@ +** Please be patient while the chart is being deployed ** +Resource name: {{ .Values.resourceName }} + diff --git a/packages/system/hami/charts/hami/templates/_commons.tpl b/packages/system/hami/charts/hami/templates/_commons.tpl new file mode 100644 index 00000000..78a262c9 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/_commons.tpl @@ -0,0 +1,49 @@ +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" $) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $tag := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if .tag }} + {{- $tag = .tag | toString -}} +{{- end -}} +{{- if $registryName }} +{{- printf "%s/%s:%s" $registryName $repositoryName $tag -}} +{{- else -}} +{{- printf "%s:%s" $repositoryName $tag -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/_helpers.tpl b/packages/system/hami/charts/hami/templates/_helpers.tpl new file mode 100644 index 00000000..ffcc61da --- /dev/null +++ b/packages/system/hami/charts/hami/templates/_helpers.tpl @@ -0,0 +1,163 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "hami-vgpu.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "hami-vgpu.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "hami-vgpu.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} + +{{/* +The app name for Scheduler +*/}} +{{- define "hami-vgpu.scheduler" -}} +{{- printf "%s-scheduler" ( include "hami-vgpu.fullname" . ) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +The app name for DevicePlugin +*/}} +{{- define "hami-vgpu.device-plugin" -}} +{{- printf "%s-device-plugin" ( include "hami-vgpu.fullname" . ) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* + The app name for MockDevicePlugin + */}} +{{- define "hami-vgpu.mock-device-plugin" -}} +{{- printf "%s-mock-device-plugin" ( include "hami-vgpu.fullname" . ) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +The tls secret name for Scheduler +*/}} +{{- define "hami-vgpu.scheduler.tls" -}} +{{- printf "%s-scheduler-tls" ( include "hami-vgpu.fullname" . ) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +The webhook name +*/}} +{{- define "hami-vgpu.scheduler.webhook" -}} +{{- printf "%s-webhook" ( include "hami-vgpu.fullname" . ) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "hami-vgpu.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "hami-vgpu.labels" -}} +helm.sh/chart: {{ include "hami-vgpu.chart" . }} +{{ include "hami-vgpu.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "hami-vgpu.selectorLabels" -}} +app.kubernetes.io/name: {{ include "hami-vgpu.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + + +{{/* + Resolve the tag for kubeScheduler. +*/}} +{{- define "resolvedKubeSchedulerTag" -}} +{{- if .Values.scheduler.kubeScheduler.image.tag }} +{{- .Values.scheduler.kubeScheduler.image.tag | trim -}} +{{- else }} +{{- include "strippedKubeVersion" . | trim -}} +{{- end }} +{{- end }} + +{{/* + Return the stripped Kubernetes version string by removing extra parts after semantic version number. + v1.31.1+k3s1 -> v1.31.1 + v1.30.8-eks-2d5f260 -> v1.30.8 + v1.31.1 -> v1.31.1 +*/}} +{{- define "strippedKubeVersion" -}} +{{ regexReplaceAll "^(v[0-9]+\\.[0-9]+\\.[0-9]+)(.*)$" .Capabilities.KubeVersion.Version "$1" }} +{{- end -}} + +{{- define "hami.scheduler.kubeScheduler.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.scheduler.kubeScheduler.image "global" .Values.global "tag" (include "resolvedKubeSchedulerTag" .)) }} +{{- end -}} + +{{- define "hami.scheduler.extender.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.scheduler.extender.image "global" .Values.global "tag" .Values.global.imageTag) }} +{{- end -}} + +{{- define "hami.devicePlugin.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.devicePlugin.image "global" .Values.global "tag" .Values.global.imageTag) }} +{{- end -}} + +{{- define "hami.mockDevicePlugin.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.mockDevicePlugin.image "global" .Values.global "tag" .Values.mockDevicePlugin.tag) }} +{{- end -}} + +{{- define "hami.devicePlugin.monitor.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.devicePlugin.monitor.image "global" .Values.global "tag" .Values.global.imageTag) }} +{{- end -}} + +{{- define "hami.scheduler.patch.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.scheduler.patch.image "global" .Values.global) }} +{{- end -}} + +{{- define "hami.scheduler.patch.new.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.scheduler.patch.imageNew "global" .Values.global) }} +{{- end -}} + +{{- define "hami.scheduler.extender.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.scheduler.extender.image) "global" .Values.global) }} +{{- end -}} + +{{- define "hami.devicePlugin.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.devicePlugin.image) "global" .Values.global) }} +{{- end -}} + +{{- define "hami.scheduler.patch.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.scheduler.patch.image) "global" .Values.global) }} +{{- end -}} + +{{- define "hami.scheduler.patch.new.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.scheduler.patch.imageNew) "global" .Values.global) }} +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml new file mode 100644 index 00000000..b36347f2 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml @@ -0,0 +1,13 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.devicePlugin.nodeConfiguration.externalConfigName) (not .Values.dra.enabled) -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "hami-vgpu.device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-device-plugin + {{- include "hami-vgpu.labels" . | nindent 4 }} +data: + config.json: | +{{- .Values.devicePlugin.nodeConfiguration.config | nindent 4 }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/device-plugin/daemonsetmock.yaml b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetmock.yaml new file mode 100644 index 00000000..a0dc4ff3 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetmock.yaml @@ -0,0 +1,55 @@ +{{- if .Values.mockDevicePlugin.enabled }} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "hami-vgpu.mock-device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +spec: + selector: + matchLabels: + app.kubernetes.io/component: hami-mock-device-plugin + {{- include "hami-vgpu.selectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + scheduler.alpha.kubernetes.io/critical-pod: "" + labels: + app.kubernetes.io/component: hami-mock-device-plugin + {{- include "hami-vgpu.selectorLabels" . | nindent 8 }} + spec: + serviceAccountName: {{ include "hami-vgpu.mock-device-plugin" . }} + tolerations: + - key: CriticalAddonsOnly + operator: Exists + containers: + - image: {{ include "hami.mockDevicePlugin.image" . }} + imagePullPolicy: {{ .Values.mockDevicePlugin.image.pullPolicy }} + name: hami-mock-dp-cntr + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + command: + - ./k8s-device-plugin + - -v=5 + - --device-config-file=/device-config.yaml + volumeMounts: + - name: dp + mountPath: /var/lib/kubelet/device-plugins + - name: sys + mountPath: /sys + - name: device-config + mountPath: /device-config.yaml + subPath: device-config.yaml + volumes: + - name: dp + hostPath: + path: /var/lib/kubelet/device-plugins + - name: sys + hostPath: + path: /sys + - name: device-config + configMap: + name: {{ include "hami-vgpu.scheduler" . }}-device +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml new file mode 100644 index 00000000..577dc0f9 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml @@ -0,0 +1,262 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) }} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "hami-vgpu.device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-device-plugin + {{- include "hami-vgpu.labels" . | nindent 4 }} + {{- with .Values.global.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.global.annotations }} + annotations: {{ toYaml .Values.global.annotations | nindent 4}} + {{- end }} +spec: + updateStrategy: + {{- with .Values.devicePlugin.updateStrategy }} + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + app.kubernetes.io/component: hami-device-plugin + {{- include "hami-vgpu.selectorLabels" . | nindent 6 }} + template: + metadata: + labels: + app.kubernetes.io/component: hami-device-plugin + hami.io/webhook: ignore + {{- include "hami-vgpu.selectorLabels" . | nindent 8 }} + annotations: + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + checksum/hami-scheduler-newversion-config: {{ include (print $.Template.BasePath "/scheduler/configmapnew.yaml") . | sha256sum }} + {{- else }} + checksum/hami-scheduler-config: {{ include (print $.Template.BasePath "/scheduler/configmap.yaml") . | sha256sum }} + {{- end }} + checksum/hami-scheduler-device-config: {{ include (print $.Template.BasePath "/scheduler/device-configmap.yaml") . | sha256sum }} + {{- if .Values.devicePlugin.podAnnotations }} + {{- toYaml .Values.devicePlugin.podAnnotations | nindent 8 }} + {{- end }} + spec: + {{- if .Values.devicePlugin.runtimeClassName }} + runtimeClassName: {{ .Values.devicePlugin.runtimeClassName }} + {{- end }} + serviceAccountName: {{ include "hami-vgpu.device-plugin" . }} + priorityClassName: system-node-critical + hostPID: true + hostNetwork: true + {{- include "hami.devicePlugin.imagePullSecrets" . | nindent 6 }} + {{- if .Values.devicePlugin.gpuOperatorToolkitReady.enabled }} + initContainers: + - name: toolkit-validation + image: {{ include "hami.devicePlugin.image" . }} + imagePullPolicy: {{ .Values.devicePlugin.image.pullPolicy }} + securityContext: + privileged: true + runAsUser: 0 + command: ["sh", "-c"] + args: + - | + echo "Waiting for NVIDIA Toolkit to be ready..." + until [ -f {{ .Values.devicePlugin.gpuOperatorToolkitReady.hostPath }}/toolkit-ready ]; do + echo "Waiting for {{ .Values.devicePlugin.gpuOperatorToolkitReady.hostPath }}/toolkit-ready..." + sleep 5 + done + echo "NVIDIA Toolkit is ready!" + volumeMounts: + - name: nvidia-validations + mountPath: {{ .Values.devicePlugin.gpuOperatorToolkitReady.hostPath | quote }} + mountPropagation: HostToContainer + readOnly: true + {{- end }} + containers: + - name: device-plugin + image: {{ include "hami.devicePlugin.image" . }} + imagePullPolicy: {{ .Values.devicePlugin.image.pullPolicy }} + lifecycle: + postStart: + exec: + command: ["/bin/sh","-c", {{ printf "/k8s-vgpu/bin/vgpu-init.sh %s/vgpu/" .Values.global.gpuHookPath | quote }}] + command: + - nvidia-device-plugin + - --config-file=/device-config.yaml + - --mig-strategy={{ .Values.devicePlugin.migStrategy }} + - --disable-core-limit={{ .Values.devicePlugin.disablecorelimit }} + {{- range .Values.devicePlugin.extraArgs }} + - {{ . }} + {{- end }} + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + - name: NVIDIA_MIG_MONITOR_DEVICES + value: all + - name: DEVICE_LIST_STRATEGY + value: {{ .Values.devicePlugin.deviceListStrategy }} + - name: HOOK_PATH + value: {{ .Values.global.gpuHookPath }} + {{- if typeIs "bool" .Values.devicePlugin.passDeviceSpecsEnabled }} + - name: PASS_DEVICE_SPECS + value: {{ .Values.devicePlugin.passDeviceSpecsEnabled | quote }} + {{- end }} + {{- if typeIs "string" .Values.devicePlugin.nvidiaDriverRoot }} + - name: NVIDIA_DRIVER_ROOT + value: {{ .Values.devicePlugin.nvidiaDriverRoot }} + {{- end }} + {{- if typeIs "string" .Values.devicePlugin.nvidiaHookPath }} + - name: NVIDIA_CDI_HOOK_PATH + value: {{ .Values.devicePlugin.nvidiaHookPath }} + {{- end }} + {{- if typeIs "bool" .Values.devicePlugin.gdrcopyEnabled }} + - name: GDRCOPY_ENABLED + value: {{ .Values.devicePlugin.gdrcopyEnabled | quote }} + {{- end }} + {{- if typeIs "bool" .Values.devicePlugin.gdsEnabled }} + - name: GDS_ENABLED + value: {{ .Values.devicePlugin.gdsEnabled | quote }} + {{- end }} + {{- if typeIs "bool" .Values.devicePlugin.mofedEnabled }} + - name: MOFED_ENABLED + value: {{ .Values.devicePlugin.mofedEnabled | quote }} + {{- end }} + {{- if eq (.Values.scheduler.defaultSchedulerPolicy.gpuSchedulerPolicy | default "spread") "topology-aware" }} + - name: ENABLE_TOPOLOGY_SCORE + value: "true" + {{- end }} + {{- with .Values.devicePlugin.extraEnvs }} + {{- . | toYaml | nindent 12 }} + {{- end }} + securityContext: + privileged: true + allowPrivilegeEscalation: true + capabilities: + drop: ["ALL"] + add: ["SYS_ADMIN"] + resources: + {{- toYaml .Values.devicePlugin.resources | nindent 12 }} + volumeMounts: + - name: device-plugin + mountPath: /var/lib/kubelet/device-plugins + - name: lib + mountPath: {{ printf "%s%s" .Values.global.gpuHookPath "/vgpu" }} + - name: usrbin + mountPath: /usrbin + - name: deviceconfig + mountPath: /config + - name: hosttmp + mountPath: /tmp + - name: device-config + mountPath: /device-config.yaml + subPath: device-config.yaml + - name: cdi-root + mountPath: /var/run/cdi + {{- if typeIs "string" .Values.devicePlugin.nvidiaDriverRoot }} + # We always mount the driver root at /driver-root in the container. + # This is required for CDI detection to work correctly. + - name: driver-root + mountPath: /driver-root + readOnly: true + {{- end }} + - name: vgpu-monitor + image: {{ include "hami.devicePlugin.monitor.image" . }} + imagePullPolicy: {{ .Values.devicePlugin.monitor.image.pullPolicy }} + command: + - "vGPUmonitor" + {{- range .Values.devicePlugin.monitor.extraArgs }} + - {{ . }} + {{- end }} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: ["ALL"] + add: ["SYS_ADMIN"] + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + - name: NVIDIA_VISIBLE_DEVICES + value: "all" + - name: NVIDIA_MIG_MONITOR_DEVICES + value: "all" + - name: HOOK_PATH + value: "{{ .Values.global.gpuHookPath }}/vgpu" + - name: HAMI_RESYNC_INTERVAL + value: {{ .Values.devicePlugin.monitor.resyncInterval | default "5m" | quote }} + {{- with .Values.devicePlugin.monitor.extraEnvs }} + {{- . | toYaml | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.devicePlugin.monitor.resources | nindent 12 }} + volumeMounts: + - name: ctrs + mountPath: {{ .Values.devicePlugin.monitor.ctrPath }} + - name: dockers + mountPath: /run/docker + - name: containerds + mountPath: /run/containerd + - name: sysinfo + mountPath: /sysinfo + - name: hostvar + mountPath: /hostvar + - name: hosttmp + mountPath: /tmp + volumes: + - name: ctrs + hostPath: + path: {{ .Values.devicePlugin.monitor.ctrPath }} + - name: hosttmp + hostPath: + path: /tmp + - name: dockers + hostPath: + path: /run/docker + - name: containerds + hostPath: + path: /run/containerd + - name: device-plugin + hostPath: + path: {{ .Values.devicePlugin.pluginPath }} + - name: lib + hostPath: + path: {{ .Values.devicePlugin.libPath }} + {{- if .Values.devicePlugin.gpuOperatorToolkitReady.enabled }} + - name: nvidia-validations + hostPath: + path: {{ .Values.devicePlugin.gpuOperatorToolkitReady.hostPath }} + type: DirectoryOrCreate + {{- end }} + {{- if typeIs "string" .Values.devicePlugin.nvidiaDriverRoot }} + - name: driver-root + hostPath: + path: {{ .Values.devicePlugin.nvidiaDriverRoot }} + type: Directory + {{- end }} + - name: cdi-root + hostPath: + path: /var/run/cdi + type: DirectoryOrCreate + - name: usrbin + hostPath: + path: /usr/bin + - name: sysinfo + hostPath: + path: /sys + - name: hostvar + hostPath: + path: /var + - name: deviceconfig + configMap: + name: {{ .Values.devicePlugin.nodeConfiguration.externalConfigName | default (include "hami-vgpu.device-plugin" .) }} + - name: device-config + configMap: + name: {{ include "hami-vgpu.scheduler" . }}-device + {{- if .Values.devicePlugin.nvidiaNodeSelector }} + nodeSelector: {{ toYaml .Values.devicePlugin.nvidiaNodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.devicePlugin.tolerations }} + tolerations: {{ toYaml .Values.devicePlugin.tolerations | nindent 8 }} + {{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml new file mode 100644 index 00000000..c51ff6c6 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml @@ -0,0 +1,29 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami-vgpu.device-plugin" . }}-monitor +rules: + - apiGroups: + - "" + resources: + - pods + verbs: + - get + - create + - watch + - list + - update + - patch + - apiGroups: + - "" + resources: + - nodes + verbs: + - get + - update + - list + - patch +{{- end -}} + + diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml new file mode 100644 index 00000000..93a118dd --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.device-plugin" . }} + labels: + app.kubernetes.io/component: "hami-device-plugin" + {{- include "hami-vgpu.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami-vgpu.device-plugin" . }}-monitor +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml new file mode 100644 index 00000000..24daca9b --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml @@ -0,0 +1,29 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "hami-vgpu.device-plugin" . }}-monitor + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-device-plugin + {{- include "hami-vgpu.labels" . | nindent 4 }} + {{- if .Values.devicePlugin.service.labels }} # Use devicePlugin instead of scheduler + {{ toYaml .Values.devicePlugin.service.labels | indent 4 }} + {{- end }} + {{- if .Values.devicePlugin.service.annotations }} # Use devicePlugin instead of scheduler + annotations: {{ toYaml .Values.devicePlugin.service.annotations | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.devicePlugin.service.type | default "NodePort" }} # Default type is NodePort + ports: + - name: monitorport + port: {{ .Values.devicePlugin.service.httpPort | default 31992 }} # Default HTTP port is 31992 + targetPort: 9394 + {{- if eq (.Values.devicePlugin.service.type | default "NodePort") "NodePort" }} # If type is NodePort, set nodePort + nodePort: {{ .Values.devicePlugin.service.httpPort | default 31992 }} + {{- end }} + protocol: TCP + selector: + app.kubernetes.io/component: hami-device-plugin + {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} +{{- end -}} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml new file mode 100644 index 00000000..b10d2cb9 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml @@ -0,0 +1,10 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami-vgpu.device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: "hami-device-plugin" + {{- include "hami-vgpu.labels" . | nindent 4 }} +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml b/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml new file mode 100644 index 00000000..cd3d14cc --- /dev/null +++ b/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml @@ -0,0 +1,11 @@ +{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +{{- if and .Values.devicePlugin.createRuntimeClass .Values.devicePlugin.runtimeClassName }} +apiVersion: node.k8s.io/v1 +kind: RuntimeClass +metadata: + name: {{ .Values.devicePlugin.runtimeClassName }} + annotations: + helm.sh/hook: pre-install,pre-upgrade +handler: nvidia +{{- end }} +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml b/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml new file mode 100644 index 00000000..b6edb605 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml @@ -0,0 +1,31 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if .Values.scheduler.certManager.enabled }} +apiVersion: cert-manager.io/v1 +kind: Certificate +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-serving-cert + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} +spec: + dnsNames: + - {{ include "hami-vgpu.scheduler" . }}.{{ include "hami-vgpu.namespace" . }}.svc + - {{ include "hami-vgpu.scheduler" . }}.{{ include "hami-vgpu.namespace" . }}.svc.cluster.local + issuerRef: + kind: Issuer + name: {{ include "hami-vgpu.scheduler" . }}-selfsigned-issuer + secretName: {{ include "hami-vgpu.scheduler.tls" . }} +--- +apiVersion: cert-manager.io/v1 +kind: Issuer +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-selfsigned-issuer + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} +spec: + selfSigned: {} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml b/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml new file mode 100644 index 00000000..9c510c00 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml @@ -0,0 +1,36 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +rules: + - apiGroups: [""] + resources: ["pods", "configmaps"] + verbs: ["get", "list", "watch", "patch"] + - apiGroups: [""] + resources: ["pods/binding"] + verbs: ["create"] + - apiGroups: [""] + resources: ["nodes"] + verbs: ["get", "list", "patch", "watch"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "get", "list"] + - apiGroups: [""] + resources: ["resourcequotas"] + verbs: ["get", "list", "watch"] +--- +{{- if .Values.mockDevicePlugin.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami-vgpu.mock-device-plugin" . }} +rules: + - apiGroups: [""] + resources: ["nodes"] + verbs: ["get", "update", "list", "patch"] +{{- end -}} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml new file mode 100644 index 00000000..69d75986 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml @@ -0,0 +1,49 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-kube + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:kube-scheduler +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-volume + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:volume-scheduler +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami-vgpu.scheduler" . }} +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml b/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml new file mode 100644 index 00000000..75889146 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml @@ -0,0 +1,142 @@ +{{- if and .Values.scheduler.kubeScheduler.enabled (not .Values.dra.enabled) -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} +data: + config.json: | + { + "kind": "Policy", + "apiVersion": "v1", + "extenders": [ + { + {{- if .Values.scheduler.admissionWebhook.enabled }} + "urlPrefix": "https://127.0.0.1:443", + "enableHttps": true, + "tlsConfig": { + "insecure": true + }, + {{- else }} + "urlPrefix": "http://127.0.0.1:80", + "enableHttps": false, + {{- end }} + "filterVerb": "filter", + "bindVerb": "bind", + "weight": 1, + "nodeCacheCapable": true, + "httpTimeout": 30000000000, + "managedResources": [ + {{- range .Values.devices.amd.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- if .Values.devices.ascend.enabled }} + {{- range .Values.devices.ascend.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- end }} + {{- if .Values.devices.mthreads.enabled }} + {{- range .Values.devices.mthreads.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- end }} + {{- if .Values.devices.enflame.enabled }} + {{- range .Values.devices.enflame.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- end }} + {{- if .Values.devices.kunlun.enabled }} + {{- range .Values.devices.kunlun.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- end }} + {{- range .Values.devices.awsneuron.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- if .Values.devices.iluvatar.enabled }} + {{- range .Values.devices.iluvatar.customresources }} + { + "name": "{{ . }}", + "ignoredByScheduler": true + }, + {{- end }} + {{- end }} + { + "name": "{{ .Values.resourceName }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.resourceMem }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.resourceCores }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.resourceMemPercentage }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.resourcePriority }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.mluResourceName }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.dcuResourceName }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.dcuResourceMem }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.dcuResourceCores }}", + "ignoredByScheduler": true + }, + { + "name": "metax-tech.com/gpu", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.metaxResourceName }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.metaxResourceCore }}", + "ignoredByScheduler": true + }, + { + "name": "{{ .Values.metaxResourceMem }}", + "ignoredByScheduler": true + } + ], + "ignoreable": false + } + ] + } +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml b/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml new file mode 100644 index 00000000..e2a91d8b --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml @@ -0,0 +1,102 @@ +{{- if and .Values.scheduler.kubeScheduler.enabled (not .Values.dra.enabled) -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-newversion + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} +data: + config.yaml: | + {{- if gt (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 25}} + apiVersion: kubescheduler.config.k8s.io/v1 + {{- else }} + apiVersion: kubescheduler.config.k8s.io/v1beta2 + {{- end }} + kind: KubeSchedulerConfiguration + leaderElection: + leaderElect: false + profiles: + - schedulerName: {{ .Values.schedulerName }} + extenders: + {{- if .Values.scheduler.admissionWebhook.enabled }} + - urlPrefix: "https://127.0.0.1:443" + enableHTTPS: true + tlsConfig: + insecure: true + {{- else }} + - urlPrefix: "http://127.0.0.1:80" + enableHTTPS: false + {{- end }} + filterVerb: filter + bindVerb: bind + nodeCacheCapable: true + weight: 1 + httpTimeout: 30s + managedResources: + - name: {{ .Values.resourceName }} + ignoredByScheduler: true + - name: {{ .Values.resourceMem }} + ignoredByScheduler: true + - name: {{ .Values.resourceCores }} + ignoredByScheduler: true + - name: {{ .Values.resourceMemPercentage }} + ignoredByScheduler: true + - name: {{ .Values.resourcePriority }} + ignoredByScheduler: true + - name: {{ .Values.mluResourceName }} + ignoredByScheduler: true + - name: {{ .Values.dcuResourceName }} + ignoredByScheduler: true + - name: {{ .Values.dcuResourceMem }} + ignoredByScheduler: true + - name: {{ .Values.dcuResourceCores }} + ignoredByScheduler: true + - name: "metax-tech.com/gpu" + ignoredByScheduler: true + - name: {{ .Values.metaxResourceName }} + ignoredByScheduler: true + - name: {{ .Values.metaxResourceCore }} + ignoredByScheduler: true + - name: {{ .Values.metaxResourceMem }} + ignoredByScheduler: true + {{- if .Values.devices.ascend.enabled }} + {{- range .Values.devices.ascend.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- end }} + {{- if .Values.devices.mthreads.enabled }} + {{- range .Values.devices.mthreads.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- end }} + {{- if .Values.devices.enflame.enabled }} + {{- range .Values.devices.enflame.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- end }} + {{- if .Values.devices.kunlun.enabled }} + {{- range .Values.devices.kunlun.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- end }} + {{- range .Values.devices.awsneuron.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- if .Values.devices.iluvatar.enabled }} + {{- range .Values.devices.iluvatar.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} + {{- end }} + {{- range .Values.devices.amd.customresources }} + - name: {{ . }} + ignoredByScheduler: true + {{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml new file mode 100644 index 00000000..6364cae3 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml @@ -0,0 +1,227 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} + {{- with .Values.global.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.global.annotations }} + annotations: {{ toYaml .Values.global.annotations | nindent 4}} + {{- end }} +spec: + {{- if .Values.scheduler.leaderElect }} + replicas: {{ .Values.scheduler.replicas }} + {{- else }} + replicas: 1 + {{- end }} + selector: + matchLabels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.selectorLabels" . | nindent 6 }} + template: + metadata: + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.selectorLabels" . | nindent 8 }} + hami.io/webhook: ignore + annotations: + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + checksum/hami-scheduler-newversion-config: {{ include (print $.Template.BasePath "/scheduler/configmapnew.yaml") . | sha256sum }} + {{- else }} + checksum/hami-scheduler-config: {{ include (print $.Template.BasePath "/scheduler/configmap.yaml") . | sha256sum }} + {{- end }} + checksum/hami-scheduler-device-config: {{ include (print $.Template.BasePath "/scheduler/device-configmap.yaml") . | sha256sum }} + {{- if .Values.scheduler.podAnnotations }} + {{- toYaml .Values.scheduler.podAnnotations | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "hami-vgpu.scheduler" . }} + priorityClassName: system-node-critical + {{- include "hami.scheduler.extender.imagePullSecrets" . | nindent 6 }} + containers: + {{- if .Values.scheduler.kubeScheduler.enabled }} + - name: kube-scheduler + image: {{ include "hami.scheduler.kubeScheduler.image" . }} + imagePullPolicy: {{ .Values.scheduler.kubeScheduler.image.pullPolicy }} + command: + - kube-scheduler + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + {{- range .Values.scheduler.kubeScheduler.extraNewArgs }} + - {{ . }} + {{- end }} + {{- else }} + - --scheduler-name={{ .Values.schedulerName }} + {{- range .Values.scheduler.kubeScheduler.extraArgs }} + - {{ . }} + {{- end }} + {{- end }} + - --leader-elect={{ .Values.scheduler.leaderElect }} + - --leader-elect-resource-name={{ .Values.schedulerName }} + - --leader-elect-resource-namespace={{ include "hami-vgpu.namespace" . }} + resources: + {{- toYaml .Values.scheduler.kubeScheduler.resources | nindent 12 }} + volumeMounts: + - name: scheduler-config + mountPath: /config + {{- end }} + {{- if .Values.scheduler.livenessProbe }} + livenessProbe: + failureThreshold: 8 + httpGet: + path: /healthz + port: 10259 + scheme: HTTPS + initialDelaySeconds: 10 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 15 + {{- end }} + - name: vgpu-scheduler-extender + image: {{ include "hami.scheduler.extender.image" . }} + imagePullPolicy: {{ .Values.scheduler.extender.image.pullPolicy }} + env: + {{- if .Values.scheduler.nodeLockExpire }} + - name: HAMI_NODELOCK_EXPIRE + value: "{{ .Values.scheduler.nodeLockExpire }}" + {{- end }} + {{- if .Values.global.managedNodeSelectorEnable }} + {{- range $key, $value := .Values.global.managedNodeSelector }} + - name: NODE_SELECTOR_{{ $key | upper | replace "-" "_" }} + value: "{{ $value }}" + {{- end }} + {{- end }} + command: + - scheduler + {{- if .Values.scheduler.admissionWebhook.enabled }} + - --http_bind=0.0.0.0:443 + - --cert_file=/tls/tls.crt + - --key_file=/tls/tls.key + {{- else }} + - --http_bind=0.0.0.0:80 + {{- end }} + - --scheduler-name={{ .Values.schedulerName }} + - --metrics-bind-address={{ .Values.scheduler.metricsBindAddress }} + - --node-scheduler-policy={{ .Values.scheduler.defaultSchedulerPolicy.nodeSchedulerPolicy }} + - --gpu-scheduler-policy={{ .Values.scheduler.defaultSchedulerPolicy.gpuSchedulerPolicy }} + - --force-overwrite-default-scheduler={{ .Values.scheduler.forceOverwriteDefaultScheduler}} + - --device-config-file=/device-config.yaml + - --leader-elect={{ .Values.scheduler.leaderElect }} + - --leader-elect-resource-name={{ .Values.schedulerName }} + - --leader-elect-resource-namespace={{ include "hami-vgpu.namespace" . }} + {{- if .Values.devices.ascend.enabled }} + - --enable-ascend=true + {{- end }} + {{- if .Values.devices.iluvatar.enabled }} + - --enable-iluvatar=true + {{- end }} + {{- if .Values.scheduler.nodeLabelSelector }} + - --node-label-selector={{- $first := true -}} + {{- range $key, $value := .Values.scheduler.nodeLabelSelector -}} + {{- if not $first }},{{ end -}} + {{- $key }}={{ $value -}} + {{- $first = false -}} + {{- end -}} + {{- end }} + {{- range .Values.scheduler.extender.extraArgs }} + - {{ . }} + {{- end }} + ports: + {{- if .Values.scheduler.admissionWebhook.enabled }} + - name: https + containerPort: 443 + protocol: TCP + {{- else }} + - name: http + containerPort: 80 + protocol: TCP + {{- end }} + - name: metrics + containerPort: {{ last (splitList ":" .Values.scheduler.metricsBindAddress) | int }} + protocol: TCP + resources: + {{- toYaml .Values.scheduler.extender.resources | nindent 12 }} + volumeMounts: + - name: device-config + mountPath: /device-config.yaml + subPath: device-config.yaml + {{- if .Values.scheduler.admissionWebhook.enabled }} + - name: tls-config + mountPath: /tls + {{- end }} + {{- if .Values.scheduler.livenessProbe }} + livenessProbe: + httpGet: + path: /healthz + {{- if .Values.scheduler.admissionWebhook.enabled }} + port: https + scheme: HTTPS + {{- else }} + port: http + scheme: HTTP + {{- end }} + initialDelaySeconds: 10 + periodSeconds: 10 + failureThreshold: 3 + timeoutSeconds: 5 + {{- end }} + {{- if .Values.scheduler.leaderElect }} + readinessProbe: + httpGet: + path: /readyz + {{- if .Values.scheduler.admissionWebhook.enabled }} + port: https + scheme: HTTPS + {{- else }} + port: http + scheme: HTTP + {{- end }} + initialDelaySeconds: 10 + periodSeconds: 10 + failureThreshold: 3 + timeoutSeconds: 5 + {{- end }} + {{- if .Values.scheduler.leaderElect }} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - hami-scheduler + topologyKey: "kubernetes.io/hostname" + {{- end }} + volumes: + {{- if .Values.scheduler.admissionWebhook.enabled }} + - name: tls-config + secret: + secretName: {{ template "hami-vgpu.scheduler.tls" . }} + {{- end }} + {{- if .Values.scheduler.kubeScheduler.enabled }} + - name: scheduler-config + configMap: + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + name: {{ template "hami-vgpu.scheduler" . }}-newversion + {{- else }} + name: {{ template "hami-vgpu.scheduler" . }} + {{- end }} + {{- end }} + - name: device-config + configMap: + name: {{ include "hami-vgpu.scheduler" . }}-device + {{- if .Values.scheduler.nodeSelector }} + nodeSelector: {{ toYaml .Values.scheduler.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.scheduler.tolerations }} + tolerations: {{ toYaml .Values.scheduler.tolerations | nindent 8 }} + {{- end }} + {{- if .Values.scheduler.nodeName }} + nodeName: {{ .Values.scheduler.nodeName }} + {{- end }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml new file mode 100644 index 00000000..ccb945ac --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml @@ -0,0 +1,410 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "hami-vgpu.scheduler" . }}-device + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} +data: + device-config.yaml: |- + {{- if .Files.Glob "files/device-config.yaml" }} + {{- .Files.Get "files/device-config.yaml" | nindent 4}} + {{- else }} + nvidia: + resourceCountName: {{ .Values.resourceName }} + resourceMemoryName: {{ .Values.resourceMem }} + resourceMemoryPercentageName: {{ .Values.resourceMemPercentage }} + resourceCoreName: {{ .Values.resourceCores }} + resourcePriorityName: {{ .Values.resourcePriority }} + overwriteEnv: false + defaultMemory: 0 + defaultCores: 0 + defaultGPUNum: 1 + memoryFactor: 1 + deviceSplitCount: {{ .Values.devicePlugin.deviceSplitCount }} + deviceMemoryScaling: {{ .Values.devicePlugin.deviceMemoryScaling }} + deviceCoreScaling: {{ .Values.devicePlugin.deviceCoreScaling }} + gpuCorePolicy: {{ .Values.devices.nvidia.gpuCorePolicy }} + libCudaLogLevel: {{ .Values.devices.nvidia.libCudaLogLevel }} + runtimeClassName: "{{ .Values.devicePlugin.runtimeClassName }}" + knownMigGeometries: + - models: [ "A30" ] + allowedGeometries: + - + - name: 1g.6gb + core: 25 + memory: 6144 + count: 4 + - + - name: 2g.12gb + core: 50 + memory: 12288 + count: 2 + - + - name: 4g.24gb + core: 100 + memory: 24576 + count: 1 + - models: [ "A100-SXM4-40GB", "A100-40GB-PCIe", "A100-PCIE-40GB"] + allowedGeometries: + - + - name: 1g.5gb + core: 14 + memory: 5120 + count: 7 + - + - name: 1g.5gb + core: 14 + memory: 5120 + count: 1 + - name: 2g.10gb + core: 28 + memory: 10240 + count: 3 + - + - name: 3g.20gb + core: 42 + memory: 20480 + count: 2 + - + - name: 7g.40gb + core: 100 + memory: 40960 + count: 1 + - models: [ "A100-SXM4-80GB", "A100-80GB-PCIe", "A100-PCIE-80GB"] + allowedGeometries: + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 7 + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 1 + - name: 2g.20gb + core: 28 + memory: 20480 + count: 3 + - + - name: 3g.40gb + core: 42 + memory: 40960 + count: 2 + - + - name: 7g.79gb + core: 100 + memory: 80896 + count: 1 + - models: [ "H100-PCIE-80GB", "H100-SXM5-80GB"] + allowedGeometries: + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 7 + - + - name: 1g.10gb + core: 14 + memory: 10240 + count: 1 + - name: 2g.20gb + core: 28 + memory: 20480 + count: 3 + - + - name: 3g.40gb + core: 42 + memory: 40960 + count: 2 + - + - name: 7g.80gb + core: 100 + memory: 81920 + count: 1 + - models: [ "H100-PCIE-94GB", "H100-SXM5-94GB"] + allowedGeometries: + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 7 + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 1 + - name: 2g.24gb + core: 28 + memory: 24576 + count: 3 + - + - name: 3g.47gb + core: 42 + memory: 48128 + count: 2 + - + - name: 7g.94gb + core: 100 + memory: 96256 + count: 1 + - models: [ "H20", "H100 on GH200"] + allowedGeometries: + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 7 + - + - name: 1g.12gb + core: 14 + memory: 12288 + count: 1 + - name: 2g.24gb + core: 28 + memory: 24576 + count: 3 + - + - name: 3g.48gb + core: 42 + memory: 49152 + count: 2 + - + - name: 7g.96gb + core: 100 + memory: 98304 + count: 1 + - models: [ "H200 NVL", "H200-SXM5"] + allowedGeometries: + - + - name: 1g.18gb + core: 14 + memory: 18432 + count: 7 + - + - name: 1g.18gb + core: 14 + memory: 18432 + count: 1 + - name: 2g.35gb + core: 28 + memory: 35840 + count: 3 + - + - name: 3g.71gb + core: 42 + memory: 72704 + count: 2 + - + - name: 7g.141gb + core: 100 + memory: 144384 + count: 1 + - models: [ "B200" ] + allowedGeometries: + - + - name: 1g.23gb + core: 14 + memory: 23552 + count: 7 + - + - name: 1g.23gb + core: 14 + memory: 23552 + count: 1 + - name: 2g.45gb + core: 28 + memory: 46080 + count: 3 + - + - name: 3g.90gb + core: 42 + memory: 92160 + count: 2 + - + - name: 7g.180gb + core: 100 + memory: 184320 + count: 1 + cambricon: + resourceCountName: {{ .Values.mluResourceName }} + resourceMemoryName: {{ .Values.mluResourceMem }} + resourceCoreName: {{ .Values.mluResourceCores }} + hygon: + resourceCountName: {{ .Values.dcuResourceName }} + resourceMemoryName: {{ .Values.dcuResourceMem }} + resourceCoreName: {{ .Values.dcuResourceCores }} + memoryFactor: 1 + metax: + resourceCountName: "metax-tech.com/gpu" + resourceVCountName: {{ .Values.metaxResourceName }} + resourceVMemoryName: {{ .Values.metaxResourceMem }} + resourceVCoreName: {{ .Values.metaxResourceCore }} + sgpuTopologyAware: {{ .Values.metaxsGPUTopologyAware }} + enflame: + resourceNameGCU: "enflame.com/gcu" + resourceNameVGCU: {{ .Values.enflameResourceNameVGCU }} + resourceNameVGCUPercentage: {{ .Values.enflameResourceNameVGCUPercentage }} + mthreads: + resourceCountName: "mthreads.com/vgpu" + resourceMemoryName: "mthreads.com/sgpu-memory" + resourceCoreName: "mthreads.com/sgpu-core" + iluvatars: + - chipName: MR-V100 + commonWord: MR-V100 + resourceCountName: iluvatar.ai/MR-V100-vgpu + resourceMemoryName: iluvatar.ai/MR-V100.vMem + resourceCoreName: iluvatar.ai/MR-V100.vCore + - chipName: MR-V50 + commonWord: MR-V50 + resourceCountName: iluvatar.ai/MR-V50-vgpu + resourceMemoryName: iluvatar.ai/MR-V50.vMem + resourceCoreName: iluvatar.ai/MR-V50.vCore + - chipName: BI-V150 + commonWord: BI-V150 + resourceCountName: iluvatar.ai/BI-V150-vgpu + resourceMemoryName: iluvatar.ai/BI-V150.vMem + resourceCoreName: iluvatar.ai/BI-V150.vCore + - chipName: BI-V100 + commonWord: BI-V100 + resourceCountName: iluvatar.ai/BI-V100-vgpu + resourceMemoryName: iluvatar.ai/BI-V100.vMem + resourceCoreName: iluvatar.ai/BI-V100.vCore + kunlun: + resourceCountName: {{ .Values.kunlunResourceName }} + resourceVCountName: {{ .Values.kunlunResourceVCountName }} + resourceVMemoryName: {{ .Values.kunlunResourceVMemoryName }} + awsneuron: + resourceCountName: "aws.amazon.com/neuron" + resourceCoreName: "aws.amazon.com/neuroncore" + amd: + resourceCountName: "amd.com/gpu" + vnpus: + - chipName: 910A + commonWord: Ascend910A + resourceName: huawei.com/Ascend910A + resourceMemoryName: huawei.com/Ascend910A-memory + memoryAllocatable: 32768 + memoryCapacity: 32768 + memoryFactor: 1 + aiCore: 30 + templates: + - name: vir02 + memory: 2184 + aiCore: 2 + - name: vir04 + memory: 4369 + aiCore: 4 + - name: vir08 + memory: 8738 + aiCore: 8 + - name: vir16 + memory: 17476 + aiCore: 16 + - chipName: 910B2 + commonWord: Ascend910B2 + resourceName: huawei.com/Ascend910B2 + resourceMemoryName: huawei.com/Ascend910B2-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + memoryFactor: 1 + aiCore: 24 + aiCPU: 6 + templates: + - name: vir03_1c_8g + memory: 8192 + aiCore: 3 + aiCPU: 1 + - name: vir06_1c_16g + memory: 16384 + aiCore: 6 + aiCPU: 1 + - name: vir12_3c_32g + memory: 32768 + aiCore: 12 + aiCPU: 3 + - chipName: 910B3 + commonWord: Ascend910B3 + resourceName: huawei.com/Ascend910B3 + resourceMemoryName: huawei.com/Ascend910B3-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + memoryFactor: 1 + aiCore: 20 + aiCPU: 7 + templates: + - name: vir05_1c_16g + memory: 16384 + aiCore: 5 + aiCPU: 1 + - name: vir10_3c_32g + memory: 32768 + aiCore: 10 + aiCPU: 3 + - chipName: 910B4-1 + commonWord: Ascend910B4-1 + resourceName: huawei.com/Ascend910B4-1 + resourceMemoryName: huawei.com/Ascend910B4-1-memory + memoryAllocatable: 65536 + memoryCapacity: 65536 + memoryFactor: 1 + aiCore: 20 + aiCPU: 7 + templates: + # NOTE: Names of vnpu template for 910B4-1 are fixed by Ascend runtime and must not be changed. + # The memory is used for scheduling so the correct values must be set. + # Template vir05_1c_8g actually provides 16GB memory, + - name: vir05_1c_8g + memory: 16384 + aiCore: 5 + aiCPU: 1 + # Template vir10_3c_16g actually provides 32GB memory + - name: vir10_3c_16g + memory: 32768 + aiCore: 10 + aiCPU: 3 + - chipName: 910B4 + commonWord: Ascend910B4 + resourceName: huawei.com/Ascend910B4 + resourceMemoryName: huawei.com/Ascend910B4-memory + memoryAllocatable: 32768 + memoryCapacity: 32768 + memoryFactor: 1 + aiCore: 20 + aiCPU: 7 + templates: + - name: vir05_1c_8g + memory: 8192 + aiCore: 5 + aiCPU: 1 + - name: vir10_3c_16g + memory: 16384 + aiCore: 10 + aiCPU: 3 + - chipName: 310P3 + commonWord: Ascend310P + resourceName: huawei.com/Ascend310P + resourceMemoryName: huawei.com/Ascend310P-memory + memoryAllocatable: 21527 + memoryCapacity: 24576 + memoryFactor: 1 + aiCore: 8 + aiCPU: 7 + templates: + - name: vir01 + memory: 3072 + aiCore: 1 + aiCPU: 1 + - name: vir02 + memory: 6144 + aiCore: 2 + aiCPU: 2 + - name: vir04 + memory: 12288 + aiCore: 4 + aiCPU: 4 + {{ end }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml new file mode 100644 index 00000000..b089ae82 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml @@ -0,0 +1,30 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +rules: + - apiGroups: + - admissionregistration.k8s.io + resources: + #- validatingwebhookconfigurations + - mutatingwebhookconfigurations + verbs: + - get + - update +{{- if .Values.podSecurityPolicy.enabled }} + - apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ include "hami-vgpu.fullname" . }}-admission +{{- end }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml new file mode 100644 index 00000000..64f01ecf --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml @@ -0,0 +1,22 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami-vgpu.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.fullname" . }}-admission + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml new file mode 100644 index 00000000..400168a7 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml @@ -0,0 +1,70 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission-create + namespace: {{ include "hami-vgpu.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +spec: + {{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 + {{- end }} + template: + metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission-create + {{- if .Values.scheduler.patch.podAnnotations }} + annotations: {{ toYaml .Values.scheduler.patch.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "hami-vgpu.labels" . | nindent 8 }} + app.kubernetes.io/component: admission-webhook + hami.io/webhook: ignore + spec: + {{- if .Values.scheduler.patch.priorityClassName }} + priorityClassName: {{ .Values.scheduler.patch.priorityClassName }} + {{- end }} + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + {{- include "hami.scheduler.patch.new.imagePullSecrets" . | nindent 6 }} + {{- else }} + {{- include "hami.scheduler.patch.imagePullSecrets" . | nindent 6 }} + {{- end }} + containers: + - name: create + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + image: {{ include "hami.scheduler.patch.new.image" . }} + imagePullPolicy: {{ .Values.scheduler.patch.imageNew.pullPolicy }} + {{- else }} + image: {{ include "hami.scheduler.patch.image" . }} + imagePullPolicy: {{ .Values.scheduler.patch.image.pullPolicy }} + {{- end }} + args: + - create + - --cert-name=tls.crt + - --key-name=tls.key + {{- if .Values.scheduler.admissionWebhook.customURL.enabled }} + - --host={{ printf "%s.%s.svc,127.0.0.1,%s" (include "hami-vgpu.scheduler" .) (include "hami-vgpu.namespace" .) .Values.scheduler.admissionWebhook.customURL.host}} + {{- else }} + - --host={{ printf "%s.%s.svc,127.0.0.1" (include "hami-vgpu.scheduler" .) (include "hami-vgpu.namespace" .) }} + {{- end }} + - --namespace={{ include "hami-vgpu.namespace" . }} + - --secret-name={{ include "hami-vgpu.scheduler.tls" . }} + restartPolicy: OnFailure + serviceAccountName: {{ include "hami-vgpu.fullname" . }}-admission + {{- if .Values.scheduler.patch.nodeSelector }} + nodeSelector: {{ toYaml .Values.scheduler.patch.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.scheduler.patch.tolerations }} + tolerations: {{ toYaml .Values.scheduler.patch.tolerations | nindent 8 }} + {{- end }} + securityContext: + runAsNonRoot: true + runAsUser: {{ .Values.scheduler.patch.runAsUser }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml new file mode 100644 index 00000000..71e97f6b --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml @@ -0,0 +1,65 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission-patch + namespace: {{ include "hami-vgpu.namespace" . }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +spec: + {{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 + {{- end }} + template: + metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission-patch + {{- if .Values.scheduler.patch.podAnnotations }} + annotations: {{ toYaml .Values.scheduler.patch.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "hami-vgpu.labels" . | nindent 8 }} + app.kubernetes.io/component: admission-webhook + hami.io/webhook: ignore + spec: + {{- if .Values.scheduler.patch.priorityClassName }} + priorityClassName: {{ .Values.scheduler.patch.priorityClassName }} + {{- end }} + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + {{- include "hami.scheduler.patch.new.imagePullSecrets" . | nindent 6 }} + {{- else }} + {{- include "hami.scheduler.patch.imagePullSecrets" . | nindent 6 }} + {{- end }} + containers: + - name: patch + {{- if ge (regexReplaceAll "[^0-9]" .Capabilities.KubeVersion.Minor "" | int) 22 }} + image: {{ include "hami.scheduler.patch.new.image" . }} + imagePullPolicy: {{ .Values.scheduler.patch.imageNew.pullPolicy }} + {{- else }} + image: {{ include "hami.scheduler.patch.image" . }} + imagePullPolicy: {{ .Values.scheduler.patch.image.pullPolicy }} + {{- end }} + args: + - patch + - --webhook-name={{ include "hami-vgpu.scheduler.webhook" . }} + - --namespace={{ include "hami-vgpu.namespace" . }} + - --patch-validating=false + - --secret-name={{ include "hami-vgpu.scheduler.tls" . }} + restartPolicy: OnFailure + serviceAccountName: {{ include "hami-vgpu.fullname" . }}-admission + {{- if .Values.scheduler.patch.nodeSelector }} + nodeSelector: {{ toYaml .Values.scheduler.patch.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.scheduler.patch.tolerations }} + tolerations: {{ toYaml .Values.scheduler.patch.tolerations | nindent 8 }} + {{- end }} + securityContext: + runAsNonRoot: true + runAsUser: {{ .Values.scheduler.patch.runAsUser }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml new file mode 100644 index 00000000..a48270e7 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml @@ -0,0 +1,40 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if .Values.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +spec: + allowPrivilegeEscalation: false + fsGroup: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + requiredDropCapabilities: + - ALL + runAsUser: + rule: MustRunAsNonRoot + seLinux: + rule: RunAsAny + supplementalGroups: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + volumes: + - configMap + - emptyDir + - projected + - secret + - downwardAPI +{{- end }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml new file mode 100644 index 00000000..74e45681 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + namespace: {{ include "hami-vgpu.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +rules: + - apiGroups: + - "" + resources: + - secrets + verbs: + - get + - create +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml new file mode 100644 index 00000000..32da5ba4 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + namespace: {{ include "hami-vgpu.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "hami-vgpu.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.fullname" . }}-admission + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml new file mode 100644 index 00000000..d2eb41de --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml @@ -0,0 +1,15 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) }} +{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami-vgpu.fullname" . }}-admission + namespace: {{ include "hami-vgpu.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "hami-vgpu.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook +{{- end }} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/role.yaml b/packages/system/hami/charts/hami/templates/scheduler/role.yaml new file mode 100644 index 00000000..6e681967 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/role.yaml @@ -0,0 +1,14 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +rules: + - apiGroups: ["coordination.k8s.io"] + resources: ["leases"] + verbs: ["create", "list", "watch", "get", "update", "patch"] +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml new file mode 100644 index 00000000..934f8223 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml @@ -0,0 +1,33 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "hami-vgpu.scheduler" . }} +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +--- +{{- if .Values.mockDevicePlugin.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "hami-vgpu.mock-device-plugin" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "hami-vgpu.mock-device-plugin" . }} +subjects: + - kind: ServiceAccount + name: {{ include "hami-vgpu.mock-device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end -}} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/service.yaml b/packages/system/hami/charts/hami/templates/scheduler/service.yaml new file mode 100644 index 00000000..3e18bc98 --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/service.yaml @@ -0,0 +1,36 @@ +{{- if not .Values.dra.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.labels" . | nindent 4 }} + {{- if .Values.scheduler.service.labels }} + {{ toYaml .Values.scheduler.service.labels | indent 4 }} + {{- end }} + {{- if .Values.scheduler.service.annotations }} + annotations: {{ toYaml .Values.scheduler.service.annotations | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.scheduler.service.type | default "NodePort" }} # Default type is NodePort + ports: + - name: http + port: {{ .Values.scheduler.service.httpPort | default 443 }} # Default HTTP port is 443 + targetPort: {{ .Values.scheduler.service.httpTargetPort | default 443 }} + {{- if eq (.Values.scheduler.service.type | default "NodePort") "NodePort" }} # If type is NodePort, set nodePort + nodePort: {{ .Values.scheduler.service.schedulerPort | default 31998 }} + {{- end }} + protocol: TCP + - name: monitor + port: {{ .Values.scheduler.service.monitorPort | default 31993 }} # Default monitoring port is 31993 + targetPort: {{ .Values.scheduler.service.monitorTargetPort | default 9395 }} + {{- if eq (.Values.scheduler.service.type | default "NodePort") "NodePort" }} # If type is NodePort, set nodePort + nodePort: {{ .Values.scheduler.service.monitorPort | default 31993 }} + {{- end }} + protocol: TCP + selector: + app.kubernetes.io/component: hami-scheduler + {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml b/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml new file mode 100644 index 00000000..929bf59a --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml @@ -0,0 +1,18 @@ +{{- if not .Values.dra.enabled -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + labels: + app.kubernetes.io/component: "hami-scheduler" + {{- include "hami-vgpu.labels" . | nindent 4 }} +--- +{{- if .Values.mockDevicePlugin.enabled }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "hami-vgpu.mock-device-plugin" . }} + namespace: {{ include "hami-vgpu.namespace" . }} +{{- end -}} +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml new file mode 100644 index 00000000..148feb5c --- /dev/null +++ b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml @@ -0,0 +1,57 @@ +{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + {{- if .Values.scheduler.certManager.enabled }} + annotations: + cert-manager.io/inject-ca-from: {{ include "hami-vgpu.namespace" . }}/{{ include "hami-vgpu.scheduler" . }}-serving-cert + {{- end }} + name: {{ include "hami-vgpu.scheduler.webhook" . }} +webhooks: + - admissionReviewVersions: + - v1beta1 + clientConfig: + {{- if .Values.scheduler.admissionWebhook.customURL.enabled }} + url: https://{{ .Values.scheduler.admissionWebhook.customURL.host}}:{{.Values.scheduler.admissionWebhook.customURL.port}}{{.Values.scheduler.admissionWebhook.customURL.path}} + {{- else }} + service: + name: {{ include "hami-vgpu.scheduler" . }} + namespace: {{ include "hami-vgpu.namespace" . }} + path: /webhook + port: {{ .Values.scheduler.service.httpPort }} + {{- end }} + failurePolicy: {{ .Values.scheduler.admissionWebhook.failurePolicy }} + matchPolicy: Equivalent + name: vgpu.hami.io + namespaceSelector: + matchExpressions: + - key: hami.io/webhook + operator: NotIn + values: + - ignore + {{- if .Values.scheduler.admissionWebhook.whitelistNamespaces }} + - key: kubernetes.io/metadata.name + operator: NotIn + values: + {{- toYaml .Values.scheduler.admissionWebhook.whitelistNamespaces | nindent 10 }} + {{- end }} + objectSelector: + matchExpressions: + - key: hami.io/webhook + operator: NotIn + values: + - ignore + reinvocationPolicy: {{ .Values.scheduler.admissionWebhook.reinvocationPolicy }} + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + resources: + - pods + scope: '*' + sideEffects: None + timeoutSeconds: 10 +{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/values.yaml b/packages/system/hami/charts/hami/values.yaml new file mode 100644 index 00000000..9fbeca70 --- /dev/null +++ b/packages/system/hami/charts/hami/values.yaml @@ -0,0 +1,476 @@ +## @section Global configuration +## @param global.imageRegistry Global Docker image registry +## @param global.imagePullSecrets Global Docker image pull secrets +global: + ## @param global.imageRegistry Global Docker image registry + imageRegistry: "" + ## E.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## @param global.imagePullSecrets Global Docker image pull secrets + imagePullSecrets: [] + imageTag: "v2.8.1" + gpuHookPath: /usr/local + labels: {} + annotations: {} + managedNodeSelectorEnable: false + managedNodeSelector: + usage: "gpu" + +nameOverride: "" +fullnameOverride: "" +namespaceOverride: "" + +#Nvidia GPU Parameters +resourceName: "nvidia.com/gpu" +resourceMem: "nvidia.com/gpumem" +resourceMemPercentage: "nvidia.com/gpumem-percentage" +resourceCores: "nvidia.com/gpucores" +resourcePriority: "nvidia.com/priority" + +#MLU Parameters +mluResourceName: "cambricon.com/vmlu" +mluResourceMem: "cambricon.com/mlu.smlu.vmemory" +mluResourceCores: "cambricon.com/mlu.smlu.vcore" + +#Hygon DCU Parameters +dcuResourceName: "hygon.com/dcunum" +dcuResourceMem: "hygon.com/dcumem" +dcuResourceCores: "hygon.com/dcucores" + +#Metax sGPU Parameters +metaxResourceName: "metax-tech.com/sgpu" +metaxResourceCore: "metax-tech.com/vcore" +metaxResourceMem: "metax-tech.com/vmemory" +metaxsGPUTopologyAware: "false" + +#Enflame VGCU Parameters +enflameResourceNameVGCU: "enflame.com/vgcu" +enflameResourceNameVGCUPercentage: "enflame.com/vgcu-percentage" + +#Kunlun XPU Parameters +kunlunResourceName: "kunlunxin.com/xpu" +kunlunResourceVCountName: "kunlunxin.com/vxpu" +kunlunResourceVMemoryName: "kunlunxin.com/vxpu-memory" + +schedulerName: "hami-scheduler" + +podSecurityPolicy: + enabled: false + +scheduler: + # @param nodeName defines the node name and the nvidia-vgpu-scheduler-scheduler will schedule to the node. + # if we install the nvidia-vgpu-scheduler-scheduler as default scheduler, we need to remove the k8s default + # scheduler pod from the cluster first, we must specify node name to skip the schedule workflow. + nodeName: "" + #nodeLabelSelector: + # "gpu": "on" + overwriteEnv: "false" + defaultSchedulerPolicy: + nodeSchedulerPolicy: binpack + gpuSchedulerPolicy: spread + metricsBindAddress: ":9395" + # If set to false, When Pod.Spec.SchedulerName equals to the const DefaultSchedulerName in k8s.io/api/core/v1 package, webhook will not overwrite it + forceOverwriteDefaultScheduler: true + livenessProbe: false + leaderElect: true + # when leaderElect is true, replicas is available, otherwise replicas is 1. + replicas: 1 + kubeScheduler: + # @param enabled indicate whether to run kube-scheduler container in the scheduler pod, it's true by default. + enabled: true + ## @param image.registry kube scheduler image registry + ## @param image.repository kube scheduler image repository + ## @param image.tag kube scheduler image tag (immutable tags are recommended) + ## @param image.pullPolicy kube scheduler image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + image: + registry: "registry.cn-hangzhou.aliyuncs.com" + repository: "google_containers/kube-scheduler" + tag: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + resources: {} + # If you do want to specify resources, uncomment the following lines, adjust them as necessary. + # and remove the curly braces after 'resources:'. +# limits: +# cpu: 1000m +# memory: 1000Mi +# requests: +# cpu: 100m +# memory: 100Mi + extraNewArgs: + - --config=/config/config.yaml + - -v=4 + extraArgs: + - --policy-config-file=/config/config.json + - -v=4 + extender: + ## @param image.registry scheduler extender image registry + ## @param image.repository scheduler extender image repository + ## @param image.tag scheduler extender image tag (immutable tags are recommended) + ## @param image.pullPolicy scheduler extender image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + image: + registry: "docker.io" + repository: "projecthami/hami" + tag: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + resources: {} + # If you do want to specify resources, uncomment the following lines, adjust them as necessary, + # and remove the curly braces after 'resources:'. +# limits: +# cpu: 1000m +# memory: 1000Mi +# requests: +# cpu: 100m +# memory: 100Mi + extraArgs: + - --debug + - -v=4 + nodeLockExpire: "5m" + podAnnotations: {} + tolerations: [] + #serviceAccountName: "hami-vgpu-scheduler-sa" + admissionWebhook: + # If set to false, the admission webhook is not installed and any pods that should use HAMi must be + # configured to use the right 'schedulerName' and other device-specific configurations. + enabled: true + customURL: + enabled: false + # must be an endpoint using https. + # should generate host certs here + host: 127.0.0.1 # hostname or ip, can be your node'IP if you want to use https://:/ + port: 31998 + path: /webhook + whitelistNamespaces: + # Specify the namespaces that the webhook will not be applied to. + # - default + # - kube-system + # - istio-system + reinvocationPolicy: Never + failurePolicy: Ignore + ## TLS Certificate Option 1: Use cert-manager to generate self-signed certificate. + ## If enabled, always takes precedence over options 2. + certManager: + enabled: false + ## TLS Certificate Option 2: Use kube-webhook-certgen to generate self-signed certificate. + ## If true and certManager.enabled is false, Helm will automatically create a self-signed cert and secret for you. + patch: + enabled: true + ## @param image.registry scheduler extender image registry + ## @param image.repository scheduler extender image repository + ## @param image.tag scheduler extender image tag (immutable tags are recommended) + ## @param image.pullPolicy scheduler extender image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + image: + registry: "docker.io" + repository: "jettech/kube-webhook-certgen" + tag: "v1.5.2" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param image.registry scheduler extender image registry + ## @param image.repository scheduler extender image repository + ## @param image.tag scheduler extender image tag (immutable tags are recommended) + ## @param image.pullPolicy scheduler extender image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + imageNew: + registry: "docker.io" + repository: "liangjw/kube-webhook-certgen" + tag: "v1.1.1" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + priorityClassName: "" + podAnnotations: {} + nodeSelector: {} + tolerations: [] + runAsUser: 2000 + service: + type: NodePort # Default type is NodePort, can be changed to ClusterIP + httpPort: 443 # HTTP port + schedulerPort: 31998 # NodePort for HTTP + monitorPort: 31993 # Monitoring port + monitorTargetPort: 9395 + httpTargetPort: 443 + labels: {} + annotations: {} + +devicePlugin: + enabled: true + gpuOperatorToolkitReady: + enabled: false + hostPath: "/run/nvidia/validations" + ## @param image.registry devicePlugin image registry + ## @param image.repository devicePlugin image repository + ## @param image.tag devicePlugin image tag (immutable tags are recommended) + ## @param image.pullPolicy devicePlugin image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + image: + registry: "docker.io" + repository: "projecthami/hami" + tag: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + monitor: + ## @param image.registry monitor image registry + ## @param image.repository monitor image repository + ## @param image.tag monitor image tag (immutable tags are recommended) + ## @param image.pullPolicy monitor image pull policy + ## @param image.pullSecrets Specify docker-registry secret names as an array + image: + registry: "docker.io" + repository: "projecthami/hami" + tag: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ctrPath: /usr/local/vgpu/containers + resyncInterval: "5m" + extraArgs: + - -v=4 + extraEnvs: {} + resources: {} + # If you do want to specify resources, uncomment the following lines, adjust them as necessary. + # and remove the curly braces after 'resources:'. +# limits: +# cpu: 1000m +# memory: 1000Mi +# requests: +# cpu: 100m +# memory: 100Mi + + deviceSplitCount: 10 + deviceMemoryScaling: 1 + deviceCoreScaling: 1 + # Node configuration for device plugin, Priority: externalConfigName > config > default config + nodeConfiguration: + # If you want to use a custom config.json, you can set the content here. + # If this is set, it will override the default config.json(An example is as follows). + config: | + { + "nodeconfig": [ + { + "name": "your-node-name", + "operatingmode": "hami-core", + "devicememoryscaling": 1, + "devicesplitcount": 10, + "migstrategy": "none", + "filterdevices": { + "uuid": [], + "index": [] + } + } + ] + } + # If you want to use an existing ConfigMap, you can set the name here. + # If this is set, the chart will not create the ConfigMap and will use the existing one. + externalConfigName: "" + # The runtime class name to be used by the device plugin, and added to the pod.spec.runtimeClassName of applications utilizing NVIDIA GPUs + runtimeClassName: "" + # Whether to create runtime class, name comes from runtimeClassName when it is set + createRuntimeClass: false + migStrategy: "none" + disablecorelimit: "false" + passDeviceSpecsEnabled: false + deviceListStrategy: "envvar" + nvidiaHookPath: null + nvidiaDriverRoot: null + gdrcopyEnabled: null + gdsEnabled: null + mofedEnabled: null + + extraArgs: + - -v=4 + extraEnvs: {} + service: + type: NodePort # Default type is NodePort, can be changed to ClusterIP + httpPort: 31992 + labels: {} + annotations: {} + + pluginPath: /var/lib/kubelet/device-plugins + libPath: /usr/local/vgpu + + podAnnotations: {} + nvidiaNodeSelector: + gpu: "on" + tolerations: [] + # The updateStrategy for DevicePlugin DaemonSet. + # If you want to update the DaemonSet by manual, set type as "OnDelete". + # We recommend use OnDelete update strategy because DevicePlugin pod restart will cause business pod restart, this behavior is destructive. + # Otherwise, you can use RollingUpdate update strategy to rolling update DevicePlugin pod. + updateStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 1 + + resources: {} + # If you do want to specify resources, uncomment the following lines, adjust them as necessary. + # and remove the curly braces after 'resources:'. +# limits: +# cpu: 1000m +# memory: 1000Mi +# requests: +# cpu: 100m +# memory: 100Mi + +mockDevicePlugin: + enabled: false + image: + registry: "docker.io" + repository: "projecthami/mock-device-plugin" + tag: "1.0.1" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] +# If this option is enabled, the DRA will be installed and the scheduler extender will not be installed. +dra: + enabled: false + +# Configuration for the hami-dra subchart, which includes DRA drivers. +# This is part of config for DRA, please refer to the DRA documentation for more details. +hami-dra: + monitor: + enabled: true + drivers: + nvidia: + enabled: true + # If you are using gpu driver on host, you need to set this to false + containerDriver: true + image: + repository: projecthami/k8s-dra-driver + tag: "v0.0.1-dev" + +devices: + amd: + customresources: + - amd.com/gpu + - amd.com/gpu-memory + awsneuron: + customresources: + - aws.amazon.com/neuron + - aws.amazon.com/neuroncore + kunlun: + enabled: true + customresources: + - kunlunxin.com/xpu + - kunlunxin.com/vxpu + - kunlunxin.com/vxpu-memory + enflame: + enabled: true + customresources: + - enflame.com/vgcu + - enflame.com/vgcu-percentage + - enflame.com/gcu + mthreads: + enabled: true + customresources: + - mthreads.com/vgpu + nvidia: + gpuCorePolicy: default + libCudaLogLevel: 1 + ascend: + enabled: false + image: "" + imagePullPolicy: IfNotPresent + extraArgs: [] + nodeSelector: + ascend: "on" + tolerations: [] + customresources: + - huawei.com/Ascend910A + - huawei.com/Ascend910A-memory + - huawei.com/Ascend910B2 + - huawei.com/Ascend910B2-memory + - huawei.com/Ascend910B3 + - huawei.com/Ascend910B3-memory + - huawei.com/Ascend910B4 + - huawei.com/Ascend910B4-memory + - huawei.com/Ascend910B4-1 + - huawei.com/Ascend910B4-1-memory + - huawei.com/Ascend310P + - huawei.com/Ascend310P-memory + iluvatar: + enabled: false + customresources: + - iluvatar.ai/BI-V100-vgpu + - iluvatar.ai/BI-V100.vCore + - iluvatar.ai/BI-V100.vMem + - iluvatar.ai/BI-V150-vgpu + - iluvatar.ai/BI-V150.vCore + - iluvatar.ai/BI-V150.vMem + - iluvatar.ai/MR-V100-vgpu + - iluvatar.ai/MR-V100.vCore + - iluvatar.ai/MR-V100.vMem + - iluvatar.ai/MR-V50-vgpu + - iluvatar.ai/MR-V50.vCore + - iluvatar.ai/MR-V50.vMem diff --git a/packages/system/hami/values.yaml b/packages/system/hami/values.yaml new file mode 100644 index 00000000..1155e2cb --- /dev/null +++ b/packages/system/hami/values.yaml @@ -0,0 +1,8 @@ +hami: + devicePlugin: + runtimeClassName: nvidia + nodeConfiguration: + config: | + { + "nodeconfig": [] + } From a3e2fbd742d0c9f8bf6a255836913f080f42b826 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 22 Apr 2026 13:25:23 +0300 Subject: [PATCH 02/35] feat(kubernetes): integrate HAMi as optional addon Add HAMi HelmRelease to the kubernetes app as a toggleable addon. When enabled, GPU Operator's built-in device plugin is automatically disabled via a values merge to avoid conflicts with HAMi's own device plugin. The HelmRelease fails fast if GPU Operator is not enabled, since HAMi depends on it for driver management and container toolkit. Assisted-By: Claude Signed-off-by: Arsolitt --- .../templates/helmreleases/gpu-operator.yaml | 13 ++++- .../templates/helmreleases/hami.yaml | 49 +++++++++++++++++++ packages/apps/kubernetes/values.schema.json | 23 +++++++++ packages/apps/kubernetes/values.yaml | 8 +++ 4 files changed, 92 insertions(+), 1 deletion(-) create mode 100644 packages/apps/kubernetes/templates/helmreleases/hami.yaml diff --git a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml index 5ef48912..995aa430 100644 --- a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml @@ -1,3 +1,11 @@ +{{- define "cozystack.defaultGpuOperatorValues" -}} +{{- if and (hasKey .Values.addons "hami") .Values.addons.hami.enabled }} +gpu-operator: + devicePlugin: + enabled: false +{{- end }} +{{- end }} + {{- if .Values.addons.gpuOperator.enabled }} apiVersion: helm.toolkit.fluxcd.io/v2 kind: HelmRelease @@ -29,7 +37,10 @@ spec: force: true remediation: retries: -1 - {{- with .Values.addons.gpuOperator.valuesOverride }} + {{- $defaults := fromYaml (include "cozystack.defaultGpuOperatorValues" .) }} + {{- $overrides := deepCopy (default (dict) .Values.addons.gpuOperator.valuesOverride) }} + {{- $merged := mergeOverwrite (default (dict) $defaults) $overrides }} + {{- with $merged }} values: {{- toYaml . | nindent 4 }} {{- end }} diff --git a/packages/apps/kubernetes/templates/helmreleases/hami.yaml b/packages/apps/kubernetes/templates/helmreleases/hami.yaml new file mode 100644 index 00000000..1f7a5358 --- /dev/null +++ b/packages/apps/kubernetes/templates/helmreleases/hami.yaml @@ -0,0 +1,49 @@ +{{- if .Values.addons.hami.enabled }} +{{- if not .Values.addons.gpuOperator.enabled }} +{{- fail "addons.hami requires addons.gpuOperator to be enabled" }} +{{- end }} +apiVersion: helm.toolkit.fluxcd.io/v2 +kind: HelmRelease +metadata: + name: {{ .Release.Name }}-hami + labels: + cozystack.io/repository: system + cozystack.io/target-cluster-name: {{ .Release.Name }} + sharding.fluxcd.io/key: tenants +spec: + releaseName: hami + chartRef: + kind: ExternalArtifact + name: cozystack-kubernetes-application-kubevirt-kubernetes-hami + namespace: cozy-system + kubeConfig: + secretRef: + name: {{ .Release.Name }}-admin-kubeconfig + key: super-admin.svc + targetNamespace: cozy-hami + storageNamespace: cozy-hami + interval: 5m + timeout: 10m + install: + createNamespace: true + remediation: + retries: -1 + upgrade: + force: true + remediation: + retries: -1 + {{- with .Values.addons.hami.valuesOverride }} + values: + {{- toYaml . | nindent 4 }} + {{- end }} + + dependsOn: + {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }} + - name: {{ .Release.Name }} + namespace: {{ .Release.Namespace }} + {{- end }} + - name: {{ .Release.Name }}-cilium + namespace: {{ .Release.Namespace }} + - name: {{ .Release.Name }}-gpu-operator + namespace: {{ .Release.Namespace }} +{{- end }} diff --git a/packages/apps/kubernetes/values.schema.json b/packages/apps/kubernetes/values.schema.json index 1beeff9c..3d7a17dd 100644 --- a/packages/apps/kubernetes/values.schema.json +++ b/packages/apps/kubernetes/values.schema.json @@ -149,6 +149,7 @@ "fluxcd", "gatewayAPI", "gpuOperator", + "hami", "ingressNginx", "monitoringAgents", "velero", @@ -268,6 +269,28 @@ } } }, + "hami": { + "description": "HAMi GPU virtualization middleware. Enables fractional GPU sharing (memory and compute isolation) for workloads. Requires GPU Operator. Note: workload containers must use glibc < 2.34 (not musl/Alpine) for full compute isolation.", + "type": "object", + "default": {}, + "required": [ + "enabled", + "valuesOverride" + ], + "properties": { + "enabled": { + "description": "Enable HAMi.", + "type": "boolean", + "default": false + }, + "valuesOverride": { + "description": "Custom Helm values overrides.", + "type": "object", + "default": {}, + "x-kubernetes-preserve-unknown-fields": true + } + } + }, "ingressNginx": { "description": "Ingress-NGINX controller.", "type": "object", diff --git a/packages/apps/kubernetes/values.yaml b/packages/apps/kubernetes/values.yaml index a67b5d69..f601b979 100644 --- a/packages/apps/kubernetes/values.yaml +++ b/packages/apps/kubernetes/values.yaml @@ -94,6 +94,10 @@ host: "" ## @field {bool} enabled - Enable FluxCD. ## @field {object} valuesOverride - Custom Helm values overrides. +## @typedef {struct} HAMiAddon - HAMi GPU virtualization middleware. +## @field {bool} enabled - Enable HAMi (requires GPU Operator). +## @field {object} valuesOverride - Custom Helm values overrides. + ## @typedef {struct} MonitoringAgentsAddon - Monitoring agents (Fluent Bit, VMAgents). ## @field {bool} enabled - Enable monitoring agents. ## @field {object} valuesOverride - Custom Helm values overrides. @@ -114,6 +118,7 @@ host: "" ## @field {GatewayAPIAddon} gatewayAPI - Gateway API addon. ## @field {IngressNginxAddon} ingressNginx - Ingress-NGINX controller. ## @field {GPUOperatorAddon} gpuOperator - NVIDIA GPU Operator. +## @field {HAMiAddon} hami - HAMi GPU virtualization middleware. ## @field {FluxCDAddon} fluxcd - FluxCD GitOps operator. ## @field {MonitoringAgentsAddon} monitoringAgents - Monitoring agents. ## @field {VerticalPodAutoscalerAddon} verticalPodAutoscaler - Vertical Pod Autoscaler. @@ -137,6 +142,9 @@ addons: gpuOperator: enabled: false valuesOverride: {} + hami: + enabled: false + valuesOverride: {} fluxcd: enabled: false valuesOverride: {} From 273eb7811a36fb69141d80360705f081a3276194 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 22 Apr 2026 13:25:29 +0300 Subject: [PATCH 03/35] docs(hami): document glibc < 2.34 limitation and upstream issues HAMi-core relies on _dl_sym (private glibc symbol removed in 2.34) for CUDA interception. This breaks compute isolation on modern container images using Ubuntu 22.04+ and makes Alpine/musl completely incompatible. Include upstream issue references and a compatibility matrix so users can make informed decisions about base image selection. Assisted-By: Claude Signed-off-by: Arsolitt --- packages/system/hami/README.md | 81 ++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) create mode 100644 packages/system/hami/README.md diff --git a/packages/system/hami/README.md b/packages/system/hami/README.md new file mode 100644 index 00000000..283f9e80 --- /dev/null +++ b/packages/system/hami/README.md @@ -0,0 +1,81 @@ +# HAMi — GPU Virtualization Middleware + +[HAMi](https://github.com/Project-HAMi/HAMi) (Heterogeneous AI Computing Virtualization Middleware) is a CNCF Sandbox project that enables fractional GPU sharing in Kubernetes. It allows workloads to request specific amounts of GPU memory and compute cores instead of claiming entire GPUs. + +## Architecture + +HAMi consists of four components: + +- **MutatingWebhook** — intercepts pod creation, injects `schedulerName: hami-scheduler` +- **Scheduler Extender** — extends kube-scheduler with GPU-aware Filter and Bind logic +- **Device Plugin** (DaemonSet) — registers vGPU resources via the Kubernetes Device Plugin API +- **HAMi-core** (`libvgpu.so`) — `LD_PRELOAD` library injected into workload containers, intercepts CUDA API calls to enforce memory and compute isolation + +## Prerequisites + +- GPU Operator must be enabled (`addons.gpuOperator.enabled: true`) +- NVIDIA driver >= 440 on host nodes +- nvidia-container-toolkit configured as the default container runtime +- GPU nodes labeled with `gpu=on` + +## Known Limitations + +### glibc < 2.34 requirement for workload containers + +HAMi-core uses `LD_PRELOAD` to intercept `dlsym()` for CUDA symbol resolution. The fallback code path relies on `_dl_sym`, a private glibc internal symbol that was removed in glibc 2.34 when libdl and libpthread were merged into libc.so. + +**This limitation affects workload containers only**, not the host OS or HAMi's own components. + +| Distribution | glibc | Result | +| --------------- | ----- | -------------------------------------------- | +| Ubuntu 18.04 | 2.27 | Full isolation (memory + compute) | +| Ubuntu 20.04 | 2.31 | Full isolation (memory + compute) | +| Ubuntu 22.04 | 2.35 | Memory isolation works, compute breaks | +| Ubuntu 24.04 | 2.39 | Both memory and compute isolation break | +| Alpine (musl) | N/A | Completely incompatible (`dlvsym` absent) | + +Most modern ML/AI base images (CUDA 12.x, PyTorch 2.x, TensorFlow 2.x) use Ubuntu 22.04+ with glibc >= 2.35, which means compute isolation will not work with these images until the upstream fix is merged. + +**Upstream tracking issues:** + +- [HAMi-core#174](https://github.com/Project-HAMi/HAMi-core/issues/174) — `_dl_sym` removal breaks HAMi-core on glibc >= 2.34 +- [HAMi#1190](https://github.com/Project-HAMi/HAMi/issues/1190) — degraded isolation across glibc versions +- [HAMi#173](https://github.com/Project-HAMi/HAMi/issues/173) — documentation incorrectly states glibc < 2.30 (actual boundary is 2.34) + +### musl libc (Alpine) incompatibility + +HAMi-core is completely incompatible with musl libc. The `dlvsym()` function used by HAMi-core is a glibc extension not available in musl. Only glibc-based container images (Debian, Ubuntu, RHEL, etc.) can use HAMi GPU isolation. + +## Usage + +Enable HAMi in your tenant Kubernetes cluster values: + +```yaml +addons: + gpuOperator: + enabled: true + hami: + enabled: true +``` + +When HAMi is enabled, GPU Operator's built-in device plugin is automatically disabled to avoid conflicts. + +### Requesting fractional GPU resources + +```yaml +resources: + limits: + nvidia.com/gpu: 1 + nvidia.com/gpumem: 3000 # 3000 MB of GPU memory + nvidia.com/gpucores: 30 # 30% of GPU compute cores +``` + +## Parameters + +| Name | Description | Default | +| --- | --- | --- | +| `hami.devicePlugin.runtimeClassName` | RuntimeClass for device plugin pods | `nvidia` | +| `hami.devicePlugin.deviceSplitCount` | Max virtual GPUs per physical GPU | `10` | +| `hami.devicePlugin.deviceMemoryScaling` | Memory overcommit factor (> 1.0 enables overcommit) | `1` | +| `hami.scheduler.defaultSchedulerPolicy.nodeSchedulerPolicy` | Node packing strategy (`binpack` or `spread`) | `binpack` | +| `hami.scheduler.defaultSchedulerPolicy.gpuSchedulerPolicy` | GPU packing strategy (`binpack` or `spread`) | `spread` | From 43035562efff34f18c3c439026fe2a233dc8d17b Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 22 Apr 2026 13:25:35 +0300 Subject: [PATCH 04/35] test(kubernetes): add helm-unittest tests for HAMi integration Cover HelmRelease rendering, gpuOperator dependency validation, ExternalArtifact chartRef, namespace targeting, dependency chain, valuesOverride passthrough, and automatic devicePlugin disable in GPU Operator when HAMi is active. Assisted-By: Claude Signed-off-by: Arsolitt --- .../tests/gpu_operator_hami_test.yaml | 80 +++++++++++ packages/apps/kubernetes/tests/hami_test.yaml | 136 ++++++++++++++++++ 2 files changed, 216 insertions(+) create mode 100644 packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml create mode 100644 packages/apps/kubernetes/tests/hami_test.yaml diff --git a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml new file mode 100644 index 00000000..33256ae6 --- /dev/null +++ b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml @@ -0,0 +1,80 @@ +suite: GPU Operator HelmRelease HAMi integration tests +templates: + - templates/helmreleases/gpu-operator.yaml +tests: + - it: should disable devicePlugin when hami is enabled + set: + addons: + gpuOperator: + enabled: true + valuesOverride: {} + hami: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.values.gpu-operator.devicePlugin.enabled + value: false + + - it: should not have values when hami is disabled and no overrides + set: + addons: + gpuOperator: + enabled: true + valuesOverride: {} + hami: + enabled: false + valuesOverride: {} + asserts: + - notExists: + path: spec.values + + - it: should allow user overrides to merge with hami defaults + set: + addons: + gpuOperator: + enabled: true + valuesOverride: + gpu-operator: + driver: + enabled: false + hami: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.values.gpu-operator.devicePlugin.enabled + value: false + - equal: + path: spec.values.gpu-operator.driver.enabled + value: false + + - it: should let user override devicePlugin back to true if needed + set: + addons: + gpuOperator: + enabled: true + valuesOverride: + gpu-operator: + devicePlugin: + enabled: true + hami: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.values.gpu-operator.devicePlugin.enabled + value: true + + - it: should not render when gpuOperator is disabled + set: + addons: + gpuOperator: + enabled: false + valuesOverride: {} + hami: + enabled: false + valuesOverride: {} + asserts: + - hasDocuments: + count: 0 diff --git a/packages/apps/kubernetes/tests/hami_test.yaml b/packages/apps/kubernetes/tests/hami_test.yaml new file mode 100644 index 00000000..e9d32236 --- /dev/null +++ b/packages/apps/kubernetes/tests/hami_test.yaml @@ -0,0 +1,136 @@ +suite: HAMi HelmRelease tests +templates: + - templates/helmreleases/hami.yaml +tests: + - it: should not render when hami is disabled + set: + addons: + hami: + enabled: false + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - hasDocuments: + count: 0 + + - it: should render HelmRelease when hami is enabled + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - hasDocuments: + count: 1 + - isKind: + of: HelmRelease + + - it: should fail when gpuOperator is not enabled + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: false + valuesOverride: {} + asserts: + - failedTemplate: + errorMessage: "addons.hami requires addons.gpuOperator to be enabled" + + - it: should have correct metadata labels + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: metadata.labels["cozystack.io/repository"] + value: system + - equal: + path: metadata.labels["sharding.fluxcd.io/key"] + value: tenants + + - it: should use ExternalArtifact chartRef + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.chartRef.kind + value: ExternalArtifact + - equal: + path: spec.chartRef.namespace + value: cozy-system + + - it: should target cozy-hami namespace + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.targetNamespace + value: cozy-hami + - equal: + path: spec.storageNamespace + value: cozy-hami + + - it: should depend on gpu-operator and cilium + release: + name: test + namespace: test-ns + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - contains: + path: spec.dependsOn + content: + name: test-cilium + namespace: test-ns + - contains: + path: spec.dependsOn + content: + name: test-gpu-operator + namespace: test-ns + + - it: should pass through valuesOverride + set: + addons: + hami: + enabled: true + valuesOverride: + hami: + devicePlugin: + deviceSplitCount: 5 + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.values.hami.devicePlugin.deviceSplitCount + value: 5 From 3c5521ee992b2dce74ff8956a6d8c581763bf640 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Thu, 23 Apr 2026 22:16:30 +0300 Subject: [PATCH 05/35] fix(hami): remove broken hami-dra subchart The hami-dra subchart renders resources even when dra.enabled=false because Helm dependency conditions don't work for vendored subcharts. The subchart also contains duplicate YAML label keys (app.kubernetes.io/component, app.kubernetes.io/name) and references unpublished container images (v0.0.1-dev). DRA support can be re-added when the upstream project stabilizes it. Signed-off-by: Arsolitt --- .../charts/hami/charts/hami-dra/.helmignore | 24 -- .../charts/hami/charts/hami-dra/Chart.yaml | 18 - .../charts/hami-dra/templates/_commons.tpl | 84 ---- .../charts/hami-dra/templates/_helpers.tpl | 73 ---- .../hami-dra-driver/deviceclass.yaml | 11 - .../nvidia-dra-driver-daemonset.yaml | 145 ------- .../templates/hami-dra-driver/rbac.yaml | 110 ----- .../monitor/monitor-clusterrole.yaml | 11 - .../monitor/monitor-clusterrolebinding.yaml | 15 - .../templates/monitor/monitor-deployment.yaml | 62 --- .../templates/monitor/monitor-service.yaml | 26 -- .../monitor/monitor-serviceaccount.yaml | 8 - .../templates/webhook/cert-manager.yaml | 29 -- .../templates/webhook/cert-secret.yaml | 13 - .../templates/webhook/device-config.yaml | 394 ------------------ .../webhook/mutatingwebhookconfiguration.yaml | 28 -- .../validatingwebhookconfiguration.yaml | 29 -- .../webhook/webhook-clusterrole.yaml | 14 - .../webhook/webhook-clusterrolebinding.yaml | 12 - .../templates/webhook/webhook-deployment.yaml | 59 --- .../templates/webhook/webhook-service.yaml | 15 - .../webhook/webhook-serviceaccount.yaml | 5 - .../charts/hami/charts/hami-dra/values.yaml | 166 -------- 23 files changed, 1351 deletions(-) delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/.helmignore delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml delete mode 100644 packages/system/hami/charts/hami/charts/hami-dra/values.yaml diff --git a/packages/system/hami/charts/hami/charts/hami-dra/.helmignore b/packages/system/hami/charts/hami/charts/hami-dra/.helmignore deleted file mode 100644 index 898df488..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/.helmignore +++ /dev/null @@ -1,24 +0,0 @@ -# Patterns to ignore when building packages. -# This supports shell glob matching, relative path matching, and -# negation (prefixed with !). Only one pattern per line. -.DS_Store -# Common VCS dirs -.git/ -.gitignore -.bzr/ -.bzrignore -.hg/ -.hgignore -.svn/ -# Common backup files -*.swp -*.bak -*.tmp -*.orig -*~ -# Various IDEs -.project -.idea/ -*.tmproj -.vscode/ - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml b/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml deleted file mode 100644 index d01f678f..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/Chart.yaml +++ /dev/null @@ -1,18 +0,0 @@ -apiVersion: v2 -appVersion: 0.1.0 -description: A Helm chart for HAMi DRA -home: https://github.com/Project-HAMi/HAMi-DRA -keywords: -- webhook -- kubernetes -- admission-controller -- hami -- dra -maintainers: -- name: hami-dra - url: https://github.com/Project-HAMi/HAMi-DRA -name: hami-dra -sources: -- https://github.com/Project-HAMi/HAMi-DRA -type: application -version: 0.1.0 diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl b/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl deleted file mode 100644 index 02fbed20..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/_commons.tpl +++ /dev/null @@ -1,84 +0,0 @@ -{{/* vim: set filetype=mustache: */}} - -{{/* -Return the proper image name -{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" $) }} -*/}} -{{- define "common.images.image" -}} -{{- $registryName := .imageRoot.registry -}} -{{- $repositoryName := .imageRoot.repository -}} -{{- $tag := .imageRoot.tag | toString -}} -{{- if .global }} - {{- if .global.imageRegistry }} - {{- $registryName = .global.imageRegistry -}} - {{- end -}} -{{- end -}} -{{- if .tag }} - {{- if .tag.imageTag }} - {{- $tag = .tag.imageTag -}} - {{- end -}} -{{- end -}} -{{- if $registryName }} -{{- printf "%s/%s:%s" $registryName $repositoryName $tag -}} -{{- else -}} -{{- printf "%s:%s" $repositoryName $tag -}} -{{- end -}} -{{- end -}} - -{{/* -Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) -{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} -*/}} -{{- define "common.images.pullSecrets" -}} - {{- $pullSecrets := list }} - - {{- if .global }} - {{- range .global.imagePullSecrets -}} - {{- $pullSecrets = append $pullSecrets . -}} - {{- end -}} - {{- end -}} - - {{- range .images -}} - {{- range .pullSecrets -}} - {{- $pullSecrets = append $pullSecrets . -}} - {{- end -}} - {{- end -}} - - {{- if (not (empty $pullSecrets)) }} -imagePullSecrets: - {{- range $pullSecrets }} - - name: {{ . }} - {{- end }} - {{- end }} -{{- end -}} - -{{/* -Renders a value that contains template. -Usage: -{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} -*/}} -{{- define "common.tplvalues.render" -}} - {{- if typeIs "string" .value }} - {{- tpl .value .context }} - {{- else }} - {{- tpl (.value | toYaml) .context }} - {{- end }} -{{- end -}} - -{{/* -Create a default fully qualified app name. -We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). -If release name contains chart name it will be used as a full name. -*/}} -{{- define "common.names.fullname" -}} -{{- if .Values.fullnameOverride -}} -{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} -{{- else -}} -{{- $name := default .Chart.Name .Values.nameOverride -}} -{{- if contains $name .Release.Name -}} -{{- .Release.Name | trunc 63 | trimSuffix "-" -}} -{{- else -}} -{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} -{{- end -}} -{{- end -}} -{{- end -}} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl b/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl deleted file mode 100644 index 99beec77..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/_helpers.tpl +++ /dev/null @@ -1,73 +0,0 @@ -{{- define "hami.dra.webhook.fullname" -}} -{{- printf "%s-%s" (include "common.names.fullname" .) "webhook" | trunc 63 | trimSuffix "-" -}} -{{- end }} - -{{- define "hami.dra.webhook.image" -}} -{{ include "common.images.image" (dict "imageRoot" .Values.webhook.image "global" .Values.global) }} -{{- end -}} - -{{- define "hami.dra.webhook.imagePullSecrets" -}} -{{ include "common.images.pullSecrets" (dict "images" (list .Values.webhook.image) "global" .Values.global) }} -{{- end -}} - -{{- define "hami.dra.driver.nvidia.image" -}} -{{ include "common.images.image" (dict "imageRoot" .Values.drivers.nvidia.image "global" .Values.global) }} -{{- end -}} - -{{- define "hami.dra.driver.nvidia.imagePullSecrets" -}} -{{ include "common.images.pullSecrets" (dict "images" (list .Values.drivers.nvidia.image) "global" .Values.global) }} -{{- end -}} - -{{/* -Common labels -*/}} -{{- define "hami-dra-webhook.labels" -}} -helm.sh/chart: {{ .Chart.Name }} -{{ include "hami-dra-webhook.selectorLabels" . }} -{{- if .Chart.AppVersion }} -app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} -{{- end }} -app.kubernetes.io/managed-by: {{ .Release.Service }} -{{- end }} - -{{/* -Selector labels -*/}} -{{- define "hami-dra-webhook.selectorLabels" -}} -app.kubernetes.io/name: {{ .Release.Name }} -app.kubernetes.io/instance: {{ .Release.Name }} -app.kubernetes.io/component: webhook -{{- end }} - -{{- define "hami.dra.monitor.fullname" -}} -{{- printf "%s-%s" (include "common.names.fullname" .) "monitor" | trunc 63 | trimSuffix "-" -}} -{{- end }} - -{{- define "hami.dra.monitor.image" -}} -{{ include "common.images.image" (dict "imageRoot" .Values.monitor.image "global" .Values.global) }} -{{- end -}} - -{{- define "hami.dra.monitor.imagePullSecrets" -}} -{{ include "common.images.pullSecrets" (dict "images" (list .Values.monitor.image) "global" .Values.global) }} -{{- end -}} - -{{/* -Common labels for monitor -*/}} -{{- define "hami-dra-monitor.labels" -}} -helm.sh/chart: {{ .Chart.Name }} -{{ include "hami-dra-monitor.selectorLabels" . }} -{{- if .Chart.AppVersion }} -app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} -{{- end }} -app.kubernetes.io/managed-by: {{ .Release.Service }} -{{- end }} - -{{/* -Selector labels for monitor -*/}} -{{- define "hami-dra-monitor.selectorLabels" -}} -app.kubernetes.io/name: {{ .Release.Name }} -app.kubernetes.io/instance: {{ .Release.Name }} -app.kubernetes.io/component: monitor -{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml deleted file mode 100644 index bcb6d2c5..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/deviceclass.yaml +++ /dev/null @@ -1,11 +0,0 @@ -{{- if .Values.drivers.nvidia.enabled }} -apiVersion: resource.k8s.io/v1 -kind: DeviceClass -metadata: - name: hami-core-gpu.project-hami.io -spec: - selectors: - - cel: - expression: |- - device.driver == "hami-core-gpu.project-hami.io" && device.attributes["hami-core-gpu.project-hami.io"].type == "hami-gpu" -{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml deleted file mode 100644 index a3fb0d01..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/nvidia-dra-driver-daemonset.yaml +++ /dev/null @@ -1,145 +0,0 @@ -{{- if .Values.drivers.nvidia.enabled }} -apiVersion: apps/v1 -kind: DaemonSet -metadata: - name: hami-dra-driver-kubelet-plugin - namespace: {{ .Release.Namespace }} -spec: - revisionHistoryLimit: 10 - selector: - matchLabels: - hami-dra-driver-component: kubelet-plugin - template: - metadata: - labels: - app.kubernetes.io/instance: hami-dra-driver - app.kubernetes.io/name: hami-dra-driver - hami-dra-driver-component: kubelet-plugin - spec: - {{- include "hami.dra.driver.nvidia.imagePullSecrets" . | nindent 6 }} - initContainers: - - name: init-container - image: {{ include "hami.dra.driver.nvidia.image" . }} - securityContext: - privileged: true - command: [bash, /usr/bin/kubelet-plugin-prestart.sh] - env: - - name: NVIDIA_DRIVER_ROOT - value: {{ if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} - - name: NVIDIA_VISIBLE_DEVICES - value: void - - name: KUBELET_REGISTRAR_DIRECTORY_PATH - value: /var/lib/kubelet/plugins_registry - - name: KUBELET_PLUGINS_DIRECTORY_PATH - value: /var/lib/kubelet/plugins - volumeMounts: - - name: driver-root-parent - mountPath: /driver-root-parent - readOnly: true - containers: - - args: - - |- - # Conditionally mask the params file to prevent this container from - # recreating any missing GPU device nodes. This is necessary, for - # example, when running under nvkind to limit the set GPUs governed - # by the plugin even though it has cgroup access to all of them. - if [ "${MASK_NVIDIA_DRIVER_PARAMS}" = "true" ]; then - cp /proc/driver/nvidia/params root/gpu-params - sed -i 's/^ModifyDeviceFiles: 1$/ModifyDeviceFiles: 0/' root/gpu-params - mount --bind root/gpu-params /proc/driver/nvidia/params - fi - hami-kubelet-plugin -v 6 - command: - - bash - - -c - env: - - name: MASK_NVIDIA_DRIVER_PARAMS - value: "" - - name: NVIDIA_DRIVER_ROOT - value: {{ if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} - - name: NVIDIA_VISIBLE_DEVICES - value: void - - name: CDI_ROOT - value: /var/run/cdi - - name: NVIDIA_MIG_CONFIG_DEVICES - value: all - - name: NODE_NAME - valueFrom: - fieldRef: - apiVersion: v1 - fieldPath: spec.nodeName - - name: NAMESPACE - valueFrom: - fieldRef: - apiVersion: v1 - fieldPath: metadata.namespace - - name: KUBELET_REGISTRAR_DIRECTORY_PATH - value: /var/lib/kubelet/plugins_registry - - name: KUBELET_PLUGINS_DIRECTORY_PATH - value: /var/lib/kubelet/plugins - - name: IMAGE_NAME - value: {{ include "hami.dra.driver.nvidia.image" . }} - lifecycle: - postStart: - exec: - command: ["/bin/bash", "-c", "/usr/bin/vgpu-init.sh /usr/local/vgpu/"] - image: {{ include "hami.dra.driver.nvidia.image" . }} - imagePullPolicy: {{ .Values.drivers.nvidia.image.pullPolicy | default "IfNotPresent" }} - name: gpus - securityContext: - privileged: true - terminationMessagePath: /dev/termination-log - terminationMessagePolicy: File - volumeMounts: - - mountPath: /var/lib/kubelet/plugins_registry - name: plugins-registry - - mountPath: /var/lib/kubelet/plugins - mountPropagation: Bidirectional - name: plugins - - mountPath: /var/run/cdi - name: cdi - - mountPath: /driver-root - mountPropagation: HostToContainer - name: driver-root - readOnly: true - - mountPath: /usr/local/vgpu - name: host-vgpu - - mountPath: /tmp - name: host-tmp - dnsPolicy: ClusterFirst - serviceAccount: hami-dra-driver-service-account - serviceAccountName: hami-dra-driver-service-account - volumes: - - hostPath: - path: /var/lib/kubelet/plugins_registry - type: "" - name: plugins-registry - - hostPath: - path: /var/lib/kubelet/plugins - type: "" - name: plugins - - hostPath: - path: /var/run/cdi - type: "" - name: cdi - - hostPath: - path: {{if .Values.drivers.nvidia.containerDriver }}/run/nvidia{{ else }}/{{ end }} - type: DirectoryOrCreate - name: driver-root-parent - - hostPath: - path: {{if .Values.drivers.nvidia.containerDriver }}/run/nvidia/driver{{ else }}/{{ end }} - type: DirectoryOrCreate - name: driver-root - - hostPath: - path: /dev - type: "" - name: host-dev - - hostPath: - path: /usr/local/vgpu - type: DirectoryOrCreate - name: host-vgpu - - hostPath: - path: /tmp - type: "" - name: host-tmp -{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml deleted file mode 100644 index 435c37cc..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/hami-dra-driver/rbac.yaml +++ /dev/null @@ -1,110 +0,0 @@ -{{- if .Values.drivers.nvidia.enabled }} -apiVersion: v1 -kind: ServiceAccount -metadata: - name: hami-dra-driver-service-account - namespace: {{ .Release.Namespace }} ---- -apiVersion: v1 -items: -- apiVersion: rbac.authorization.k8s.io/v1 - kind: Role - metadata: - name: hami-dra-driver-role - namespace: {{ .Release.Namespace }} - rules: - - apiGroups: - - apps - resources: - - daemonsets - - deployments - verbs: - - get - - list - - watch - - create - - update - - patch - - delete -kind: List -metadata: - resourceVersion: "" ---- -apiVersion: rbac.authorization.k8s.io/v1 -kind: RoleBinding -metadata: - name: hami-dra-driver-role-binding - namespace: {{ .Release.Namespace }} -roleRef: - apiGroup: rbac.authorization.k8s.io - kind: Role - name: hami-dra-driver-role -subjects: -- kind: ServiceAccount - name: hami-dra-driver-service-account - namespace: {{ .Release.Namespace }} ---- -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRole -metadata: - name: hami-dra-driver-clusterrole -rules: -- apiGroups: - - resource.k8s.io - resources: - - resourceclaims - verbs: - - get - - list - - watch -- apiGroups: - - resource.k8s.io - resources: - - resourceclaimtemplates - verbs: - - get - - list - - watch - - create - - update - - delete -- apiGroups: - - resource.k8s.io - resources: - - resourceslices - verbs: - - get - - list - - watch - - create - - update - - delete -- apiGroups: - - resource.k8s.io - resources: - - resourceclaims/status - verbs: - - update -- apiGroups: - - "" - resources: - - nodes - verbs: - - get - - list - - watch - - update ---- -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRoleBinding -metadata: - name: hami-dra-driver-clusterrole-binding-hami-dra-driver -roleRef: - apiGroup: rbac.authorization.k8s.io - kind: ClusterRole - name: hami-dra-driver-clusterrole -subjects: -- kind: ServiceAccount - name: hami-dra-driver-service-account - namespace: {{ .Release.Namespace }} -{{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml deleted file mode 100644 index 45c24863..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrole.yaml +++ /dev/null @@ -1,11 +0,0 @@ -{{- if .Values.monitor.enabled }} -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRole -metadata: - name: {{ include "hami.dra.monitor.fullname" . }} -rules: -- apiGroups: ["resource.k8s.io"] - resources: ["resourceslices", "resourceclaims"] - verbs: ["get", "list", "watch"] -{{- end }} - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml deleted file mode 100644 index 766d3098..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-clusterrolebinding.yaml +++ /dev/null @@ -1,15 +0,0 @@ -{{- if .Values.monitor.enabled }} -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRoleBinding -metadata: - name: {{ include "hami.dra.monitor.fullname" . }} -roleRef: - apiGroup: rbac.authorization.k8s.io - kind: ClusterRole - name: {{ include "hami.dra.monitor.fullname" . }} -subjects: - - kind: ServiceAccount - name: {{ include "hami.dra.monitor.fullname" . }} - namespace: {{ .Release.Namespace }} -{{- end }} - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml deleted file mode 100644 index b544b376..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-deployment.yaml +++ /dev/null @@ -1,62 +0,0 @@ -{{- if .Values.monitor.enabled }} -apiVersion: apps/v1 -kind: Deployment -metadata: - name: {{ include "hami.dra.monitor.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: - app.kubernetes.io/name: {{ include "hami.dra.monitor.fullname" . }} - {{- include "hami-dra-monitor.labels" . | nindent 4 }} -spec: - replicas: {{ .Values.monitor.replicas | default 1 }} - selector: - matchLabels: - {{- include "hami-dra-monitor.selectorLabels" . | nindent 6 }} - template: - metadata: - labels: - {{- include "hami-dra-monitor.selectorLabels" . | nindent 8 }} - spec: - {{- include "hami.dra.monitor.imagePullSecrets" . | nindent 6 }} - serviceAccountName: {{ include "hami.dra.monitor.fullname" . }} - containers: - - name: monitor - image: {{ include "hami.dra.monitor.image" . }} - imagePullPolicy: {{ .Values.monitor.image.pullPolicy | default "IfNotPresent" }} - command: - - /bin/monitor - - --v={{ .Values.monitor.logLevel | default 2 }} - - --metrics-bind-address={{ .Values.monitor.metricsBindAddress | default ":8080" }} - - --health-probe-bind-address={{ .Values.monitor.healthProbeBindAddress | default ":8000" }} - - --kube-api-qps={{ .Values.monitor.kubeAPIQPS | default 40.0 }} - - --kube-api-burst={{ .Values.monitor.kubeAPIBurst | default 60 }} - - --collect-interval={{ .Values.monitor.collectInterval | default "30s" }} - ports: - - containerPort: 8080 - name: metrics - protocol: TCP - - containerPort: 8000 - name: health - protocol: TCP - {{- if .Values.monitor.resources }} - resources: - {{- toYaml .Values.monitor.resources | nindent 12 }} - {{- end }} - livenessProbe: - httpGet: - path: /healthz - port: 8000 - initialDelaySeconds: 10 - periodSeconds: 10 - timeoutSeconds: 5 - failureThreshold: 3 - readinessProbe: - httpGet: - path: /readyz - port: 8000 - initialDelaySeconds: 5 - periodSeconds: 5 - timeoutSeconds: 3 - failureThreshold: 3 -{{- end }} - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml deleted file mode 100644 index d740cc38..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-service.yaml +++ /dev/null @@ -1,26 +0,0 @@ -{{- if .Values.monitor.enabled }} -apiVersion: v1 -kind: Service -metadata: - name: {{ include "hami.dra.monitor.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: - {{- include "hami-dra-monitor.selectorLabels" . | nindent 4 }} -spec: - type: {{ .Values.monitor.service.type | default "ClusterIP" }} - selector: - {{- include "hami-dra-monitor.selectorLabels" . | nindent 4 }} - ports: - - port: 8080 - targetPort: 8080 - name: metrics - protocol: TCP - {{- if and (eq (.Values.monitor.service.type | default "ClusterIP") "NodePort") .Values.monitor.service.nodePort.metrics }} - nodePort: {{ .Values.monitor.service.nodePort.metrics }} - {{- end }} - - port: 8000 - targetPort: 8000 - name: health - protocol: TCP -{{- end }} - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml deleted file mode 100644 index c61ad454..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/monitor/monitor-serviceaccount.yaml +++ /dev/null @@ -1,8 +0,0 @@ -{{- if .Values.monitor.enabled }} -apiVersion: v1 -kind: ServiceAccount -metadata: - name: {{ include "hami.dra.monitor.fullname" . }} - namespace: {{ .Release.Namespace }} -{{- end }} - diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml deleted file mode 100644 index dd31c71d..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-manager.yaml +++ /dev/null @@ -1,29 +0,0 @@ -{{- if .Values.certs.certManager.enabled }} -apiVersion: cert-manager.io/v1 -kind: Certificate -metadata: - name: {{ .Release.Name }}-dra-webhook-serving-cert - namespace: {{ .Release.Namespace }} - labels: - {{- include "hami-dra-webhook.labels" . | nindent 4 }} -spec: - dnsNames: - - {{ .Release.Name }}-dra-webhook.{{ .Release.Namespace }}.svc - - {{ .Release.Name }}-dra-webhook.{{ .Release.Namespace }}.svc.cluster.local - issuerRef: - kind: Issuer - name: {{ .Release.Name }}-dra-webhook-selfsigned-issuer - secretName: {{ .Release.Name }}-dra-webhook-tls - privateKey: - rotationPolicy: {{ .Values.certs.certManager.privateKeyRotationPolicy | default "Never" }} ---- -apiVersion: cert-manager.io/v1 -kind: Issuer -metadata: - name: {{ .Release.Name }}-dra-webhook-selfsigned-issuer - namespace: {{ .Release.Namespace }} - labels: - app.kubernetes.io/component: hami-dra-webhook -spec: - selfSigned: {} -{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml deleted file mode 100644 index eadbb517..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/cert-secret.yaml +++ /dev/null @@ -1,13 +0,0 @@ -{{- if eq .Values.certs.mode "custom" }} -apiVersion: v1 -kind: Secret -metadata: - name: {{ include "hami-dra-webhook.tlsSecretName" . }} - namespace: {{ .Release.Namespace }} -type: kubernetes.io/tls -data: - tls.crt: | - {{- .Values.certs.custom.crt | b64enc | indent 4 }} - tls.key: | - {{- .Values.certs.custom.key | b64enc | indent 4 }} -{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml deleted file mode 100644 index 97283f3e..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/device-config.yaml +++ /dev/null @@ -1,394 +0,0 @@ -apiVersion: v1 -kind: ConfigMap -metadata: - name: {{ include "hami.dra.webhook.fullname" . }}-device-config - namespace: {{ .Release.Namespace }} - labels: - app.kubernetes.io/component: hami-scheduler - {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} -data: - device-config.yaml: |- - {{- if .Files.Glob "files/device-config.yaml" }} - {{- .Files.Get "files/device-config.yaml" | nindent 4}} - {{- else }} - nvidia: - resourceCountName: {{ .Values.resourceName }} - resourceMemoryName: {{ .Values.resourceMem }} - resourceMemoryPercentageName: {{ .Values.resourceMemPercentage }} - resourceCoreName: {{ .Values.resourceCores }} - resourcePriorityName: {{ .Values.resourcePriority }} - overwriteEnv: false - defaultMemory: 0 - defaultCores: 0 - defaultGPUNum: 1 - knownMigGeometries: - - models: [ "A30" ] - allowedGeometries: - - - - name: 1g.6gb - core: 25 - memory: 6144 - count: 4 - - - - name: 2g.12gb - core: 50 - memory: 12288 - count: 2 - - - - name: 4g.24gb - core: 100 - memory: 24576 - count: 1 - - models: [ "A100-SXM4-40GB", "A100-40GB-PCIe", "A100-PCIE-40GB"] - allowedGeometries: - - - - name: 1g.5gb - core: 14 - memory: 5120 - count: 7 - - - - name: 1g.5gb - core: 14 - memory: 5120 - count: 1 - - name: 2g.10gb - core: 28 - memory: 10240 - count: 3 - - - - name: 3g.20gb - core: 42 - memory: 20480 - count: 2 - - - - name: 7g.40gb - core: 100 - memory: 40960 - count: 1 - - models: [ "A100-SXM4-80GB", "A100-80GB-PCIe", "A100-PCIE-80GB"] - allowedGeometries: - - - - name: 1g.10gb - core: 14 - memory: 10240 - count: 7 - - - - name: 1g.10gb - core: 14 - memory: 10240 - count: 1 - - name: 2g.20gb - core: 28 - memory: 20480 - count: 3 - - - - name: 3g.40gb - core: 42 - memory: 40960 - count: 2 - - - - name: 7g.79gb - core: 100 - memory: 80896 - count: 1 - - models: [ "H100-PCIE-80GB", "H100-SXM5-80GB"] - allowedGeometries: - - - - name: 1g.10gb - core: 14 - memory: 10240 - count: 7 - - - - name: 1g.10gb - core: 14 - memory: 10240 - count: 1 - - name: 2g.20gb - core: 28 - memory: 20480 - count: 3 - - - - name: 3g.40gb - core: 42 - memory: 40960 - count: 2 - - - - name: 7g.80gb - core: 100 - memory: 81920 - count: 1 - - models: [ "H100-PCIE-94GB", "H100-SXM5-94GB"] - allowedGeometries: - - - - name: 1g.12gb - core: 14 - memory: 12288 - count: 7 - - - - name: 1g.12gb - core: 14 - memory: 12288 - count: 1 - - name: 2g.24gb - core: 28 - memory: 24576 - count: 3 - - - - name: 3g.47gb - core: 42 - memory: 48128 - count: 2 - - - - name: 7g.94gb - core: 100 - memory: 96256 - count: 1 - - models: [ "H20", "H100 on GH200"] - allowedGeometries: - - - - name: 1g.12gb - core: 14 - memory: 12288 - count: 7 - - - - name: 1g.12gb - core: 14 - memory: 12288 - count: 1 - - name: 2g.24gb - core: 28 - memory: 24576 - count: 3 - - - - name: 3g.48gb - core: 42 - memory: 49152 - count: 2 - - - - name: 7g.96gb - core: 100 - memory: 98304 - count: 1 - - models: [ "H200 NVL", "H200-SXM5"] - allowedGeometries: - - - - name: 1g.18gb - core: 14 - memory: 18432 - count: 7 - - - - name: 1g.18gb - core: 14 - memory: 18432 - count: 1 - - name: 2g.35gb - core: 28 - memory: 35840 - count: 3 - - - - name: 3g.71gb - core: 42 - memory: 72704 - count: 2 - - - - name: 7g.141gb - core: 100 - memory: 144384 - count: 1 - - models: [ "B200" ] - allowedGeometries: - - - - name: 1g.23gb - core: 14 - memory: 23552 - count: 7 - - - - name: 1g.23gb - core: 14 - memory: 23552 - count: 1 - - name: 2g.45gb - core: 28 - memory: 46080 - count: 3 - - - - name: 3g.90gb - core: 42 - memory: 92160 - count: 2 - - - - name: 7g.180gb - core: 100 - memory: 184320 - count: 1 - cambricon: - resourceCountName: {{ .Values.mluResourceName }} - resourceMemoryName: {{ .Values.mluResourceMem }} - resourceCoreName: {{ .Values.mluResourceCores }} - hygon: - resourceCountName: {{ .Values.dcuResourceName }} - resourceMemoryName: {{ .Values.dcuResourceMem }} - resourceCoreName: {{ .Values.dcuResourceCores }} - metax: - resourceCountName: "metax-tech.com/gpu" - resourceVCountName: {{ .Values.metaxResourceName }} - resourceVMemoryName: {{ .Values.metaxResourceMem }} - resourceVCoreName: {{ .Values.metaxResourceCore }} - sgpuTopologyAware: {{ .Values.metaxsGPUTopologyAware }} - enflame: - resourceNameGCU: "enflame.com/gcu" - resourceNameVGCU: {{ .Values.enflameResourceNameVGCU }} - resourceNameVGCUPercentage: {{ .Values.enflameResourceNameVGCUPercentage }} - mthreads: - resourceCountName: "mthreads.com/vgpu" - resourceMemoryName: "mthreads.com/sgpu-memory" - resourceCoreName: "mthreads.com/sgpu-core" - iluvatars: - - chipName: MR-V100 - commonWord: MR-V100 - resourceCountName: iluvatar.ai/MR-V100-vgpu - resourceMemoryName: iluvatar.ai/MR-V100.vMem - resourceCoreName: iluvatar.ai/MR-V100.vCore - - chipName: MR-V50 - commonWord: MR-V50 - resourceCountName: iluvatar.ai/MR-V50-vgpu - resourceMemoryName: iluvatar.ai/MR-V50.vMem - resourceCoreName: iluvatar.ai/MR-V50.vCore - - chipName: BI-V150 - commonWord: BI-V150 - resourceCountName: iluvatar.ai/BI-V150-vgpu - resourceMemoryName: iluvatar.ai/BI-V150.vMem - resourceCoreName: iluvatar.ai/BI-V150.vCore - - chipName: BI-V100 - commonWord: BI-V100 - resourceCountName: iluvatar.ai/BI-V100-vgpu - resourceMemoryName: iluvatar.ai/BI-V100.vMem - resourceCoreName: iluvatar.ai/BI-V100.vCore - kunlun: - resourceCountName: {{ .Values.kunlunResourceName }} - resourceVCountName: {{ .Values.kunlunResourceVCountName }} - resourceVMemoryName: {{ .Values.kunlunResourceVMemoryName }} - awsneuron: - resourceCountName: "aws.amazon.com/neuron" - resourceCoreName: "aws.amazon.com/neuroncore" - amd: - resourceCountName: "amd.com/gpu" - vnpus: - - chipName: 910A - commonWord: Ascend910A - resourceName: huawei.com/Ascend910A - resourceMemoryName: huawei.com/Ascend910A-memory - memoryAllocatable: 32768 - memoryCapacity: 32768 - aiCore: 30 - templates: - - name: vir02 - memory: 2184 - aiCore: 2 - - name: vir04 - memory: 4369 - aiCore: 4 - - name: vir08 - memory: 8738 - aiCore: 8 - - name: vir16 - memory: 17476 - aiCore: 16 - - chipName: 910B2 - commonWord: Ascend910B2 - resourceName: huawei.com/Ascend910B2 - resourceMemoryName: huawei.com/Ascend910B2-memory - memoryAllocatable: 65536 - memoryCapacity: 65536 - aiCore: 24 - aiCPU: 6 - templates: - - name: vir03_1c_8g - memory: 8192 - aiCore: 3 - aiCPU: 1 - - name: vir06_1c_16g - memory: 16384 - aiCore: 6 - aiCPU: 1 - - name: vir12_3c_32g - memory: 32768 - aiCore: 12 - aiCPU: 3 - - chipName: 910B3 - commonWord: Ascend910B3 - resourceName: huawei.com/Ascend910B3 - resourceMemoryName: huawei.com/Ascend910B3-memory - memoryAllocatable: 65536 - memoryCapacity: 65536 - aiCore: 20 - aiCPU: 7 - templates: - - name: vir05_1c_16g - memory: 16384 - aiCore: 5 - aiCPU: 1 - - name: vir10_3c_32g - memory: 32768 - aiCore: 10 - aiCPU: 3 - - chipName: 910B4-1 - commonWord: Ascend910B4-1 - resourceName: huawei.com/Ascend910B4-1 - resourceMemoryName: huawei.com/Ascend910B4-1-memory - memoryAllocatable: 65536 - memoryCapacity: 65536 - aiCore: 20 - aiCPU: 7 - templates: - # NOTE: Names of vnpu template for 910B4-1 are fixed by Ascend runtime and must not be changed. - # The memory is used for scheduling so the correct values must be set. - # Template vir05_1c_8g actually provides 16GB memory, - - name: vir05_1c_8g - memory: 16384 - aiCore: 5 - aiCPU: 1 - # Template vir10_3c_16g actually provides 32GB memory - - name: vir10_3c_16g - memory: 32768 - aiCore: 10 - aiCPU: 3 - - chipName: 910B4 - commonWord: Ascend910B4 - resourceName: huawei.com/Ascend910B4 - resourceMemoryName: huawei.com/Ascend910B4-memory - memoryAllocatable: 32768 - memoryCapacity: 32768 - aiCore: 20 - aiCPU: 7 - templates: - - name: vir05_1c_8g - memory: 8192 - aiCore: 5 - aiCPU: 1 - - name: vir10_3c_16g - memory: 16384 - aiCore: 10 - aiCPU: 3 - - chipName: 310P3 - commonWord: Ascend310P - resourceName: huawei.com/Ascend310P - resourceMemoryName: huawei.com/Ascend310P-memory - memoryAllocatable: 21527 - memoryCapacity: 24576 - aiCore: 8 - aiCPU: 7 - templates: - - name: vir01 - memory: 3072 - aiCore: 1 - aiCPU: 1 - - name: vir02 - memory: 6144 - aiCore: 2 - aiCPU: 2 - - name: vir04 - memory: 12288 - aiCore: 4 - aiCPU: 4 - {{ end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml deleted file mode 100644 index c763b6aa..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/mutatingwebhookconfiguration.yaml +++ /dev/null @@ -1,28 +0,0 @@ -{{- if .Values.webhook.config.mutating.enabled }} -apiVersion: admissionregistration.k8s.io/v1 -kind: MutatingWebhookConfiguration -metadata: - name: {{ .Release.Name }}-mutatingwebhookconfiguration - annotations: - cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ .Release.Name }}-dra-webhook-serving-cert -webhooks: - - name: mutate.hami.io - admissionReviewVersions: ["v1"] - clientConfig: - service: - name: {{ .Release.Name }}-dra-webhook - namespace: {{ .Release.Namespace }} - path: /mutate - rules: - - apiGroups: - - "" - apiVersions: - - v1 - operations: - - CREATE - resources: - - pods - scope: '*' - sideEffects: None - timeoutSeconds: 10 -{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml deleted file mode 100644 index acdcbb96..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/validatingwebhookconfiguration.yaml +++ /dev/null @@ -1,29 +0,0 @@ -{{- if .Values.webhook.config.validating.enabled }} -apiVersion: admissionregistration.k8s.io/v1 -kind: ValidatingWebhookConfiguration -metadata: - name: {{ .Release.Name }}-validatingwebhookconfiguration - annotations: - cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ .Release.Name }}-dra-webhook-serving-cert -webhooks: - - name: validate.hami.io - admissionReviewVersions: ["v1"] - clientConfig: - service: - name: {{ .Release.Name }}-dra-webhook - namespace: {{ .Release.Namespace }} - path: /validate - rules: - - apiGroups: - - "" - apiVersions: - - v1 - operations: - - DELETE - resources: - - pods - scope: '*' - sideEffects: None - timeoutSeconds: 10 - failurePolicy: Ignore -{{- end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml deleted file mode 100644 index 28916a36..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrole.yaml +++ /dev/null @@ -1,14 +0,0 @@ -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRole -metadata: - name: {{ include "hami.dra.webhook.fullname" . }} -rules: -- apiGroups: [""] - resources: ["pods"] - verbs: ["get", "list", "watch"] -- apiGroups: ["admissionregistration.k8s.io"] - resources: ["mutatingwebhookconfigurations", "validatingwebhookconfigurations"] - verbs: ["get", "list", "watch"] -- apiGroups: ["resource.k8s.io"] - resources: ["resourceclaims"] - verbs: ["*"] diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml deleted file mode 100644 index daad52f2..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-clusterrolebinding.yaml +++ /dev/null @@ -1,12 +0,0 @@ -apiVersion: rbac.authorization.k8s.io/v1 -kind: ClusterRoleBinding -metadata: - name: {{ include "hami.dra.webhook.fullname" . }} -roleRef: - apiGroup: rbac.authorization.k8s.io - kind: ClusterRole - name: {{ include "hami.dra.webhook.fullname" . }} -subjects: - - kind: ServiceAccount - name: {{ include "hami.dra.webhook.fullname" . }} - namespace: {{ .Release.Namespace }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml deleted file mode 100644 index 8e3cf90c..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-deployment.yaml +++ /dev/null @@ -1,59 +0,0 @@ -apiVersion: apps/v1 -kind: Deployment -metadata: - name: {{ include "hami.dra.webhook.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: - app.kubernetes.io/name: {{ include "hami.dra.webhook.fullname" . }} - {{- include "hami-dra-webhook.labels" . | nindent 4 }} -spec: - replicas: 1 - selector: - matchLabels: - {{- include "hami-dra-webhook.selectorLabels" . | nindent 6 }} - template: - metadata: - labels: - {{- include "hami-dra-webhook.selectorLabels" . | nindent 8 }} - spec: - {{- include "hami.dra.webhook.imagePullSecrets" . | nindent 6 }} - serviceAccountName: {{ include "hami.dra.webhook.fullname" . }} - containers: - - name: webhook - image: {{ include "hami.dra.webhook.image" . }} - imagePullPolicy: {{ .Values.webhook.image.pullPolicy | default "IfNotPresent" }} - command: - - /bin/webhook - - --v=5 - - --bind-address=0.0.0.0 - - --secure-port=8443 - - --cert-dir=/tls - - --tls-cert-file-name=tls.crt - - --tls-private-key-file-name=tls.key - - --metrics-bind-address=:8080 - - --health-probe-bind-address=:8000 - - --device-config-file=/device-config.yaml - ports: - - containerPort: 8443 - name: webhook - protocol: TCP - - containerPort: 8080 - name: metrics - protocol: TCP - - containerPort: 8000 - name: health - protocol: TCP - volumeMounts: - - name: device-config - mountPath: /device-config.yaml - subPath: device-config.yaml - - name: tls-config - mountPath: /tls - readOnly: true - volumes: - - name: device-config - configMap: - name: {{ include "hami.dra.webhook.fullname" . }}-device-config - - name: tls-config - secret: - secretName: {{ if .Values.certs.certManager.enabled }}{{ .Release.Name }}-dra-webhook-tls{{ else }}{{ .Release.Name }}-tls{{ end }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml deleted file mode 100644 index 290174ec..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-service.yaml +++ /dev/null @@ -1,15 +0,0 @@ -apiVersion: v1 -kind: Service -metadata: - name: {{ .Release.Name }}-dra-webhook - namespace: {{ .Release.Namespace }} - labels: - {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} -spec: - type: "ClusterIP" - selector: - {{- include "hami-dra-webhook.selectorLabels" . | nindent 4 }} - ports: - - port: 443 - targetPort: 8443 - name: webhook diff --git a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml b/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml deleted file mode 100644 index b0dc2fb2..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/templates/webhook/webhook-serviceaccount.yaml +++ /dev/null @@ -1,5 +0,0 @@ -apiVersion: v1 -kind: ServiceAccount -metadata: - name: {{ include "hami.dra.webhook.fullname" . }} - namespace: {{ .Release.Namespace }} diff --git a/packages/system/hami/charts/hami/charts/hami-dra/values.yaml b/packages/system/hami/charts/hami/charts/hami-dra/values.yaml deleted file mode 100644 index ebbbfed7..00000000 --- a/packages/system/hami/charts/hami/charts/hami-dra/values.yaml +++ /dev/null @@ -1,166 +0,0 @@ -## @section Global configuration -## @param global.imageRegistry Global Docker image registry -## @param global.imagePullSecrets Global Docker image pull secrets -global: - ## @param global.imageRegistry Global Docker image registry - imageRegistry: "" - ## E.g. - ## imagePullSecrets: - ## - myRegistryKeySecretName - ## @param global.imagePullSecrets Global Docker image pull secrets - imagePullSecrets: [] - -#Nvidia GPU Parameters -resourceName: "nvidia.com/gpu" -resourceMem: "nvidia.com/gpumem" -resourceMemPercentage: "nvidia.com/gpumem-percentage" -resourceCores: "nvidia.com/gpucores" -resourcePriority: "nvidia.com/priority" - -#MLU Parameters -mluResourceName: "cambricon.com/vmlu" -mluResourceMem: "cambricon.com/mlu.smlu.vmemory" -mluResourceCores: "cambricon.com/mlu.smlu.vcore" - -#Hygon DCU Parameters -dcuResourceName: "hygon.com/dcunum" -dcuResourceMem: "hygon.com/dcumem" -dcuResourceCores: "hygon.com/dcucores" - -#Metax sGPU Parameters -metaxResourceName: "metax-tech.com/sgpu" -metaxResourceCore: "metax-tech.com/vcore" -metaxResourceMem: "metax-tech.com/vmemory" -metaxsGPUTopologyAware: "false" - -#Enflame VGCU Parameters -enflameResourceNameVGCU: "enflame.com/vgcu" -enflameResourceNameVGCUPercentage: "enflame.com/vgcu-percentage" - -#Kunlun XPU Parameters -kunlunResourceName: "kunlunxin.com/xpu" -kunlunResourceVCountName: "kunlunxin.com/vxpu" -kunlunResourceVMemoryName: "kunlunxin.com/vxpu-memory" - -# Webhook deployment configuration -webhook: - image: - registry: ghcr.io - repository: project-hami/hami-dra-webhook - tag: "v0.1.0" - ## Specify a imagePullPolicy - ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' - ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images - ## - pullPolicy: Always - ## Optionally specify an array of imagePullSecrets. - ## Secrets must be manually created in the namespace. - ## Example: - ## pullSecrets: - ## - myRegistryKeySecretName - ## - pullSecrets: [] - ## @param resources controllerManager resource requests and limits - resources: - # If you do want to specify resources, uncomment the following - # lines, adjust them as necessary, and remove the curly braces after 'resources:'. - limits: - cpu: 500m - memory: 512Mi - requests: - cpu: 100m - memory: 128Mi - ## @param nodeSelector controllerManager node labels for pod assignment - args: - webhookName: "" # Default: {{ .Release.Name }}-hami-dra-webhook - secretName: "" # Default: {{ .Release.Name }}-hami-dra-webhook-tls - # Webhook configuration - config: - mutating: - enabled: true - validating: - enabled: true - -# Monitor deployment configuration -monitor: - enabled: true - replicas: 1 - image: - registry: ghcr.io - repository: project-hami/hami-dra-monitor - tag: "v0.1.0" - ## Specify a imagePullPolicy - ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' - ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images - ## - pullPolicy: Always - ## Optionally specify an array of imagePullSecrets. - ## Secrets must be manually created in the namespace. - ## Example: - ## pullSecrets: - ## - myRegistryKeySecretName - ## - pullSecrets: [] - ## @param resources monitor resource requests and limits - resources: - limits: - cpu: 500m - memory: 512Mi - requests: - cpu: 100m - memory: 128Mi - ## Monitor configuration - logLevel: 2 - metricsBindAddress: ":8080" - healthProbeBindAddress: ":8000" - kubeAPIQPS: 40.0 - kubeAPIBurst: 60 - collectInterval: "30s" - ## Monitor service configuration - service: - ## Service type: ClusterIP, NodePort, or LoadBalancer - ## Defaults to ClusterIP - type: ClusterIP - ## NodePort configuration (only used when type is NodePort) - nodePort: - ## Metrics port (NodePort). If not specified, Kubernetes will assign a random port - metrics: "" - -# Certificate configuration -certs: - # Custom certificate (used when mode is "custom") - custom: - crt: "" - key: "" - # Cert-manager configuration (used when mode is "cert-manager") - certManager: - enabled: true - # Private key rotation policy: "Never" or "Always" - # In cert-manager >= v1.18.0, the default changed from "Never" to "Always" - # Setting to "Never" avoids frequent certificate rotation for webhooks - privateKeyRotationPolicy: "Never" - issuer: - clusterIssuerName: "" # Required when type is "clusterIssuer" - -# DRA Drivers configuration -drivers: - nvidia: - enabled: true - # If you are using gpu driver on host, you need to set this to false - containerDriver: true - image: - registry: ghcr.io - repository: projecthami/k8s-dra-driver - tag: "v0.0.1-dev" - ## Specify a imagePullPolicy - ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' - ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images - ## - pullPolicy: IfNotPresent - ## Optionally specify an array of imagePullSecrets. - ## Secrets must be manually created in the namespace. - ## Example: - ## pullSecrets: - ## - myRegistryKeySecretName - ## - pullSecrets: [] From 385ea7a17f8cfc4526c50db036c105c63a5817fc Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Thu, 23 Apr 2026 22:16:34 +0300 Subject: [PATCH 06/35] feat(platform): register HAMi as optional system package Add PackageSource for HAMi with dependency on gpu-operator. Include HAMi in the iaas bundle as an optional package, allowing host-level deployment alongside the existing kubernetes addon path. Signed-off-by: Arsolitt --- packages/core/platform/sources/hami.yaml | 24 +++++++++++++++++++ .../core/platform/templates/bundles/iaas.yaml | 1 + 2 files changed, 25 insertions(+) create mode 100644 packages/core/platform/sources/hami.yaml diff --git a/packages/core/platform/sources/hami.yaml b/packages/core/platform/sources/hami.yaml new file mode 100644 index 00000000..0184e405 --- /dev/null +++ b/packages/core/platform/sources/hami.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: cozystack.io/v1alpha1 +kind: PackageSource +metadata: + name: cozystack.hami +spec: + sourceRef: + kind: OCIRepository + name: cozystack-packages + namespace: cozy-system + path: / + variants: + - name: default + dependsOn: + - cozystack.gpu-operator + components: + - name: hami + path: system/hami + valuesFiles: + - values.yaml + install: + privileged: true + namespace: cozy-hami + releaseName: hami diff --git a/packages/core/platform/templates/bundles/iaas.yaml b/packages/core/platform/templates/bundles/iaas.yaml index ced0a322..66ec98b2 100644 --- a/packages/core/platform/templates/bundles/iaas.yaml +++ b/packages/core/platform/templates/bundles/iaas.yaml @@ -10,6 +10,7 @@ {{include "cozystack.platform.package.default" (list "cozystack.kubevirt-cdi" $) }} {{include "cozystack.platform.package.optional.default" (list "cozystack.vm-default-images" $) }} {{include "cozystack.platform.package.optional.default" (list "cozystack.gpu-operator" $) }} +{{include "cozystack.platform.package.optional.default" (list "cozystack.hami" $) }} {{include "cozystack.platform.package.default" (list "cozystack.kamaji" $) }} {{include "cozystack.platform.package.default" (list "cozystack.capi-operator" $) }} {{include "cozystack.platform.package.default" (list "cozystack.capi-provider-bootstrap-kubeadm" $) }} From 3b3540448975391ad7582db58d83ce5b18b15129 Mon Sep 17 00:00:00 2001 From: Denis Chernosov Date: Fri, 24 Apr 2026 11:32:20 +0400 Subject: [PATCH 07/35] fix(cozystack-engine): add managed Kubernetes without visible control-plane nodes support to lineage-controller-webhook (#2417) Signed-off-by: Denis Chernosov --- .../templates/daemonset.yaml | 2 + .../templates/deployment.yaml | 49 +++++++++++++++++++ .../templates/pdb.yaml | 11 +++++ .../lineage-controller-webhook/values.yaml | 5 ++ 4 files changed, 67 insertions(+) create mode 100644 packages/system/lineage-controller-webhook/templates/deployment.yaml create mode 100644 packages/system/lineage-controller-webhook/templates/pdb.yaml diff --git a/packages/system/lineage-controller-webhook/templates/daemonset.yaml b/packages/system/lineage-controller-webhook/templates/daemonset.yaml index 860aee6e..536ea24a 100644 --- a/packages/system/lineage-controller-webhook/templates/daemonset.yaml +++ b/packages/system/lineage-controller-webhook/templates/daemonset.yaml @@ -1,3 +1,4 @@ +{{- if not .Values.lineageControllerWebhook.deployment.enabled }} apiVersion: apps/v1 kind: DaemonSet metadata: @@ -51,3 +52,4 @@ spec: secret: secretName: lineage-controller-webhook-cert defaultMode: 0400 +{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/templates/deployment.yaml b/packages/system/lineage-controller-webhook/templates/deployment.yaml new file mode 100644 index 00000000..87717fd3 --- /dev/null +++ b/packages/system/lineage-controller-webhook/templates/deployment.yaml @@ -0,0 +1,49 @@ +{{- if .Values.lineageControllerWebhook.deployment.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: lineage-controller-webhook + labels: + app: lineage-controller-webhook +spec: + replicas: {{ .Values.lineageControllerWebhook.deployment.replicas }} + selector: + matchLabels: + app: lineage-controller-webhook + template: + metadata: + labels: + app: lineage-controller-webhook + spec: + serviceAccountName: lineage-controller-webhook + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: kubernetes.io/hostname + labelSelector: + matchLabels: + app: lineage-controller-webhook + containers: + - name: lineage-controller-webhook + image: "{{ .Values.lineageControllerWebhook.image }}" + args: + {{- if .Values.lineageControllerWebhook.debug }} + - --zap-log-level=debug + {{- else }} + - --zap-log-level=info + {{- end }} + ports: + - name: webhook + containerPort: 9443 + volumeMounts: + - name: webhook-certs + mountPath: /tmp/k8s-webhook-server/serving-certs + readOnly: true + volumes: + - name: webhook-certs + secret: + secretName: lineage-controller-webhook-cert + defaultMode: 0400 +{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/templates/pdb.yaml b/packages/system/lineage-controller-webhook/templates/pdb.yaml new file mode 100644 index 00000000..b0a9d4e4 --- /dev/null +++ b/packages/system/lineage-controller-webhook/templates/pdb.yaml @@ -0,0 +1,11 @@ +{{- if .Values.lineageControllerWebhook.deployment.enabled }} +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + name: lineage-controller-webhook +spec: + minAvailable: {{ if gt (int .Values.lineageControllerWebhook.deployment.replicas) 1 }}1{{ else }}0{{ end }} + selector: + matchLabels: + app: lineage-controller-webhook +{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/values.yaml b/packages/system/lineage-controller-webhook/values.yaml index c5671548..2b84f4e1 100644 --- a/packages/system/lineage-controller-webhook/values.yaml +++ b/packages/system/lineage-controller-webhook/values.yaml @@ -2,9 +2,14 @@ lineageControllerWebhook: image: ghcr.io/cozystack/cozystack/lineage-controller-webhook:v1.3.0@sha256:e8984709686a5eaf19b89da378d7b8c688ea5607e0783a88d9c9e4ccfca96fb0 debug: false localK8sAPIEndpoint: + # incompatable with Deployment mode enabled: true # nodeSelector for the DaemonSet # Talos uses empty value: "node-role.kubernetes.io/control-plane": "" # Generic k8s (k3s, kubeadm) uses: "node-role.kubernetes.io/control-plane": "true" nodeSelector: node-role.kubernetes.io/control-plane: "" + # if enabled, replace DaemonSet by Deployment + deployment: + enabled: false + replicas: 1 From ab7deb2b055c2a677c4c84c1bb22271306ebf372 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 13:03:49 +0300 Subject: [PATCH 08/35] chore(kubernetes): regenerate after HAMi addon integration Run make generate to update generated types, schema, README, and CRD definitions for the new HAMi addon. Signed-off-by: Arsolitt --- api/apps/v1alpha1/kubernetes/types.go | 12 ++++++++++++ packages/apps/kubernetes/README.md | 3 +++ packages/apps/kubernetes/values.schema.json | 4 ++-- .../system/kubernetes-rd/cozyrds/kubernetes.yaml | 4 ++-- 4 files changed, 19 insertions(+), 4 deletions(-) diff --git a/api/apps/v1alpha1/kubernetes/types.go b/api/apps/v1alpha1/kubernetes/types.go index 774fcdc5..39a05567 100644 --- a/api/apps/v1alpha1/kubernetes/types.go +++ b/api/apps/v1alpha1/kubernetes/types.go @@ -66,6 +66,9 @@ type Addons struct { // NVIDIA GPU Operator. // +kubebuilder:default:={} GpuOperator GPUOperatorAddon `json:"gpuOperator"` + // HAMi GPU virtualization middleware. + // +kubebuilder:default:={} + Hami HAMiAddon `json:"hami"` // Ingress-NGINX controller. // +kubebuilder:default:={} IngressNginx IngressNginxAddon `json:"ingressNginx"` @@ -157,6 +160,15 @@ type GatewayAPIAddon struct { Enabled bool `json:"enabled"` } +type HAMiAddon struct { + // Enable HAMi (requires GPU Operator). + // +kubebuilder:default:=false + Enabled bool `json:"enabled"` + // Custom Helm values overrides. + // +kubebuilder:default:={} + ValuesOverride k8sRuntime.RawExtension `json:"valuesOverride"` +} + type IngressNginxAddon struct { // Enable the controller (requires nodes labeled `ingress-nginx`). // +kubebuilder:default:=false diff --git a/packages/apps/kubernetes/README.md b/packages/apps/kubernetes/README.md index d62d3a39..d705af64 100644 --- a/packages/apps/kubernetes/README.md +++ b/packages/apps/kubernetes/README.md @@ -128,6 +128,9 @@ See the reference for components utilized in this service: | `addons.gpuOperator` | NVIDIA GPU Operator. | `object` | `{}` | | `addons.gpuOperator.enabled` | Enable GPU Operator. | `bool` | `false` | | `addons.gpuOperator.valuesOverride` | Custom Helm values overrides. | `object` | `{}` | +| `addons.hami` | HAMi GPU virtualization middleware. | `object` | `{}` | +| `addons.hami.enabled` | Enable HAMi (requires GPU Operator). | `bool` | `false` | +| `addons.hami.valuesOverride` | Custom Helm values overrides. | `object` | `{}` | | `addons.fluxcd` | FluxCD GitOps operator. | `object` | `{}` | | `addons.fluxcd.enabled` | Enable FluxCD. | `bool` | `false` | | `addons.fluxcd.valuesOverride` | Custom Helm values overrides. | `object` | `{}` | diff --git a/packages/apps/kubernetes/values.schema.json b/packages/apps/kubernetes/values.schema.json index 3d7a17dd..1e457f1f 100644 --- a/packages/apps/kubernetes/values.schema.json +++ b/packages/apps/kubernetes/values.schema.json @@ -270,7 +270,7 @@ } }, "hami": { - "description": "HAMi GPU virtualization middleware. Enables fractional GPU sharing (memory and compute isolation) for workloads. Requires GPU Operator. Note: workload containers must use glibc < 2.34 (not musl/Alpine) for full compute isolation.", + "description": "HAMi GPU virtualization middleware.", "type": "object", "default": {}, "required": [ @@ -279,7 +279,7 @@ ], "properties": { "enabled": { - "description": "Enable HAMi.", + "description": "Enable HAMi (requires GPU Operator).", "type": "boolean", "default": false }, diff --git a/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml b/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml index 5e9e8f94..cdf900e1 100644 --- a/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml +++ b/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml @@ -8,7 +8,7 @@ spec: singular: kubernetes plural: kuberneteses openAPISchema: |- - {"title":"Chart Values","type":"object","properties":{"storageClass":{"description":"StorageClass used to store the data.","type":"string","default":"replicated"},"nodeGroups":{"description":"Worker nodes configuration map.","type":"object","default":{"md0":{"ephemeralStorage":"20Gi","gpus":[],"instanceType":"u1.medium","maxReplicas":10,"minReplicas":0,"resources":{},"roles":["ingress-nginx"]}},"additionalProperties":{"type":"object","required":["ephemeralStorage","instanceType","maxReplicas","minReplicas","resources"],"properties":{"ephemeralStorage":{"description":"Ephemeral storage size.","default":"20Gi","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"gpus":{"description":"List of GPUs to attach (NVIDIA driver requires at least 4 GiB RAM).","type":"array","items":{"type":"object","required":["name"],"properties":{"name":{"description":"Name of GPU, such as \"nvidia.com/AD102GL_L40S\".","type":"string"}}}},"instanceType":{"description":"Virtual machine instance type.","type":"string","default":"u1.medium"},"maxReplicas":{"description":"Maximum number of replicas.","type":"integer","default":10},"minReplicas":{"description":"Minimum number of replicas.","type":"integer","default":0},"resources":{"description":"CPU and memory resources for each worker node.","type":"object","properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"roles":{"description":"List of node roles.","type":"array","items":{"type":"string"}}}}},"version":{"description":"Kubernetes major.minor version to deploy","type":"string","default":"v1.35","enum":["v1.35","v1.34","v1.33","v1.32","v1.31","v1.30"]},"host":{"description":"External hostname for Kubernetes cluster. Defaults to `.` if empty.","type":"string","default":""},"addons":{"description":"Cluster addons configuration.","type":"object","default":{},"required":["certManager","cilium","coredns","fluxcd","gatewayAPI","gpuOperator","ingressNginx","monitoringAgents","velero","verticalPodAutoscaler"],"properties":{"certManager":{"description":"Cert-manager addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable cert-manager.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"cilium":{"description":"Cilium CNI plugin.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"coredns":{"description":"CoreDNS addon.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"fluxcd":{"description":"FluxCD GitOps operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable FluxCD.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"gatewayAPI":{"description":"Gateway API addon.","type":"object","default":{},"required":["enabled"],"properties":{"enabled":{"description":"Enable Gateway API.","type":"boolean","default":false}}},"gpuOperator":{"description":"NVIDIA GPU Operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable GPU Operator.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"ingressNginx":{"description":"Ingress-NGINX controller.","type":"object","default":{},"required":["enabled","exposeMethod","valuesOverride"],"properties":{"enabled":{"description":"Enable the controller (requires nodes labeled `ingress-nginx`).","type":"boolean","default":false},"exposeMethod":{"description":"Method to expose the controller. Allowed values: `Proxied`, `LoadBalancer`.","type":"string","default":"Proxied","enum":["Proxied","LoadBalancer"]},"hosts":{"description":"Domains routed to this tenant cluster when `exposeMethod` is `Proxied`.","type":"array","default":[],"items":{"type":"string"}},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"monitoringAgents":{"description":"Monitoring agents.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable monitoring agents.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"velero":{"description":"Velero backup/restore addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable Velero.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"verticalPodAutoscaler":{"description":"Vertical Pod Autoscaler.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}}}},"controlPlane":{"description":"Kubernetes control-plane configuration.","type":"object","default":{},"required":["apiServer","controllerManager","konnectivity","replicas","scheduler"],"properties":{"apiServer":{"description":"API Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for API Server.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"large","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"controllerManager":{"description":"Controller Manager configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Controller Manager.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"konnectivity":{"description":"Konnectivity configuration.","type":"object","default":{},"required":["server"],"properties":{"server":{"description":"Konnectivity Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Konnectivity.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"replicas":{"description":"Number of control-plane replicas.","type":"integer","default":2},"scheduler":{"description":"Scheduler configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Scheduler.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}}}} + {"title":"Chart Values","type":"object","properties":{"storageClass":{"description":"StorageClass used to store the data.","type":"string","default":"replicated"},"nodeGroups":{"description":"Worker nodes configuration map.","type":"object","default":{"md0":{"ephemeralStorage":"20Gi","gpus":[],"instanceType":"u1.medium","maxReplicas":10,"minReplicas":0,"resources":{},"roles":["ingress-nginx"]}},"additionalProperties":{"type":"object","required":["ephemeralStorage","instanceType","maxReplicas","minReplicas","resources"],"properties":{"ephemeralStorage":{"description":"Ephemeral storage size.","default":"20Gi","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"gpus":{"description":"List of GPUs to attach (NVIDIA driver requires at least 4 GiB RAM).","type":"array","items":{"type":"object","required":["name"],"properties":{"name":{"description":"Name of GPU, such as \"nvidia.com/AD102GL_L40S\".","type":"string"}}}},"instanceType":{"description":"Virtual machine instance type.","type":"string","default":"u1.medium"},"maxReplicas":{"description":"Maximum number of replicas.","type":"integer","default":10},"minReplicas":{"description":"Minimum number of replicas.","type":"integer","default":0},"resources":{"description":"CPU and memory resources for each worker node.","type":"object","properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"roles":{"description":"List of node roles.","type":"array","items":{"type":"string"}}}}},"version":{"description":"Kubernetes major.minor version to deploy","type":"string","default":"v1.35","enum":["v1.35","v1.34","v1.33","v1.32","v1.31","v1.30"]},"host":{"description":"External hostname for Kubernetes cluster. Defaults to `.` if empty.","type":"string","default":""},"addons":{"description":"Cluster addons configuration.","type":"object","default":{},"required":["certManager","cilium","coredns","fluxcd","gatewayAPI","gpuOperator","hami","ingressNginx","monitoringAgents","velero","verticalPodAutoscaler"],"properties":{"certManager":{"description":"Cert-manager addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable cert-manager.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"cilium":{"description":"Cilium CNI plugin.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"coredns":{"description":"CoreDNS addon.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"fluxcd":{"description":"FluxCD GitOps operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable FluxCD.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"gatewayAPI":{"description":"Gateway API addon.","type":"object","default":{},"required":["enabled"],"properties":{"enabled":{"description":"Enable Gateway API.","type":"boolean","default":false}}},"gpuOperator":{"description":"NVIDIA GPU Operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable GPU Operator.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"hami":{"description":"HAMi GPU virtualization middleware.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable HAMi (requires GPU Operator).","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"ingressNginx":{"description":"Ingress-NGINX controller.","type":"object","default":{},"required":["enabled","exposeMethod","valuesOverride"],"properties":{"enabled":{"description":"Enable the controller (requires nodes labeled `ingress-nginx`).","type":"boolean","default":false},"exposeMethod":{"description":"Method to expose the controller. Allowed values: `Proxied`, `LoadBalancer`.","type":"string","default":"Proxied","enum":["Proxied","LoadBalancer"]},"hosts":{"description":"Domains routed to this tenant cluster when `exposeMethod` is `Proxied`.","type":"array","default":[],"items":{"type":"string"}},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"monitoringAgents":{"description":"Monitoring agents.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable monitoring agents.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"velero":{"description":"Velero backup/restore addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable Velero.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"verticalPodAutoscaler":{"description":"Vertical Pod Autoscaler.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}}}},"controlPlane":{"description":"Kubernetes control-plane configuration.","type":"object","default":{},"required":["apiServer","controllerManager","konnectivity","replicas","scheduler"],"properties":{"apiServer":{"description":"API Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for API Server.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"large","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"controllerManager":{"description":"Controller Manager configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Controller Manager.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"konnectivity":{"description":"Konnectivity configuration.","type":"object","default":{},"required":["server"],"properties":{"server":{"description":"Konnectivity Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Konnectivity.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"replicas":{"description":"Number of control-plane replicas.","type":"integer","default":2},"scheduler":{"description":"Scheduler configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Scheduler.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}}}} release: prefix: kubernetes- labels: @@ -26,7 +26,7 @@ spec: tags: - compute icon: <svg width="144" height="144" viewBox="0 0 144 144" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect width="144" height="144" rx="24" fill="url(#paint0_linear_681_2845)"/>
<path d="M71.9968 19C70.3039 19.0002 68.9312 20.5322 68.9314 22.4221C68.9314 22.4511 68.9373 22.4788 68.9379 22.5076C68.9354 22.7644 68.9231 23.0737 68.9314 23.2973C68.9717 24.3873 69.2082 25.2216 69.3506 26.2258C69.6084 28.3752 69.8245 30.1569 69.6912 31.813C69.5615 32.4375 69.1037 33.0086 68.6956 33.4056L68.6235 34.7086C66.7839 34.8617 64.9319 35.1421 63.0821 35.5641C55.1226 37.3798 48.2695 41.4991 43.052 47.0609C42.7134 46.8288 42.1211 46.4019 41.945 46.2712C41.3977 46.3454 40.8445 46.5151 40.1241 46.0935C38.7522 45.1657 37.5028 43.8851 35.991 42.3424C35.2982 41.6044 34.7966 40.9018 33.9735 40.1904C33.7866 40.0289 33.5014 39.8104 33.2923 39.6442C32.6489 39.1288 31.89 38.86 31.157 38.8348C30.2147 38.8024 29.3075 39.1725 28.7138 39.9206C27.6584 41.2506 27.9963 43.2833 29.4671 44.4614C29.482 44.4734 29.4979 44.4827 29.5129 44.4943C29.715 44.6589 29.9625 44.8698 30.1483 45.0076C31.0217 45.6555 31.8195 45.9872 32.6897 46.5015C34.5231 47.6391 36.043 48.5823 37.2486 49.7196C37.7194 50.2237 37.8016 51.1122 37.8643 51.4964L38.8468 52.3782C33.5872 60.3308 31.153 70.1539 32.5915 80.1627L31.3077 80.5378C30.9693 80.9768 30.4912 81.6676 29.9911 81.8738C28.4138 82.3729 26.6387 82.5562 24.4956 82.7819C23.4894 82.866 22.6213 82.8158 21.5546 83.0188C21.3198 83.0635 20.9927 83.1491 20.7358 83.2097C20.7269 83.2116 20.7186 83.2142 20.7096 83.2162C20.6956 83.2195 20.6772 83.2263 20.6638 83.2294C18.857 83.668 17.6963 85.3365 18.0699 86.9805C18.4437 88.6248 20.2086 89.6248 22.0262 89.2312C22.0393 89.2282 22.0584 89.2277 22.072 89.2246C22.0926 89.2199 22.1106 89.2099 22.131 89.2049C22.3844 89.149 22.7019 89.0868 22.9236 89.0272C23.9723 88.7451 24.7318 88.3306 25.6746 87.9677C27.7029 87.2368 29.3828 86.6262 31.0195 86.3883C31.703 86.3345 32.4232 86.812 32.7814 87.0134L34.1177 86.7831C37.1926 96.3613 43.6366 104.103 51.7963 108.961L51.2396 110.303C51.4403 110.824 51.6616 111.53 51.5121 112.045C50.9171 113.595 49.898 115.231 48.7374 117.055C48.1755 117.898 47.6004 118.552 47.0934 119.516C46.972 119.747 46.8175 120.102 46.7004 120.346C45.9125 122.039 46.4904 123.99 48.0038 124.722C49.5268 125.459 51.4171 124.682 52.2352 122.985C52.2364 122.982 52.2406 122.98 52.2417 122.978C52.2426 122.976 52.2409 122.973 52.2417 122.971C52.3582 122.731 52.5233 122.415 52.6216 122.188C53.056 121.189 53.2005 120.332 53.5059 119.365C54.317 117.318 54.7626 115.17 55.8791 113.832C56.1849 113.466 56.6833 113.325 57.2001 113.186L57.8944 111.922C65.008 114.665 72.9705 115.402 80.9245 113.587C82.7391 113.173 84.4908 112.637 86.1843 111.994C86.3794 112.342 86.742 113.011 86.8393 113.179C87.3644 113.351 87.9377 113.439 88.4047 114.133C89.2401 115.567 89.8114 117.263 90.5073 119.312C90.8128 120.279 90.9638 121.136 91.3981 122.136C91.4971 122.363 91.6614 122.684 91.778 122.925C92.5944 124.628 94.4907 125.407 96.0159 124.669C97.5292 123.937 98.1077 121.986 97.3194 120.293C97.2023 120.049 97.0412 119.695 96.9198 119.464C96.4127 118.499 95.8377 117.852 95.2758 117.009C94.1152 115.185 93.1526 113.67 92.5575 112.12C92.3087 111.32 92.5995 110.823 92.7933 110.303C92.6772 110.17 92.4288 109.414 92.2824 109.059C100.762 104.029 107.017 95.9985 109.955 86.7239C110.351 86.7865 111.041 86.9091 111.265 86.9542C111.726 86.6487 112.149 86.2501 112.981 86.3159C114.617 86.5537 116.297 87.1645 118.326 87.8953C119.268 88.2581 120.028 88.6793 121.077 88.9614C121.298 89.021 121.616 89.0766 121.869 89.1325C121.889 89.1375 121.908 89.1475 121.928 89.1522C121.942 89.1553 121.961 89.1558 121.974 89.1588C123.792 89.552 125.557 88.5526 125.93 86.9081C126.303 85.2641 125.143 83.5952 123.336 83.157C123.074 83.097 122.701 82.995 122.446 82.9465C121.379 82.7435 120.511 82.7935 119.505 82.7095C117.361 82.4839 115.586 82.3004 114.009 81.8014C113.366 81.5507 112.908 80.7819 112.686 80.4655L111.448 80.1035C112.09 75.438 111.917 70.5825 110.806 65.7243C109.685 60.8208 107.704 56.3361 105.062 52.3848C105.379 52.0948 105.979 51.5612 106.149 51.4043C106.199 50.8517 106.156 50.2722 106.725 49.6603C107.931 48.523 109.451 47.5799 111.284 46.4423C112.154 45.9279 112.959 45.5964 113.832 44.9484C114.03 44.8019 114.299 44.5699 114.507 44.4022C115.977 43.2237 116.316 41.1911 115.26 39.8614C114.204 38.5317 112.159 38.4065 110.688 39.585C110.479 39.7516 110.195 39.9688 110.007 40.1312C109.184 40.8426 108.676 41.5452 107.983 42.2832C106.471 43.8259 105.222 45.113 103.85 46.0409C103.255 46.3885 102.385 46.2682 101.99 46.2449L100.824 47.0806C94.1753 40.0763 85.1235 35.5982 75.3766 34.7283C75.3494 34.3179 75.3137 33.5761 75.3046 33.3529C74.9056 32.9693 74.4235 32.6418 74.3024 31.813C74.1691 30.1569 74.3917 28.3752 74.6496 26.2258C74.7919 25.2216 75.0284 24.3873 75.0688 23.2973C75.078 23.0495 75.0632 22.69 75.0622 22.4221C75.062 20.5322 73.6898 18.9998 71.9968 19ZM68.1585 42.8886L67.248 59.0447L67.1825 59.0776C67.1214 60.5229 65.9375 61.677 64.4839 61.677C63.8884 61.677 63.3388 61.4849 62.8922 61.1571L62.866 61.1703L49.6807 51.7794C53.7331 47.7759 58.9164 44.8172 64.89 43.4546C65.9812 43.2056 67.0719 43.0209 68.1585 42.8886ZM75.8417 42.8886C82.8159 43.7504 89.2657 46.9232 94.2081 51.786L81.108 61.1176L81.0621 61.0979C79.8994 61.9512 78.2611 61.7394 77.3548 60.5978C76.9835 60.1301 76.7887 59.5801 76.7653 59.0249L76.7522 59.0184L75.8417 42.8886ZM44.8991 57.814L56.9382 68.633L56.9251 68.6988C58.0117 69.6479 58.172 71.2949 57.2657 72.4368C56.8944 72.9045 56.3975 73.2182 55.8639 73.3647L55.8508 73.4173L40.4188 77.8923C39.6334 70.6765 41.3261 63.6621 44.8991 57.814ZM99.0094 57.8206C100.798 60.7336 102.153 63.9871 102.959 67.5143C103.756 70.9991 103.956 74.4778 103.627 77.8397L88.1166 73.3515L88.1035 73.2857C86.7145 72.9043 85.8609 71.4848 86.1843 70.0611C86.3168 69.4778 86.6249 68.9844 87.0423 68.6198L87.0358 68.5869L99.0094 57.8206ZM69.5274 69.4688H74.4596L77.5251 73.3186L76.4247 78.1226L71.9968 80.2614L67.5558 78.1161L66.4554 73.312L69.5274 69.4688ZM85.3393 82.6437C85.5489 82.6331 85.7576 82.652 85.9616 82.6898L85.9878 82.6569L101.95 85.3682C99.6142 91.9624 95.144 97.675 89.1711 101.498L82.9747 86.4606L82.9944 86.4343C82.4252 85.1055 82.9948 83.5472 84.3044 82.9135C84.6397 82.7513 84.99 82.6614 85.3393 82.6437ZM58.5298 82.7095C59.748 82.7267 60.8406 83.5761 61.1237 84.822C61.2562 85.4052 61.1917 85.9831 60.973 86.4935L61.0189 86.5527L54.888 101.439C49.1559 97.7432 44.5904 92.2099 42.1481 85.4208L57.9731 82.7227L57.9993 82.7556C58.1763 82.7229 58.3558 82.7071 58.5298 82.7095ZM71.8986 89.2312C72.3229 89.2155 72.7534 89.303 73.1627 89.501C73.6992 89.7606 74.1136 90.1692 74.3745 90.6592H74.4334L82.2346 104.821C81.2221 105.162 80.1813 105.454 79.1167 105.697C73.1505 107.058 67.2032 106.645 61.818 104.802L69.5995 90.6658H69.6126C70.0795 89.7888 70.965 89.2656 71.8986 89.2312Z" fill="white" stroke="white" stroke-width="0.25"/>
<defs>
<linearGradient id="paint0_linear_681_2845" x1="10" y1="15.5" x2="144" y2="131.5" gradientUnits="userSpaceOnUse">
<stop stop-color="#4D87FF"/>
<stop offset="1" stop-color="#0547D0"/>
</linearGradient>
</defs>
</svg>
 - keysOrder: [["apiVersion"], ["appVersion"], ["kind"], ["metadata"], ["metadata", "name"], ["spec", "storageClass"], ["spec", "nodeGroups"], ["spec", "nodeGroups", "md0"], ["spec", "nodeGroups", "md0", "minReplicas"], ["spec", "nodeGroups", "md0", "maxReplicas"], ["spec", "nodeGroups", "md0", "instanceType"], ["spec", "nodeGroups", "md0", "ephemeralStorage"], ["spec", "nodeGroups", "md0", "roles"], ["spec", "nodeGroups", "md0", "resources"], ["spec", "nodeGroups", "md0", "gpus"], ["spec", "version"], ["spec", "host"], ["spec", "addons"], ["spec", "addons", "certManager"], ["spec", "addons", "certManager", "enabled"], ["spec", "addons", "certManager", "valuesOverride"], ["spec", "addons", "cilium"], ["spec", "addons", "cilium", "valuesOverride"], ["spec", "addons", "gatewayAPI"], ["spec", "addons", "gatewayAPI", "enabled"], ["spec", "addons", "ingressNginx"], ["spec", "addons", "ingressNginx", "enabled"], ["spec", "addons", "ingressNginx", "exposeMethod"], ["spec", "addons", "ingressNginx", "hosts"], ["spec", "addons", "ingressNginx", "valuesOverride"], ["spec", "addons", "gpuOperator"], ["spec", "addons", "gpuOperator", "enabled"], ["spec", "addons", "gpuOperator", "valuesOverride"], ["spec", "addons", "fluxcd"], ["spec", "addons", "fluxcd", "enabled"], ["spec", "addons", "fluxcd", "valuesOverride"], ["spec", "addons", "monitoringAgents"], ["spec", "addons", "monitoringAgents", "enabled"], ["spec", "addons", "monitoringAgents", "valuesOverride"], ["spec", "addons", "verticalPodAutoscaler"], ["spec", "addons", "verticalPodAutoscaler", "valuesOverride"], ["spec", "addons", "velero"], ["spec", "addons", "velero", "enabled"], ["spec", "addons", "velero", "valuesOverride"], ["spec", "addons", "coredns"], ["spec", "addons", "coredns", "valuesOverride"], ["spec", "controlPlane"], ["spec", "controlPlane", "replicas"], ["spec", "controlPlane", "apiServer"], ["spec", "controlPlane", "apiServer", "resources"], ["spec", "controlPlane", "apiServer", "resourcesPreset"], ["spec", "controlPlane", "controllerManager"], ["spec", "controlPlane", "controllerManager", "resources"], ["spec", "controlPlane", "controllerManager", "resourcesPreset"], ["spec", "controlPlane", "scheduler"], ["spec", "controlPlane", "scheduler", "resources"], ["spec", "controlPlane", "scheduler", "resourcesPreset"], ["spec", "controlPlane", "konnectivity"], ["spec", "controlPlane", "konnectivity", "server"], ["spec", "controlPlane", "konnectivity", "server", "resources"], ["spec", "controlPlane", "konnectivity", "server", "resourcesPreset"]] + keysOrder: [["apiVersion"], ["appVersion"], ["kind"], ["metadata"], ["metadata", "name"], ["spec", "storageClass"], ["spec", "nodeGroups"], ["spec", "nodeGroups", "md0"], ["spec", "nodeGroups", "md0", "minReplicas"], ["spec", "nodeGroups", "md0", "maxReplicas"], ["spec", "nodeGroups", "md0", "instanceType"], ["spec", "nodeGroups", "md0", "ephemeralStorage"], ["spec", "nodeGroups", "md0", "roles"], ["spec", "nodeGroups", "md0", "resources"], ["spec", "nodeGroups", "md0", "gpus"], ["spec", "version"], ["spec", "host"], ["spec", "addons"], ["spec", "addons", "certManager"], ["spec", "addons", "certManager", "enabled"], ["spec", "addons", "certManager", "valuesOverride"], ["spec", "addons", "cilium"], ["spec", "addons", "cilium", "valuesOverride"], ["spec", "addons", "gatewayAPI"], ["spec", "addons", "gatewayAPI", "enabled"], ["spec", "addons", "ingressNginx"], ["spec", "addons", "ingressNginx", "enabled"], ["spec", "addons", "ingressNginx", "exposeMethod"], ["spec", "addons", "ingressNginx", "hosts"], ["spec", "addons", "ingressNginx", "valuesOverride"], ["spec", "addons", "gpuOperator"], ["spec", "addons", "gpuOperator", "enabled"], ["spec", "addons", "gpuOperator", "valuesOverride"], ["spec", "addons", "hami"], ["spec", "addons", "hami", "enabled"], ["spec", "addons", "hami", "valuesOverride"], ["spec", "addons", "fluxcd"], ["spec", "addons", "fluxcd", "enabled"], ["spec", "addons", "fluxcd", "valuesOverride"], ["spec", "addons", "monitoringAgents"], ["spec", "addons", "monitoringAgents", "enabled"], ["spec", "addons", "monitoringAgents", "valuesOverride"], ["spec", "addons", "verticalPodAutoscaler"], ["spec", "addons", "verticalPodAutoscaler", "valuesOverride"], ["spec", "addons", "velero"], ["spec", "addons", "velero", "enabled"], ["spec", "addons", "velero", "valuesOverride"], ["spec", "addons", "coredns"], ["spec", "addons", "coredns", "valuesOverride"], ["spec", "controlPlane"], ["spec", "controlPlane", "replicas"], ["spec", "controlPlane", "apiServer"], ["spec", "controlPlane", "apiServer", "resources"], ["spec", "controlPlane", "apiServer", "resourcesPreset"], ["spec", "controlPlane", "controllerManager"], ["spec", "controlPlane", "controllerManager", "resources"], ["spec", "controlPlane", "controllerManager", "resourcesPreset"], ["spec", "controlPlane", "scheduler"], ["spec", "controlPlane", "scheduler", "resources"], ["spec", "controlPlane", "scheduler", "resourcesPreset"], ["spec", "controlPlane", "konnectivity"], ["spec", "controlPlane", "konnectivity", "server"], ["spec", "controlPlane", "konnectivity", "server", "resources"], ["spec", "controlPlane", "konnectivity", "server", "resourcesPreset"]] secrets: exclude: [] include: From 2734dc0bcb96aaa087cbff6b2ee261e1bde8bffa Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 14:00:48 +0300 Subject: [PATCH 09/35] fix(hami): clean up leftover hami-dra references and harden defaults Remove broken hami-dra subchart dependency from vendored chart (Chart.yaml, Chart.lock, values.yaml) and strip DRA condition guards from all templates since the subchart was already deleted. Override devicePlugin updateStrategy to OnDelete to prevent destructive rolling updates of GPU workloads. Align gpu-operator template with project pattern (unconditional values emission). Add nodeConfiguration format documentation and test for conflicting valuesOverride scenario. Signed-off-by: Arsolitt --- .../templates/helmreleases/gpu-operator.yaml | 6 ++--- .../tests/gpu_operator_hami_test.yaml | 25 ++++++++++++++++++- packages/system/hami/charts/hami/Chart.lock | 6 ----- packages/system/hami/charts/hami/Chart.yaml | 6 +---- .../templates/device-plugin/configmap.yaml | 2 +- .../device-plugin/daemonsetnvidia.yaml | 2 +- .../templates/device-plugin/monitorrole.yaml | 2 +- .../device-plugin/monitorrolebinding.yaml | 2 +- .../device-plugin/monitorservice.yaml | 2 +- .../device-plugin/monitorserviceaccount.yaml | 2 +- .../device-plugin/runtime-class.yaml | 4 +-- .../hami/templates/scheduler/certmanager.yaml | 2 +- .../hami/templates/scheduler/clusterrole.yaml | 2 -- .../scheduler/clusterrolebinding.yaml | 4 +-- .../hami/templates/scheduler/configmap.yaml | 2 +- .../templates/scheduler/configmapnew.yaml | 2 +- .../hami/templates/scheduler/deployment.yaml | 4 +-- .../templates/scheduler/device-configmap.yaml | 4 +-- .../scheduler/job-patch/clusterrole.yaml | 4 +-- .../job-patch/clusterrolebinding.yaml | 4 +-- .../scheduler/job-patch/job-createSecret.yaml | 4 +-- .../scheduler/job-patch/job-patchWebhook.yaml | 4 +-- .../templates/scheduler/job-patch/psp.yaml | 4 +-- .../templates/scheduler/job-patch/role.yaml | 4 +-- .../scheduler/job-patch/rolebinding.yaml | 4 +-- .../scheduler/job-patch/serviceaccount.yaml | 4 +-- .../charts/hami/templates/scheduler/role.yaml | 4 +-- .../hami/templates/scheduler/rolebinding.yaml | 2 -- .../hami/templates/scheduler/service.yaml | 4 +-- .../templates/scheduler/serviceaccount.yaml | 2 -- .../hami/templates/scheduler/webhook.yaml | 2 +- packages/system/hami/charts/hami/values.yaml | 18 ------------- packages/system/hami/values.yaml | 4 +++ 33 files changed, 55 insertions(+), 92 deletions(-) delete mode 100644 packages/system/hami/charts/hami/Chart.lock diff --git a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml index 995aa430..7a5ecaf1 100644 --- a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml @@ -1,5 +1,5 @@ {{- define "cozystack.defaultGpuOperatorValues" -}} -{{- if and (hasKey .Values.addons "hami") .Values.addons.hami.enabled }} +{{- if .Values.addons.hami.enabled }} gpu-operator: devicePlugin: enabled: false @@ -40,10 +40,8 @@ spec: {{- $defaults := fromYaml (include "cozystack.defaultGpuOperatorValues" .) }} {{- $overrides := deepCopy (default (dict) .Values.addons.gpuOperator.valuesOverride) }} {{- $merged := mergeOverwrite (default (dict) $defaults) $overrides }} - {{- with $merged }} values: - {{- toYaml . | nindent 4 }} - {{- end }} + {{- if $merged }}{{ toYaml $merged | nindent 4 }}{{ end }} dependsOn: {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }} diff --git a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml index 33256ae6..11de743a 100644 --- a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml +++ b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml @@ -26,8 +26,9 @@ tests: enabled: false valuesOverride: {} asserts: - - notExists: + - equal: path: spec.values + value: null - it: should allow user overrides to merge with hami defaults set: @@ -66,6 +67,28 @@ tests: path: spec.values.gpu-operator.devicePlugin.enabled value: true + - it: should let user explicitly override devicePlugin.enabled to true with hami enabled + set: + addons: + gpuOperator: + enabled: true + valuesOverride: + gpu-operator: + devicePlugin: + enabled: true + driver: + enabled: false + hami: + enabled: true + valuesOverride: {} + asserts: + - equal: + path: spec.values.gpu-operator.devicePlugin.enabled + value: true + - equal: + path: spec.values.gpu-operator.driver.enabled + value: false + - it: should not render when gpuOperator is disabled set: addons: diff --git a/packages/system/hami/charts/hami/Chart.lock b/packages/system/hami/charts/hami/Chart.lock deleted file mode 100644 index 25856c07..00000000 --- a/packages/system/hami/charts/hami/Chart.lock +++ /dev/null @@ -1,6 +0,0 @@ -dependencies: -- name: hami-dra - repository: https://project-hami.github.io/HAMi-DRA/ - version: 0.1.0 -digest: sha256:374551539570bcee82c1c4dea93eac59e6f410b6d5967d188efd630e203d43bb -generated: "2026-04-17T04:06:47.689117678Z" diff --git a/packages/system/hami/charts/hami/Chart.yaml b/packages/system/hami/charts/hami/Chart.yaml index aba7e95c..55f32ab6 100644 --- a/packages/system/hami/charts/hami/Chart.yaml +++ b/packages/system/hami/charts/hami/Chart.yaml @@ -1,10 +1,6 @@ apiVersion: v2 appVersion: 2.8.1 -dependencies: -- condition: dra.enabled - name: hami-dra - repository: https://project-hami.github.io/HAMi-DRA/ - version: 0.1.0 +dependencies: [] description: Heterogeneous AI Computing Virtualization Middleware keywords: - vgpu diff --git a/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml index b36347f2..db2ddacb 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.devicePlugin.nodeConfiguration.externalConfigName) (not .Values.dra.enabled) -}} +{{- if and .Values.devicePlugin.enabled (not .Values.devicePlugin.nodeConfiguration.externalConfigName) -}} apiVersion: v1 kind: ConfigMap metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml index 577dc0f9..1f4c24f3 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/daemonsetnvidia.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) }} +{{- if .Values.devicePlugin.enabled }} apiVersion: apps/v1 kind: DaemonSet metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml index c51ff6c6..377f6a86 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +{{- if .Values.devicePlugin.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml index 93a118dd..2f0a14ba 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorrolebinding.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +{{- if .Values.devicePlugin.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml index 24daca9b..0fb156cc 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +{{- if .Values.devicePlugin.enabled -}} apiVersion: v1 kind: Service metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml index b10d2cb9..6e3c2a44 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorserviceaccount.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} +{{- if .Values.devicePlugin.enabled -}} apiVersion: v1 kind: ServiceAccount metadata: diff --git a/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml b/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml index cd3d14cc..ebcc2c9c 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/runtime-class.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.devicePlugin.enabled (not .Values.dra.enabled) -}} -{{- if and .Values.devicePlugin.createRuntimeClass .Values.devicePlugin.runtimeClassName }} +{{- if and .Values.devicePlugin.enabled .Values.devicePlugin.createRuntimeClass .Values.devicePlugin.runtimeClassName -}} apiVersion: node.k8s.io/v1 kind: RuntimeClass metadata: @@ -7,5 +6,4 @@ metadata: annotations: helm.sh/hook: pre-install,pre-upgrade handler: nvidia -{{- end }} {{- end -}} diff --git a/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml b/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml index b6edb605..e6d28721 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/certmanager.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if .Values.scheduler.admissionWebhook.enabled -}} {{- if .Values.scheduler.certManager.enabled }} apiVersion: cert-manager.io/v1 kind: Certificate diff --git a/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml b/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml index 9c510c00..81c4fddf 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/clusterrole.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: @@ -33,4 +32,3 @@ rules: resources: ["nodes"] verbs: ["get", "update", "list", "patch"] {{- end -}} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml index 69d75986..aa0f3c66 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: @@ -45,5 +44,4 @@ roleRef: subjects: - kind: ServiceAccount name: {{ include "hami-vgpu.scheduler" . }} - namespace: {{ include "hami-vgpu.namespace" . }} -{{- end }} \ No newline at end of file + namespace: {{ include "hami-vgpu.namespace" . }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml b/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml index 75889146..109ecbce 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/configmap.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.scheduler.kubeScheduler.enabled (not .Values.dra.enabled) -}} +{{- if .Values.scheduler.kubeScheduler.enabled -}} apiVersion: v1 kind: ConfigMap metadata: diff --git a/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml b/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml index e2a91d8b..6f6db097 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/configmapnew.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.scheduler.kubeScheduler.enabled (not .Values.dra.enabled) -}} +{{- if .Values.scheduler.kubeScheduler.enabled -}} apiVersion: v1 kind: ConfigMap metadata: diff --git a/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml index 6364cae3..12911a42 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: apps/v1 kind: Deployment metadata: @@ -223,5 +222,4 @@ spec: {{- end }} {{- if .Values.scheduler.nodeName }} nodeName: {{ .Values.scheduler.nodeName }} - {{- end }} -{{- end }} \ No newline at end of file + {{- end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml index ccb945ac..8738a06f 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: v1 kind: ConfigMap metadata: @@ -406,5 +405,4 @@ data: memory: 12288 aiCore: 4 aiCPU: 4 - {{ end }} -{{- end }} \ No newline at end of file + {{ end }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml index b089ae82..412b1094 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: @@ -27,4 +26,3 @@ rules: - {{ include "hami-vgpu.fullname" . }}-admission {{- end }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml index 64f01ecf..2b82f926 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrolebinding.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: @@ -19,4 +18,3 @@ subjects: name: {{ include "hami-vgpu.fullname" . }}-admission namespace: {{ include "hami-vgpu.namespace" . }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml index 400168a7..0e36d95f 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-createSecret.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: batch/v1 kind: Job metadata: @@ -67,4 +66,3 @@ spec: runAsNonRoot: true runAsUser: {{ .Values.scheduler.patch.runAsUser }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml index 71e97f6b..ce52042c 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/job-patchWebhook.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: batch/v1 kind: Job metadata: @@ -62,4 +61,3 @@ spec: runAsNonRoot: true runAsUser: {{ .Values.scheduler.patch.runAsUser }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml index a48270e7..1e9cd7da 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} {{- if .Values.podSecurityPolicy.enabled }} apiVersion: policy/v1beta1 kind: PodSecurityPolicy @@ -37,4 +36,3 @@ spec: - downwardAPI {{- end }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml index 74e45681..56682f8e 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/role.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: @@ -20,4 +19,3 @@ rules: - get - create {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml index 32da5ba4..7239b128 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/rolebinding.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: @@ -20,4 +19,3 @@ subjects: name: {{ include "hami-vgpu.fullname" . }}-admission namespace: {{ include "hami-vgpu.namespace" . }} {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml index d2eb41de..857c6a8d 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/serviceaccount.yaml @@ -1,5 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) }} -{{- if and (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} +{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) }} apiVersion: v1 kind: ServiceAccount metadata: @@ -12,4 +11,3 @@ metadata: {{- include "hami-vgpu.labels" . | nindent 4 }} app.kubernetes.io/component: admission-webhook {{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/role.yaml b/packages/system/hami/charts/hami/templates/scheduler/role.yaml index 6e681967..90987a4f 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/role.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/role.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: @@ -10,5 +9,4 @@ metadata: rules: - apiGroups: ["coordination.k8s.io"] resources: ["leases"] - verbs: ["create", "list", "watch", "get", "update", "patch"] -{{- end }} \ No newline at end of file + verbs: ["create", "list", "watch", "get", "update", "patch"] \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml index 934f8223..96e175a1 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/rolebinding.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: @@ -30,4 +29,3 @@ subjects: name: {{ include "hami-vgpu.mock-device-plugin" . }} namespace: {{ include "hami-vgpu.namespace" . }} {{- end -}} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/service.yaml b/packages/system/hami/charts/hami/templates/scheduler/service.yaml index 3e18bc98..70378c5c 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/service.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/service.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled }} apiVersion: v1 kind: Service metadata: @@ -32,5 +31,4 @@ spec: protocol: TCP selector: app.kubernetes.io/component: hami-scheduler - {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} -{{- end }} \ No newline at end of file + {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} \ No newline at end of file diff --git a/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml b/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml index 929bf59a..0435c003 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/serviceaccount.yaml @@ -1,4 +1,3 @@ -{{- if not .Values.dra.enabled -}} apiVersion: v1 kind: ServiceAccount metadata: @@ -15,4 +14,3 @@ metadata: name: {{ include "hami-vgpu.mock-device-plugin" . }} namespace: {{ include "hami-vgpu.namespace" . }} {{- end -}} -{{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml index 148feb5c..7296eb4e 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml @@ -1,4 +1,4 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (not .Values.dra.enabled) -}} +{{- if .Values.scheduler.admissionWebhook.enabled -}} apiVersion: admissionregistration.k8s.io/v1 kind: MutatingWebhookConfiguration metadata: diff --git a/packages/system/hami/charts/hami/values.yaml b/packages/system/hami/charts/hami/values.yaml index 9fbeca70..02feeada 100644 --- a/packages/system/hami/charts/hami/values.yaml +++ b/packages/system/hami/charts/hami/values.yaml @@ -392,24 +392,6 @@ mockDevicePlugin: ## - myRegistryKeySecretName ## pullSecrets: [] -# If this option is enabled, the DRA will be installed and the scheduler extender will not be installed. -dra: - enabled: false - -# Configuration for the hami-dra subchart, which includes DRA drivers. -# This is part of config for DRA, please refer to the DRA documentation for more details. -hami-dra: - monitor: - enabled: true - drivers: - nvidia: - enabled: true - # If you are using gpu driver on host, you need to set this to false - containerDriver: true - image: - repository: projecthami/k8s-dra-driver - tag: "v0.0.1-dev" - devices: amd: customresources: diff --git a/packages/system/hami/values.yaml b/packages/system/hami/values.yaml index 1155e2cb..1d1407b7 100644 --- a/packages/system/hami/values.yaml +++ b/packages/system/hami/values.yaml @@ -1,6 +1,10 @@ hami: devicePlugin: runtimeClassName: nvidia + updateStrategy: + type: OnDelete + # See upstream charts/hami/values.yaml for nodeConfiguration format. + # Each entry: {"name": "node-name", "operatingmode": "hami-core", "devicesplitcount": N, ...} nodeConfiguration: config: | { From 37d5ff0c6f0566ca18495e871c5ad626f7976ca1 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 14:07:17 +0300 Subject: [PATCH 10/35] fix(hami): align templates with project patterns and clean dead code Unconditionally emit values in hami.yaml matching the project pattern. Remove duplicate test case and add coverage for omitted valuesOverride key. Delete dead PSP template and RBAC rules (policy/v1beta1 removed in K8s 1.25). Override kube-scheduler image registry to registry.k8s.io to avoid Chinese registry for international users. Signed-off-by: Arsolitt --- .../templates/helmreleases/hami.yaml | 4 +- .../tests/gpu_operator_hami_test.yaml | 29 ++++++-------- .../scheduler/job-patch/clusterrole.yaml | 7 ---- .../templates/scheduler/job-patch/psp.yaml | 38 ------------------- packages/system/hami/charts/hami/values.yaml | 3 -- packages/system/hami/values.yaml | 5 +++ 6 files changed, 18 insertions(+), 68 deletions(-) delete mode 100644 packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml diff --git a/packages/apps/kubernetes/templates/helmreleases/hami.yaml b/packages/apps/kubernetes/templates/helmreleases/hami.yaml index 1f7a5358..ac4714da 100644 --- a/packages/apps/kubernetes/templates/helmreleases/hami.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/hami.yaml @@ -32,10 +32,8 @@ spec: force: true remediation: retries: -1 - {{- with .Values.addons.hami.valuesOverride }} values: - {{- toYaml . | nindent 4 }} - {{- end }} + {{- if .Values.addons.hami.valuesOverride }}{{ toYaml .Values.addons.hami.valuesOverride | nindent 4 }}{{ end }} dependsOn: {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }} diff --git a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml index 11de743a..c3ec30f2 100644 --- a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml +++ b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml @@ -30,6 +30,18 @@ tests: path: spec.values value: null + - it: should apply hami defaults when valuesOverride key is omitted + set: + addons: + gpuOperator: + enabled: true + hami: + enabled: true + asserts: + - equal: + path: spec.values.gpu-operator.devicePlugin.enabled + value: false + - it: should allow user overrides to merge with hami defaults set: addons: @@ -50,23 +62,6 @@ tests: path: spec.values.gpu-operator.driver.enabled value: false - - it: should let user override devicePlugin back to true if needed - set: - addons: - gpuOperator: - enabled: true - valuesOverride: - gpu-operator: - devicePlugin: - enabled: true - hami: - enabled: true - valuesOverride: {} - asserts: - - equal: - path: spec.values.gpu-operator.devicePlugin.enabled - value: true - - it: should let user explicitly override devicePlugin.enabled to true with hami enabled set: addons: diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml index 412b1094..77e891cc 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/job-patch/clusterrole.yaml @@ -18,11 +18,4 @@ rules: verbs: - get - update -{{- if .Values.podSecurityPolicy.enabled }} - - apiGroups: ['extensions'] - resources: ['podsecuritypolicies'] - verbs: ['use'] - resourceNames: - - {{ include "hami-vgpu.fullname" . }}-admission -{{- end }} {{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml b/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml deleted file mode 100644 index 1e9cd7da..00000000 --- a/packages/system/hami/charts/hami/templates/scheduler/job-patch/psp.yaml +++ /dev/null @@ -1,38 +0,0 @@ -{{- if and .Values.scheduler.admissionWebhook.enabled (.Values.scheduler.patch.enabled) (not .Values.scheduler.certManager.enabled) -}} -{{- if .Values.podSecurityPolicy.enabled }} -apiVersion: policy/v1beta1 -kind: PodSecurityPolicy -metadata: - name: {{ include "hami-vgpu.fullname" . }}-admission - annotations: - "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade - "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded - labels: - {{- include "hami-vgpu.labels" . | nindent 4 }} - app.kubernetes.io/component: admission-webhook -spec: - allowPrivilegeEscalation: false - fsGroup: - ranges: - - max: 65535 - min: 1 - rule: MustRunAs - requiredDropCapabilities: - - ALL - runAsUser: - rule: MustRunAsNonRoot - seLinux: - rule: RunAsAny - supplementalGroups: - ranges: - - max: 65535 - min: 1 - rule: MustRunAs - volumes: - - configMap - - emptyDir - - projected - - secret - - downwardAPI -{{- end }} -{{- end }} diff --git a/packages/system/hami/charts/hami/values.yaml b/packages/system/hami/charts/hami/values.yaml index 02feeada..01caca0b 100644 --- a/packages/system/hami/charts/hami/values.yaml +++ b/packages/system/hami/charts/hami/values.yaml @@ -55,9 +55,6 @@ kunlunResourceVMemoryName: "kunlunxin.com/vxpu-memory" schedulerName: "hami-scheduler" -podSecurityPolicy: - enabled: false - scheduler: # @param nodeName defines the node name and the nvidia-vgpu-scheduler-scheduler will schedule to the node. # if we install the nvidia-vgpu-scheduler-scheduler as default scheduler, we need to remove the k8s default diff --git a/packages/system/hami/values.yaml b/packages/system/hami/values.yaml index 1d1407b7..f45d2998 100644 --- a/packages/system/hami/values.yaml +++ b/packages/system/hami/values.yaml @@ -1,4 +1,9 @@ hami: + scheduler: + kubeScheduler: + image: + registry: registry.k8s.io + repository: kube-scheduler devicePlugin: runtimeClassName: nvidia updateStrategy: From 6a9c310a4bfdb8bab3cd4f52724205adfbd2219e Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 15:31:24 +0300 Subject: [PATCH 11/35] fix(hami): conditional values emission and cosmetic template cleanup Only emit values key in hami.yaml when valuesOverride has content, matching gpu-operator pattern. Add test verifying empty valuesOverride does not produce spec.values. Fix trailing whitespace and missing newlines in vendored chart templates. Signed-off-by: Arsolitt --- .../kubernetes/templates/helmreleases/hami.yaml | 4 +++- packages/apps/kubernetes/tests/hami_test.yaml | 15 +++++++++++++++ .../hami/charts/hami/templates/_commons.tpl | 2 +- .../hami/templates/device-plugin/configmap.yaml | 2 +- .../hami/templates/device-plugin/monitorrole.yaml | 3 +-- .../templates/device-plugin/monitorservice.yaml | 2 +- .../templates/scheduler/clusterrolebinding.yaml | 2 +- .../hami/templates/scheduler/deployment.yaml | 2 +- .../templates/scheduler/device-configmap.yaml | 2 +- .../charts/hami/templates/scheduler/role.yaml | 2 +- .../charts/hami/templates/scheduler/service.yaml | 2 +- .../charts/hami/templates/scheduler/webhook.yaml | 2 +- 12 files changed, 28 insertions(+), 12 deletions(-) diff --git a/packages/apps/kubernetes/templates/helmreleases/hami.yaml b/packages/apps/kubernetes/templates/helmreleases/hami.yaml index ac4714da..8733e675 100644 --- a/packages/apps/kubernetes/templates/helmreleases/hami.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/hami.yaml @@ -32,8 +32,10 @@ spec: force: true remediation: retries: -1 + {{- if .Values.addons.hami.valuesOverride }} values: - {{- if .Values.addons.hami.valuesOverride }}{{ toYaml .Values.addons.hami.valuesOverride | nindent 4 }}{{ end }} + {{- toYaml .Values.addons.hami.valuesOverride | nindent 4 }} + {{- end }} dependsOn: {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }} diff --git a/packages/apps/kubernetes/tests/hami_test.yaml b/packages/apps/kubernetes/tests/hami_test.yaml index e9d32236..bdbe990f 100644 --- a/packages/apps/kubernetes/tests/hami_test.yaml +++ b/packages/apps/kubernetes/tests/hami_test.yaml @@ -118,6 +118,21 @@ tests: name: test-gpu-operator namespace: test-ns + - it: should not render spec.values when valuesOverride is empty + set: + addons: + hami: + enabled: true + valuesOverride: {} + gpuOperator: + enabled: true + valuesOverride: {} + asserts: + - hasDocuments: + count: 1 + - notExists: + path: spec.values + - it: should pass through valuesOverride set: addons: diff --git a/packages/system/hami/charts/hami/templates/_commons.tpl b/packages/system/hami/charts/hami/templates/_commons.tpl index 78a262c9..b68018e4 100644 --- a/packages/system/hami/charts/hami/templates/_commons.tpl +++ b/packages/system/hami/charts/hami/templates/_commons.tpl @@ -46,4 +46,4 @@ imagePullSecrets: - name: {{ . }} {{- end }} {{- end }} -{{- end -}} \ No newline at end of file +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml index db2ddacb..74631e24 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/configmap.yaml @@ -10,4 +10,4 @@ metadata: data: config.json: | {{- .Values.devicePlugin.nodeConfiguration.config | nindent 4 }} -{{- end }} \ No newline at end of file +{{- end }} diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml index 377f6a86..6ac757f2 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorrole.yaml @@ -25,5 +25,4 @@ rules: - list - patch {{- end -}} - - + diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml index 0fb156cc..104664ea 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml @@ -26,4 +26,4 @@ spec: selector: app.kubernetes.io/component: hami-device-plugin {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} -{{- end -}} \ No newline at end of file +{{- end -}} diff --git a/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml index aa0f3c66..a81d425c 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/clusterrolebinding.yaml @@ -44,4 +44,4 @@ roleRef: subjects: - kind: ServiceAccount name: {{ include "hami-vgpu.scheduler" . }} - namespace: {{ include "hami-vgpu.namespace" . }} \ No newline at end of file + namespace: {{ include "hami-vgpu.namespace" . }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml index 12911a42..1d89e189 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/deployment.yaml @@ -222,4 +222,4 @@ spec: {{- end }} {{- if .Values.scheduler.nodeName }} nodeName: {{ .Values.scheduler.nodeName }} - {{- end }} \ No newline at end of file + {{- end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml index 8738a06f..873b813b 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/device-configmap.yaml @@ -405,4 +405,4 @@ data: memory: 12288 aiCore: 4 aiCPU: 4 - {{ end }} \ No newline at end of file + {{ end }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/role.yaml b/packages/system/hami/charts/hami/templates/scheduler/role.yaml index 90987a4f..5f7d7e44 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/role.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/role.yaml @@ -9,4 +9,4 @@ metadata: rules: - apiGroups: ["coordination.k8s.io"] resources: ["leases"] - verbs: ["create", "list", "watch", "get", "update", "patch"] \ No newline at end of file + verbs: ["create", "list", "watch", "get", "update", "patch"] diff --git a/packages/system/hami/charts/hami/templates/scheduler/service.yaml b/packages/system/hami/charts/hami/templates/scheduler/service.yaml index 70378c5c..d7538fed 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/service.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/service.yaml @@ -31,4 +31,4 @@ spec: protocol: TCP selector: app.kubernetes.io/component: hami-scheduler - {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} \ No newline at end of file + {{- include "hami-vgpu.selectorLabels" . | nindent 4 }} diff --git a/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml index 7296eb4e..db9f8029 100644 --- a/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml +++ b/packages/system/hami/charts/hami/templates/scheduler/webhook.yaml @@ -54,4 +54,4 @@ webhooks: scope: '*' sideEffects: None timeoutSeconds: 10 -{{- end }} \ No newline at end of file +{{- end }} From 1131e2f113a8fda8402bf9c92014bff9aaf29f25 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 15:33:07 +0300 Subject: [PATCH 12/35] docs(hami): reference upstream repo for nodeConfiguration format Signed-off-by: Arsolitt --- packages/system/hami/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/system/hami/values.yaml b/packages/system/hami/values.yaml index f45d2998..64b372a6 100644 --- a/packages/system/hami/values.yaml +++ b/packages/system/hami/values.yaml @@ -8,7 +8,7 @@ hami: runtimeClassName: nvidia updateStrategy: type: OnDelete - # See upstream charts/hami/values.yaml for nodeConfiguration format. + # See https://github.com/Project-HAMi/HAMi/blob/v2.8.1/deployments/charts/hami/values.yaml # Each entry: {"name": "node-name", "operatingmode": "hami-core", "devicesplitcount": N, ...} nodeConfiguration: config: | From 3eeda2ba3596851393fd62d3d352cdd1017be267 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Fri, 24 Apr 2026 16:12:34 +0300 Subject: [PATCH 13/35] chore(kubernetes): regenerate code after hami addon addition Signed-off-by: Arsolitt --- .../kubernetes/zz_generated.deepcopy.go | 17 +++++++++++++++++ api/backups/v1alpha1/zz_generated.deepcopy.go | 5 +++++ 2 files changed, 22 insertions(+) diff --git a/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go b/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go index 2cbe3ba1..3f1cb5ce 100644 --- a/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go +++ b/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go @@ -49,6 +49,7 @@ func (in *Addons) DeepCopyInto(out *Addons) { in.Fluxcd.DeepCopyInto(&out.Fluxcd) out.GatewayAPI = in.GatewayAPI in.GpuOperator.DeepCopyInto(&out.GpuOperator) + in.Hami.DeepCopyInto(&out.Hami) in.IngressNginx.DeepCopyInto(&out.IngressNginx) in.MonitoringAgents.DeepCopyInto(&out.MonitoringAgents) in.Velero.DeepCopyInto(&out.Velero) @@ -260,6 +261,22 @@ func (in *GatewayAPIAddon) DeepCopy() *GatewayAPIAddon { return out } +// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil. +func (in *HAMiAddon) DeepCopyInto(out *HAMiAddon) { + *out = *in + in.ValuesOverride.DeepCopyInto(&out.ValuesOverride) +} + +// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new HAMiAddon. +func (in *HAMiAddon) DeepCopy() *HAMiAddon { + if in == nil { + return nil + } + out := new(HAMiAddon) + in.DeepCopyInto(out) + return out +} + // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil. func (in *IngressNginxAddon) DeepCopyInto(out *IngressNginxAddon) { *out = *in diff --git a/api/backups/v1alpha1/zz_generated.deepcopy.go b/api/backups/v1alpha1/zz_generated.deepcopy.go index 89f6171f..61b8f839 100644 --- a/api/backups/v1alpha1/zz_generated.deepcopy.go +++ b/api/backups/v1alpha1/zz_generated.deepcopy.go @@ -620,6 +620,11 @@ func (in *RestoreJobSpec) DeepCopyInto(out *RestoreJobSpec) { *out = new(v1.TypedLocalObjectReference) (*in).DeepCopyInto(*out) } + if in.Options != nil { + in, out := &in.Options, &out.Options + *out = new(runtime.RawExtension) + (*in).DeepCopyInto(*out) + } } // DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new RestoreJobSpec. From d8d870cc2af73925561ae2f9aa936613b47ad0fe Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Mon, 27 Apr 2026 13:24:27 +0300 Subject: [PATCH 14/35] fix(hami): use RollingUpdate strategy for device plugin DaemonSet OnDelete requires manual pod deletion to apply updates. RollingUpdate with maxUnavailable constraint matches upstream default and is consistent with all other system packages. Signed-off-by: Arsolitt --- packages/system/hami/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/system/hami/values.yaml b/packages/system/hami/values.yaml index 64b372a6..76e8d631 100644 --- a/packages/system/hami/values.yaml +++ b/packages/system/hami/values.yaml @@ -7,7 +7,7 @@ hami: devicePlugin: runtimeClassName: nvidia updateStrategy: - type: OnDelete + type: RollingUpdate # See https://github.com/Project-HAMi/HAMi/blob/v2.8.1/deployments/charts/hami/values.yaml # Each entry: {"name": "node-name", "operatingmode": "hami-core", "devicesplitcount": N, ...} nodeConfiguration: From 36852548e576e153981eab0146614442b5bc9a15 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Mon, 27 Apr 2026 13:29:15 +0300 Subject: [PATCH 15/35] fix(hami): correct label indentation in device-plugin monitorservice Use nindent instead of indent with leading whitespace to prevent broken YAML rendering when devicePlugin.service.labels is set. Signed-off-by: Arsolitt --- .../charts/hami/templates/device-plugin/monitorservice.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml index 104664ea..88f1b214 100644 --- a/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml +++ b/packages/system/hami/charts/hami/templates/device-plugin/monitorservice.yaml @@ -7,8 +7,8 @@ metadata: labels: app.kubernetes.io/component: hami-device-plugin {{- include "hami-vgpu.labels" . | nindent 4 }} - {{- if .Values.devicePlugin.service.labels }} # Use devicePlugin instead of scheduler - {{ toYaml .Values.devicePlugin.service.labels | indent 4 }} + {{- with .Values.devicePlugin.service.labels }} + {{- toYaml . | nindent 4 }} {{- end }} {{- if .Values.devicePlugin.service.annotations }} # Use devicePlugin instead of scheduler annotations: {{ toYaml .Values.devicePlugin.service.annotations | nindent 4 }} From f0e033ebcb2fc727bc8fb473507de34edacbf898 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Mon, 27 Apr 2026 13:44:08 +0300 Subject: [PATCH 16/35] style(kubernetes): use with instead of if for hami valuesOverride Signed-off-by: Arsolitt --- packages/apps/kubernetes/templates/helmreleases/hami.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/apps/kubernetes/templates/helmreleases/hami.yaml b/packages/apps/kubernetes/templates/helmreleases/hami.yaml index 8733e675..1f7a5358 100644 --- a/packages/apps/kubernetes/templates/helmreleases/hami.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/hami.yaml @@ -32,9 +32,9 @@ spec: force: true remediation: retries: -1 - {{- if .Values.addons.hami.valuesOverride }} + {{- with .Values.addons.hami.valuesOverride }} values: - {{- toYaml .Values.addons.hami.valuesOverride | nindent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} dependsOn: From c53f10475025c6675e5270f359f97f619db7c80f Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Mon, 27 Apr 2026 13:44:12 +0300 Subject: [PATCH 17/35] docs(hami): clarify that parameter defaults come from upstream chart Signed-off-by: Arsolitt --- packages/system/hami/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/system/hami/README.md b/packages/system/hami/README.md index 283f9e80..d648364d 100644 --- a/packages/system/hami/README.md +++ b/packages/system/hami/README.md @@ -72,6 +72,8 @@ resources: ## Parameters +Default values shown below are inherited from the upstream HAMi chart and may change with upstream updates. + | Name | Description | Default | | --- | --- | --- | | `hami.devicePlugin.runtimeClassName` | RuntimeClass for device plugin pods | `nvidia` | From 9ba5e587810f44d522d5876e38f12f87c3dde3bb Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Mon, 27 Apr 2026 13:44:17 +0300 Subject: [PATCH 18/35] fix(kubernetes): avoid rendering empty values key in gpu-operator HelmRelease Wrap the values: block in a conditional so the key is omitted entirely when no defaults or overrides produce content. Previously the template always emitted values: null, triggering unnecessary FluxCD reconciliation. Signed-off-by: Arsolitt --- .../apps/kubernetes/templates/helmreleases/gpu-operator.yaml | 4 +++- packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml | 3 +-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml index 7a5ecaf1..15849495 100644 --- a/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml @@ -40,8 +40,10 @@ spec: {{- $defaults := fromYaml (include "cozystack.defaultGpuOperatorValues" .) }} {{- $overrides := deepCopy (default (dict) .Values.addons.gpuOperator.valuesOverride) }} {{- $merged := mergeOverwrite (default (dict) $defaults) $overrides }} + {{- if $merged }} values: - {{- if $merged }}{{ toYaml $merged | nindent 4 }}{{ end }} + {{- toYaml $merged | nindent 4 }} + {{- end }} dependsOn: {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }} diff --git a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml index c3ec30f2..4fa754fb 100644 --- a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml +++ b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml @@ -26,9 +26,8 @@ tests: enabled: false valuesOverride: {} asserts: - - equal: + - notExists: path: spec.values - value: null - it: should apply hami defaults when valuesOverride key is omitted set: From 1dc02d44f4ea15253ffd799e85a54ed79ae87fd1 Mon Sep 17 00:00:00 2001 From: Timofei Larkin Date: Mon, 27 Apr 2026 10:27:46 +0300 Subject: [PATCH 19/35] refactor(lineage-controller-webhook): align with cozystack-api shape MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Collapse the chart to a single Deployment shape that mirrors cozystack-api: 2 replicas, soft (preferred) nodeAffinity to node-role.kubernetes.io/control-plane via Exists, permissive tolerations, soft podAntiAffinity on hostname, an unconditional PodDisruptionBudget with maxUnavailable: 1, and a Service with spec.trafficDistribution: PreferClose. The same shape works on Talos / kubeadm / k3s and on managed Kubernetes / Cozy-in-Cozy tenant clusters without per-distro overrides — fixing #2417 by making the soft control-plane affinity gracefully fall back to worker scheduling when no control-plane nodes are visible. Drop the DaemonSet path entirely. The previous PR's deployment.enabled toggle, the workload-kind switch in templates/workload.yaml, the fail-guard for localK8sAPIEndpoint+nodeAffinity=[], the conditional PDB, and the values-shape knobs for nodeAffinity and tolerations all go away as a consequence. Override the standard Deployment fields through the usual component-values mechanism if a non-default topology is ever needed. Mark localK8sAPIEndpoint.enabled deprecated and flip the default to false. The flag injects KUBERNETES_SERVICE_HOST=status.hostIP, which is only valid when the pod is actually scheduled on an apiserver- bearing node. With the new soft control-plane affinity, the pod can land off-control-plane and crash-loop. The latency motivation for the flag is real but pending separate webhook performance work; once addressed, the flag can be removed. Revert all changes to packages/core/platform/images/migrations/migrations/20. The earlier ds/...-or-deploy/... fallback was over-engineered: per run-migrations.sh, migration 20 fires only when CURRENT < 20 (i.e. direct upgrades from pre-0.37 to 1.3+), and that path is unsupported anyway. The original ds/... rollout-status line is dead code on every supported install and upgrade path. Add helm-unittest coverage for: the default Deployment shape (replicas, soft nodeAffinity, soft podAntiAffinity, tolerations); no env vars at the default localK8sAPIEndpoint.enabled=false; PDB rendered unconditionally with maxUnavailable: 1, including at replicas=1 (the no-op case); replicas value drives spec.replicas; and that localK8sAPIEndpoint.enabled=true does inject the env vars. The Service test continues to assert trafficDistribution: PreferClose with no internalTrafficPolicy. Add a slim README documenting the topology, parameters, and the deprecation note for localK8sAPIEndpoint. Co-Authored-By: Claude Opus 4.7 (1M context) Signed-off-by: Timofei Larkin --- .../platform/templates/bundles/system.yaml | 3 - .../lineage-controller-webhook/Makefile | 5 + .../lineage-controller-webhook/README.md | 67 +++++++++++++ .../templates/deployment.yaml | 49 --------- .../templates/pdb.yaml | 4 +- .../templates/service.yaml | 2 +- .../{daemonset.yaml => workload.yaml} | 27 +++-- .../tests/service_test.yaml | 30 ++++++ .../tests/workload_test.yaml | 99 +++++++++++++++++++ .../lineage-controller-webhook/values.yaml | 18 ++-- 10 files changed, 230 insertions(+), 74 deletions(-) create mode 100644 packages/system/lineage-controller-webhook/README.md delete mode 100644 packages/system/lineage-controller-webhook/templates/deployment.yaml rename packages/system/lineage-controller-webhook/templates/{daemonset.yaml => workload.yaml} (67%) create mode 100644 packages/system/lineage-controller-webhook/tests/service_test.yaml create mode 100644 packages/system/lineage-controller-webhook/tests/workload_test.yaml diff --git a/packages/core/platform/templates/bundles/system.yaml b/packages/core/platform/templates/bundles/system.yaml index 43ea7266..6c587c82 100644 --- a/packages/core/platform/templates/bundles/system.yaml +++ b/packages/core/platform/templates/bundles/system.yaml @@ -105,9 +105,6 @@ {{- /* cozystack-api DaemonSet */ -}} {{- $apiValues := dict "cozystackAPI" (dict "nodeSelector" $genericNodeSelector) -}} {{- $_ := set $cozystackEngineComponents "cozystack-api" (dict "values" $apiValues) -}} -{{- /* lineage-controller-webhook DaemonSet */ -}} -{{- $lineageValues := dict "lineageControllerWebhook" (dict "nodeSelector" $genericNodeSelector) -}} -{{- $_ := set $cozystackEngineComponents "lineage-controller-webhook" (dict "values" $lineageValues) -}} {{- end -}} {{- if .Values.authentication.oidc.enabled }} {{include "cozystack.platform.package" (list "cozystack.cozystack-engine" "oidc" $ $cozystackEngineComponents) }} diff --git a/packages/system/lineage-controller-webhook/Makefile b/packages/system/lineage-controller-webhook/Makefile index d5bada31..cdc1cf01 100644 --- a/packages/system/lineage-controller-webhook/Makefile +++ b/packages/system/lineage-controller-webhook/Makefile @@ -4,8 +4,13 @@ NAMESPACE=cozy-system include ../../../hack/common-envs.mk include ../../../hack/package.mk +.PHONY: test + image: image-lineage-controller-webhook +test: + helm unittest . + image-lineage-controller-webhook: docker buildx build -f images/lineage-controller-webhook/Dockerfile ../../.. \ --tag $(REGISTRY)/lineage-controller-webhook:$(call settag,$(TAG)) \ diff --git a/packages/system/lineage-controller-webhook/README.md b/packages/system/lineage-controller-webhook/README.md new file mode 100644 index 00000000..1e43c9c8 --- /dev/null +++ b/packages/system/lineage-controller-webhook/README.md @@ -0,0 +1,67 @@ +# lineage-controller-webhook + +Cozystack system package for the **lineage controller webhook** — a mutating +admission webhook that stamps "lineage" labels onto tenant workloads, linking +each resource back to the Cozystack `Application` that ultimately owns it. + +The webhook intercepts CREATE and UPDATE on `pods`, `secrets`, `services`, +`persistentvolumeclaims`, `ingresses.networking.k8s.io`, and +`workloadmonitors.cozystack.io` outside system namespaces. For each request it +walks the ownership graph upward (Kubernetes `ownerReferences`, then the +`HelmRelease` Flux installed the resource with, then the Cozystack +`Application`-derived CRD that produced the HelmRelease) and writes the +discovered application's group, kind and name as labels +(`apps.cozystack.io/application.{group,kind,name}`) on the incoming object. +Those labels let the aggregated API server, the Cozystack dashboard, and other +lineage-aware consumers reason about which application a resource belongs to. + +The webhook serves TLS on port 9443 with a cert-manager issued certificate, and +runs with `failurePolicy: Fail` — every CREATE/UPDATE on the resources above +is gated on the webhook being reachable. + +## Topology + +The chart ships a single shape, modelled on `cozystack-api`: + +- **Deployment** with two replicas (override via `replicas`). +- **Soft `nodeAffinity`** preferring `node-role.kubernetes.io/control-plane` + (`Exists`, so it matches both Talos's empty value and k3s/kubeadm's `"true"`). + Soft means: the pod lands on a control-plane node when one is reachable, and + on any worker otherwise — no override needed for managed Kubernetes, + Cozy-in-Cozy tenants, or any other cluster where control-plane nodes aren't + visible. +- **Permissive `tolerations`** (`[{operator: Exists}]`) so the pod can land on + tainted control-plane nodes when the soft affinity is satisfiable. +- **Soft `podAntiAffinity`** on `kubernetes.io/hostname` so replicas spread + across nodes when possible (best-effort). +- **`PodDisruptionBudget`** with `maxUnavailable: 1`, unconditional. At + `replicas: 1` it's a useful no-op (allows full drain); at `replicas >= 2` + it caps disruption to one pod. +- **`Service` with `spec.trafficDistribution: PreferClose`** so the apiserver + prefers a webhook endpoint on its own node when one exists, and transparently + falls over to a remote endpoint otherwise. Requires Kubernetes ≥ 1.31; on + older clusters the field is silently ignored and traffic uses default + cluster-wide distribution. + +## Parameters + +All keys live under the top-level `lineageControllerWebhook:` map. + +| Name | Description | Value | +| ----------------------------- | --------------------------------------------------------- | -------------------------------------------------------------------------------- | +| `image` | Container image (digest-pinned) | `ghcr.io/cozystack/cozystack/lineage-controller-webhook:v1.3.0@sha256:e898…6fb0` | +| `debug` | Enable `--zap-log-level=debug` instead of `info` | `false` | +| `replicas` | Deployment replica count | `2` | +| `localK8sAPIEndpoint.enabled` | **Deprecated.** See note below. | `false` | + +### `localK8sAPIEndpoint.enabled` (deprecated) + +When enabled, this injects `KUBERNETES_SERVICE_HOST=status.hostIP` and +`KUBERNETES_SERVICE_PORT=6443` so the webhook talks to the kube-apiserver on +its own node. It was originally added to avoid latency on the +webhook-to-apiserver path, but it is only valid when the pod is actually +scheduled on an apiserver-bearing node — which the chart's soft control-plane +affinity no longer guarantees. With this flag enabled and the pod scheduled +off a control-plane node, the controller will crash-loop dialing a non- +apiserver hostIP. Slated for removal once the latency motivation is addressed +in the webhook itself; **leave disabled**. diff --git a/packages/system/lineage-controller-webhook/templates/deployment.yaml b/packages/system/lineage-controller-webhook/templates/deployment.yaml deleted file mode 100644 index 87717fd3..00000000 --- a/packages/system/lineage-controller-webhook/templates/deployment.yaml +++ /dev/null @@ -1,49 +0,0 @@ -{{- if .Values.lineageControllerWebhook.deployment.enabled }} -apiVersion: apps/v1 -kind: Deployment -metadata: - name: lineage-controller-webhook - labels: - app: lineage-controller-webhook -spec: - replicas: {{ .Values.lineageControllerWebhook.deployment.replicas }} - selector: - matchLabels: - app: lineage-controller-webhook - template: - metadata: - labels: - app: lineage-controller-webhook - spec: - serviceAccountName: lineage-controller-webhook - affinity: - podAntiAffinity: - preferredDuringSchedulingIgnoredDuringExecution: - - weight: 100 - podAffinityTerm: - topologyKey: kubernetes.io/hostname - labelSelector: - matchLabels: - app: lineage-controller-webhook - containers: - - name: lineage-controller-webhook - image: "{{ .Values.lineageControllerWebhook.image }}" - args: - {{- if .Values.lineageControllerWebhook.debug }} - - --zap-log-level=debug - {{- else }} - - --zap-log-level=info - {{- end }} - ports: - - name: webhook - containerPort: 9443 - volumeMounts: - - name: webhook-certs - mountPath: /tmp/k8s-webhook-server/serving-certs - readOnly: true - volumes: - - name: webhook-certs - secret: - secretName: lineage-controller-webhook-cert - defaultMode: 0400 -{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/templates/pdb.yaml b/packages/system/lineage-controller-webhook/templates/pdb.yaml index b0a9d4e4..0786c8ff 100644 --- a/packages/system/lineage-controller-webhook/templates/pdb.yaml +++ b/packages/system/lineage-controller-webhook/templates/pdb.yaml @@ -1,11 +1,9 @@ -{{- if .Values.lineageControllerWebhook.deployment.enabled }} apiVersion: policy/v1 kind: PodDisruptionBudget metadata: name: lineage-controller-webhook spec: - minAvailable: {{ if gt (int .Values.lineageControllerWebhook.deployment.replicas) 1 }}1{{ else }}0{{ end }} + maxUnavailable: 1 selector: matchLabels: app: lineage-controller-webhook -{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/templates/service.yaml b/packages/system/lineage-controller-webhook/templates/service.yaml index c5df90fb..fbb3ad54 100644 --- a/packages/system/lineage-controller-webhook/templates/service.yaml +++ b/packages/system/lineage-controller-webhook/templates/service.yaml @@ -5,7 +5,7 @@ metadata: labels: app: lineage-controller-webhook spec: - internalTrafficPolicy: Local + trafficDistribution: PreferClose type: ClusterIP ports: - port: 443 diff --git a/packages/system/lineage-controller-webhook/templates/daemonset.yaml b/packages/system/lineage-controller-webhook/templates/workload.yaml similarity index 67% rename from packages/system/lineage-controller-webhook/templates/daemonset.yaml rename to packages/system/lineage-controller-webhook/templates/workload.yaml index 536ea24a..097919c6 100644 --- a/packages/system/lineage-controller-webhook/templates/daemonset.yaml +++ b/packages/system/lineage-controller-webhook/templates/workload.yaml @@ -1,11 +1,11 @@ -{{- if not .Values.lineageControllerWebhook.deployment.enabled }} apiVersion: apps/v1 -kind: DaemonSet +kind: Deployment metadata: name: lineage-controller-webhook labels: app: lineage-controller-webhook spec: + replicas: {{ .Values.lineageControllerWebhook.replicas }} selector: matchLabels: app: lineage-controller-webhook @@ -14,13 +14,25 @@ spec: labels: app: lineage-controller-webhook spec: - {{- with .Values.lineageControllerWebhook.nodeSelector }} - nodeSelector: - {{- toYaml . | nindent 8 }} - {{- end }} + serviceAccountName: lineage-controller-webhook tolerations: - operator: Exists - serviceAccountName: lineage-controller-webhook + affinity: + nodeAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + preference: + matchExpressions: + - key: node-role.kubernetes.io/control-plane + operator: Exists + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: kubernetes.io/hostname + labelSelector: + matchLabels: + app: lineage-controller-webhook containers: - name: lineage-controller-webhook image: "{{ .Values.lineageControllerWebhook.image }}" @@ -52,4 +64,3 @@ spec: secret: secretName: lineage-controller-webhook-cert defaultMode: 0400 -{{- end }} \ No newline at end of file diff --git a/packages/system/lineage-controller-webhook/tests/service_test.yaml b/packages/system/lineage-controller-webhook/tests/service_test.yaml new file mode 100644 index 00000000..3cdbddd8 --- /dev/null +++ b/packages/system/lineage-controller-webhook/tests/service_test.yaml @@ -0,0 +1,30 @@ +suite: lineage-controller-webhook service +templates: + - templates/service.yaml + +release: + name: lineage-controller-webhook + namespace: cozy-system + +tests: + - it: renders a ClusterIP service on 443 -> 9443 with PreferClose traffic distribution + asserts: + - isKind: + of: Service + - equal: + path: spec.type + value: ClusterIP + - equal: + path: spec.trafficDistribution + value: PreferClose + - notExists: + path: spec.internalTrafficPolicy + - equal: + path: spec.ports[0].port + value: 443 + - equal: + path: spec.ports[0].targetPort + value: 9443 + - equal: + path: spec.selector.app + value: lineage-controller-webhook diff --git a/packages/system/lineage-controller-webhook/tests/workload_test.yaml b/packages/system/lineage-controller-webhook/tests/workload_test.yaml new file mode 100644 index 00000000..bcb24014 --- /dev/null +++ b/packages/system/lineage-controller-webhook/tests/workload_test.yaml @@ -0,0 +1,99 @@ +suite: lineage-controller-webhook workload + PDB +templates: + - templates/workload.yaml + - templates/pdb.yaml + +release: + name: lineage-controller-webhook + namespace: cozy-system + +tests: + # ---- Default Deployment shape ---------------------------------------------- + + - it: defaults render a 2-replica Deployment with soft control-plane nodeAffinity, soft podAntiAffinity, and Exists tolerations + template: templates/workload.yaml + asserts: + - isKind: + of: Deployment + - equal: + path: spec.replicas + value: 2 + - equal: + path: spec.template.spec.tolerations + value: + - operator: Exists + - equal: + path: spec.template.spec.affinity.nodeAffinity.preferredDuringSchedulingIgnoredDuringExecution + value: + - weight: 100 + preference: + matchExpressions: + - key: node-role.kubernetes.io/control-plane + operator: Exists + - notExists: + path: spec.template.spec.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution + - equal: + path: spec.template.spec.affinity.podAntiAffinity.preferredDuringSchedulingIgnoredDuringExecution[0].podAffinityTerm.topologyKey + value: kubernetes.io/hostname + + - it: defaults inject no localK8sAPIEndpoint env vars (knob is opt-in) + template: templates/workload.yaml + asserts: + - notExists: + path: spec.template.spec.containers[0].env + + # ---- PDB -------------------------------------------------------------------- + + - it: PDB renders unconditionally with maxUnavailable=1 at the default replica count + template: templates/pdb.yaml + asserts: + - isKind: + of: PodDisruptionBudget + - equal: + path: spec.maxUnavailable + value: 1 + - notExists: + path: spec.minAvailable + + - it: PDB still renders at replicas=1 (no-op, but consistent shape) + set: + lineageControllerWebhook.replicas: 1 + template: templates/pdb.yaml + asserts: + - isKind: + of: PodDisruptionBudget + - equal: + path: spec.maxUnavailable + value: 1 + + # ---- Replica override ------------------------------------------------------- + + - it: replicas value drives spec.replicas + set: + lineageControllerWebhook.replicas: 5 + template: templates/workload.yaml + asserts: + - equal: + path: spec.replicas + value: 5 + + # ---- Deprecated localK8sAPIEndpoint knob ----------------------------------- + + - it: localK8sAPIEndpoint.enabled=true injects KUBERNETES_SERVICE_HOST and PORT env vars + set: + lineageControllerWebhook.localK8sAPIEndpoint.enabled: true + template: templates/workload.yaml + asserts: + - contains: + path: spec.template.spec.containers[0].env + content: + name: KUBERNETES_SERVICE_HOST + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.hostIP + - contains: + path: spec.template.spec.containers[0].env + content: + name: KUBERNETES_SERVICE_PORT + value: "6443" diff --git a/packages/system/lineage-controller-webhook/values.yaml b/packages/system/lineage-controller-webhook/values.yaml index 2b84f4e1..e56d332d 100644 --- a/packages/system/lineage-controller-webhook/values.yaml +++ b/packages/system/lineage-controller-webhook/values.yaml @@ -1,15 +1,13 @@ lineageControllerWebhook: image: ghcr.io/cozystack/cozystack/lineage-controller-webhook:v1.3.0@sha256:e8984709686a5eaf19b89da378d7b8c688ea5607e0783a88d9c9e4ccfca96fb0 debug: false + replicas: 2 + # DEPRECATED. Injects KUBERNETES_SERVICE_HOST=status.hostIP and + # KUBERNETES_SERVICE_PORT=6443 so the webhook talks to the apiserver on its + # own node — only valid when the pod is actually scheduled on an apiserver- + # bearing node. Now that the chart's nodeAffinity to control-plane is soft + # (preferred, not required), the pod can land off-control-plane and crash- + # loop dialing a non-apiserver hostIP. Slated for removal once webhook + # performance work obviates the locality motivation. Leave disabled. localK8sAPIEndpoint: - # incompatable with Deployment mode - enabled: true - # nodeSelector for the DaemonSet - # Talos uses empty value: "node-role.kubernetes.io/control-plane": "" - # Generic k8s (k3s, kubeadm) uses: "node-role.kubernetes.io/control-plane": "true" - nodeSelector: - node-role.kubernetes.io/control-plane: "" - # if enabled, replace DaemonSet by Deployment - deployment: enabled: false - replicas: 1 From 3a8359fa73f5cd96d8363c48d31414d8cadf3447 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Tue, 28 Apr 2026 18:59:43 +0300 Subject: [PATCH 20/35] chore(kubernetes): regenerate deepcopy after merge Run `make generate` to pick up the Images type added in main. Signed-off-by: Arsolitt --- .../v1alpha1/kubernetes/zz_generated.deepcopy.go | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go b/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go index 3f1cb5ce..e021fbaa 100644 --- a/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go +++ b/api/apps/v1alpha1/kubernetes/zz_generated.deepcopy.go @@ -136,6 +136,7 @@ func (in *ConfigSpec) DeepCopyInto(out *ConfigSpec) { } in.Addons.DeepCopyInto(&out.Addons) in.ControlPlane.DeepCopyInto(&out.ControlPlane) + out.Images = in.Images } // DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new ConfigSpec. @@ -277,6 +278,21 @@ func (in *HAMiAddon) DeepCopy() *HAMiAddon { return out } +// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil. +func (in *Images) DeepCopyInto(out *Images) { + *out = *in +} + +// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new Images. +func (in *Images) DeepCopy() *Images { + if in == nil { + return nil + } + out := new(Images) + in.DeepCopyInto(out) + return out +} + // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil. func (in *IngressNginxAddon) DeepCopyInto(out *IngressNginxAddon) { *out = *in From 80b86b0c1a39266488b84473724a54b0d3ad7d9c Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Tue, 28 Apr 2026 19:02:35 +0300 Subject: [PATCH 21/35] chore(kubernetes): regenerate CRD after merge conflict resolution Per-package `make generate` corrects keysOrder placement and openAPISchema formatting in the kubernetes CRD definition. Signed-off-by: Arsolitt --- api/apps/v1alpha1/kubernetes/types.go | 2 +- packages/system/kubernetes-rd/cozyrds/kubernetes.yaml | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/api/apps/v1alpha1/kubernetes/types.go b/api/apps/v1alpha1/kubernetes/types.go index e0143445..88a3c97e 100644 --- a/api/apps/v1alpha1/kubernetes/types.go +++ b/api/apps/v1alpha1/kubernetes/types.go @@ -6,7 +6,7 @@ package kubernetes import ( resource "k8s.io/apimachinery/pkg/api/resource" - v1 "k8s.io/apimachinery/pkg/apis/meta/v1" + "k8s.io/apimachinery/pkg/apis/meta/v1" k8sRuntime "k8s.io/apimachinery/pkg/runtime" ) diff --git a/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml b/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml index b4ada238..f81eaff0 100644 --- a/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml +++ b/packages/system/kubernetes-rd/cozyrds/kubernetes.yaml @@ -22,7 +22,7 @@ spec: singular: kubernetes plural: kuberneteses openAPISchema: |- - {"title":"Chart Values","type":"object","properties":{"storageClass":{"description":"StorageClass used to store the data.","type":"string","default":"replicated"},"nodeGroups":{"description":"Worker nodes configuration map.","type":"object","default":{"md0":{"ephemeralStorage":"20Gi","gpus":[],"instanceType":"u1.medium","maxReplicas":10,"minReplicas":0,"resources":{},"roles":["ingress-nginx"]}},"additionalProperties":{"type":"object","required":["ephemeralStorage","instanceType","maxReplicas","minReplicas","resources"],"properties":{"ephemeralStorage":{"description":"Ephemeral storage size.","default":"20Gi","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"gpus":{"description":"List of GPUs to attach (NVIDIA driver requires at least 4 GiB RAM).","type":"array","items":{"type":"object","required":["name"],"properties":{"name":{"description":"Name of GPU, such as \"nvidia.com/AD102GL_L40S\".","type":"string"}}}},"instanceType":{"description":"Virtual machine instance type.","type":"string","default":"u1.medium"},"maxReplicas":{"description":"Maximum number of replicas.","type":"integer","default":10},"minReplicas":{"description":"Minimum number of replicas.","type":"integer","default":0},"resources":{"description":"CPU and memory resources for each worker node.","type":"object","properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"roles":{"description":"List of node roles.","type":"array","items":{"type":"string"}}}}},"version":{"description":"Kubernetes major.minor version to deploy","type":"string","default":"v1.35","enum":["v1.35","v1.34","v1.33","v1.32","v1.31","v1.30"]},"host":{"description":"External hostname for Kubernetes cluster. Defaults to `.` if empty.","type":"string","default":""},"addons":{"description":"Cluster addons configuration.","type":"object","default":{},"required":["certManager","cilium","coredns","fluxcd","gatewayAPI","gpuOperator","hami","ingressNginx","monitoringAgents","velero","verticalPodAutoscaler"],"properties":{"certManager":{"description":"Cert-manager addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable cert-manager.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"cilium":{"description":"Cilium CNI plugin.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"coredns":{"description":"CoreDNS addon.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"fluxcd":{"description":"FluxCD GitOps operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable FluxCD.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"gatewayAPI":{"description":"Gateway API addon.","type":"object","default":{},"required":["enabled"],"properties":{"enabled":{"description":"Enable Gateway API.","type":"boolean","default":false}}},"gpuOperator":{"description":"NVIDIA GPU Operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable GPU Operator.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"ingressNginx":{"description":"Ingress-NGINX controller.","type":"object","default":{},"required":["enabled","exposeMethod","valuesOverride"],"properties":{"enabled":{"description":"Enable the controller (requires nodes labeled `ingress-nginx`).","type":"boolean","default":false},"exposeMethod":{"description":"Method to expose the controller. Allowed values: `Proxied`, `LoadBalancer`.","type":"string","default":"Proxied","enum":["Proxied","LoadBalancer"]},"hosts":{"description":"Domains routed to this tenant cluster when `exposeMethod` is `Proxied`.","type":"array","default":[],"items":{"type":"string"}},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"monitoringAgents":{"description":"Monitoring agents.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable monitoring agents.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"velero":{"description":"Velero backup/restore addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable Velero.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"verticalPodAutoscaler":{"description":"Vertical Pod Autoscaler.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"hami":{"description":"HAMi GPU virtualization middleware.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable HAMi (requires GPU Operator).","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}}}},"controlPlane":{"description":"Kubernetes control-plane configuration.","type":"object","default":{},"required":["apiServer","controllerManager","konnectivity","replicas","scheduler"],"properties":{"apiServer":{"description":"API Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for API Server.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"large","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"controllerManager":{"description":"Controller Manager configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Controller Manager.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"konnectivity":{"description":"Konnectivity configuration.","type":"object","default":{},"required":["server"],"properties":{"server":{"description":"Konnectivity Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Konnectivity.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"replicas":{"description":"Number of control-plane replicas.","type":"integer","default":2},"scheduler":{"description":"Scheduler configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Scheduler.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"images":{"description":"Optional image overrides for air-gapped or rate-limited registries.","type":"object","default":{},"properties":{"waitForKubeconfig":{"description":"Image used by the wait-for-kubeconfig init container. Empty falls back to images/busybox.tag.","type":"string","default":""}}}}} + {"title":"Chart Values","type":"object","properties":{"storageClass":{"description":"StorageClass used to store the data.","type":"string","default":"replicated"},"nodeGroups":{"description":"Worker nodes configuration map.","type":"object","default":{"md0":{"ephemeralStorage":"20Gi","gpus":[],"instanceType":"u1.medium","maxReplicas":10,"minReplicas":0,"resources":{},"roles":["ingress-nginx"]}},"additionalProperties":{"type":"object","required":["ephemeralStorage","instanceType","maxReplicas","minReplicas","resources"],"properties":{"ephemeralStorage":{"description":"Ephemeral storage size.","default":"20Gi","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"gpus":{"description":"List of GPUs to attach (NVIDIA driver requires at least 4 GiB RAM).","type":"array","items":{"type":"object","required":["name"],"properties":{"name":{"description":"Name of GPU, such as \"nvidia.com/AD102GL_L40S\".","type":"string"}}}},"instanceType":{"description":"Virtual machine instance type.","type":"string","default":"u1.medium"},"maxReplicas":{"description":"Maximum number of replicas.","type":"integer","default":10},"minReplicas":{"description":"Minimum number of replicas.","type":"integer","default":0},"resources":{"description":"CPU and memory resources for each worker node.","type":"object","properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"roles":{"description":"List of node roles.","type":"array","items":{"type":"string"}}}}},"version":{"description":"Kubernetes major.minor version to deploy","type":"string","default":"v1.35","enum":["v1.35","v1.34","v1.33","v1.32","v1.31","v1.30"]},"host":{"description":"External hostname for Kubernetes cluster. Defaults to `.` if empty.","type":"string","default":""},"addons":{"description":"Cluster addons configuration.","type":"object","default":{},"required":["certManager","cilium","coredns","fluxcd","gatewayAPI","gpuOperator","hami","ingressNginx","monitoringAgents","velero","verticalPodAutoscaler"],"properties":{"certManager":{"description":"Cert-manager addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable cert-manager.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"cilium":{"description":"Cilium CNI plugin.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"coredns":{"description":"CoreDNS addon.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"fluxcd":{"description":"FluxCD GitOps operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable FluxCD.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"gatewayAPI":{"description":"Gateway API addon.","type":"object","default":{},"required":["enabled"],"properties":{"enabled":{"description":"Enable Gateway API.","type":"boolean","default":false}}},"gpuOperator":{"description":"NVIDIA GPU Operator.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable GPU Operator.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"hami":{"description":"HAMi GPU virtualization middleware.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable HAMi (requires GPU Operator).","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"ingressNginx":{"description":"Ingress-NGINX controller.","type":"object","default":{},"required":["enabled","exposeMethod","valuesOverride"],"properties":{"enabled":{"description":"Enable the controller (requires nodes labeled `ingress-nginx`).","type":"boolean","default":false},"exposeMethod":{"description":"Method to expose the controller. Allowed values: `Proxied`, `LoadBalancer`.","type":"string","default":"Proxied","enum":["Proxied","LoadBalancer"]},"hosts":{"description":"Domains routed to this tenant cluster when `exposeMethod` is `Proxied`.","type":"array","default":[],"items":{"type":"string"}},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"monitoringAgents":{"description":"Monitoring agents.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable monitoring agents.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"velero":{"description":"Velero backup/restore addon.","type":"object","default":{},"required":["enabled","valuesOverride"],"properties":{"enabled":{"description":"Enable Velero.","type":"boolean","default":false},"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}},"verticalPodAutoscaler":{"description":"Vertical Pod Autoscaler.","type":"object","default":{},"required":["valuesOverride"],"properties":{"valuesOverride":{"description":"Custom Helm values overrides.","type":"object","default":{},"x-kubernetes-preserve-unknown-fields":true}}}}},"controlPlane":{"description":"Kubernetes control-plane configuration.","type":"object","default":{},"required":["apiServer","controllerManager","konnectivity","replicas","scheduler"],"properties":{"apiServer":{"description":"API Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for API Server.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"large","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"controllerManager":{"description":"Controller Manager configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Controller Manager.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}},"konnectivity":{"description":"Konnectivity configuration.","type":"object","default":{},"required":["server"],"properties":{"server":{"description":"Konnectivity Server configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Konnectivity.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"replicas":{"description":"Number of control-plane replicas.","type":"integer","default":2},"scheduler":{"description":"Scheduler configuration.","type":"object","default":{},"required":["resources","resourcesPreset"],"properties":{"resources":{"description":"CPU and memory resources for Scheduler.","type":"object","default":{},"properties":{"cpu":{"description":"CPU available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true},"memory":{"description":"Memory (RAM) available.","pattern":"^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$","anyOf":[{"type":"integer"},{"type":"string"}],"x-kubernetes-int-or-string":true}}},"resourcesPreset":{"description":"Preset if `resources` omitted.","type":"string","default":"micro","enum":["nano","micro","small","medium","large","xlarge","2xlarge"]}}}}},"images":{"description":"Optional image overrides for air-gapped or rate-limited registries.","type":"object","default":{},"properties":{"waitForKubeconfig":{"description":"Image used by the wait-for-kubeconfig init container. Empty falls back to images/busybox.tag.","type":"string","default":""}}}}} release: prefix: kubernetes- labels: @@ -40,7 +40,7 @@ spec: tags: - compute icon: <svg width="144" height="144" viewBox="0 0 144 144" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect width="144" height="144" rx="24" fill="url(#paint0_linear_681_2845)"/>
<path d="M71.9968 19C70.3039 19.0002 68.9312 20.5322 68.9314 22.4221C68.9314 22.4511 68.9373 22.4788 68.9379 22.5076C68.9354 22.7644 68.9231 23.0737 68.9314 23.2973C68.9717 24.3873 69.2082 25.2216 69.3506 26.2258C69.6084 28.3752 69.8245 30.1569 69.6912 31.813C69.5615 32.4375 69.1037 33.0086 68.6956 33.4056L68.6235 34.7086C66.7839 34.8617 64.9319 35.1421 63.0821 35.5641C55.1226 37.3798 48.2695 41.4991 43.052 47.0609C42.7134 46.8288 42.1211 46.4019 41.945 46.2712C41.3977 46.3454 40.8445 46.5151 40.1241 46.0935C38.7522 45.1657 37.5028 43.8851 35.991 42.3424C35.2982 41.6044 34.7966 40.9018 33.9735 40.1904C33.7866 40.0289 33.5014 39.8104 33.2923 39.6442C32.6489 39.1288 31.89 38.86 31.157 38.8348C30.2147 38.8024 29.3075 39.1725 28.7138 39.9206C27.6584 41.2506 27.9963 43.2833 29.4671 44.4614C29.482 44.4734 29.4979 44.4827 29.5129 44.4943C29.715 44.6589 29.9625 44.8698 30.1483 45.0076C31.0217 45.6555 31.8195 45.9872 32.6897 46.5015C34.5231 47.6391 36.043 48.5823 37.2486 49.7196C37.7194 50.2237 37.8016 51.1122 37.8643 51.4964L38.8468 52.3782C33.5872 60.3308 31.153 70.1539 32.5915 80.1627L31.3077 80.5378C30.9693 80.9768 30.4912 81.6676 29.9911 81.8738C28.4138 82.3729 26.6387 82.5562 24.4956 82.7819C23.4894 82.866 22.6213 82.8158 21.5546 83.0188C21.3198 83.0635 20.9927 83.1491 20.7358 83.2097C20.7269 83.2116 20.7186 83.2142 20.7096 83.2162C20.6956 83.2195 20.6772 83.2263 20.6638 83.2294C18.857 83.668 17.6963 85.3365 18.0699 86.9805C18.4437 88.6248 20.2086 89.6248 22.0262 89.2312C22.0393 89.2282 22.0584 89.2277 22.072 89.2246C22.0926 89.2199 22.1106 89.2099 22.131 89.2049C22.3844 89.149 22.7019 89.0868 22.9236 89.0272C23.9723 88.7451 24.7318 88.3306 25.6746 87.9677C27.7029 87.2368 29.3828 86.6262 31.0195 86.3883C31.703 86.3345 32.4232 86.812 32.7814 87.0134L34.1177 86.7831C37.1926 96.3613 43.6366 104.103 51.7963 108.961L51.2396 110.303C51.4403 110.824 51.6616 111.53 51.5121 112.045C50.9171 113.595 49.898 115.231 48.7374 117.055C48.1755 117.898 47.6004 118.552 47.0934 119.516C46.972 119.747 46.8175 120.102 46.7004 120.346C45.9125 122.039 46.4904 123.99 48.0038 124.722C49.5268 125.459 51.4171 124.682 52.2352 122.985C52.2364 122.982 52.2406 122.98 52.2417 122.978C52.2426 122.976 52.2409 122.973 52.2417 122.971C52.3582 122.731 52.5233 122.415 52.6216 122.188C53.056 121.189 53.2005 120.332 53.5059 119.365C54.317 117.318 54.7626 115.17 55.8791 113.832C56.1849 113.466 56.6833 113.325 57.2001 113.186L57.8944 111.922C65.008 114.665 72.9705 115.402 80.9245 113.587C82.7391 113.173 84.4908 112.637 86.1843 111.994C86.3794 112.342 86.742 113.011 86.8393 113.179C87.3644 113.351 87.9377 113.439 88.4047 114.133C89.2401 115.567 89.8114 117.263 90.5073 119.312C90.8128 120.279 90.9638 121.136 91.3981 122.136C91.4971 122.363 91.6614 122.684 91.778 122.925C92.5944 124.628 94.4907 125.407 96.0159 124.669C97.5292 123.937 98.1077 121.986 97.3194 120.293C97.2023 120.049 97.0412 119.695 96.9198 119.464C96.4127 118.499 95.8377 117.852 95.2758 117.009C94.1152 115.185 93.1526 113.67 92.5575 112.12C92.3087 111.32 92.5995 110.823 92.7933 110.303C92.6772 110.17 92.4288 109.414 92.2824 109.059C100.762 104.029 107.017 95.9985 109.955 86.7239C110.351 86.7865 111.041 86.9091 111.265 86.9542C111.726 86.6487 112.149 86.2501 112.981 86.3159C114.617 86.5537 116.297 87.1645 118.326 87.8953C119.268 88.2581 120.028 88.6793 121.077 88.9614C121.298 89.021 121.616 89.0766 121.869 89.1325C121.889 89.1375 121.908 89.1475 121.928 89.1522C121.942 89.1553 121.961 89.1558 121.974 89.1588C123.792 89.552 125.557 88.5526 125.93 86.9081C126.303 85.2641 125.143 83.5952 123.336 83.157C123.074 83.097 122.701 82.995 122.446 82.9465C121.379 82.7435 120.511 82.7935 119.505 82.7095C117.361 82.4839 115.586 82.3004 114.009 81.8014C113.366 81.5507 112.908 80.7819 112.686 80.4655L111.448 80.1035C112.09 75.438 111.917 70.5825 110.806 65.7243C109.685 60.8208 107.704 56.3361 105.062 52.3848C105.379 52.0948 105.979 51.5612 106.149 51.4043C106.199 50.8517 106.156 50.2722 106.725 49.6603C107.931 48.523 109.451 47.5799 111.284 46.4423C112.154 45.9279 112.959 45.5964 113.832 44.9484C114.03 44.8019 114.299 44.5699 114.507 44.4022C115.977 43.2237 116.316 41.1911 115.26 39.8614C114.204 38.5317 112.159 38.4065 110.688 39.585C110.479 39.7516 110.195 39.9688 110.007 40.1312C109.184 40.8426 108.676 41.5452 107.983 42.2832C106.471 43.8259 105.222 45.113 103.85 46.0409C103.255 46.3885 102.385 46.2682 101.99 46.2449L100.824 47.0806C94.1753 40.0763 85.1235 35.5982 75.3766 34.7283C75.3494 34.3179 75.3137 33.5761 75.3046 33.3529C74.9056 32.9693 74.4235 32.6418 74.3024 31.813C74.1691 30.1569 74.3917 28.3752 74.6496 26.2258C74.7919 25.2216 75.0284 24.3873 75.0688 23.2973C75.078 23.0495 75.0632 22.69 75.0622 22.4221C75.062 20.5322 73.6898 18.9998 71.9968 19ZM68.1585 42.8886L67.248 59.0447L67.1825 59.0776C67.1214 60.5229 65.9375 61.677 64.4839 61.677C63.8884 61.677 63.3388 61.4849 62.8922 61.1571L62.866 61.1703L49.6807 51.7794C53.7331 47.7759 58.9164 44.8172 64.89 43.4546C65.9812 43.2056 67.0719 43.0209 68.1585 42.8886ZM75.8417 42.8886C82.8159 43.7504 89.2657 46.9232 94.2081 51.786L81.108 61.1176L81.0621 61.0979C79.8994 61.9512 78.2611 61.7394 77.3548 60.5978C76.9835 60.1301 76.7887 59.5801 76.7653 59.0249L76.7522 59.0184L75.8417 42.8886ZM44.8991 57.814L56.9382 68.633L56.9251 68.6988C58.0117 69.6479 58.172 71.2949 57.2657 72.4368C56.8944 72.9045 56.3975 73.2182 55.8639 73.3647L55.8508 73.4173L40.4188 77.8923C39.6334 70.6765 41.3261 63.6621 44.8991 57.814ZM99.0094 57.8206C100.798 60.7336 102.153 63.9871 102.959 67.5143C103.756 70.9991 103.956 74.4778 103.627 77.8397L88.1166 73.3515L88.1035 73.2857C86.7145 72.9043 85.8609 71.4848 86.1843 70.0611C86.3168 69.4778 86.6249 68.9844 87.0423 68.6198L87.0358 68.5869L99.0094 57.8206ZM69.5274 69.4688H74.4596L77.5251 73.3186L76.4247 78.1226L71.9968 80.2614L67.5558 78.1161L66.4554 73.312L69.5274 69.4688ZM85.3393 82.6437C85.5489 82.6331 85.7576 82.652 85.9616 82.6898L85.9878 82.6569L101.95 85.3682C99.6142 91.9624 95.144 97.675 89.1711 101.498L82.9747 86.4606L82.9944 86.4343C82.4252 85.1055 82.9948 83.5472 84.3044 82.9135C84.6397 82.7513 84.99 82.6614 85.3393 82.6437ZM58.5298 82.7095C59.748 82.7267 60.8406 83.5761 61.1237 84.822C61.2562 85.4052 61.1917 85.9831 60.973 86.4935L61.0189 86.5527L54.888 101.439C49.1559 97.7432 44.5904 92.2099 42.1481 85.4208L57.9731 82.7227L57.9993 82.7556C58.1763 82.7229 58.3558 82.7071 58.5298 82.7095ZM71.8986 89.2312C72.3229 89.2155 72.7534 89.303 73.1627 89.501C73.6992 89.7606 74.1136 90.1692 74.3745 90.6592H74.4334L82.2346 104.821C81.2221 105.162 80.1813 105.454 79.1167 105.697C73.1505 107.058 67.2032 106.645 61.818 104.802L69.5995 90.6658H69.6126C70.0795 89.7888 70.965 89.2656 71.8986 89.2312Z" fill="white" stroke="white" stroke-width="0.25"/>
<defs>
<linearGradient id="paint0_linear_681_2845" x1="10" y1="15.5" x2="144" y2="131.5" gradientUnits="userSpaceOnUse">
<stop stop-color="#4D87FF"/>
<stop offset="1" stop-color="#0547D0"/>
</linearGradient>
</defs>
</svg>
 - keysOrder: [["apiVersion"],["appVersion"],["kind"],["metadata"],["metadata","name"],["spec","storageClass"],["spec","nodeGroups"],["spec","nodeGroups","md0"],["spec","nodeGroups","md0","minReplicas"],["spec","nodeGroups","md0","maxReplicas"],["spec","nodeGroups","md0","instanceType"],["spec","nodeGroups","md0","ephemeralStorage"],["spec","nodeGroups","md0","roles"],["spec","nodeGroups","md0","resources"],["spec","nodeGroups","md0","gpus"],["spec","version"],["spec","host"],["spec","addons"],["spec","addons","certManager"],["spec","addons","certManager","enabled"],["spec","addons","certManager","valuesOverride"],["spec","addons","cilium"],["spec","addons","cilium","valuesOverride"],["spec","addons","gatewayAPI"],["spec","addons","gatewayAPI","enabled"],["spec","addons","ingressNginx"],["spec","addons","ingressNginx","enabled"],["spec","addons","ingressNginx","exposeMethod"],["spec","addons","ingressNginx","hosts"],["spec","addons","ingressNginx","valuesOverride"],["spec","addons","gpuOperator"],["spec","addons","gpuOperator","enabled"],["spec","addons","gpuOperator","valuesOverride"],["spec","addons","fluxcd"],["spec","addons","fluxcd","enabled"],["spec","addons","fluxcd","valuesOverride"],["spec","addons","monitoringAgents"],["spec","addons","monitoringAgents","enabled"],["spec","addons","monitoringAgents","valuesOverride"],["spec","addons","verticalPodAutoscaler"],["spec","addons","verticalPodAutoscaler","valuesOverride"],["spec","addons","velero"],["spec","addons","velero","enabled"],["spec","addons","velero","valuesOverride"],["spec","addons","coredns"],["spec","addons","coredns","valuesOverride"],["spec","controlPlane"],["spec","controlPlane","replicas"],["spec","controlPlane","apiServer"],["spec","controlPlane","apiServer","resources"],["spec","controlPlane","apiServer","resourcesPreset"],["spec","controlPlane","controllerManager"],["spec","controlPlane","controllerManager","resources"],["spec","controlPlane","controllerManager","resourcesPreset"],["spec","controlPlane","scheduler"],["spec","controlPlane","scheduler","resources"],["spec","controlPlane","scheduler","resourcesPreset"],["spec","controlPlane","konnectivity"],["spec","controlPlane","konnectivity","server"],["spec","controlPlane","konnectivity","server","resources"],["spec","controlPlane","konnectivity","server","resourcesPreset"],["spec","addons","hami"],["spec","addons","hami","enabled"],["spec","addons","hami","valuesOverride"],["spec","images"],["spec","images","waitForKubeconfig"]] + keysOrder: [["apiVersion"], ["appVersion"], ["kind"], ["metadata"], ["metadata", "name"], ["spec", "storageClass"], ["spec", "nodeGroups"], ["spec", "nodeGroups", "md0"], ["spec", "nodeGroups", "md0", "minReplicas"], ["spec", "nodeGroups", "md0", "maxReplicas"], ["spec", "nodeGroups", "md0", "instanceType"], ["spec", "nodeGroups", "md0", "ephemeralStorage"], ["spec", "nodeGroups", "md0", "roles"], ["spec", "nodeGroups", "md0", "resources"], ["spec", "nodeGroups", "md0", "gpus"], ["spec", "version"], ["spec", "host"], ["spec", "addons"], ["spec", "addons", "certManager"], ["spec", "addons", "certManager", "enabled"], ["spec", "addons", "certManager", "valuesOverride"], ["spec", "addons", "cilium"], ["spec", "addons", "cilium", "valuesOverride"], ["spec", "addons", "gatewayAPI"], ["spec", "addons", "gatewayAPI", "enabled"], ["spec", "addons", "ingressNginx"], ["spec", "addons", "ingressNginx", "enabled"], ["spec", "addons", "ingressNginx", "exposeMethod"], ["spec", "addons", "ingressNginx", "hosts"], ["spec", "addons", "ingressNginx", "valuesOverride"], ["spec", "addons", "gpuOperator"], ["spec", "addons", "gpuOperator", "enabled"], ["spec", "addons", "gpuOperator", "valuesOverride"], ["spec", "addons", "hami"], ["spec", "addons", "hami", "enabled"], ["spec", "addons", "hami", "valuesOverride"], ["spec", "addons", "fluxcd"], ["spec", "addons", "fluxcd", "enabled"], ["spec", "addons", "fluxcd", "valuesOverride"], ["spec", "addons", "monitoringAgents"], ["spec", "addons", "monitoringAgents", "enabled"], ["spec", "addons", "monitoringAgents", "valuesOverride"], ["spec", "addons", "verticalPodAutoscaler"], ["spec", "addons", "verticalPodAutoscaler", "valuesOverride"], ["spec", "addons", "velero"], ["spec", "addons", "velero", "enabled"], ["spec", "addons", "velero", "valuesOverride"], ["spec", "addons", "coredns"], ["spec", "addons", "coredns", "valuesOverride"], ["spec", "controlPlane"], ["spec", "controlPlane", "replicas"], ["spec", "controlPlane", "apiServer"], ["spec", "controlPlane", "apiServer", "resources"], ["spec", "controlPlane", "apiServer", "resourcesPreset"], ["spec", "controlPlane", "controllerManager"], ["spec", "controlPlane", "controllerManager", "resources"], ["spec", "controlPlane", "controllerManager", "resourcesPreset"], ["spec", "controlPlane", "scheduler"], ["spec", "controlPlane", "scheduler", "resources"], ["spec", "controlPlane", "scheduler", "resourcesPreset"], ["spec", "controlPlane", "konnectivity"], ["spec", "controlPlane", "konnectivity", "server"], ["spec", "controlPlane", "konnectivity", "server", "resources"], ["spec", "controlPlane", "konnectivity", "server", "resourcesPreset"], ["spec", "images"], ["spec", "images", "waitForKubeconfig"]] secrets: exclude: [] include: From 805b3b17cbc4d89206203bc24b45c1412c29a2c8 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Tue, 28 Apr 2026 19:11:26 +0300 Subject: [PATCH 22/35] fix(kubernetes): add CI values to GPU Operator HAMi tests Tests need _namespace.etcd from values-ci.yaml after the merge introduced an etcd-namespace guard on the gpu-operator HelmRelease condition. Signed-off-by: Arsolitt --- packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml index 4fa754fb..44528470 100644 --- a/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml +++ b/packages/apps/kubernetes/tests/gpu_operator_hami_test.yaml @@ -1,6 +1,8 @@ suite: GPU Operator HelmRelease HAMi integration tests templates: - templates/helmreleases/gpu-operator.yaml +values: + - values-ci.yaml tests: - it: should disable devicePlugin when hami is enabled set: From 9ee5f5d2f4f319f90c4ae1cb58d46f1844c17500 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 2 Apr 2026 14:58:45 +0300 Subject: [PATCH 23/35] feat(gpu-operator): update NVIDIA GPU Operator from v25.3.0 to v26.3.0 Update vendored upstream chart to v26.3.0. Key changes: - CDI enabled by default - Driver version 580.126.20 - NFD subchart updated to 0.18.3 - Component versions bumped (toolkit v1.19.0, device-plugin v0.19.0, dcgm-exporter 4.5.2) - Pin chart version in Makefile for reproducibility Assisted-By: Claude Signed-off-by: Aleksei Sviridkin --- packages/system/gpu-operator/Makefile | 2 +- .../charts/gpu-operator/Chart.lock | 8 +- .../charts/gpu-operator/Chart.yaml | 8 +- .../charts/node-feature-discovery/Chart.yaml | 5 +- .../charts/node-feature-discovery/README.md | 2 +- .../crds/nfd-api-crds.yaml | 77 ++++ .../templates/_helpers.tpl | 19 + .../templates/master-pdb.yaml | 17 + .../templates/master.yaml | 35 +- .../templates/nfd-gc-pdb.yaml | 17 + .../templates/nfd-gc.yaml | 46 +- .../templates/post-delete-job.yaml | 8 + .../templates/prometheus.yaml | 2 +- .../templates/topologyupdater.yaml | 26 +- .../templates/worker.yaml | 30 +- .../charts/node-feature-discovery/values.yaml | 77 ++-- .../crds/nvidia.com_clusterpolicies.yaml | 431 ++++++++++++++++-- .../crds/nvidia.com_nvidiadrivers.yaml | 248 +++++++++- .../gpu-operator/templates/cleanup_crd.yaml | 19 +- .../gpu-operator/templates/clusterpolicy.yaml | 83 +++- .../gpu-operator/templates/extra-objects.yaml | 8 + .../templates/nodefeaturerules.yaml | 108 +---- .../gpu-operator/templates/nvidiadriver.yaml | 11 +- .../gpu-operator/templates/operator.yaml | 9 +- .../charts/gpu-operator/templates/role.yaml | 11 + .../gpu-operator/templates/rolebinding.yaml | 1 + .../templates/serviceaccount.yaml | 1 + .../gpu-operator/templates/upgrade_crd.yaml | 13 +- .../gpu-operator/templates/validations.yaml | 3 + .../charts/gpu-operator/values.yaml | 213 ++++----- 30 files changed, 1152 insertions(+), 386 deletions(-) create mode 100644 packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master-pdb.yaml create mode 100644 packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc-pdb.yaml create mode 100644 packages/system/gpu-operator/charts/gpu-operator/templates/extra-objects.yaml create mode 100644 packages/system/gpu-operator/charts/gpu-operator/templates/validations.yaml diff --git a/packages/system/gpu-operator/Makefile b/packages/system/gpu-operator/Makefile index 49b26e26..11ca047e 100644 --- a/packages/system/gpu-operator/Makefile +++ b/packages/system/gpu-operator/Makefile @@ -8,4 +8,4 @@ update: rm -rf charts helm repo add nvidia https://helm.ngc.nvidia.com/nvidia helm repo update nvidia - helm pull nvidia/gpu-operator --untar --untardir charts + helm pull nvidia/gpu-operator --untar --untardir charts --version v26.3.0 diff --git a/packages/system/gpu-operator/charts/gpu-operator/Chart.lock b/packages/system/gpu-operator/charts/gpu-operator/Chart.lock index 14674306..707da9d1 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/Chart.lock +++ b/packages/system/gpu-operator/charts/gpu-operator/Chart.lock @@ -1,6 +1,6 @@ dependencies: - name: node-feature-discovery - repository: https://kubernetes-sigs.github.io/node-feature-discovery/charts - version: 0.17.2 -digest: sha256:4c55d30d958027ef8997a2976449326de3c90049025c3ebb9bee017cad32cc3f -generated: "2025-02-25T09:08:49.128088-08:00" + repository: oci://registry.k8s.io/nfd/charts + version: 0.18.3 +digest: sha256:1bce3b80da1e6d47a0befbaa6a2f758aeac6d20382e900f0c301f45020afbebc +generated: "2026-01-23T15:08:56.617442-08:00" diff --git a/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml b/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml index f14fc2ad..c2138a54 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml @@ -1,10 +1,10 @@ apiVersion: v2 -appVersion: v25.3.0 +appVersion: v26.3.0 dependencies: - condition: nfd.enabled name: node-feature-discovery - repository: https://kubernetes-sigs.github.io/node-feature-discovery/charts - version: v0.17.2 + repository: oci://registry.k8s.io/nfd/charts + version: 0.18.3 description: NVIDIA GPU Operator creates/configures/manages GPUs atop Kubernetes home: https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/overview.html icon: https://assets.nvidiagrid.net/ngc/logos/GPUoperator.png @@ -20,4 +20,4 @@ kubeVersion: '>= 1.16.0-0' name: gpu-operator sources: - https://github.com/NVIDIA/gpu-operator -version: v25.3.0 +version: v26.3.0 diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/Chart.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/Chart.yaml index f62d84c2..8609178c 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/Chart.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/Chart.yaml @@ -1,8 +1,9 @@ apiVersion: v2 -appVersion: v0.17.2 +appVersion: v0.18.3 description: 'Detects hardware features available on each node in a Kubernetes cluster, and advertises those features using node labels. ' home: https://github.com/kubernetes-sigs/node-feature-discovery +icon: https://kubernetes-sigs.github.io/node-feature-discovery/v0.18/assets/images/nfd/favicon.svg keywords: - feature-discovery - feature-detection @@ -11,4 +12,4 @@ name: node-feature-discovery sources: - https://github.com/kubernetes-sigs/node-feature-discovery type: application -version: 0.17.2 +version: 0.18.3 diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/README.md b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/README.md index 02f7b170..2b46e4af 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/README.md +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/README.md @@ -6,5 +6,5 @@ labels. NFD provides flexible configuration and extension points for a wide range of vendor and application specific node labeling needs. See -[NFD documentation](https://kubernetes-sigs.github.io/node-feature-discovery/v0.17/deployment/helm.html) +[NFD documentation](https://kubernetes-sigs.github.io/node-feature-discovery/v0.18/deployment/helm.html) for deployment instructions. diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml index 9f62da6f..69e306c3 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml @@ -204,11 +204,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -240,11 +248,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -295,11 +311,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -331,11 +355,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -356,6 +388,19 @@ spec: name: description: Name of the rule. type: string + vars: + additionalProperties: + type: string + description: |- + Vars is the variables to store if the rule matches. Variables can be + referenced from other rules enabling more complex rule hierarchies. + type: object + varsTemplate: + description: |- + VarsTemplate specifies a template to expand for dynamically generating + multiple variables. Data (after template expansion) must be keys with an + optional value ([=]) separated by newlines. + type: string required: - name type: object @@ -498,11 +543,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -534,11 +587,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -589,11 +650,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input @@ -625,11 +694,19 @@ spec: - Exists - DoesNotExist - Gt + - Ge - Lt + - Le - GtLt + - GeLe - IsTrue - IsFalse type: string + type: + description: |- + Type defines the value type for specific operators. + The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. + type: string value: description: |- Value is the list of values that the operand evaluates the input diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/_helpers.tpl b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/_helpers.tpl index 928ece78..b540e3bb 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/_helpers.tpl +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/_helpers.tpl @@ -105,3 +105,22 @@ Create the name of the service account which nfd-gc will use {{ default "default" .Values.gc.serviceAccount.name }} {{- end -}} {{- end -}} + +{{/* +imagePullSecrets helper - uses local values or falls back to global values +*/}} +{{- define "node-feature-discovery.imagePullSecrets" -}} +{{- $imagePullSecrets := list -}} +{{- if .Values.imagePullSecrets -}} + {{- range .Values.imagePullSecrets -}} + {{- $imagePullSecrets = append $imagePullSecrets . -}} + {{- end -}} +{{- else if and .Values.global .Values.global.imagePullSecrets -}} + {{- range .Values.global.imagePullSecrets -}} + {{- $imagePullSecrets = append $imagePullSecrets . -}} + {{- end -}} +{{- end -}} +{{- if $imagePullSecrets -}} +{{- $imagePullSecrets | toJson }} +{{- end -}} +{{- end -}} diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master-pdb.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master-pdb.yaml new file mode 100644 index 00000000..532b0e6d --- /dev/null +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master-pdb.yaml @@ -0,0 +1,17 @@ +{{- if .Values.master.enable }} +{{- if .Values.master.podDisruptionBudget.enable -}} +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + name: {{ include "node-feature-discovery.fullname" . }}-master + namespace: {{ include "node-feature-discovery.namespace" . }} + labels: + {{- include "node-feature-discovery.labels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "node-feature-discovery.selectorLabels" . | nindent 6 }} + role: master +{{- toYaml (omit .Values.master.podDisruptionBudget "enable") | nindent 2 }} +{{- end }} +{{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master.yaml index da3ca240..666af5c5 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/master.yaml @@ -29,13 +29,11 @@ spec: {{- toYaml . | nindent 8 }} {{- end }} spec: + dnsPolicy: {{ .Values.master.dnsPolicy }} {{- with .Values.priorityClassName }} priorityClassName: {{ . }} {{- end }} - {{- with .Values.imagePullSecrets }} - imagePullSecrets: - {{- toYaml . | nindent 8 }} - {{- end }} + imagePullSecrets: {{ include "node-feature-discovery.imagePullSecrets" . }} serviceAccountName: {{ include "node-feature-discovery.master.serviceAccountName" . }} enableServiceLinks: false securityContext: @@ -48,8 +46,9 @@ spec: image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} startupProbe: - grpc: - port: {{ .Values.master.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.master.startupProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -63,8 +62,9 @@ spec: timeoutSeconds: {{ . }} {{- end }} livenessProbe: - grpc: - port: {{ .Values.master.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.master.livenessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -78,8 +78,9 @@ spec: timeoutSeconds: {{ . }} {{- end }} readinessProbe: - grpc: - port: {{ .Values.master.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.master.readinessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -96,17 +97,15 @@ spec: successThreshold: {{ . }} {{- end }} ports: - - containerPort: {{ .Values.master.metricsPort | default "8081" }} - name: metrics - - containerPort: {{ .Values.master.healthPort | default "8082" }} - name: health + - containerPort: {{ .Values.master.port | default "8080" }} + name: http env: - name: NODE_NAME valueFrom: fieldRef: fieldPath: spec.nodeName {{- with .Values.master.extraEnvs }} - {{- toYaml . | nindent 8 }} + {{- toYaml . | nindent 10 }} {{- end}} command: - "nfd-master" @@ -126,9 +125,6 @@ spec: {{- if .Values.master.enableTaints }} - "-enable-taints" {{- end }} - {{- if .Values.master.featureRulesController | kindIs "invalid" | not }} - - "-featurerules-controller={{ .Values.master.featureRulesController }}" - {{- end }} {{- if .Values.master.resyncPeriod }} - "-resync-period={{ .Values.master.resyncPeriod }}" {{- end }} @@ -139,8 +135,7 @@ spec: {{- range $key, $value := .Values.featureGates }} - "-feature-gates={{ $key }}={{ $value }}" {{- end }} - - "-metrics={{ .Values.master.metricsPort | default "8081" }}" - - "-grpc-health={{ .Values.master.healthPort | default "8082" }}" + - "-port={{ .Values.master.port | default "8080" }}" {{- with .Values.master.extraArgs }} {{- toYaml . | nindent 12 }} {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc-pdb.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc-pdb.yaml new file mode 100644 index 00000000..373ed92c --- /dev/null +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc-pdb.yaml @@ -0,0 +1,17 @@ +{{- if .Values.gc.enable }} +{{- if .Values.gc.podDisruptionBudget.enable -}} +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + name: {{ include "node-feature-discovery.fullname" . }}-gc + namespace: {{ include "node-feature-discovery.namespace" . }} + labels: + {{- include "node-feature-discovery.labels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "node-feature-discovery.selectorLabels" . | nindent 6 }} + role: gc +{{- toYaml (omit .Values.gc.podDisruptionBudget "enable") | nindent 2 }} +{{- end }} +{{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml index 3642aa64..c0e8d083 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml @@ -29,14 +29,11 @@ spec: {{- end }} spec: serviceAccountName: {{ include "node-feature-discovery.gc.serviceAccountName" . }} - dnsPolicy: ClusterFirstWithHostNet + dnsPolicy: {{ .Values.gc.dnsPolicy }} {{- with .Values.priorityClassName }} priorityClassName: {{ . }} {{- end }} - {{- with .Values.imagePullSecrets }} - imagePullSecrets: - {{- toYaml . | nindent 8 }} - {{- end }} + imagePullSecrets: {{ include "node-feature-discovery.imagePullSecrets" . }} securityContext: {{- toYaml .Values.gc.podSecurityContext | nindent 8 }} hostNetwork: {{ .Values.gc.hostNetwork }} @@ -44,6 +41,41 @@ spec: - name: gc image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: "{{ .Values.image.pullPolicy }}" + livenessProbe: + httpGet: + path: /healthz + port: http + {{- with .Values.gc.livenessProbe.initialDelaySeconds }} + initialDelaySeconds: {{ . }} + {{- end }} + {{- with .Values.gc.livenessProbe.failureThreshold }} + failureThreshold: {{ . }} + {{- end }} + {{- with .Values.gc.livenessProbe.periodSeconds }} + periodSeconds: {{ . }} + {{- end }} + {{- with .Values.gc.livenessProbe.timeoutSeconds }} + timeoutSeconds: {{ . }} + {{- end }} + readinessProbe: + httpGet: + path: /healthz + port: http + {{- with .Values.gc.readinessProbe.initialDelaySeconds }} + initialDelaySeconds: {{ . }} + {{- end }} + {{- with .Values.gc.readinessProbe.failureThreshold }} + failureThreshold: {{ . }} + {{- end }} + {{- with .Values.gc.readinessProbe.periodSeconds }} + periodSeconds: {{ . }} + {{- end }} + {{- with .Values.gc.readinessProbe.timeoutSeconds }} + timeoutSeconds: {{ . }} + {{- end }} + {{- with .Values.gc.readinessProbe.successThreshold }} + successThreshold: {{ . }} + {{- end }} env: - name: NODE_NAME valueFrom: @@ -70,8 +102,8 @@ spec: readOnlyRootFilesystem: true runAsNonRoot: true ports: - - name: metrics - containerPort: {{ .Values.gc.metricsPort | default "8081"}} + - name: http + containerPort: {{ .Values.gc.port | default "8080"}} {{- with .Values.gc.nodeSelector }} nodeSelector: diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml index 4364f1aa..ddb1c9db 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml @@ -1,3 +1,4 @@ +{{- if .Values.postDeleteCleanup }} apiVersion: v1 kind: ServiceAccount metadata: @@ -66,6 +67,7 @@ spec: role: prune spec: serviceAccountName: {{ include "node-feature-discovery.fullname" . }}-prune + imagePullSecrets: {{ include "node-feature-discovery.imagePullSecrets" . }} containers: - name: nfd-master securityContext: @@ -92,3 +94,9 @@ spec: tolerations: {{- toYaml . | nindent 8 }} {{- end }} + {{- with .Values.master.resources }} + resources: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} + diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/prometheus.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/prometheus.yaml index 3d680e24..bed37f4c 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/prometheus.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/prometheus.yaml @@ -14,7 +14,7 @@ spec: - honorLabels: true interval: {{ .Values.prometheus.scrapeInterval }} path: /metrics - port: metrics + port: http scheme: http namespaceSelector: matchNames: diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/topologyupdater.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/topologyupdater.yaml index 9a466f88..010e8a0b 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/topologyupdater.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/topologyupdater.yaml @@ -29,14 +29,11 @@ spec: {{- end }} spec: serviceAccountName: {{ include "node-feature-discovery.topologyUpdater.serviceAccountName" . }} - dnsPolicy: ClusterFirstWithHostNet + dnsPolicy: {{ .Values.topologyUpdater.dnsPolicy }} {{- with .Values.priorityClassName }} priorityClassName: {{ . }} {{- end }} - {{- with .Values.imagePullSecrets }} - imagePullSecrets: - {{- toYaml . | nindent 8 }} - {{- end }} + imagePullSecrets: {{ include "node-feature-discovery.imagePullSecrets" . }} securityContext: {{- toYaml .Values.topologyUpdater.podSecurityContext | nindent 8 }} hostNetwork: {{ .Values.topologyUpdater.hostNetwork }} @@ -45,8 +42,9 @@ spec: image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: "{{ .Values.image.pullPolicy }}" livenessProbe: - grpc: - port: {{ .Values.topologyUpdater.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.topologyUpdater.livenessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -60,8 +58,9 @@ spec: timeoutSeconds: {{ . }} {{- end }} readinessProbe: - grpc: - port: {{ .Values.topologyUpdater.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.topologyUpdater.readinessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -113,16 +112,13 @@ spec: # Disable kubelet state tracking by giving an empty path - "-kubelet-state-dir=" {{- end }} - - "-metrics={{ .Values.topologyUpdater.metricsPort | default "8081"}}" - - "-grpc-health={{ .Values.topologyUpdater.healthPort | default "8082" }}" + - "-port={{ .Values.topologyUpdater.port | default "8080"}}" {{- with .Values.topologyUpdater.extraArgs }} {{- toYaml . | nindent 10 }} {{- end }} ports: - - containerPort: {{ .Values.topologyUpdater.metricsPort | default "8081"}} - name: metrics - - containerPort: {{ .Values.topologyUpdater.healthPort | default "8082" }} - name: health + - containerPort: {{ .Values.topologyUpdater.port | default "8080"}} + name: http volumeMounts: {{- if .Values.topologyUpdater.kubeletConfigPath | empty | not }} - name: kubelet-config diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/worker.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/worker.yaml index 4aadd800..58c3e041 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/worker.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/templates/worker.yaml @@ -13,6 +13,10 @@ metadata: {{- end }} spec: revisionHistoryLimit: {{ .Values.worker.revisionHistoryLimit }} + {{- with .Values.worker.updateStrategy }} + updateStrategy: + {{- toYaml . | nindent 4 }} + {{- end}} selector: matchLabels: {{- include "node-feature-discovery.selectorLabels" . | nindent 6 }} @@ -28,14 +32,11 @@ spec: {{- toYaml . | nindent 8 }} {{- end }} spec: - dnsPolicy: ClusterFirstWithHostNet + dnsPolicy: {{ .Values.worker.dnsPolicy }} {{- with .Values.priorityClassName }} priorityClassName: {{ . }} {{- end }} - {{- with .Values.imagePullSecrets }} - imagePullSecrets: - {{- toYaml . | nindent 8 }} - {{- end }} + imagePullSecrets: {{ include "node-feature-discovery.imagePullSecrets" . }} serviceAccountName: {{ include "node-feature-discovery.worker.serviceAccountName" . }} securityContext: {{- toYaml .Values.worker.podSecurityContext | nindent 8 }} @@ -47,8 +48,9 @@ spec: image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} livenessProbe: - grpc: - port: {{ .Values.worker.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.worker.livenessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -62,8 +64,9 @@ spec: timeoutSeconds: {{ . }} {{- end }} readinessProbe: - grpc: - port: {{ .Values.worker.healthPort | default "8082" }} + httpGet: + path: /healthz + port: http {{- with .Values.worker.readinessProbe.initialDelaySeconds }} initialDelaySeconds: {{ . }} {{- end }} @@ -104,16 +107,13 @@ spec: {{- range $key, $value := .Values.featureGates }} - "-feature-gates={{ $key }}={{ $value }}" {{- end }} - - "-metrics={{ .Values.worker.metricsPort | default "8081"}}" - - "-grpc-health={{ .Values.worker.healthPort | default "8082" }}" + - "-port={{ .Values.worker.port | default "8080"}}" {{- with .Values.worker.extraArgs }} {{- toYaml . | nindent 8 }} {{- end }} ports: - - containerPort: {{ .Values.worker.metricsPort | default "8081"}} - name: metrics - - containerPort: {{ .Values.worker.healthPort | default "8082" }} - name: health + - containerPort: {{ .Values.worker.port | default "8080"}} + name: http volumeMounts: - name: host-boot mountPath: "/host-boot" diff --git a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/values.yaml b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/values.yaml index 18aa7bcb..86712bd2 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/values.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/charts/node-feature-discovery/values.yaml @@ -15,17 +15,20 @@ featureGates: priorityClassName: "" +postDeleteCleanup: true + master: enable: true extraArgs: [] extraEnvs: [] hostNetwork: false + dnsPolicy: ClusterFirstWithHostNet config: ### # noPublish: false - # autoDefaultNs: true # extraLabelNs: ["added.ns.io","added.kubernets.io"] # denyLabelNs: ["denied.ns.io","denied.kubernetes.io"] # enableTaints: false + # informerPageSize: 200 # labelWhiteList: "foo" # resyncPeriod: "2h" # restrictions: @@ -66,15 +69,12 @@ master: # retryPeriod: 2s # nfdApiParallelism: 10 ### - metricsPort: 8081 - healthPort: 8082 + port: 8080 instance: - featureApi: resyncPeriod: denyLabelNs: [] extraLabelNs: [] enableTaints: false - featureRulesController: null nfdApiParallelism: null deploymentAnnotations: {} replicaCount: 1 @@ -120,26 +120,21 @@ master: nodeSelector: {} tolerations: - - key: "node-role.kubernetes.io/master" - operator: "Equal" - value: "" - effect: "NoSchedule" - key: "node-role.kubernetes.io/control-plane" operator: "Equal" value: "" effect: "NoSchedule" + podDisruptionBudget: + enable: false + minAvailable: 1 + unhealthyPodEvictionPolicy: AlwaysAllow + annotations: {} affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - - weight: 1 - preference: - matchExpressions: - - key: "node-role.kubernetes.io/master" - operator: In - values: [""] - weight: 1 preference: matchExpressions: @@ -148,20 +143,14 @@ master: values: [""] startupProbe: - grpc: - port: 8082 failureThreshold: 30 # periodSeconds: 10 - livenessProbe: - grpc: - port: 8082 + livenessProbe: {} # failureThreshold: 3 # initialDelaySeconds: 0 # periodSeconds: 10 # timeoutSeconds: 1 readinessProbe: - grpc: - port: 8082 failureThreshold: 10 # initialDelaySeconds: 0 # periodSeconds: 10 @@ -173,6 +162,7 @@ worker: extraArgs: [] extraEnvs: [] hostNetwork: false + dnsPolicy: ClusterFirstWithHostNet config: ### #core: # labelWhiteList: @@ -416,8 +406,7 @@ worker: # matchName: {op: In, value: ["SWAP", "X86", "ARM"]} ### - metricsPort: 8081 - healthPort: 8082 + port: 8080 daemonsetAnnotations: {} podSecurityContext: {} # fsGroup: 2000 @@ -431,15 +420,11 @@ worker: # runAsUser: 1000 livenessProbe: - grpc: - port: 8082 initialDelaySeconds: 10 # failureThreshold: 3 # periodSeconds: 10 # timeoutSeconds: 1 readinessProbe: - grpc: - port: 8082 initialDelaySeconds: 5 failureThreshold: 10 # periodSeconds: 10 @@ -483,6 +468,12 @@ worker: priorityClassName: "" + updateStrategy: {} + # type: RollingUpdate + # rollingUpdate: + # maxSurge: 0 + # maxUnavailable: "10%" + topologyUpdater: config: ### ## key = node name, value = list of resources to be excluded. @@ -499,6 +490,7 @@ topologyUpdater: extraArgs: [] extraEnvs: [] hostNetwork: false + dnsPolicy: ClusterFirstWithHostNet serviceAccount: create: true @@ -511,8 +503,7 @@ topologyUpdater: rbac: create: true - metricsPort: 8081 - healthPort: 8082 + port: 8080 kubeletConfigPath: kubeletPodResourcesSockPath: updateInterval: 60s @@ -526,17 +517,13 @@ topologyUpdater: drop: [ "ALL" ] readOnlyRootFilesystem: true runAsUser: 0 - + livenessProbe: - grpc: - port: 8082 initialDelaySeconds: 10 # failureThreshold: 3 # periodSeconds: 10 # timeoutSeconds: 1 readinessProbe: - grpc: - port: 8082 initialDelaySeconds: 5 failureThreshold: 10 # periodSeconds: 10 @@ -563,6 +550,7 @@ gc: extraEnvs: [] hostNetwork: false replicaCount: 1 + dnsPolicy: ClusterFirstWithHostNet serviceAccount: create: true @@ -575,6 +563,18 @@ gc: podSecurityContext: {} + livenessProbe: + initialDelaySeconds: 10 + # failureThreshold: 3 + # periodSeconds: 10 + # timeoutSeconds: 1 + readinessProbe: + initialDelaySeconds: 5 + # failureThreshold: 3 + # periodSeconds: 10 + # timeoutSeconds: 1 + # successThreshold: 1 + resources: limits: memory: 1Gi @@ -582,7 +582,7 @@ gc: cpu: 10m memory: 128Mi - metricsPort: 8081 + port: 8080 nodeSelector: {} tolerations: [] @@ -590,6 +590,11 @@ gc: deploymentAnnotations: {} affinity: {} + podDisruptionBudget: + enable: false + minAvailable: 1 + unhealthyPodEvictionPolicy: AlwaysAllow + # specify how many old ReplicaSets for the Deployment to retain. revisionHistoryLimit: diff --git a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml index 5a9f99e1..030581fc 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml @@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: - controller-gen.kubebuilder.io/version: v0.17.2 + controller-gen.kubebuilder.io/version: v0.20.1 name: clusterpolicies.nvidia.com spec: group: nvidia.com @@ -136,13 +136,21 @@ spec: properties: default: default: false - description: Default indicates whether to use CDI as the default - mechanism for providing GPU access to containers. + description: 'Deprecated: This field is no longer used. Setting + cdi.enabled=true will configure CDI as the default mechanism + for making GPUs accessible to containers.' type: boolean enabled: + default: true + description: Enabled indicates whether the Container Device Interface + (CDI) should be used as the mechanism for making GPUs accessible + to containers. + type: boolean + nriPluginEnabled: default: false - description: Enabled indicates whether CDI can be used to make - GPUs accessible to containers. + description: NRIPluginEnabled indicates whether an NRI Plugin + should be run as a means of injecting CDI devices to gpu management + containers. type: boolean type: object daemonsets: @@ -164,6 +172,239 @@ spec: (scope and select) objects. May match selectors of replication controllers and services. type: object + podSecurityContext: + description: 'Optional: Set pod-level security context for all + DaemonSet pods (applies as defaults to all containers)' + properties: + appArmorProfile: + description: |- + appArmorProfile is the AppArmor options to use by the containers in this pod. + Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: |- + localhostProfile indicates a profile loaded on the node that should be used. + The profile must be preconfigured on the node to work. + Must match the loaded name of the profile. + Must be set if and only if type is "Localhost". + type: string + type: + description: |- + type indicates which kind of AppArmor profile will be applied. + Valid options are: + Localhost - a profile pre-loaded on the node. + RuntimeDefault - the container runtime's default profile. + Unconfined - no AppArmor enforcement. + type: string + required: + - type + type: object + fsGroup: + description: |- + A special supplemental group that applies to all containers in a pod. + Some volume types allow the Kubelet to change the ownership of that volume + to be owned by the pod: + + 1. The owning GID will be the FSGroup + 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) + 3. The permission bits are OR'd with rw-rw---- + + If unset, the Kubelet will not modify the ownership and permissions of any volume. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + fsGroupChangePolicy: + description: |- + fsGroupChangePolicy defines behavior of changing ownership and permission of the volume + before being exposed inside Pod. This field will only apply to + volume types which support fsGroup based ownership(and permissions). + It will have no effect on ephemeral volume types such as: secret, configmaps + and emptydir. + Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. + Note that this field cannot be set when spec.os.name is windows. + type: string + runAsGroup: + description: |- + The GID to run the entrypoint of the container process. + Uses runtime default if unset. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence + for that container. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: |- + Indicates that the container must run as a non-root user. + If true, the Kubelet will validate the image at runtime to ensure that it + does not run as UID 0 (root) and fail to start the container if it does. + If unset or false, no such validation will be performed. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: |- + The UID to run the entrypoint of the container process. + Defaults to user specified in image metadata if unspecified. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence + for that container. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxChangePolicy: + description: |- + seLinuxChangePolicy defines how the container's SELinux label is applied to all volumes used by the Pod. + It has no effect on nodes that do not support SELinux or to volumes does not support SELinux. + Valid values are "MountOption" and "Recursive". + + "Recursive" means relabeling of all files on all Pod volumes by the container runtime. + This may be slow for large volumes, but allows mixing privileged and unprivileged Pods sharing the same volume on the same node. + + "MountOption" mounts all eligible Pod volumes with `-o context` mount option. + This requires all Pods that share the same volume to use the same SELinux label. + It is not possible to share the same volume among privileged and unprivileged Pods. + Eligible volumes are in-tree FibreChannel and iSCSI volumes, and all CSI volumes + whose CSI driver announces SELinux support by setting spec.seLinuxMount: true in their + CSIDriver instance. Other volumes are always re-labelled recursively. + "MountOption" value is allowed only when SELinuxMount feature gate is enabled. + + If not specified and SELinuxMount feature gate is enabled, "MountOption" is used. + If not specified and SELinuxMount feature gate is disabled, "MountOption" is used for ReadWriteOncePod volumes + and "Recursive" for all other volumes. + + This field affects only Pods that have SELinux label set, either in PodSecurityContext or in SecurityContext of all containers. + + All Pods that use the same volume should use the same seLinuxChangePolicy, otherwise some pods can get stuck in ContainerCreating state. + Note that this field cannot be set when spec.os.name is windows. + type: string + seLinuxOptions: + description: |- + The SELinux context to be applied to all containers. + If unspecified, the container runtime will allocate a random SELinux context for each + container. May also be set in SecurityContext. If set in + both SecurityContext and PodSecurityContext, the value specified in SecurityContext + takes precedence for that container. + Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies + to the container. + type: string + role: + description: Role is a SELinux role label that applies + to the container. + type: string + type: + description: Type is a SELinux type label that applies + to the container. + type: string + user: + description: User is a SELinux user label that applies + to the container. + type: string + type: object + seccompProfile: + description: |- + The seccomp options to use by the containers in this pod. + Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: |- + localhostProfile indicates a profile defined in a file on the node should be used. + The profile must be preconfigured on the node to work. + Must be a descending path, relative to the kubelet's configured seccomp profile location. + Must be set if type is "Localhost". Must NOT be set for any other type. + type: string + type: + description: |- + type indicates which kind of seccomp profile will be applied. + Valid options are: + + Localhost - a profile defined in a file on the node should be used. + RuntimeDefault - the container runtime default profile should be used. + Unconfined - no profile should be applied. + type: string + required: + - type + type: object + supplementalGroups: + description: |- + A list of groups applied to the first process run in each container, in + addition to the container's primary GID and fsGroup (if specified). If + the SupplementalGroupsPolicy feature is enabled, the + supplementalGroupsPolicy field determines whether these are in addition + to or instead of any group memberships defined in the container image. + If unspecified, no additional groups are added, though group memberships + defined in the container image may still be used, depending on the + supplementalGroupsPolicy field. + Note that this field cannot be set when spec.os.name is windows. + items: + format: int64 + type: integer + type: array + x-kubernetes-list-type: atomic + supplementalGroupsPolicy: + description: |- + Defines how supplemental groups of the first container processes are calculated. + Valid values are "Merge" and "Strict". If not specified, "Merge" is used. + (Alpha) Using the field requires the SupplementalGroupsPolicy feature gate to be enabled + and the container runtime must implement support for this feature. + Note that this field cannot be set when spec.os.name is windows. + type: string + sysctls: + description: |- + Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported + sysctls (by the container runtime) might fail to launch. + Note that this field cannot be set when spec.os.name is windows. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + x-kubernetes-list-type: atomic + windowsOptions: + description: |- + The Windows specific settings applied to all containers. + If unspecified, the options within a container's SecurityContext will be used. + If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: |- + GMSACredentialSpec is where the GMSA admission webhook + (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the + GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the + GMSA credential spec to use. + type: string + hostProcess: + description: |- + HostProcess determines if a container should be run as a 'Host Process' container. + All of a Pod's containers must have the same effective HostProcess value + (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). + In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: |- + The UserName in Windows to run the entrypoint of the container process. + Defaults to the user specified in image metadata if unspecified. + May also be set in PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object priorityClassName: type: string rollingUpdate: @@ -193,9 +434,10 @@ spec: operator: description: |- Operator represents a key's relationship to the value. - Valid operators are Exists and Equal. Defaults to Equal. + Valid operators are Exists, Equal, Lt, and Gt. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + Lt and Gt perform numeric comparisons (requires feature gate TaintTolerationComparisonOperators). type: string tolerationSeconds: description: |- @@ -337,6 +579,27 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork allows the DCGM-Exporter daemon set to + expose metrics port on the host's network namespace. + type: boolean + hostPID: + description: HostPID allows the DCGM-Exporter daemon set to access + the host's PID namespace + type: boolean + hpcJobMapping: + description: 'Optional: HPC job mapping configuration for NVIDIA + DCGM Exporter' + properties: + directory: + description: |- + Directory path where HPC job mapping files are created by the workload manager + Defaults to /var/lib/dcgm-exporter/job-mapping if not specified + type: string + enabled: + description: Enable HPC job mapping for DCGM Exporter + type: boolean + type: object image: description: NVIDIA DCGM Exporter image name pattern: '[a-zA-Z0-9\-]+' @@ -381,6 +644,19 @@ spec: More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object + service: + description: 'Optional: Service configuration for NVIDIA DCGM + Exporter' + properties: + internalTrafficPolicy: + description: InternalTrafficPolicy describes how nodes distribute + service traffic they receive on the ClusterIP. + type: string + type: + description: Type represents the ServiceType which describes + ingress methods for a service + type: string + type: object serviceMonitor: description: 'Optional: ServiceMonitor configuration for NVIDIA DCGM Exporter' @@ -418,7 +694,7 @@ spec: action: default: replace description: |- - Action to perform based on the regex matching. + action to perform based on the regex matching. `Uppercase` and `Lowercase` actions require Prometheus >= v2.36.0. `DropEqual` and `KeepEqual` actions require Prometheus >= v2.41.0. @@ -450,41 +726,41 @@ spec: type: string modulus: description: |- - Modulus to take of the hash of the source label values. + modulus to take of the hash of the source label values. Only applicable when the action is `HashMod`. format: int64 type: integer regex: - description: Regular expression against which the extracted - value is matched. + description: regex defines the regular expression against + which the extracted value is matched. type: string replacement: description: |- - Replacement value against which a Replace action is performed if the + replacement value against which a Replace action is performed if the regular expression matches. Regex capture groups are available. type: string separator: - description: Separator is the string between concatenated + description: separator defines the string between concatenated SourceLabels. type: string sourceLabels: description: |- - The source labels select values from existing labels. Their content is + sourceLabels defines the source labels select values from existing labels. Their content is concatenated using the configured Separator and matched against the configured regular expression. items: description: |- - LabelName is a valid Prometheus label name which may only contain ASCII - letters, numbers, as well as underscores. - pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + LabelName is a valid Prometheus label name. + For Prometheus 3.x, a label name is valid if it contains UTF-8 characters. + For Prometheus 2.x, a label name is only valid if it contains ASCII characters, letters, numbers, as well as underscores. type: string type: array targetLabel: description: |- - Label to which the resulting string is written in a replacement. + targetLabel defines the label to which the resulting string is written in a replacement. It is mandatory for `Replace`, `HashMod`, `Lowercase`, `Uppercase`, `KeepEqual` and `DropEqual` actions. @@ -666,11 +942,18 @@ spec: licensing' properties: configMapName: + description: 'Deprecated: ConfigMapName has been deprecated + in favour of SecretName. Please use secrets to handle the + licensing server configuration more securely' type: string nlsEnabled: description: NLSEnabled indicates if NVIDIA Licensing System is used for licensing. type: boolean + secretName: + description: SecretName indicates the name of the secret containing + the licensing token + type: string type: object livenessProbe: description: NVIDIA Driver container liveness probe settings @@ -844,6 +1127,10 @@ spec: More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object + secretEnv: + description: 'Optional: SecretEnv represents the name of the Kubernetes + Secret with secret environment variables for the NVIDIA Driver' + type: string startupProbe: description: NVIDIA Driver container startup probe settings properties: @@ -1323,6 +1610,82 @@ spec: description: Kata Manager image tag type: string type: object + kataSandboxDevicePlugin: + description: KataSandboxDevicePlugin component spec + properties: + args: + description: 'Optional: List of arguments' + items: + type: string + type: array + enabled: + description: Enabled indicates if deployment of NVIDIA component + through operator is enabled + type: boolean + env: + description: 'Optional: List of environment variables' + items: + description: EnvVar represents an environment variable present + in a Container. + properties: + name: + description: Name of the environment variable. + type: string + value: + description: Value of the environment variable. + type: string + required: + - name + type: object + type: array + image: + description: NVIDIA component image name + pattern: '[a-zA-Z0-9\-]+' + type: string + imagePullPolicy: + description: Image pull policy + type: string + imagePullSecrets: + description: Image pull secrets + items: + type: string + type: array + repository: + description: NVIDIA component image repository + type: string + resources: + description: 'Optional: Define resources requests and limits for + each pod' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: |- + Limits describes the maximum amount of compute resources allowed. + More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: |- + Requests describes the minimum amount of compute resources required. + If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, + otherwise to an implementation-defined value. Requests cannot exceed Limits. + More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ + type: object + type: object + version: + description: NVIDIA component image tag + type: string + type: object mig: description: MIG spec properties: @@ -1356,8 +1719,8 @@ spec: - "" type: string name: - default: default-mig-parted-config - description: ConfigMap name + description: ConfigMap name. If not specified, MIG configuration + will be dynamically generated from hardware. type: string type: object enabled: @@ -1524,16 +1887,12 @@ spec: queryable and should be preserved when modifying objects. type: object defaultRuntime: - default: docker - description: Runtime defines container runtime type - enum: - - docker - - crio - - containerd + description: 'Deprecated: DefaultRuntime is no longer used by + the gpu-operator. This is instead, detected at runtime.' type: string initContainer: - description: InitContainerSpec describes configuration for initContainer - image used with all components + description: 'Deprecated: InitContainerSpec describes configuration + for initContainer image used with all components' properties: image: description: Image represents image name @@ -1570,8 +1929,6 @@ spec: image should be used on OpenShift to build and install driver modules type: boolean - required: - - defaultRuntime type: object psa: description: PSA defines spec for PodSecurityAdmission configuration @@ -1686,6 +2043,15 @@ spec: Enabled indicates if the GPU Operator should manage additional operands required for sandbox workloads (i.e. VFIO Manager, vGPU Manager, and additional device plugins) type: boolean + mode: + default: kubevirt + description: |- + Mode indicates the sandbox mode. Accepted values are "kubevirt" + and "kata". The default value is "kubevirt". + enum: + - kubevirt + - kata + type: string type: object toolkit: description: Toolkit component spec @@ -2267,6 +2633,13 @@ spec: items: type: string type: array + kernelModuleConfig: + description: 'Optional: Kernel module configuration parameters + for the vGPU manager' + properties: + name: + type: string + type: object repository: description: NVIDIA vGPU Manager image repository type: string diff --git a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml index 97e023bf..20697b9b 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml @@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: - controller-gen.kubebuilder.io/version: v0.17.2 + controller-gen.kubebuilder.io/version: v0.20.1 name: nvidiadrivers.nvidia.com spec: group: nvidia.com @@ -234,11 +234,16 @@ spec: description: 'Optional: Licensing configuration for NVIDIA vGPU licensing' properties: name: + description: 'Deprecated: ConfigMapName has been deprecated in + favour of SecretName. Please use secrets to handle the licensing + server configuration more securely' type: string nlsEnabled: description: NLSEnabled indicates if NVIDIA Licensing System is used for licensing. type: boolean + secretName: + type: string type: object livenessProbe: description: NVIDIA Driver container liveness probe settings @@ -522,6 +527,239 @@ spec: description: NodeSelector specifies a selector for installation of NVIDIA driver type: object + podSecurityContext: + description: 'Optional: Set pod-level security context for driver + pod' + properties: + appArmorProfile: + description: |- + appArmorProfile is the AppArmor options to use by the containers in this pod. + Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: |- + localhostProfile indicates a profile loaded on the node that should be used. + The profile must be preconfigured on the node to work. + Must match the loaded name of the profile. + Must be set if and only if type is "Localhost". + type: string + type: + description: |- + type indicates which kind of AppArmor profile will be applied. + Valid options are: + Localhost - a profile pre-loaded on the node. + RuntimeDefault - the container runtime's default profile. + Unconfined - no AppArmor enforcement. + type: string + required: + - type + type: object + fsGroup: + description: |- + A special supplemental group that applies to all containers in a pod. + Some volume types allow the Kubelet to change the ownership of that volume + to be owned by the pod: + + 1. The owning GID will be the FSGroup + 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) + 3. The permission bits are OR'd with rw-rw---- + + If unset, the Kubelet will not modify the ownership and permissions of any volume. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + fsGroupChangePolicy: + description: |- + fsGroupChangePolicy defines behavior of changing ownership and permission of the volume + before being exposed inside Pod. This field will only apply to + volume types which support fsGroup based ownership(and permissions). + It will have no effect on ephemeral volume types such as: secret, configmaps + and emptydir. + Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. + Note that this field cannot be set when spec.os.name is windows. + type: string + runAsGroup: + description: |- + The GID to run the entrypoint of the container process. + Uses runtime default if unset. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence + for that container. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: |- + Indicates that the container must run as a non-root user. + If true, the Kubelet will validate the image at runtime to ensure that it + does not run as UID 0 (root) and fail to start the container if it does. + If unset or false, no such validation will be performed. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: |- + The UID to run the entrypoint of the container process. + Defaults to user specified in image metadata if unspecified. + May also be set in SecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence + for that container. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxChangePolicy: + description: |- + seLinuxChangePolicy defines how the container's SELinux label is applied to all volumes used by the Pod. + It has no effect on nodes that do not support SELinux or to volumes does not support SELinux. + Valid values are "MountOption" and "Recursive". + + "Recursive" means relabeling of all files on all Pod volumes by the container runtime. + This may be slow for large volumes, but allows mixing privileged and unprivileged Pods sharing the same volume on the same node. + + "MountOption" mounts all eligible Pod volumes with `-o context` mount option. + This requires all Pods that share the same volume to use the same SELinux label. + It is not possible to share the same volume among privileged and unprivileged Pods. + Eligible volumes are in-tree FibreChannel and iSCSI volumes, and all CSI volumes + whose CSI driver announces SELinux support by setting spec.seLinuxMount: true in their + CSIDriver instance. Other volumes are always re-labelled recursively. + "MountOption" value is allowed only when SELinuxMount feature gate is enabled. + + If not specified and SELinuxMount feature gate is enabled, "MountOption" is used. + If not specified and SELinuxMount feature gate is disabled, "MountOption" is used for ReadWriteOncePod volumes + and "Recursive" for all other volumes. + + This field affects only Pods that have SELinux label set, either in PodSecurityContext or in SecurityContext of all containers. + + All Pods that use the same volume should use the same seLinuxChangePolicy, otherwise some pods can get stuck in ContainerCreating state. + Note that this field cannot be set when spec.os.name is windows. + type: string + seLinuxOptions: + description: |- + The SELinux context to be applied to all containers. + If unspecified, the container runtime will allocate a random SELinux context for each + container. May also be set in SecurityContext. If set in + both SecurityContext and PodSecurityContext, the value specified in SecurityContext + takes precedence for that container. + Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to + the container. + type: string + role: + description: Role is a SELinux role label that applies to + the container. + type: string + type: + description: Type is a SELinux type label that applies to + the container. + type: string + user: + description: User is a SELinux user label that applies to + the container. + type: string + type: object + seccompProfile: + description: |- + The seccomp options to use by the containers in this pod. + Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: |- + localhostProfile indicates a profile defined in a file on the node should be used. + The profile must be preconfigured on the node to work. + Must be a descending path, relative to the kubelet's configured seccomp profile location. + Must be set if type is "Localhost". Must NOT be set for any other type. + type: string + type: + description: |- + type indicates which kind of seccomp profile will be applied. + Valid options are: + + Localhost - a profile defined in a file on the node should be used. + RuntimeDefault - the container runtime default profile should be used. + Unconfined - no profile should be applied. + type: string + required: + - type + type: object + supplementalGroups: + description: |- + A list of groups applied to the first process run in each container, in + addition to the container's primary GID and fsGroup (if specified). If + the SupplementalGroupsPolicy feature is enabled, the + supplementalGroupsPolicy field determines whether these are in addition + to or instead of any group memberships defined in the container image. + If unspecified, no additional groups are added, though group memberships + defined in the container image may still be used, depending on the + supplementalGroupsPolicy field. + Note that this field cannot be set when spec.os.name is windows. + items: + format: int64 + type: integer + type: array + x-kubernetes-list-type: atomic + supplementalGroupsPolicy: + description: |- + Defines how supplemental groups of the first container processes are calculated. + Valid values are "Merge" and "Strict". If not specified, "Merge" is used. + (Alpha) Using the field requires the SupplementalGroupsPolicy feature gate to be enabled + and the container runtime must implement support for this feature. + Note that this field cannot be set when spec.os.name is windows. + type: string + sysctls: + description: |- + Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported + sysctls (by the container runtime) might fail to launch. + Note that this field cannot be set when spec.os.name is windows. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + x-kubernetes-list-type: atomic + windowsOptions: + description: |- + The Windows specific settings applied to all containers. + If unspecified, the options within a container's SecurityContext will be used. + If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: |- + GMSACredentialSpec is where the GMSA admission webhook + (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the + GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA + credential spec to use. + type: string + hostProcess: + description: |- + HostProcess determines if a container should be run as a 'Host Process' container. + All of a Pod's containers must have the same effective HostProcess value + (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). + In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: |- + The UserName in Windows to run the entrypoint of the container process. + Defaults to the user specified in image metadata if unspecified. + May also be set in PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object priorityClassName: description: 'Optional: Set priorityClassName' type: string @@ -616,6 +854,10 @@ spec: More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object + secretEnv: + description: 'Optional: SecretEnv represents the name of the Kubernetes + Secret with secret environment variables for the NVIDIA Driver' + type: string startupProbe: description: NVIDIA Driver container startup probe settings properties: @@ -675,9 +917,10 @@ spec: operator: description: |- Operator represents a key's relationship to the value. - Valid operators are Exists and Equal. Defaults to Equal. + Valid operators are Exists, Equal, Lt, and Gt. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + Lt and Gt perform numeric comparisons (requires feature gate TaintTolerationComparisonOperators). type: string tolerationSeconds: description: |- @@ -798,6 +1041,7 @@ spec: - ignored - ready - notReady + - disabled type: string required: - state diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/cleanup_crd.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/cleanup_crd.yaml index 670bedc2..0d426f95 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/cleanup_crd.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/cleanup_crd.yaml @@ -35,16 +35,13 @@ spec: image: {{ include "gpu-operator.fullimage" . }} imagePullPolicy: {{ .Values.operator.imagePullPolicy }} command: - - /bin/sh - - -c - - > - kubectl delete clusterpolicy cluster-policy; - kubectl delete crd clusterpolicies.nvidia.com; - kubectl delete crd nvidiadrivers.nvidia.com --ignore-not-found=true; - {{- if .Values.nfd.enabled -}} - kubectl delete crd nodefeatures.nfd.k8s-sigs.io --ignore-not-found=true; - kubectl delete crd nodefeaturegroups.nfd.k8s-sigs.io --ignore-not-found=true; - kubectl delete crd nodefeaturerules.nfd.k8s-sigs.io --ignore-not-found=true; - {{- end }} + - /usr/bin/manage-crds + args: + - delete + - --filepath=/opt/gpu-operator/nvidia.com_clusterpolicies.yaml + - --filepath=/opt/gpu-operator/nvidia.com_nvidiadrivers.yaml + {{- if .Values.nfd.enabled }} + - --filepath=/opt/gpu-operator/nfd-api-crds.yaml + {{- end }} restartPolicy: OnFailure {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml index 763716d7..978b5dc8 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml @@ -89,45 +89,58 @@ spec: plugin: {{- if .Values.validator.plugin.env }} env: {{ toYaml .Values.validator.plugin.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.cuda }} cuda: {{- if .Values.validator.cuda.env }} env: {{ toYaml .Values.validator.cuda.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.driver }} driver: {{- if .Values.validator.driver.env }} env: {{ toYaml .Values.validator.driver.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.toolkit }} toolkit: {{- if .Values.validator.toolkit.env }} env: {{ toYaml .Values.validator.toolkit.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.vfioPCI }} vfioPCI: {{- if .Values.validator.vfioPCI.env }} env: {{ toYaml .Values.validator.vfioPCI.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.vgpuManager }} vgpuManager: {{- if .Values.validator.vgpuManager.env }} env: {{ toYaml .Values.validator.vgpuManager.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} {{- if .Values.validator.vgpuDevices }} vgpuDevices: {{- if .Values.validator.vgpuDevices.env }} env: {{ toYaml .Values.validator.vgpuDevices.env | nindent 8 }} + {{- else }} + env: [] {{- end }} {{- end }} - mig: {{- if .Values.mig.strategy }} strategy: {{ .Values.mig.strategy }} @@ -136,7 +149,12 @@ spec: enabled: {{ .Values.psa.enabled }} cdi: enabled: {{ .Values.cdi.enabled }} + {{- if .Values.cdi.default }} default: {{ .Values.cdi.default }} + {{- end }} + {{- if and (.Values.cdi.enabled) (.Values.cdi.nriPluginEnabled) }} + nriPluginEnabled: {{ .Values.cdi.nriPluginEnabled }} + {{- end }} driver: enabled: {{ .Values.driver.enabled }} useNvidiaDriverCRD: {{ .Values.driver.nvidiaDriverCRD.enabled }} @@ -200,6 +218,9 @@ spec: {{- if .Values.driver.kernelModuleConfig }} kernelModuleConfig: {{ toYaml .Values.driver.kernelModuleConfig | nindent 6 }} {{- end }} + {{- if .Values.driver.secretEnv }} + secretEnv: {{ .Values.driver.secretEnv }} + {{- end }} {{- if .Values.driver.resources }} resources: {{ toYaml .Values.driver.resources | nindent 6 }} {{- end }} @@ -258,6 +279,9 @@ spec: {{- if .Values.vgpuManager.args }} args: {{ toYaml .Values.vgpuManager.args | nindent 6 }} {{- end }} + {{- if .Values.vgpuManager.kernelModuleConfig }} + kernelModuleConfig: {{ toYaml .Values.vgpuManager.kernelModuleConfig | nindent 6 }} + {{- end }} driverManager: {{- if .Values.vgpuManager.driverManager.repository }} repository: {{ .Values.vgpuManager.driverManager.repository }} @@ -276,7 +300,9 @@ spec: {{- end }} kataManager: enabled: {{ .Values.kataManager.enabled }} + {{- if .Values.kataManager.config }} config: {{ toYaml .Values.kataManager.config | nindent 6 }} + {{- end }} {{- if .Values.kataManager.repository }} repository: {{ .Values.kataManager.repository }} {{- end }} @@ -394,7 +420,7 @@ spec: resources: {{ toYaml .Values.ccManager.resources | nindent 6 }} {{- end }} {{- if .Values.ccManager.env }} - env: {{ toYaml .Values.vfioManager.env | nindent 6 }} + env: {{ toYaml .Values.ccManager.env | nindent 6 }} {{- end }} {{- if .Values.ccManager.args }} args: {{ toYaml .Values.ccManager.args | nindent 6 }} @@ -453,8 +479,8 @@ spec: {{- end }} {{- if .Values.devicePlugin.config.name }} config: - name: {{ .Values.devicePlugin.config.name }} - default: {{ .Values.devicePlugin.config.default }} + name: {{ .Values.devicePlugin.config.name | quote }} + default: {{ .Values.devicePlugin.config.default | quote }} {{- end }} dcgm: enabled: {{ .Values.dcgm.enabled }} @@ -515,6 +541,18 @@ spec: {{- if .Values.dcgmExporter.serviceMonitor }} serviceMonitor: {{ toYaml .Values.dcgmExporter.serviceMonitor | nindent 6 }} {{- end }} + {{- if .Values.dcgmExporter.service }} + service: {{ toYaml .Values.dcgmExporter.service | nindent 6 }} + {{- end }} + {{- if .Values.dcgmExporter.hostPID }} + hostPID: {{ .Values.dcgmExporter.hostPID }} + {{- end }} + {{- if .Values.dcgmExporter.hostNetwork }} + hostNetwork: {{ .Values.dcgmExporter.hostNetwork }} + {{- end }} + {{- if .Values.dcgmExporter.hpcJobMapping }} + hpcJobMapping: {{ toYaml .Values.dcgmExporter.hpcJobMapping | nindent 6 }} + {{- end }} gfd: enabled: {{ .Values.gfd.enabled }} {{- if .Values.gfd.repository }} @@ -569,8 +607,10 @@ spec: {{- end }} {{- if .Values.migManager.config }} config: + {{- if .Values.migManager.config.name }} name: {{ .Values.migManager.config.name }} - default: {{ .Values.migManager.config.default }} + {{- end }} + default: {{ .Values.migManager.config.default | quote }} {{- end }} {{- if .Values.migManager.gpuClientsConfig }} gpuClientsConfig: {{ toYaml .Values.migManager.gpuClientsConfig | nindent 6 }} @@ -599,7 +639,7 @@ spec: {{- if .Values.nodeStatusExporter.args }} args: {{ toYaml .Values.nodeStatusExporter.args | nindent 6 }} {{- end }} - {{- if .Values.gds.enabled }} + {{- if .Values.gds }} gds: enabled: {{ .Values.gds.enabled }} {{- if .Values.gds.repository }} @@ -650,6 +690,9 @@ spec: {{- if .Values.sandboxWorkloads.defaultWorkload }} defaultWorkload: {{ .Values.sandboxWorkloads.defaultWorkload }} {{- end }} + {{- if .Values.sandboxWorkloads.mode }} + mode: {{ .Values.sandboxWorkloads.mode | quote }} + {{- end }} sandboxDevicePlugin: {{- if .Values.sandboxDevicePlugin.enabled }} enabled: {{ .Values.sandboxDevicePlugin.enabled }} @@ -678,3 +721,31 @@ spec: {{- if .Values.sandboxDevicePlugin.args }} args: {{ toYaml .Values.sandboxDevicePlugin.args | nindent 6 }} {{- end }} + kataSandboxDevicePlugin: + {{- if ne .Values.kataSandboxDevicePlugin.enabled nil }} + enabled: {{ .Values.kataSandboxDevicePlugin.enabled }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.repository }} + repository: {{ .Values.kataSandboxDevicePlugin.repository }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.image }} + image: {{ .Values.kataSandboxDevicePlugin.image }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.version }} + version: {{ .Values.kataSandboxDevicePlugin.version | quote }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.imagePullPolicy }} + imagePullPolicy: {{ .Values.kataSandboxDevicePlugin.imagePullPolicy }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.kataSandboxDevicePlugin.imagePullSecrets | nindent 6 }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.resources }} + resources: {{ toYaml .Values.kataSandboxDevicePlugin.resources | nindent 6 }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.env }} + env: {{ toYaml .Values.kataSandboxDevicePlugin.env | nindent 6 }} + {{- end }} + {{- if .Values.kataSandboxDevicePlugin.args }} + args: {{ toYaml .Values.kataSandboxDevicePlugin.args | nindent 6 }} + {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/extra-objects.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/extra-objects.yaml new file mode 100644 index 00000000..fc9a76b8 --- /dev/null +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/extra-objects.yaml @@ -0,0 +1,8 @@ +{{ range .Values.extraObjects }} +--- +{{ if typeIs "string" . }} + {{- tpl . $ }} +{{- else }} + {{- tpl (toYaml .) $ }} +{{- end }} +{{ end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/nodefeaturerules.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/nodefeaturerules.yaml index 6076b3d3..4584cffc 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/nodefeaturerules.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/nodefeaturerules.yaml @@ -2,106 +2,32 @@ apiVersion: nfd.k8s-sigs.io/v1alpha1 kind: NodeFeatureRule metadata: - name: nvidia-nfd-nodefeaturerules + name: nvidia-kernel-modules spec: rules: - - name: "TDX rule" + - name: kernel-module-gdrdrv labels: - tdx.enabled: "true" + nvidia.com/gdrcopy.capable: "true" matchFeatures: - - feature: cpu.security + - feature: kernel.loadedmodule matchExpressions: - tdx.enabled: {op: IsTrue} - - name: "TDX total keys rule" - extendedResources: - tdx.total_keys: "@cpu.security.tdx.total_keys" + gdrdrv: + op: Exists + - name: kernel-module-nvidia_fs + labels: + nvidia.com/gds.capable: "true" matchFeatures: - - feature: cpu.security + - feature: kernel.loadedmodule matchExpressions: - tdx.enabled: {op: IsTrue} - - name: "SEV-SNP rule" + nvidia_fs: + op: Exists + - name: kernel-module-nvidia_peermem labels: - sev.snp.enabled: "true" + nvidia.com/peermem.capable: "true" matchFeatures: - - feature: cpu.security - matchExpressions: - sev.snp.enabled: - op: IsTrue - - name: "SEV-ES rule" - labels: - sev.es.enabled: "true" - matchFeatures: - - feature: cpu.security - matchExpressions: - sev.es.enabled: - op: IsTrue - - name: SEV system capacities - extendedResources: - sev_asids: '@cpu.security.sev.asids' - sev_es: '@cpu.security.sev.encrypted_state_ids' - matchFeatures: - - feature: cpu.security - matchExpressions: - sev.enabled: - op: Exists - - name: "NVIDIA H100" - labels: - "nvidia.com/gpu.H100": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device + - feature: kernel.loadedmodule matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2339"]} - - name: "NVIDIA H100 PCIe" - labels: - "nvidia.com/gpu.H100.pcie": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2331"]} - - name: "NVIDIA H100 80GB HBM3" - labels: - "nvidia.com/gpu.H100.HBM3": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2330"]} - - name: "NVIDIA H800" - labels: - "nvidia.com/gpu.H800": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2324"]} - - name: "NVIDIA H800 PCIE" - labels: - "nvidia.com/gpu.H800.pcie": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2322"]} - - name: "NVIDIA CC Enabled" - labels: - "nvidia.com/cc.capable": "true" - matchAny: # TDX/SEV + Hopper GPU - - matchFeatures: - - feature: rule.matched - matchExpressions: - nvidia.com/gpu.family: {op: In, value: ["hopper"]} - sev.snp.enabled: {op: IsTrue} - - matchFeatures: - - feature: rule.matched - matchExpressions: - nvidia.com/gpu.family: {op: In, value: ["hopper"]} - tdx.enabled: {op: IsTrue} + nvidia_peermem: + op: Exists {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml index cbe56713..60c36575 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml @@ -1,3 +1,4 @@ +{{- if .Values.driver.enabled }} {{- if and .Values.driver.nvidiaDriverCRD.enabled .Values.driver.nvidiaDriverCRD.deployDefaultCR }} apiVersion: nvidia.com/v1alpha1 kind: NVIDIADriver @@ -48,7 +49,11 @@ spec: certConfig: name: {{ .Values.driver.certConfig.name }} {{- end }} - {{- if .Values.driver.licensingConfig.configMapName }} + {{- if .Values.driver.licensingConfig.secretName }} + licensingConfig: + secretName: {{ .Values.driver.licensingConfig.secretName }} + nlsEnabled: {{ .Values.driver.licensingConfig.nlsEnabled | default true }} + {{- else if .Values.driver.licensingConfig.configMapName }} licensingConfig: name: {{ .Values.driver.licensingConfig.configMapName }} nlsEnabled: {{ .Values.driver.licensingConfig.nlsEnabled | default true }} @@ -61,6 +66,9 @@ spec: kernelModuleConfig: name: {{ .Values.driver.kernelModuleConfig.name }} {{- end }} + {{- if .Values.driver.secretEnv }} + secretEnv: {{ .Values.driver.secretEnv }} + {{- end }} {{- if .Values.driver.resources }} resources: {{ toYaml .Values.driver.resources | nindent 6 }} {{- end }} @@ -117,3 +125,4 @@ spec: {{- end }} {{- end }} {{- end }} +{{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/operator.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/operator.yaml index 6f484826..c6ec3bf4 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/operator.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/operator.yaml @@ -2,6 +2,7 @@ apiVersion: apps/v1 kind: Deployment metadata: name: gpu-operator + namespace: {{ .Release.Namespace }} labels: {{- include "gpu-operator.labels" . | nindent 4 }} app.kubernetes.io/component: "gpu-operator" @@ -58,10 +59,6 @@ spec: fieldPath: metadata.namespace - name: "DRIVER_MANAGER_IMAGE" value: "{{ include "driver-manager.fullimage" . }}" - volumeMounts: - - name: host-os-release - mountPath: "/host-etc/os-release" - readOnly: true livenessProbe: httpGet: path: /healthz @@ -81,10 +78,6 @@ spec: ports: - name: metrics containerPort: 8080 - volumes: - - name: host-os-release - hostPath: - path: "/etc/os-release" {{- with .Values.operator.nodeSelector }} nodeSelector: {{- toYaml . | nindent 8 }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/role.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/role.yaml index 9e5bcede..dc4674c5 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/role.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/role.yaml @@ -2,6 +2,7 @@ apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: name: gpu-operator + namespace: {{ .Release.Namespace }} labels: {{- include "gpu-operator.labels" . | nindent 4 }} app.kubernetes.io/component: "gpu-operator" @@ -82,3 +83,13 @@ rules: - watch - update - delete +- apiGroups: + - "nfd.k8s-sigs.io" + resources: + - "nodefeatures" + verbs: + - get + - list + - watch + - create + - update diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/rolebinding.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/rolebinding.yaml index c915a465..732d8d52 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/rolebinding.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/rolebinding.yaml @@ -2,6 +2,7 @@ kind: RoleBinding apiVersion: rbac.authorization.k8s.io/v1 metadata: name: gpu-operator + namespace: {{ .Release.Namespace }} labels: {{- include "gpu-operator.labels" . | nindent 4 }} app.kubernetes.io/component: "gpu-operator" diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/serviceaccount.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/serviceaccount.yaml index 50555e53..79a3b642 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/serviceaccount.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/serviceaccount.yaml @@ -2,6 +2,7 @@ apiVersion: v1 kind: ServiceAccount metadata: name: gpu-operator + namespace: {{ .Release.Namespace }} labels: {{- include "gpu-operator.labels" . | nindent 4 }} app.kubernetes.io/component: "gpu-operator" diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/upgrade_crd.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/upgrade_crd.yaml index 6552558a..e887b3a8 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/upgrade_crd.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/upgrade_crd.yaml @@ -4,6 +4,7 @@ apiVersion: v1 kind: ServiceAccount metadata: name: gpu-operator-upgrade-crd-hook-sa + namespace: {{ .Release.Namespace }} annotations: helm.sh/hook: pre-upgrade helm.sh/hook-delete-policy: hook-succeeded,before-hook-creation @@ -83,13 +84,13 @@ spec: image: {{ include "gpu-operator.fullimage" . }} imagePullPolicy: {{ .Values.operator.imagePullPolicy }} command: - - /bin/sh - - -c - - > - kubectl apply -f /opt/gpu-operator/nvidia.com_clusterpolicies.yaml; - kubectl apply -f /opt/gpu-operator/nvidia.com_nvidiadrivers.yaml; + - /usr/bin/manage-crds + args: + - apply + - --filepath=/opt/gpu-operator/nvidia.com_clusterpolicies.yaml + - --filepath=/opt/gpu-operator/nvidia.com_nvidiadrivers.yaml {{- if .Values.nfd.enabled }} - kubectl apply -f /opt/gpu-operator/nfd-api-crds.yaml; + - --filepath=/opt/gpu-operator/nfd-api-crds.yaml {{- end }} restartPolicy: OnFailure {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/validations.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/validations.yaml new file mode 100644 index 00000000..573786d2 --- /dev/null +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/validations.yaml @@ -0,0 +1,3 @@ +{{- if and (eq .Values.cdi.enabled false) (eq .Values.cdi.nriPluginEnabled true) }} +{{ fail "the NRI Plugin cannot be enabled when CDI is disabled" }} +{{- end}} diff --git a/packages/system/gpu-operator/charts/gpu-operator/values.yaml b/packages/system/gpu-operator/charts/gpu-operator/values.yaml index 2806eac3..222b0e38 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/values.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/values.yaml @@ -13,12 +13,14 @@ psa: enabled: false cdi: - enabled: false - default: false + enabled: true + nriPluginEnabled: false sandboxWorkloads: enabled: false defaultWorkload: "container" + # Sandbox mode: "kubevirt" (default) or "kata". When "kata", the Kata device plugin is deployed on vm-passthrough nodes. + mode: "kubevirt" hostPaths: # rootFS represents the path to the root filesystem of the host. @@ -50,8 +52,8 @@ daemonsets: maxUnavailable: "1" validator: - repository: nvcr.io/nvidia/cloud-native - image: gpu-operator-validator + repository: nvcr.io/nvidia + image: gpu-operator # If version is not specified, then default is to use chart.AppVersion #version: "" imagePullPolicy: IfNotPresent @@ -60,9 +62,7 @@ validator: args: [] resources: {} plugin: - env: - - name: WITH_WORKLOAD - value: "false" + env: [] operator: repository: nvcr.io/nvidia @@ -79,16 +79,7 @@ operator: # upgrade CRD on chart upgrade, requires --disable-openapi-validation flag # to be passed during helm upgrade. upgradeCRD: true - initContainer: - image: cuda - repository: nvcr.io/nvidia - version: 12.8.1-base-ubi9 - imagePullPolicy: IfNotPresent tolerations: - - key: "node-role.kubernetes.io/master" - operator: "Equal" - value: "" - effect: "NoSchedule" - key: "node-role.kubernetes.io/control-plane" operator: "Equal" value: "" @@ -98,12 +89,6 @@ operator: affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - - weight: 1 - preference: - matchExpressions: - - key: "node-role.kubernetes.io/master" - operator: In - values: [""] - weight: 1 preference: matchExpressions: @@ -146,7 +131,7 @@ driver: usePrecompiled: false repository: nvcr.io/nvidia image: driver - version: "570.124.06" + version: "580.126.20" imagePullPolicy: IfNotPresent imagePullSecrets: [] startupProbe: @@ -192,25 +177,13 @@ driver: timeoutSeconds: 300 deleteEmptyDir: false manager: - image: k8s-driver-manager repository: nvcr.io/nvidia/cloud-native + image: k8s-driver-manager # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4 # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0 - version: v0.8.0 + version: v0.10.0 imagePullPolicy: IfNotPresent - env: - - name: ENABLE_GPU_POD_EVICTION - value: "true" - - name: ENABLE_AUTO_DRAIN - value: "false" - - name: DRAIN_USE_FORCE - value: "false" - - name: DRAIN_POD_SELECTOR_LABEL - value: "" - - name: DRAIN_TIMEOUT_SECONDS - value: "0s" - - name: DRAIN_DELETE_EMPTYDIR_DATA - value: "false" + env: [] env: [] resources: {} # Private mirror repository configuration @@ -221,7 +194,7 @@ driver: name: "" # vGPU licensing configuration licensingConfig: - configMapName: "" + secretName: "" nlsEnabled: true # vGPU topology daemon configuration virtualTopology: @@ -229,12 +202,14 @@ driver: # kernel module configuration for NVIDIA driver kernelModuleConfig: name: "" + # Name of Kubernetes Secret which contains secrets to be passed in as environment variables + secretEnv: "" toolkit: enabled: true repository: nvcr.io/nvidia/k8s image: container-toolkit - version: v1.17.5-ubuntu20.04 + version: v1.19.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -245,23 +220,11 @@ devicePlugin: enabled: true repository: nvcr.io/nvidia image: k8s-device-plugin - version: v0.17.1 + version: v0.19.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] args: [] - env: - - name: PASS_DEVICE_SPECS - value: "true" - - name: FAIL_ON_INIT_ERROR - value: "true" - - name: DEVICE_LIST_STRATEGY - value: envvar - - name: DEVICE_ID_STRATEGY - value: uuid - - name: NVIDIA_VISIBLE_DEVICES - value: all - - name: NVIDIA_DRIVER_CAPABILITIES - value: all + env: [] resources: {} # Plugin configuration # Use "name" to either point to an existing ConfigMap or to create a new one with a list of configurations(i.e with create=true). @@ -303,7 +266,7 @@ dcgm: enabled: false repository: nvcr.io/nvidia/cloud-native image: dcgm - version: 4.1.1-2-ubuntu22.04 + version: 4.5.2-1-ubuntu22.04 imagePullPolicy: IfNotPresent args: [] env: [] @@ -313,16 +276,19 @@ dcgmExporter: enabled: true repository: nvcr.io/nvidia/k8s image: dcgm-exporter - version: 4.1.1-4.0.4-ubuntu22.04 + version: 4.5.1-4.8.0-distroless imagePullPolicy: IfNotPresent - env: - - name: DCGM_EXPORTER_LISTEN - value: ":9400" - - name: DCGM_EXPORTER_KUBERNETES - value: "true" - - name: DCGM_EXPORTER_COLLECTORS - value: "/etc/dcgm-exporter/dcp-metrics-included.csv" + env: [] resources: {} + hostPID: false + hostNetwork: false + # HPC job mapping configuration for correlating GPU metrics with HPC workload manager jobs + # This is used by HPC workload managers like Slurm to label GPU metrics with job IDs + # hpcJobMapping: + # enabled: true + # directory: /var/lib/dcgm-exporter/job-mapping + service: + internalTrafficPolicy: Cluster serviceMonitor: enabled: false interval: 15s @@ -359,31 +325,34 @@ gfd: enabled: true repository: nvcr.io/nvidia image: k8s-device-plugin - version: v0.17.1 + version: v0.19.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] - env: - - name: GFD_SLEEP_INTERVAL - value: 60s - - name: GFD_FAIL_ON_INIT_ERROR - value: "true" + env: [] resources: {} migManager: enabled: true repository: nvcr.io/nvidia/cloud-native image: k8s-mig-manager - version: v0.12.1-ubuntu20.04 + version: v0.14.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] - env: - - name: WITH_REBOOT - value: "false" + env: [] resources: {} # MIG configuration - # Use "name" to either point to an existing ConfigMap or to create a new one with a list of configurations(i.e with create=true). - # Use "data" to build an integrated ConfigMap from a set of configurations as - # part of this helm chart. An example of setting "data" might be: + # NOTE: MIG manager automatically generates configuration from hardware on each node. + # Only provide a custom config if you need settings that differ from hardware discovery. + # + # To use an existing ConfigMap: + # - Set name="your-configmap-name" with create=false + # - ConfigMap MUST have a key named "config.yaml" + # + # To create a new ConfigMap via Helm: + # - Set create=true, name="your-configmap-name", and provide data below + # - If create=true but data is empty, ConfigMap creation is skipped + # + # Example of creating a custom ConfigMap: # config: # name: custom-mig-parted-configs # create: true @@ -415,17 +384,19 @@ migManager: default: "all-disabled" # Create a ConfigMap (default: false) create: false - # ConfigMap name (either existing or to create a new one with create=true above) + # ConfigMap name (either existing or to create with create=true) + # If name is provided, mig-manager will use this config instead of auto-generated one. + # REQUIREMENT: Custom ConfigMaps must contain a key named "config.yaml" name: "" - # Data section for the ConfigMap to create (i.e only applies when create=true) + # Data section for the ConfigMap (required only if create=true) data: {} gpuClientsConfig: name: "" nodeStatusExporter: enabled: false - repository: nvcr.io/nvidia/cloud-native - image: gpu-operator-validator + repository: nvcr.io/nvidia + image: gpu-operator # If version is not specified, then default is to use chart.AppVersion #version: "" imagePullPolicy: IfNotPresent @@ -436,7 +407,7 @@ gds: enabled: false repository: nvcr.io/nvidia/cloud-native image: nvidia-fs - version: "2.20.5" + version: "2.27.3" imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -446,7 +417,7 @@ gdrcopy: enabled: false repository: nvcr.io/nvidia/cloud-native image: gdrdrv - version: "v2.4.4" + version: "v2.5.1" imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -462,23 +433,22 @@ vgpuManager: env: [] resources: {} driverManager: - image: k8s-driver-manager repository: nvcr.io/nvidia/cloud-native + image: k8s-driver-manager # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4 # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0 - version: v0.8.0 + version: v0.10.0 imagePullPolicy: IfNotPresent - env: - - name: ENABLE_GPU_POD_EVICTION - value: "false" - - name: ENABLE_AUTO_DRAIN - value: "false" + env: [] + # kernel module configuration for vGPU manager + kernelModuleConfig: + name: "" vgpuDeviceManager: enabled: true repository: nvcr.io/nvidia/cloud-native image: vgpu-device-manager - version: v0.3.0 + version: v0.4.2 imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -488,45 +458,25 @@ vgpuDeviceManager: vfioManager: enabled: true - repository: nvcr.io/nvidia - image: cuda - version: 12.8.1-base-ubi9 + repository: nvcr.io/nvidia/cloud-native + image: k8s-driver-manager + version: v0.10.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] resources: {} driverManager: - image: k8s-driver-manager repository: nvcr.io/nvidia/cloud-native + image: k8s-driver-manager # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4 # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0 - version: v0.8.0 + version: v0.10.0 imagePullPolicy: IfNotPresent - env: - - name: ENABLE_GPU_POD_EVICTION - value: "false" - - name: ENABLE_AUTO_DRAIN - value: "false" + env: [] kataManager: enabled: false - config: - artifactsDir: "/opt/nvidia-gpu-operator/artifacts/runtimeclasses" - runtimeClasses: - - name: kata-nvidia-gpu - nodeSelector: {} - artifacts: - url: nvcr.io/nvidia/cloud-native/kata-gpu-artifacts:ubuntu22.04-535.54.03 - pullSecret: "" - - name: kata-nvidia-gpu-snp - nodeSelector: - "nvidia.com/cc.capable": "true" - artifacts: - url: nvcr.io/nvidia/cloud-native/kata-gpu-artifacts:ubuntu22.04-535.86.10-snp - pullSecret: "" - repository: nvcr.io/nvidia/cloud-native - image: k8s-kata-manager - version: v0.2.3 + config: {} imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -536,7 +486,19 @@ sandboxDevicePlugin: enabled: true repository: nvcr.io/nvidia image: kubevirt-gpu-device-plugin - version: v1.3.1 + version: v1.5.0 + imagePullPolicy: IfNotPresent + imagePullSecrets: [] + args: [] + env: [] + resources: {} + +# Kata sandbox device plugin (used when sandboxWorkloads.mode is "kata"). +kataSandboxDevicePlugin: + enabled: true + repository: nvcr.io/nvidia/cloud-native + image: nvidia-sandbox-device-plugin + version: "v0.0.2" imagePullPolicy: IfNotPresent imagePullSecrets: [] args: [] @@ -544,11 +506,11 @@ sandboxDevicePlugin: resources: {} ccManager: - enabled: false - defaultMode: "off" + enabled: true + defaultMode: "on" repository: nvcr.io/nvidia/cloud-native image: k8s-cc-manager - version: v0.1.1 + version: v0.3.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] env: @@ -556,8 +518,11 @@ ccManager: value: "0x2339,0x2331,0x2330,0x2324,0x2322,0x233d" resources: {} +# Array of extra K8s manifests to deploy +# Supports use of custom Helm templates +extraObjects: [] + node-feature-discovery: - enableNodeFeatureApi: true priorityClassName: system-node-critical gc: enable: true @@ -571,10 +536,6 @@ node-feature-discovery: # disable creation to avoid duplicate serviceaccount creation by master spec below create: false tolerations: - - key: "node-role.kubernetes.io/master" - operator: "Equal" - value: "" - effect: "NoSchedule" - key: "node-role.kubernetes.io/control-plane" operator: "Equal" value: "" From 8c866934081d7ec6824f058f075f8c2e3230e195 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 2 Apr 2026 15:09:52 +0300 Subject: [PATCH 24/35] feat(gpu-operator): add vGPU variant for mediated device support Add vGPU mode as a new variant alongside the existing passthrough (default) variant. This enables sharing a single physical GPU across multiple VMs using NVIDIA mediated devices. Changes: - Add values-talos-vgpu.yaml with vGPU Manager and vGPU Device Manager enabled - Add 'vgpu' variant to PackageSource - Add documentation for vGPU setup (driver image, NLS licensing, profiles, KubeVirt) Users select the vgpu variant via Package CR and provide their proprietary vGPU Manager image coordinates through component values. Assisted-By: Claude Signed-off-by: Aleksei Sviridkin --- docs/gpu-vgpu.md | 167 ++++++++++++++++++ .../core/platform/sources/gpu-operator.yaml | 13 ++ .../gpu-operator/values-talos-vgpu.yaml | 16 ++ 3 files changed, 196 insertions(+) create mode 100644 docs/gpu-vgpu.md create mode 100644 packages/system/gpu-operator/values-talos-vgpu.yaml diff --git a/docs/gpu-vgpu.md b/docs/gpu-vgpu.md new file mode 100644 index 00000000..77b3e80d --- /dev/null +++ b/docs/gpu-vgpu.md @@ -0,0 +1,167 @@ +# GPU Operator: vGPU Support + +This document describes how to configure the GPU Operator package with NVIDIA vGPU support for sharing a single physical GPU across multiple virtual machines using mediated devices. + +## Prerequisites + +- NVIDIA GPU with vGPU support (e.g., NVIDIA L40S, A100, A30, etc.) +- Talos Linux as the host OS +- NVIDIA vGPU Software license (NVIDIA AI Enterprise or vGPU subscription) +- Access to the NVIDIA Licensing Portal ([ui.licensing.nvidia.com](https://ui.licensing.nvidia.com)) + +## Variants + +The GPU Operator package supports two variants: + +- **`default`** — GPU passthrough mode (vfio-pci). The entire GPU is passed through to a single VM. +- **`vgpu`** — vGPU mode. A physical GPU is shared between multiple VMs using NVIDIA mediated devices. + +## Building the vGPU Manager Image + +The vGPU Manager driver is proprietary and must be obtained from NVIDIA: + +1. Log in to the [NVIDIA Licensing Portal](https://ui.licensing.nvidia.com) +2. Download the NVIDIA vGPU Software package for your GPU and target Linux version +3. Build a container image containing the vGPU Manager driver: + +```bash +# Example Containerfile +FROM ubuntu:22.04 +ARG DRIVER_VERSION +COPY NVIDIA-Linux-x86_64-${DRIVER_VERSION}-vgpu-kvm.run /opt/ +RUN chmod +x /opt/NVIDIA-Linux-x86_64-${DRIVER_VERSION}-vgpu-kvm.run +``` + +4. Push the image to your private registry: + +```bash +docker build --build-arg DRIVER_VERSION=550.90.05 --tag registry.example.com/nvidia/vgpu-manager:550.90.05 . +docker push registry.example.com/nvidia/vgpu-manager:550.90.05 +``` + +> Refer to the [NVIDIA GPU Operator documentation](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/install-gpu-operator-vgpu.html) for detailed instructions on building the vGPU Manager image. + +## Deploying with vGPU Variant + +Create a Package CR with the `vgpu` variant and provide your vGPU Manager image coordinates: + +```yaml +apiVersion: cozystack.io/v1alpha1 +kind: Package +metadata: + name: cozystack.gpu-operator +spec: + variant: vgpu + components: + gpu-operator: + values: + gpu-operator: + vgpuManager: + repository: registry.example.com/nvidia + version: "550.90.05" +``` + +If your registry requires authentication, create an `imagePullSecret` in the `cozy-gpu-operator` namespace and reference it: + +```yaml +gpu-operator: + vgpuManager: + repository: registry.example.com/nvidia + version: "550.90.05" + imagePullSecrets: + - name: nvidia-registry-secret +``` + +## NVIDIA License Server (NLS) Configuration + +vGPU requires a license server. Configure NLS by passing the license server address via a ConfigMap: + +1. Create a ConfigMap with the NLS client configuration in the `cozy-gpu-operator` namespace: + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: licensing-config + namespace: cozy-gpu-operator +data: + gridd.conf: | + ServerAddress=nls.example.com + ServerPort=443 + FeatureType=1 +``` + +2. Reference the ConfigMap in the Package values: + +```yaml +gpu-operator: + vgpuManager: + repository: registry.example.com/nvidia + version: "550.90.05" + driver: + licensingConfig: + configMapName: licensing-config +``` + +## vGPU Profiles + +Each GPU model supports specific vGPU profiles that determine how the GPU is partitioned. To list available profiles for your GPU, consult the [NVIDIA vGPU User Guide](https://docs.nvidia.com/grid/latest/grid-vgpu-user-guide/). + +Example profiles for NVIDIA L40S: + +| Profile | Frame Buffer | Max Instances | Use Case | +| --- | --- | --- | --- | +| NVIDIA L40S-1Q | 1 GB | 48 | Light 3D/VDI | +| NVIDIA L40S-2Q | 2 GB | 24 | Medium 3D/VDI | +| NVIDIA L40S-4Q | 4 GB | 12 | Heavy 3D/VDI | +| NVIDIA L40S-6Q | 6 GB | 8 | Professional 3D | +| NVIDIA L40S-8Q | 8 GB | 6 | AI/ML inference | +| NVIDIA L40S-12Q | 12 GB | 4 | AI/ML training | +| NVIDIA L40S-24Q | 24 GB | 2 | Large AI workloads | +| NVIDIA L40S-48Q | 48 GB | 1 | Full GPU equivalent | + +Custom vGPU device configuration can be provided via a ConfigMap: + +```yaml +gpu-operator: + vgpuDeviceManager: + enabled: true + config: + name: vgpu-devices-config + default: default +``` + +## KubeVirt Integration + +To use vGPU with KubeVirt VMs, configure `mediatedDeviceTypes` in the KubeVirt CR. This maps vGPU profiles to node selectors: + +```yaml +apiVersion: kubevirt.io/v1 +kind: KubeVirt +metadata: + name: kubevirt +spec: + configuration: + mediatedDevicesConfiguration: + mediatedDeviceTypes: + - nvidia-592 # NVIDIA L40S-24Q + permittedHostDevices: + mediatedDevices: + - mdevNameSelector: NVIDIA L40S-24Q + resourceName: nvidia.com/NVIDIA_L40S-24Q +``` + +Then reference the vGPU resource in a VirtualMachine spec: + +```yaml +apiVersion: kubevirt.io/v1 +kind: VirtualMachine +spec: + template: + spec: + domain: + devices: + gpus: + - name: gpu1 + deviceName: nvidia.com/NVIDIA_L40S-24Q +``` diff --git a/packages/core/platform/sources/gpu-operator.yaml b/packages/core/platform/sources/gpu-operator.yaml index e41cc9b2..10d36d65 100644 --- a/packages/core/platform/sources/gpu-operator.yaml +++ b/packages/core/platform/sources/gpu-operator.yaml @@ -23,3 +23,16 @@ spec: privileged: true namespace: cozy-gpu-operator releaseName: gpu-operator + - name: vgpu + dependsOn: + - cozystack.networking + components: + - name: gpu-operator + path: system/gpu-operator + valuesFiles: + - values.yaml + - values-talos-vgpu.yaml + install: + privileged: true + namespace: cozy-gpu-operator + releaseName: gpu-operator diff --git a/packages/system/gpu-operator/values-talos-vgpu.yaml b/packages/system/gpu-operator/values-talos-vgpu.yaml new file mode 100644 index 00000000..00ed8219 --- /dev/null +++ b/packages/system/gpu-operator/values-talos-vgpu.yaml @@ -0,0 +1,16 @@ +gpu-operator: + sandboxWorkloads: + enabled: true + driver: + enabled: false + devicePlugin: + enabled: false + vgpuManager: + enabled: true + repository: "" + image: vgpu-manager + version: "" + vgpuDeviceManager: + enabled: true + config: + default: default From 6a45f0e65dbbced5d5bf1afba4f1729488e70d8d Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 2 Apr 2026 15:47:33 +0300 Subject: [PATCH 25/35] docs(gpu-vgpu): fix driver container build instructions and NLS config Replace simplified Containerfile with NVIDIA's Makefile-based build system from gitlab.com/nvidia/container-images/driver. The GPU Operator expects pre-compiled kernel modules, not a raw .run file. Add EULA notice about public redistribution of vGPU driver images. Add note about NLS ServerPort being deployment-dependent. Assisted-By: Claude Signed-off-by: Aleksei Sviridkin --- docs/gpu-vgpu.md | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/docs/gpu-vgpu.md b/docs/gpu-vgpu.md index 77b3e80d..5935c96e 100644 --- a/docs/gpu-vgpu.md +++ b/docs/gpu-vgpu.md @@ -18,28 +18,32 @@ The GPU Operator package supports two variants: ## Building the vGPU Manager Image -The vGPU Manager driver is proprietary and must be obtained from NVIDIA: +The vGPU Manager driver is proprietary and must be obtained from NVIDIA. The GPU Operator expects a pre-built driver container image — it does not install the driver from a raw `.run` file at runtime. 1. Log in to the [NVIDIA Licensing Portal](https://ui.licensing.nvidia.com) -2. Download the NVIDIA vGPU Software package for your GPU and target Linux version -3. Build a container image containing the vGPU Manager driver: +2. Navigate to **Software Downloads** and download the NVIDIA vGPU Software package for your GPU +3. Build the driver container image using NVIDIA's Makefile-based build system: ```bash -# Example Containerfile -FROM ubuntu:22.04 -ARG DRIVER_VERSION -COPY NVIDIA-Linux-x86_64-${DRIVER_VERSION}-vgpu-kvm.run /opt/ -RUN chmod +x /opt/NVIDIA-Linux-x86_64-${DRIVER_VERSION}-vgpu-kvm.run -``` +# Clone the NVIDIA driver container repository +git clone https://gitlab.com/nvidia/container-images/driver.git +cd driver -4. Push the image to your private registry: +# Place the downloaded .run file in the appropriate directory +cp NVIDIA-Linux-x86_64-550.90.05-vgpu-kvm.run vgpu/ -```bash -docker build --build-arg DRIVER_VERSION=550.90.05 --tag registry.example.com/nvidia/vgpu-manager:550.90.05 . +# Build using the provided Makefile +make OS_TAG=ubuntu22.04 \ + VGPU_DRIVER_VERSION=550.90.05 \ + PRIVATE_REGISTRY=registry.example.com/nvidia + +# Push to your private registry docker push registry.example.com/nvidia/vgpu-manager:550.90.05 ``` -> Refer to the [NVIDIA GPU Operator documentation](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/install-gpu-operator-vgpu.html) for detailed instructions on building the vGPU Manager image. +> **Important:** The build process compiles kernel modules against the host kernel version. Refer to the [NVIDIA GPU Operator vGPU documentation](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/install-gpu-operator-vgpu.html) for the complete build procedure and supported OS/kernel combinations. +> +> Uploading the vGPU driver to a publicly available registry is a violation of the NVIDIA vGPU EULA. ## Deploying with vGPU Variant @@ -89,6 +93,7 @@ data: ServerAddress=nls.example.com ServerPort=443 FeatureType=1 + # ServerPort depends on your NLS deployment (commonly 443 for DLS or 7070 for legacy NLS) ``` 2. Reference the ConfigMap in the Package values: From dbe37e7ed48797275622c988d5c8a558f2804faf Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 2 Apr 2026 15:57:11 +0300 Subject: [PATCH 26/35] fix(gpu-operator): use Secret instead of ConfigMap for licensing config ConfigMap-based licensing configuration (configMapName) is deprecated in GPU Operator v26.x. Switch to Secret-based configuration (secretName) as recommended by the updated CRD schema. Assisted-By: Claude Signed-off-by: Aleksei Sviridkin --- docs/gpu-vgpu.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/gpu-vgpu.md b/docs/gpu-vgpu.md index 5935c96e..1c402096 100644 --- a/docs/gpu-vgpu.md +++ b/docs/gpu-vgpu.md @@ -78,25 +78,25 @@ gpu-operator: ## NVIDIA License Server (NLS) Configuration -vGPU requires a license server. Configure NLS by passing the license server address via a ConfigMap: +vGPU requires a license server. Configure NLS by passing the license server address via a Secret: -1. Create a ConfigMap with the NLS client configuration in the `cozy-gpu-operator` namespace: +1. Create a Secret with the NLS client configuration in the `cozy-gpu-operator` namespace: ```yaml apiVersion: v1 -kind: ConfigMap +kind: Secret metadata: name: licensing-config namespace: cozy-gpu-operator -data: +stringData: gridd.conf: | ServerAddress=nls.example.com ServerPort=443 - FeatureType=1 + FeatureType=1 # 1 for vGPU (vPC/vWS), 2 for Virtual Compute Server (vCS) # ServerPort depends on your NLS deployment (commonly 443 for DLS or 7070 for legacy NLS) ``` -2. Reference the ConfigMap in the Package values: +2. Reference the Secret in the Package values: ```yaml gpu-operator: @@ -105,7 +105,7 @@ gpu-operator: version: "550.90.05" driver: licensingConfig: - configMapName: licensing-config + secretName: licensing-config ``` ## vGPU Profiles From 5a61a33b85096ad4f8d439eb04c2d93c64765eae Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Tue, 28 Apr 2026 23:04:39 +0300 Subject: [PATCH 27/35] chore(gpu-operator): bump to v26.3.1 Pull latest patch release: GDRCopy v2.5.2, Kata Sandbox Device Plugin v0.0.3, multi-arch digest fix for KubeVirt GPU Device Plugin (no longer amd64-only), and OS release name detection fix. NFD remains v0.18.3. Assisted-By: Claude Signed-off-by: Aleksei Sviridkin --- packages/system/gpu-operator/Makefile | 2 +- .../charts/gpu-operator/Chart.yaml | 4 +- .../crds/nvidia.com_clusterpolicies.yaml | 60 +++++++++++++++++++ .../crds/nvidia.com_nvidiadrivers.yaml | 4 ++ .../gpu-operator/templates/clusterpolicy.yaml | 45 ++++++++++++++ .../gpu-operator/templates/nvidiadriver.yaml | 3 + .../charts/gpu-operator/values.yaml | 24 ++++++-- 7 files changed, 133 insertions(+), 9 deletions(-) diff --git a/packages/system/gpu-operator/Makefile b/packages/system/gpu-operator/Makefile index 11ca047e..a8b3b43f 100644 --- a/packages/system/gpu-operator/Makefile +++ b/packages/system/gpu-operator/Makefile @@ -8,4 +8,4 @@ update: rm -rf charts helm repo add nvidia https://helm.ngc.nvidia.com/nvidia helm repo update nvidia - helm pull nvidia/gpu-operator --untar --untardir charts --version v26.3.0 + helm pull nvidia/gpu-operator --untar --untardir charts --version v26.3.1 diff --git a/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml b/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml index c2138a54..1e1ddabe 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/Chart.yaml @@ -1,5 +1,5 @@ apiVersion: v2 -appVersion: v26.3.0 +appVersion: v26.3.1 dependencies: - condition: nfd.enabled name: node-feature-discovery @@ -20,4 +20,4 @@ kubeVersion: '>= 1.16.0-0' name: gpu-operator sources: - https://github.com/NVIDIA/gpu-operator -version: v26.3.0 +version: v26.3.1 diff --git a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml index 030581fc..29737027 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_clusterpolicies.yaml @@ -82,6 +82,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the CC Manager pod + uses the host's network namespace. + type: boolean image: description: CC Manager image name pattern: '[a-zA-Z0-9\-]+' @@ -489,6 +493,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the DCGM pod uses the + host's network namespace. + type: boolean hostPort: description: 'Deprecated: HostPort represents host port that needs to be bound for DCGM engine (Default: 5555)' @@ -815,6 +823,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Device Plugin pod + uses the host's network namespace. + type: boolean image: description: NVIDIA Device Plugin image name pattern: '[a-zA-Z0-9\-]+' @@ -907,6 +919,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Driver pod uses + the host's network namespace. + type: boolean image: description: NVIDIA Driver image name pattern: '[a-zA-Z0-9\-]+' @@ -1419,6 +1435,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the GPU Feature Discovery + pod uses the host's network namespace. + type: boolean image: description: GFD image name pattern: '[a-zA-Z0-9\-]+' @@ -1562,6 +1582,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Kata Manager pod + uses the host's network namespace. + type: boolean image: description: Kata Manager image name pattern: '[a-zA-Z0-9\-]+' @@ -1638,6 +1662,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Kata Sandbox Device + Plugin pod uses the host's network namespace. + type: boolean image: description: NVIDIA component image name pattern: '[a-zA-Z0-9\-]+' @@ -1751,6 +1779,10 @@ spec: description: ConfigMap name type: string type: object + hostNetwork: + description: HostNetwork indicates whether the MIG Manager pod + uses the host's network namespace. + type: boolean image: description: NVIDIA MIG Manager image name pattern: '[a-zA-Z0-9\-]+' @@ -1827,6 +1859,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Node Status Exporter + pod uses the host's network namespace. + type: boolean image: description: Node Status Exporter image name pattern: '[a-zA-Z0-9\-]+' @@ -1976,6 +2012,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Sandbox Device + Plugin pod uses the host's network namespace. + type: boolean image: description: NVIDIA Sandbox Device Plugin image name pattern: '[a-zA-Z0-9\-]+' @@ -2081,6 +2121,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Container Toolkit + pod uses the host's network namespace. + type: boolean image: description: NVIDIA Container Toolkit image name pattern: '[a-zA-Z0-9\-]+' @@ -2197,6 +2241,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the Validator pod uses + the host's network namespace. + type: boolean image: description: Validator image name pattern: '[a-zA-Z0-9\-]+' @@ -2415,6 +2463,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the VFIO Manager pod + uses the host's network namespace. + type: boolean image: description: VFIO Manager image name pattern: '[a-zA-Z0-9\-]+' @@ -2503,6 +2555,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the vGPU Device Manager + pod uses the host's network namespace. + type: boolean image: description: NVIDIA vGPU Device Manager image name pattern: '[a-zA-Z0-9\-]+' @@ -2621,6 +2677,10 @@ spec: - name type: object type: array + hostNetwork: + description: HostNetwork indicates whether the vGPU Manager pod + uses the host's network namespace. + type: boolean image: description: NVIDIA vGPU Manager image name pattern: '[a-zA-Z0-9\-]+' diff --git a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml index 20697b9b..81c23415 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/crds/nvidia.com_nvidiadrivers.yaml @@ -192,6 +192,10 @@ spec: description: NVIDIA GPUDirect Storage Driver image tag type: string type: object + hostNetwork: + description: HostNetwork indicates whether the Driver pod uses the + host's network namespace. + type: boolean image: default: nvcr.io/nvidia/driver description: NVIDIA Driver container image name diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml index 978b5dc8..6e5c6a9c 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/clusterpolicy.yaml @@ -85,6 +85,9 @@ spec: {{- if .Values.validator.args }} args: {{ toYaml .Values.validator.args | nindent 6 }} {{- end }} + {{- if .Values.validator.hostNetwork }} + hostNetwork: {{ .Values.validator.hostNetwork }} + {{- end }} {{- if .Values.validator.plugin }} plugin: {{- if .Values.validator.plugin.env }} @@ -253,6 +256,9 @@ spec: timeoutSeconds: {{ .Values.driver.upgradePolicy.drain.timeoutSeconds }} deleteEmptyDir: {{ .Values.driver.upgradePolicy.drain.deleteEmptyDir | default false}} {{- end }} + {{- if .Values.driver.hostNetwork }} + hostNetwork: {{ .Values.driver.hostNetwork }} + {{- end }} vgpuManager: enabled: {{ .Values.vgpuManager.enabled }} {{- if .Values.vgpuManager.repository }} @@ -282,6 +288,9 @@ spec: {{- if .Values.vgpuManager.kernelModuleConfig }} kernelModuleConfig: {{ toYaml .Values.vgpuManager.kernelModuleConfig | nindent 6 }} {{- end }} + {{- if .Values.vgpuManager.hostNetwork }} + hostNetwork: {{ .Values.vgpuManager.hostNetwork }} + {{- end }} driverManager: {{- if .Values.vgpuManager.driverManager.repository }} repository: {{ .Values.vgpuManager.driverManager.repository }} @@ -327,6 +336,9 @@ spec: {{- if .Values.kataManager.args }} args: {{ toYaml .Values.kataManager.args | nindent 6 }} {{- end }} + {{- if .Values.kataManager.hostNetwork }} + hostNetwork: {{ .Values.kataManager.hostNetwork }} + {{- end }} vfioManager: enabled: {{ .Values.vfioManager.enabled }} {{- if .Values.vfioManager.repository }} @@ -369,6 +381,9 @@ spec: {{- if .Values.vfioManager.driverManager.env }} env: {{ toYaml .Values.vfioManager.driverManager.env | nindent 8 }} {{- end }} + {{- if .Values.vfioManager.hostNetwork }} + hostNetwork: {{ .Values.vfioManager.hostNetwork }} + {{- end }} vgpuDeviceManager: enabled: {{ .Values.vgpuDeviceManager.enabled }} {{- if .Values.vgpuDeviceManager.repository }} @@ -398,6 +413,9 @@ spec: {{- if .Values.vgpuDeviceManager.config }} config: {{ toYaml .Values.vgpuDeviceManager.config | nindent 6 }} {{- end }} + {{- if .Values.vgpuDeviceManager.hostNetwork }} + hostNetwork: {{ .Values.vgpuDeviceManager.hostNetwork }} + {{- end }} ccManager: enabled: {{ .Values.ccManager.enabled }} defaultMode: {{ .Values.ccManager.defaultMode | quote }} @@ -425,6 +443,9 @@ spec: {{- if .Values.ccManager.args }} args: {{ toYaml .Values.ccManager.args | nindent 6 }} {{- end }} + {{- if .Values.ccManager.hostNetwork }} + hostNetwork: {{ .Values.ccManager.hostNetwork }} + {{- end }} toolkit: enabled: {{ .Values.toolkit.enabled }} {{- if .Values.toolkit.repository }} @@ -451,6 +472,9 @@ spec: {{- if .Values.toolkit.installDir }} installDir: {{ .Values.toolkit.installDir }} {{- end }} + {{- if .Values.toolkit.hostNetwork }} + hostNetwork: {{ .Values.toolkit.hostNetwork }} + {{- end }} devicePlugin: enabled: {{ .Values.devicePlugin.enabled }} {{- if .Values.devicePlugin.repository }} @@ -482,6 +506,9 @@ spec: name: {{ .Values.devicePlugin.config.name | quote }} default: {{ .Values.devicePlugin.config.default | quote }} {{- end }} + {{- if .Values.devicePlugin.hostNetwork }} + hostNetwork: {{ .Values.devicePlugin.hostNetwork }} + {{- end }} dcgm: enabled: {{ .Values.dcgm.enabled }} {{- if .Values.dcgm.repository }} @@ -508,6 +535,9 @@ spec: {{- if .Values.dcgm.args }} args: {{ toYaml .Values.dcgm.args | nindent 6 }} {{- end }} + {{- if .Values.dcgm.hostNetwork }} + hostNetwork: {{ .Values.dcgm.hostNetwork }} + {{- end }} dcgmExporter: enabled: {{ .Values.dcgmExporter.enabled }} {{- if .Values.dcgmExporter.repository }} @@ -579,6 +609,9 @@ spec: {{- if .Values.gfd.args }} args: {{ toYaml .Values.gfd.args | nindent 6 }} {{- end }} + {{- if .Values.gfd.hostNetwork }} + hostNetwork: {{ .Values.gfd.hostNetwork }} + {{- end }} migManager: enabled: {{ .Values.migManager.enabled }} {{- if .Values.migManager.repository }} @@ -615,6 +648,9 @@ spec: {{- if .Values.migManager.gpuClientsConfig }} gpuClientsConfig: {{ toYaml .Values.migManager.gpuClientsConfig | nindent 6 }} {{- end }} + {{- if .Values.migManager.hostNetwork }} + hostNetwork: {{ .Values.migManager.hostNetwork }} + {{- end }} nodeStatusExporter: enabled: {{ .Values.nodeStatusExporter.enabled }} {{- if .Values.nodeStatusExporter.repository }} @@ -639,6 +675,9 @@ spec: {{- if .Values.nodeStatusExporter.args }} args: {{ toYaml .Values.nodeStatusExporter.args | nindent 6 }} {{- end }} + {{- if .Values.nodeStatusExporter.hostNetwork }} + hostNetwork: {{ .Values.nodeStatusExporter.hostNetwork }} + {{- end }} {{- if .Values.gds }} gds: enabled: {{ .Values.gds.enabled }} @@ -721,6 +760,9 @@ spec: {{- if .Values.sandboxDevicePlugin.args }} args: {{ toYaml .Values.sandboxDevicePlugin.args | nindent 6 }} {{- end }} + {{- if .Values.sandboxDevicePlugin.hostNetwork }} + hostNetwork: {{ .Values.sandboxDevicePlugin.hostNetwork }} + {{- end }} kataSandboxDevicePlugin: {{- if ne .Values.kataSandboxDevicePlugin.enabled nil }} enabled: {{ .Values.kataSandboxDevicePlugin.enabled }} @@ -749,3 +791,6 @@ spec: {{- if .Values.kataSandboxDevicePlugin.args }} args: {{ toYaml .Values.kataSandboxDevicePlugin.args | nindent 6 }} {{- end }} + {{- if .Values.kataSandboxDevicePlugin.hostNetwork }} + hostNetwork: {{ .Values.kataSandboxDevicePlugin.hostNetwork }} + {{- end }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml b/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml index 60c36575..1a059a49 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/templates/nvidiadriver.yaml @@ -78,6 +78,9 @@ spec: {{- if .Values.driver.args }} args: {{ toYaml .Values.driver.args | nindent 6 }} {{- end }} + {{- if .Values.driver.hostNetwork }} + hostNetwork: {{ .Values.driver.hostNetwork }} + {{- end }} {{- if .Values.gds.enabled }} gds: enabled: {{ .Values.gds.enabled }} diff --git a/packages/system/gpu-operator/charts/gpu-operator/values.yaml b/packages/system/gpu-operator/charts/gpu-operator/values.yaml index 222b0e38..6ee3c2f0 100644 --- a/packages/system/gpu-operator/charts/gpu-operator/values.yaml +++ b/packages/system/gpu-operator/charts/gpu-operator/values.yaml @@ -61,6 +61,7 @@ validator: env: [] args: [] resources: {} + hostNetwork: false plugin: env: [] @@ -204,6 +205,7 @@ driver: name: "" # Name of Kubernetes Secret which contains secrets to be passed in as environment variables secretEnv: "" + hostNetwork: false toolkit: enabled: true @@ -215,6 +217,7 @@ toolkit: env: [] resources: {} installDir: "/usr/local/nvidia" + hostNetwork: false devicePlugin: enabled: true @@ -259,6 +262,7 @@ devicePlugin: mps: # MPS root path on the host root: "/run/nvidia/mps" + hostNetwork: false # standalone dcgm hostengine dcgm: @@ -271,6 +275,7 @@ dcgm: args: [] env: [] resources: {} + hostNetwork: false dcgmExporter: enabled: true @@ -330,6 +335,7 @@ gfd: imagePullSecrets: [] env: [] resources: {} + hostNetwork: false migManager: enabled: true @@ -392,6 +398,7 @@ migManager: data: {} gpuClientsConfig: name: "" + hostNetwork: false nodeStatusExporter: enabled: false @@ -402,6 +409,7 @@ nodeStatusExporter: imagePullPolicy: IfNotPresent imagePullSecrets: [] resources: {} + hostNetwork: false gds: enabled: false @@ -417,7 +425,7 @@ gdrcopy: enabled: false repository: nvcr.io/nvidia/cloud-native image: gdrdrv - version: "v2.5.1" + version: "v2.5.2" imagePullPolicy: IfNotPresent imagePullSecrets: [] env: [] @@ -443,6 +451,7 @@ vgpuManager: # kernel module configuration for vGPU manager kernelModuleConfig: name: "" + hostNetwork: false vgpuDeviceManager: enabled: true @@ -455,6 +464,7 @@ vgpuDeviceManager: config: name: "" default: "default" + hostNetwork: false vfioManager: enabled: true @@ -473,6 +483,7 @@ vfioManager: version: v0.10.0 imagePullPolicy: IfNotPresent env: [] + hostNetwork: false kataManager: enabled: false @@ -481,6 +492,7 @@ kataManager: imagePullSecrets: [] env: [] resources: {} + hostNetwork: false sandboxDevicePlugin: enabled: true @@ -492,31 +504,31 @@ sandboxDevicePlugin: args: [] env: [] resources: {} + hostNetwork: false # Kata sandbox device plugin (used when sandboxWorkloads.mode is "kata"). kataSandboxDevicePlugin: enabled: true repository: nvcr.io/nvidia/cloud-native image: nvidia-sandbox-device-plugin - version: "v0.0.2" + version: "v0.0.3" imagePullPolicy: IfNotPresent imagePullSecrets: [] args: [] env: [] resources: {} + hostNetwork: false ccManager: enabled: true defaultMode: "on" repository: nvcr.io/nvidia/cloud-native image: k8s-cc-manager - version: v0.3.0 + version: v0.4.0 imagePullPolicy: IfNotPresent imagePullSecrets: [] - env: - - name: CC_CAPABLE_DEVICE_IDS - value: "0x2339,0x2331,0x2330,0x2324,0x2322,0x233d" resources: {} + hostNetwork: false # Array of extra K8s manifests to deploy # Supports use of custom Helm templates From 4541c20e3403a5eda85a15ae3a02b80e6cc2ebbd Mon Sep 17 00:00:00 2001 From: "cozystack-ci[bot]" <274107086+cozystack-ci[bot]@users.noreply.github.com> Date: Wed, 29 Apr 2026 04:38:30 +0000 Subject: [PATCH 28/35] docs: add changelog for v1.3.1 Signed-off-by: cozystack-ci[bot] <274107086+cozystack-ci[bot]@users.noreply.github.com> --- docs/changelogs/v1.3.1.md | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 docs/changelogs/v1.3.1.md diff --git a/docs/changelogs/v1.3.1.md b/docs/changelogs/v1.3.1.md new file mode 100644 index 00000000..55e6a796 --- /dev/null +++ b/docs/changelogs/v1.3.1.md @@ -0,0 +1,38 @@ +# v1.3.1 (2026-04-29) + +This is a patch release containing fixes and minor improvements. + +## Fixes and Improvements + +* **[linstor-gui] Add package for LINBIT linstor-gui web UI**: [linstor-gui] Add package for LINBIT linstor-gui web UI ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2382) in #2382) +* **fix(kamaji): increase memory limits and add startup probe**: fix(kamaji): increase memory limits and add startup probe ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2421) in #2421) +* **fix(backups): move velero-configmap Role to velero chart**: fix(backups): move velero-configmap Role to velero chart ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2459) in #2459) +* **fix(etcd): remove destructive post-upgrade cert-regeneration hook**: fix(etcd): remove destructive post-upgrade cert-regeneration hook ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2462) in #2462) +* **[Backport release-1.3] fix(backups): move velero-configmap Role to velero chart**: [Backport release-1.3] fix(backups): move velero-configmap Role to velero chart ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2467) in #2467) +* **fix(api): prevent IDOR in TenantNamespace Get and Watch handlers**: fix(api): prevent IDOR in TenantNamespace Get and Watch handlers ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2471) in #2471) +* **[Backport release-1.3] fix(kamaji): increase memory limits and add startup probe**: [Backport release-1.3] fix(kamaji): increase memory limits and add startup probe ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2491) in #2491) +* **feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix**: feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix ([**@kvaps**](https://github.com/cozystack/cozystack/pull/2496) in #2496) +* **build(linstor): include linstor-gui in root image build target**: build(linstor): include linstor-gui in root image build target ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2498) in #2498) +* **[Backport release-1.3] feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix**: [Backport release-1.3] feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2505) in #2505) +* **[Backport release-1.3] fix(etcd): remove destructive post-upgrade cert-regeneration hook**: [Backport release-1.3] fix(etcd): remove destructive post-upgrade cert-regeneration hook ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2511) in #2511) +* **[Backport release-1.3] build(linstor): include linstor-gui in root image build target**: [Backport release-1.3] build(linstor): include linstor-gui in root image build target ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2518) in #2518) +* **[Backport release-1.3] fix(api): prevent IDOR in TenantNamespace Get and Watch handlers**: [Backport release-1.3] fix(api): prevent IDOR in TenantNamespace Get and Watch handlers ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2524) in #2524) +* **fix namespaces creation**: fix namespaces creation ([**@kvaps**](https://github.com/cozystack/cozystack/pull/435) in #435) + +## Documentation + +* **[website] [docs] Update managed apps reference for v1.3.0**: Documentation updates ([**@myasnikovdaniil**](https://github.com/cozystack/website/pull/507) in cozystack/website#507) +* **[website] feat(blog): add Cozystack 1.3 release announcement**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/512) in cozystack/website#512) +* **[website] fix(telemetry): use April 2026 data as placeholder for quarter and year periods**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/511) in cozystack/website#511) +* **[website] fix(oss-health): correct April 2026 telemetry snapshot and pause fetch cron**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/508) in cozystack/website#508) + +## Contributors + +We thank the following contributors for this release: + +* [**@IvanHunters**](https://github.com/IvanHunters) +* [**@app/github-actions**](https://github.com/app/github-actions) +* [**@kvaps**](https://github.com/kvaps) +* [**@myasnikovdaniil**](https://github.com/myasnikovdaniil) + +**Full Changelog**: https://github.com/cozystack/cozystack/compare/v1.3.0...v1.3.1 From 875a940033fea97a4800797989b0e004bbb8eca4 Mon Sep 17 00:00:00 2001 From: Myasnikov Daniil Date: Wed, 29 Apr 2026 12:22:08 +0500 Subject: [PATCH 29/35] docs(changelog): rewrite v1.3.1 with the actual release contents The AI-generated v1.3.1 changelog (#2480) was generated from git log v1.3.0..main rather than git log v1.3.0..v1.3.1, because the workflow checked out main while the v1.3.1 tag points to release-1.3. As a result the changelog included: - 8 PRs that were merged to main but never shipped in v1.3.1 - 6 backport PRs that were merged to release-1.3 *after* v1.3.1 was tagged - Both originals and their backports as separate duplicate entries - A 2024 PR (#435) that has nothing to do with this range - Generic "Documentation updates" placeholders for website entries - Title duplicated as both the bold label and the description (`* **fix(...): X**: fix(...): X (...)`) - The cozystack-ci bot listed as a human contributor The actual v1.3.1 release range (v1.3.0..v1.3.1) contains exactly one user-facing change: 41bcb0be [Backport release-1.3] fix(backups): move velero-configmap Role to velero chart (#2467) which is the backport of #2459 (myasnikovdaniil) shipped via #2467 (IvanHunters). This commit replaces the contents of docs/changelogs/v1.3.1.md with that one entry, the matching two-person contributors list, and the standard footer. The workflow + docs fixes that prevent this regression for future patch releases will land in a separate PR against main. Signed-off-by: Myasnikov Daniil --- docs/changelogs/v1.3.1.md | 34 ++++++++-------------------------- 1 file changed, 8 insertions(+), 26 deletions(-) diff --git a/docs/changelogs/v1.3.1.md b/docs/changelogs/v1.3.1.md index 55e6a796..e8318ff4 100644 --- a/docs/changelogs/v1.3.1.md +++ b/docs/changelogs/v1.3.1.md @@ -1,38 +1,20 @@ -# v1.3.1 (2026-04-29) + -This is a patch release containing fixes and minor improvements. +# v1.3.1 (2026-04-23) -## Fixes and Improvements +A patch release with a single bug fix in the backup subsystem. -* **[linstor-gui] Add package for LINBIT linstor-gui web UI**: [linstor-gui] Add package for LINBIT linstor-gui web UI ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2382) in #2382) -* **fix(kamaji): increase memory limits and add startup probe**: fix(kamaji): increase memory limits and add startup probe ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2421) in #2421) -* **fix(backups): move velero-configmap Role to velero chart**: fix(backups): move velero-configmap Role to velero chart ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2459) in #2459) -* **fix(etcd): remove destructive post-upgrade cert-regeneration hook**: fix(etcd): remove destructive post-upgrade cert-regeneration hook ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2462) in #2462) -* **[Backport release-1.3] fix(backups): move velero-configmap Role to velero chart**: [Backport release-1.3] fix(backups): move velero-configmap Role to velero chart ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2467) in #2467) -* **fix(api): prevent IDOR in TenantNamespace Get and Watch handlers**: fix(api): prevent IDOR in TenantNamespace Get and Watch handlers ([**@IvanHunters**](https://github.com/cozystack/cozystack/pull/2471) in #2471) -* **[Backport release-1.3] fix(kamaji): increase memory limits and add startup probe**: [Backport release-1.3] fix(kamaji): increase memory limits and add startup probe ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2491) in #2491) -* **feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix**: feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix ([**@kvaps**](https://github.com/cozystack/cozystack/pull/2496) in #2496) -* **build(linstor): include linstor-gui in root image build target**: build(linstor): include linstor-gui in root image build target ([**@myasnikovdaniil**](https://github.com/cozystack/cozystack/pull/2498) in #2498) -* **[Backport release-1.3] feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix**: [Backport release-1.3] feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2505) in #2505) -* **[Backport release-1.3] fix(etcd): remove destructive post-upgrade cert-regeneration hook**: [Backport release-1.3] fix(etcd): remove destructive post-upgrade cert-regeneration hook ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2511) in #2511) -* **[Backport release-1.3] build(linstor): include linstor-gui in root image build target**: [Backport release-1.3] build(linstor): include linstor-gui in root image build target ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2518) in #2518) -* **[Backport release-1.3] fix(api): prevent IDOR in TenantNamespace Get and Watch handlers**: [Backport release-1.3] fix(api): prevent IDOR in TenantNamespace Get and Watch handlers ([**@app/github-actions**](https://github.com/cozystack/cozystack/pull/2524) in #2524) -* **fix namespaces creation**: fix namespaces creation ([**@kvaps**](https://github.com/cozystack/cozystack/pull/435) in #435) +## Fixes -## Documentation - -* **[website] [docs] Update managed apps reference for v1.3.0**: Documentation updates ([**@myasnikovdaniil**](https://github.com/cozystack/website/pull/507) in cozystack/website#507) -* **[website] feat(blog): add Cozystack 1.3 release announcement**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/512) in cozystack/website#512) -* **[website] fix(telemetry): use April 2026 data as placeholder for quarter and year periods**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/511) in cozystack/website#511) -* **[website] fix(oss-health): correct April 2026 telemetry snapshot and pause fetch cron**: Documentation updates ([**@tym83**](https://github.com/cozystack/website/pull/508) in cozystack/website#508) +* **fix(backups): move velero-configmap Role to velero chart**: The `backupstrategy-controller` (a default package) declared a Role/RoleBinding scoped to the `cozy-velero` namespace for managing `ResourceModifier` ConfigMaps. On bundles where Velero was not enabled, that namespace did not exist and the HelmRelease failed with `namespaces "cozy-velero" not found`, blocking installation. The Role/RoleBinding now lives in the velero chart, so it is created only when velero is actually deployed. ([**@myasnikovdaniil**](https://github.com/myasnikovdaniil) in #2459, backport #2467) ## Contributors -We thank the following contributors for this release: +Thanks to everyone who contributed to this patch release: * [**@IvanHunters**](https://github.com/IvanHunters) -* [**@app/github-actions**](https://github.com/app/github-actions) -* [**@kvaps**](https://github.com/kvaps) * [**@myasnikovdaniil**](https://github.com/myasnikovdaniil) **Full Changelog**: https://github.com/cozystack/cozystack/compare/v1.3.0...v1.3.1 From 1e0d8acb3553e0702a4c96a5775d4aadd6338c6b Mon Sep 17 00:00:00 2001 From: Myasnikov Daniil Date: Wed, 29 Apr 2026 12:46:18 +0500 Subject: [PATCH 30/35] docs(changelog): add 1.3.1 entries for backports landed after auto-gen The auto-generated changelog only listed #2459/#2467 (velero-configmap Role move). Five additional PRs were backported and merged into release-1.3 between then and the v1.3.1 tag (2026-04-28): - #2471/#2524 - fix(api): IDOR in TenantNamespace Get/Watch - #2496/#2505 - feat(linstor): linstor-csi v1.10.6 (Protocol-C dual-attach) - #2462/#2511 - fix(etcd): remove destructive post-upgrade hook - #2421/#2491 - fix(kamaji): memory limits + startup probe - #2498/#2518 - build(linstor): wire linstor-gui into root build target Update the release date to match the actual tag (2026-04-28), rewrite the intro paragraph, and add @kvaps to contributors. Signed-off-by: Myasnikov Daniil --- docs/changelogs/v1.3.1.md | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/docs/changelogs/v1.3.1.md b/docs/changelogs/v1.3.1.md index e8318ff4..0f149d0d 100644 --- a/docs/changelogs/v1.3.1.md +++ b/docs/changelogs/v1.3.1.md @@ -2,19 +2,36 @@ https://github.com/cozystack/cozystack/releases/tag/v1.3.1 --> -# v1.3.1 (2026-04-23) +# v1.3.1 (2026-04-28) -A patch release with a single bug fix in the backup subsystem. +Patch release covering a TenantNamespace IDOR fix in the API, a destructive `post-upgrade` hook removed from the etcd chart, kamaji controller stability, a `linstor-csi` bump that fixes live migration on Protocol-A/B DRBD resources, the missing `linstor-gui` build wiring, and a velero RBAC fix that unblocked installs on bundles without Velero. + +## Security + +* **fix(api): prevent IDOR in TenantNamespace Get and Watch handlers**: Two IDOR (Insecure Direct Object Reference) vulnerabilities allowed authenticated users to read TenantNamespace metadata they had no RoleBinding for. The `Get` and `Watch` handlers now go through a new `hasAccessToNamespace()` helper that lists RoleBindings scoped only to the target namespace (orders of magnitude faster than the previous all-cluster scan), returns `NotFound` instead of leaking existence on unauthorized access, and applies the same check on the `Watch` filter path. Includes regression tests for the unauthorized paths. ([**@IvanHunters**](https://github.com/IvanHunters) in #2471, backport #2524) + +## Features + +* **feat(linstor): bump linstor-csi to v1.10.6 with Protocol-C dual-attach fix**: Live migration of KubeVirt VMs on Protocol-A/B (async) DRBD volumes no longer fails with `Protocol C required`. `linstor-csi` v1.10.6 now installs a `Protocol=C` override on the resource-definition during dual-attach and reverts it on detach, so `replicated-async` StorageClasses and other Protocol-A/B resource groups support live migration without manual `drbdadm adjust` intervention. ([**@kvaps**](https://github.com/kvaps) in #2496, backport #2505) ## Fixes * **fix(backups): move velero-configmap Role to velero chart**: The `backupstrategy-controller` (a default package) declared a Role/RoleBinding scoped to the `cozy-velero` namespace for managing `ResourceModifier` ConfigMaps. On bundles where Velero was not enabled, that namespace did not exist and the HelmRelease failed with `namespaces "cozy-velero" not found`, blocking installation. The Role/RoleBinding now lives in the velero chart, so it is created only when velero is actually deployed. ([**@myasnikovdaniil**](https://github.com/myasnikovdaniil) in #2459, backport #2467) +* **fix(etcd): remove destructive post-upgrade cert-regeneration hook**: The etcd chart ran a `post-upgrade` Helm hook on every upgrade that deleted etcd TLS Secrets (`etcd-ca-tls`, `etcd-peer-ca-tls`, `etcd-client-tls`, `etcd-peer-tls`, `etcd-server-tls`) and then deleted etcd pods, forcing cert-manager to re-issue the entire etcd CA chain. On clusters with Kamaji-managed tenant control planes this put every tenant `kube-apiserver` into CrashLoopBackOff until each DataStore was manually re-reconciled. The hook was a one-shot `2.6.0 → 2.6.1` migration that became a permanent footgun once chart versioning moved to `0.0.0+` (always `< 2.6.1` per semver) and after the underlying `rotationPolicy: Always` issue was fixed in `47d81f70`. The hook is now removed entirely. ([**@myasnikovdaniil**](https://github.com/myasnikovdaniil) in #2462, backport #2511) + +* **fix(kamaji): increase memory limits and add startup probe**: The kamaji controller frequently entered CrashLoopBackOff due to OOMKills (exit 137) within ~20–25 seconds of startup, with the readiness probe failing while the controller was still finishing initialization. Memory limit raised from 500Mi to 512Mi, request from 100Mi to 256Mi, and a 60-second startup probe (12 attempts × 5s periods) is added so the controller has room to boot before liveness/readiness probes engage. ([**@IvanHunters**](https://github.com/IvanHunters) in #2421, backport #2491) + +## Build + +* **build(linstor): include linstor-gui in root image build target**: The `linstor-gui` package (added in #2382) was never wired into the root `Makefile`'s `build:` target, so CI never built or published the image. `ghcr.io/cozystack/cozystack/linstor-gui` returned `NAME_UNKNOWN` and `values.yaml` stayed pinned to `tag: 2.3.0` without a digest. The missing build line is added so the next CI run publishes the image and the per-package `Makefile` digest-pins `values.yaml` automatically. ([**@myasnikovdaniil**](https://github.com/myasnikovdaniil) in #2498, backport #2518) + ## Contributors Thanks to everyone who contributed to this patch release: * [**@IvanHunters**](https://github.com/IvanHunters) +* [**@kvaps**](https://github.com/kvaps) * [**@myasnikovdaniil**](https://github.com/myasnikovdaniil) **Full Changelog**: https://github.com/cozystack/cozystack/compare/v1.3.0...v1.3.1 From ba8c1a0535d2e0462fb8269df0750ea6f57fdd0b Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 29 Apr 2026 11:13:12 +0300 Subject: [PATCH 31/35] docs(hami): drop HAMi#173 reference from glibc tracking issues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HAMi#173 was closed as "not planned" and only suggests a typo fix (< 2.3.0 → < 2.30); it does not establish the actual 2.34 boundary. HAMi-core#174 (symbol-level cause) and HAMi#1190 (empirical per-glibc behavior) cover the same ground accurately. Signed-off-by: Arsolitt --- packages/system/hami/README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/system/hami/README.md b/packages/system/hami/README.md index d648364d..aa80d48a 100644 --- a/packages/system/hami/README.md +++ b/packages/system/hami/README.md @@ -38,9 +38,8 @@ Most modern ML/AI base images (CUDA 12.x, PyTorch 2.x, TensorFlow 2.x) use Ubunt **Upstream tracking issues:** -- [HAMi-core#174](https://github.com/Project-HAMi/HAMi-core/issues/174) — `_dl_sym` removal breaks HAMi-core on glibc >= 2.34 -- [HAMi#1190](https://github.com/Project-HAMi/HAMi/issues/1190) — degraded isolation across glibc versions -- [HAMi#173](https://github.com/Project-HAMi/HAMi/issues/173) — documentation incorrectly states glibc < 2.30 (actual boundary is 2.34) +- [HAMi-core#174](https://github.com/Project-HAMi/HAMi-core/issues/174) — `_dl_sym` removal in glibc 2.34 breaks HAMi-core's CUDA symbol resolution at the symbol level +- [HAMi#1190](https://github.com/Project-HAMi/HAMi/issues/1190) — maintainer thread confirming the empirical per-glibc-version isolation behavior shown in the table above ### musl libc (Alpine) incompatibility From 9876acec2fafbadeb09741f70e01250171a42a48 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 29 Apr 2026 11:13:24 +0300 Subject: [PATCH 32/35] docs(hami): clarify gpu-operator devicePlugin override behavior The HAMi-driven default of disabling gpu-operator's device plugin is applied via valuesOverride and can be re-enabled by users for advanced topologies (mixed HAMi / vanilla NVIDIA device plugin pools). Document this explicitly so the README aligns with the existing template merge order. Signed-off-by: Arsolitt --- packages/system/hami/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/system/hami/README.md b/packages/system/hami/README.md index aa80d48a..68669ac7 100644 --- a/packages/system/hami/README.md +++ b/packages/system/hami/README.md @@ -57,7 +57,7 @@ addons: enabled: true ``` -When HAMi is enabled, GPU Operator's built-in device plugin is automatically disabled to avoid conflicts. +When HAMi is enabled, GPU Operator's built-in device plugin is automatically disabled to avoid conflicts. This default is preserved by setting `addons.gpuOperator.valuesOverride.gpu-operator.devicePlugin.enabled: false`; advanced topologies that partition GPU pools (e.g. some nodes use HAMi while others run the standard NVIDIA device plugin via node selectors) can re-enable it explicitly through `valuesOverride`. ### Requesting fractional GPU resources From d5caffcc8de0177b248899b03391c312d20dde54 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 29 Apr 2026 11:13:42 +0300 Subject: [PATCH 33/35] fix(kubernetes): gate HAMi HelmRelease on _namespace.etcd Match the pattern used by every other tenant-cluster addon HelmRelease (gpu-operator, cilium, fluxcd, ...): only render when the upstream etcd namespace is ready, not just when the addon is enabled. Add values-ci.yaml to the HAMi test suite so the new gate has the fixture it needs. Signed-off-by: Arsolitt --- packages/apps/kubernetes/templates/helmreleases/hami.yaml | 2 +- packages/apps/kubernetes/tests/hami_test.yaml | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/packages/apps/kubernetes/templates/helmreleases/hami.yaml b/packages/apps/kubernetes/templates/helmreleases/hami.yaml index 1f7a5358..f1538c7c 100644 --- a/packages/apps/kubernetes/templates/helmreleases/hami.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/hami.yaml @@ -1,4 +1,4 @@ -{{- if .Values.addons.hami.enabled }} +{{- if and .Values.addons.hami.enabled .Values._namespace.etcd }} {{- if not .Values.addons.gpuOperator.enabled }} {{- fail "addons.hami requires addons.gpuOperator to be enabled" }} {{- end }} diff --git a/packages/apps/kubernetes/tests/hami_test.yaml b/packages/apps/kubernetes/tests/hami_test.yaml index bdbe990f..27f7c75b 100644 --- a/packages/apps/kubernetes/tests/hami_test.yaml +++ b/packages/apps/kubernetes/tests/hami_test.yaml @@ -1,6 +1,8 @@ suite: HAMi HelmRelease tests templates: - templates/helmreleases/hami.yaml +values: + - values-ci.yaml tests: - it: should not render when hami is disabled set: From 9b5848ed268bfe3bc04b42bae38cc724c00a3bf0 Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 29 Apr 2026 11:13:55 +0300 Subject: [PATCH 34/35] fix(platform): register HAMi as kubernetes-application component MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The HelmRelease at packages/apps/kubernetes/templates/helmreleases/hami.yaml references chartRef.name 'cozystack-kubernetes-application-kubevirt-kubernetes-hami', but that component was missing from the kubernetes-application PackageSource. The HelmRelease would sit in Stalled: ArtifactNotFound at install time. Add kubernetes-hami next to kubernetes-gpu-operator under variant kubevirt, mirroring the existing pattern for every other tenant-cluster addon. The standalone cozystack.hami PackageSource is retained — same shape as gpu-operator, which is registered both standalone (for bundles/iaas) and as a kubernetes-application component (for tenant-cluster HelmReleases). Signed-off-by: Arsolitt --- packages/core/platform/sources/kubernetes-application.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/core/platform/sources/kubernetes-application.yaml b/packages/core/platform/sources/kubernetes-application.yaml index 9787cb19..088383ad 100644 --- a/packages/core/platform/sources/kubernetes-application.yaml +++ b/packages/core/platform/sources/kubernetes-application.yaml @@ -52,6 +52,8 @@ spec: path: system/cilium - name: kubernetes-gpu-operator path: system/gpu-operator + - name: kubernetes-hami + path: system/hami - name: kubernetes-vertical-pod-autoscaler path: system/vertical-pod-autoscaler - name: kubernetes-prometheus-operator-crds From 5d58d0f340f7157370305cc469317f4fa21944af Mon Sep 17 00:00:00 2001 From: Arsolitt Date: Wed, 29 Apr 2026 11:14:41 +0300 Subject: [PATCH 35/35] chore(hami): document and partially automate vendor patches in Makefile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The `update:` recipe now reproduces the top-level vendoring overrides (remove broken hami-dra subchart, clear Chart.yaml dependencies, strip dra/hami-dra/podSecurityPolicy from upstream values.yaml) after `helm pull`, so they no longer silently disappear on the next bump. Template-level patches (DRA guards in scheduler/*, indent fix in device-plugin/monitorservice.yaml) are documented with rationale and commit references — they remain a manual step because automating them would be fragile across upstream template restructures. Signed-off-by: Arsolitt --- packages/system/hami/Makefile | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/packages/system/hami/Makefile b/packages/system/hami/Makefile index b7a169c2..83663a66 100644 --- a/packages/system/hami/Makefile +++ b/packages/system/hami/Makefile @@ -4,8 +4,40 @@ export NAMESPACE=cozy-$(NAME) include ../../../hack/common-envs.mk include ../../../hack/package.mk +# When bumping the HAMi version, run `make update` and then review +# the resulting diff in `charts/hami/`. The recipe below reproduces the +# top-level vendoring overrides automatically: +# +# 1. Removes the broken hami-dra subchart. Upstream's NVIDIA DRA driver +# path requires kubelet DRA support that cozystack does not enable +# and has no upstream fix tracked. See commit 3c5521e. +# 2. Empties Chart.yaml dependencies and drops Chart.lock so Helm does +# not try to re-pull hami-dra at build time. See commit 2734dc0. +# 3. Strips dra/hami-dra/podSecurityPolicy blocks from the upstream +# values.yaml since the corresponding code paths are gone. PSP is +# removed from Kubernetes 1.25+ and is unused by cozystack. +# +# Template-level patches are NOT reproduced automatically: +# +# * Scheduler templates have `{{- if .Values.dra.enabled }}` blocks +# that need to be removed because the dra value is gone (commit +# 2734dc0 stripped them). +# * device-plugin/monitorservice.yaml uses `indent` with leading +# whitespace; it must be rewritten to `nindent` for the labels block +# to render correctly when devicePlugin.service.labels is set +# (commit 3685254). +# +# After `make update`, run `git diff -- charts/hami/templates/` and +# replay these template patches against the new upstream version, then +# verify with `helm unittest`. If upstream restructured the affected +# files, the patches may need to be redesigned rather than reapplied. + update: rm -rf charts helm repo add hami-charts https://project-hami.github.io/HAMi/ helm repo update hami-charts helm pull hami-charts/hami --untar --untardir charts + rm -rf charts/hami/charts/hami-dra + yq --inplace '.dependencies = []' charts/hami/Chart.yaml + rm -f charts/hami/Chart.lock + yq --inplace 'del(.dra) | del(.["hami-dra"]) | del(.podSecurityPolicy)' charts/hami/values.yaml