<!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Introduced new HelmRelease configurations for cert-manager, monitoring agents, and Victoria Metrics Operator in Kubernetes. - Added resource specifications for `vmselect` in the VMCluster configuration. - Enhanced resource management for `vmselect` with defined limits and requests for memory and CPU. - **Bug Fixes** - Adjusted resource limits for Redis failover memory allocation. - **Documentation** - Updated README and release notes for various components, enhancing clarity and usability. - **Chores** - Updated image versions across multiple components for consistency and performance improvements. - Modified migration scripts to facilitate transitions and manage resources effectively. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Andrei Kvapil <kvapss@gmail.com>
93 lines
3.1 KiB
YAML
93 lines
3.1 KiB
YAML
apiVersion: operator.victoriametrics.com/v1beta1
|
|
kind: VMRule
|
|
metadata:
|
|
name: alerts-node-exporter.rules
|
|
spec:
|
|
groups:
|
|
- name: node-exporter.rules
|
|
params: {}
|
|
rules:
|
|
- annotations: {}
|
|
expr: |-
|
|
count without (cpu, mode) (
|
|
node_cpu_seconds_total{job="node-exporter",mode="idle"}
|
|
)
|
|
labels: {}
|
|
record: instance:node_num_cpu:sum
|
|
- annotations: {}
|
|
expr: |-
|
|
1 - avg without (cpu) (
|
|
sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m]))
|
|
)
|
|
labels: {}
|
|
record: instance:node_cpu_utilisation:rate5m
|
|
- annotations: {}
|
|
expr: |-
|
|
(
|
|
node_load1{job="node-exporter"}
|
|
/
|
|
instance:node_num_cpu:sum{job="node-exporter"}
|
|
)
|
|
labels: {}
|
|
record: instance:node_load1_per_cpu:ratio
|
|
- annotations: {}
|
|
expr: |-
|
|
1 - (
|
|
(
|
|
node_memory_MemAvailable_bytes{job="node-exporter"}
|
|
or
|
|
(
|
|
node_memory_Buffers_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_Cached_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_MemFree_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_Slab_bytes{job="node-exporter"}
|
|
)
|
|
)
|
|
/
|
|
node_memory_MemTotal_bytes{job="node-exporter"}
|
|
)
|
|
labels: {}
|
|
record: instance:node_memory_utilisation:ratio
|
|
- annotations: {}
|
|
expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
|
|
labels: {}
|
|
record: instance:node_vmstat_pgmajfault:rate5m
|
|
- annotations: {}
|
|
expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
|
labels: {}
|
|
record: instance_device:node_disk_io_time_seconds:rate5m
|
|
- annotations: {}
|
|
expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
|
labels: {}
|
|
record: instance_device:node_disk_io_time_weighted_seconds:rate5m
|
|
- annotations: {}
|
|
expr: |-
|
|
sum without (device) (
|
|
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
labels: {}
|
|
record: instance:node_network_receive_bytes_excluding_lo:rate5m
|
|
- annotations: {}
|
|
expr: |-
|
|
sum without (device) (
|
|
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
labels: {}
|
|
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
|
|
- annotations: {}
|
|
expr: |-
|
|
sum without (device) (
|
|
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
labels: {}
|
|
record: instance:node_network_receive_drop_excluding_lo:rate5m
|
|
- annotations: {}
|
|
expr: |-
|
|
sum without (device) (
|
|
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
labels: {}
|
|
record: instance:node_network_transmit_drop_excluding_lo:rate5m
|