DCGM exporter metrics carry the exporter's own namespace
(cozy-gpu-operator), not the workload namespace. Recording rules that
filtered namespace!~"cozy-.*" silently dropped all DCGM series,
producing empty dashboard panels.
Replace namespace-level hardware aggregations with node-level
equivalents (grouped by Hostname), keep namespace-level allocation
rules that use kube_pod_container_resource_requests (which carries the
real workload namespace), and rename pod-level efficiency rules to
gpu-level since DCGM cannot attribute hardware metrics to individual
pods.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
The Pending GPU pods counter on gpu-quotas joined raw
kube_pod_container_resource_requests (per-container series) against
kube_pod_status_phase (per-pod series). Multi-container pods were
counted once per requesting container instead of once per pod, so the
widget over-reported whenever a Pending pod had more than one GPU
container. Collapse the requests to pod level before the join.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Pod-level panels on the efficiency dashboard and DCGM-level panels on
the performance dashboard ignored the $namespace template variable, so
changing it left the visualizations unchanged. Add the filter to each
query. Performance-side queries use the `$namespace|` empty-tolerant
form so host-level DCGM series without a namespace label remain
visible when a specific namespace is selected.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Clarify that the "Average utilization" panel on gpu-fleet reflects the
legacy NVML view (DCGM_FI_DEV_GPU_UTIL) rather than engine-active
profiling. For AI/LLM workloads the NVML number is optimistic; the
gpu-efficiency dashboard carries the profiling-based view.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Align pod:tensor_saturation:avg5m with namespace:tensor_active:avg and
DCGM's native 0..1 range by dropping the * 100 from the recording rule
and multiplying at display time in gpu-efficiency.json. Also scope
pod:util_per_watt:avg5m with avg by (Hostname, gpu, UUID, namespace,
pod) so the series mirrors pod:tensor_saturation's grouping and stays
usable in topk queries.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
- gpu-efficiency: scope Tensor Saturation, Util-per-Watt and Power
Throttle stats to the $namespace selector. Cluster-wide means were
misleading when a user had narrowed the dashboard to specific
tenants — the headline numbers lied relative to the panels below.
- gpu-fleet: show per-node power draw as % of combined TDP cap
(DCGM_FI_DEV_POWER_MGMT_LIMIT) instead of raw watts. Thresholds
(60 / 80 %) generalize across GPU SKUs without per-model tuning.
- gpu-quotas: read cluster:gpu_count:allocated from the recording
rules instead of recomputing sum(kube_pod_container_resource_requests)
inline. Keeps the dashboard aligned with the canonical definition
in gpu-recording.rules.yaml so the two can't drift.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
- gpu-fleet: cluster-wide admin view — inventory, capacity (total /
allocated / free), per-node utilization and power, throttling,
temperatures, XID errors.
- gpu-tenants: per-namespace view — live allocation, utilization,
tensor saturation, power, and 24h GPU-hours / kWh integrations for
billing inputs.
Register both under gpu/* in dashboards-infra.list so they ship as
GrafanaDashboard CRs and fall under the bats cross-check introduced
earlier on this branch.
Update examples/README to spell out which DCGM counters each of the
five gpu/* dashboards actually needs on top of the upstream default
CSV — gpu-performance needs profiling and throttling counters,
gpu-efficiency needs profiling, gpu-tenants needs only
DCGM_FI_PROF_PIPE_TENSOR_ACTIVE for its tensor panel, and gpu-fleet
and gpu-quotas work on the default counter set alone.
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Strip Grafana export boilerplate (__inputs, __elements, __requires,
default annotations, embedded datasource inputs) and tighten panel
layouts across the three GPU dashboards. All three continue to use
the $ds_prometheus template variable.
Assisted-By: Claude <noreply@anthropic.com>
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Revise gpu-performance and add two new dashboards, registered in
dashboards-infra.list:
- gpu-efficiency (GPU Efficiency Score) — utilization vs. capacity
and workload efficiency signals.
- gpu-quotas (GPU Quotas & Allocation) — per-namespace requested vs.
used GPUs for tenant capacity planning.
All three dashboards use the $ds_prometheus template variable, per
the project convention.
Assisted-By: Claude <noreply@anthropic.com>
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Add the gpu/gpu-performance dashboard and register it in the infra
dashboard list. The dashboard provides:
- Cluster overview: total/allocated GPUs, average utilization,
aggregate power draw.
- Utilization: GPU util (NVML), tensor pipe active (realistic load
for LLM/AI workloads), graphics engine active, memory copy util.
- Memory: VRAM used/free per GPU.
- Power and temperature per GPU.
- Health: XID errors, power and thermal throttling.
The dashboard relies on DCGM_FI_* metrics plus the cluster:gpu_* and
namespace:gpu_* recording rules added to monitoring-agents.
The JSON follows the cozystack convention — Prometheus data source is
selected via the $ds_prometheus template variable.
Assisted-By: Claude <noreply@anthropic.com>
Signed-off-by: Arsolitt <arsolitt@gmail.com>
Add documentation explaining how to enable Hubble for network
observability in Grafana. Include four pre-built Hubble dashboards
(overview, dns-namespace, l7-http-metrics, network-overview) and
register them in the monitoring hub's dashboard list.
Closes#749
Signed-off-by: majiayu000 <1835304752@qq.com>
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Expanded the monitored dashboards with a new storage dashboard entry.
- Introduced proactive alert configurations that cover key storage
components.
- Added templated alert management to streamline dynamic configuration.
- Enhanced metric collection by integrating monitoring endpoints for
storage components.
- Delivered a comprehensive dashboard offering real-time insights into
storage performance.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Andrei Kvapil <kvapss@gmail.com>
Co-authored-by: Andrei Kvapil <kvapss@gmail.com>
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Introduced a comprehensive Grafana dashboard for Goldpinger, offering
real-time insights into node health, error occurrences, and response
times with intuitive filtering.
- Expanded deployment configurations to include Goldpinger across
environments, streamlining release management and dependency handling.
- Launched a dedicated deployment package featuring customizable
templates for secure, efficient Kubernetes deployments—including
workloads, services, ingress, and monitoring integrations.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Introduced a new dashboard for Flux Control Plane monitoring that
visualizes key performance metrics like CPU, memory, API requests, and
more.
- Added a second dashboard for Flux Cluster Stats to display resource
reconciliation, operation durations, and readiness indicators.
- Seamlessly integrated these dashboards into the monitoring workflow
with dynamic querying and periodic refresh options.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Enhanced etcd monitoring with new metrics exposure, pod scraping
configuration, and comprehensive alert rules for proactive
observability.
- Introduced a new `VMPodScrape` resource for improved pod metrics
collection.
- Added a new PrometheusRule configuration for monitoring etcd clusters
with various alert conditions.
- **Chores**
- Upgraded the etcd release from version 2.4.0 to 2.5.0.
- Consolidated and renamed monitoring dashboard references for better
consistency.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Added PrometheusRule configuration to monitor virtual machine (VM) and
virtual machine instance (VMI) states.
- Introduced ServiceMonitor resource for Kubevirt metrics monitoring.
- Added `monitorNamespace` configuration in KubeVirt custom resource.
- **Monitoring Enhancements**
- Implemented alerts for VMs and VMIs not running for more than 10
minutes.
- Configured metrics endpoint with HTTPS support.
- **Version Updates**
- Updated version mappings for several packages, reflecting new commit
hashes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Co-authored-by: Andrei Kvapil <kvapss@gmail.com>
Signed-off-by: Andrei Kvapil <kvapss@gmail.com>
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Added a new data source configuration for Prometheus.
- Introduced new panels for network metrics in Kubernetes dashboards.
- New "Bar gauge" panel type added to the Kubernetes global views.
- Enhanced visualizations with new properties for displaying metrics.
- **Bug Fixes**
- Updated Prometheus expressions to improve data filtering and accuracy.
- **Version Updates**
- Upgraded Grafana and plugin versions across multiple dashboard
configurations.
- **Improvements**
- Enhanced dashboard layouts and usability with new visualization
options.
- Adjusted configurations for better performance and clarity in
monitoring metrics.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Andrei Kvapil <kvapss@gmail.com>
