128 lines
6.8 KiB
YAML
128 lines
6.8 KiB
YAML
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
|
|
apiVersion: operator.victoriametrics.com/v1beta1
|
|
kind: VMRule
|
|
metadata:
|
|
name: vm-health
|
|
namespace: monitoring
|
|
labels:
|
|
app.kubernetes.io/part-of: victoria-metrics
|
|
spec:
|
|
groups:
|
|
- name: vm-health
|
|
rules:
|
|
- alert: TooManyRestarts
|
|
expr: changes(process_start_time_seconds{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[15m]) > 2
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "{{ $labels.job }} too many restarts (instance {{ $labels.instance }})"
|
|
description: >
|
|
Job {{ $labels.job }} (instance {{ $labels.instance }}) has restarted more than twice in the last 15 minutes.
|
|
It might be crashlooping.
|
|
- alert: ServiceDown
|
|
expr: up{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Service {{ $labels.job }} is down on {{ $labels.instance }}"
|
|
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
|
|
- alert: ProcessNearFDLimits
|
|
expr: (process_max_fds - process_open_fds) < 100
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Number of free file descriptors is less than 100 for \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") for the last 5m"
|
|
description: |
|
|
Exhausting OS file descriptors limit can cause severe degradation of the process.
|
|
Consider to increase the limit as fast as possible.
|
|
- alert: TooHighMemoryUsage
|
|
expr: (min_over_time(process_resident_memory_anon_bytes[10m]) / vm_available_memory_bytes) > 0.8
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "It is more than 80% of memory used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\")"
|
|
description: |
|
|
Too high memory usage may result into multiple issues such as OOMs or degraded performance.
|
|
Consider to either increase available memory or decrease the load on the process.
|
|
- alert: TooHighCPUUsage
|
|
expr: rate(process_cpu_seconds_total[5m]) / process_cpu_cores_available > 0.9
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "More than 90% of CPU is used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
|
|
description: >
|
|
Too high CPU usage may be a sign of insufficient resources and make process unstable.
|
|
Consider to either increase available CPU resources or decrease the load on the process.
|
|
- alert: TooHighGoroutineSchedulingLatency
|
|
expr: histogram_quantile(0.99, sum(rate(go_sched_latencies_seconds_bucket{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[5m])) by (le, job, instance)) > 0.1
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "\"{{ $labels.job }}\"(\"{{ $labels.instance }}\") has insufficient CPU resources for >15m"
|
|
description: >
|
|
Go runtime is unable to schedule goroutines execution in acceptable time. This is usually a sign of
|
|
insufficient CPU resources or CPU throttling.
|
|
- alert: TooManyLogs
|
|
expr: sum(increase(vm_log_messages_total{level="error"}[5m])) without (app_version, location) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
|
|
description: >
|
|
Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.
|
|
Worth to check logs for specific error messages.
|
|
- alert: TooManyTSIDMisses
|
|
expr: increase(vm_missing_tsids_for_metric_id_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Unexpected TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes"
|
|
description: |
|
|
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
|
|
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
|
|
then this is OK - the alert must go away in a few minutes after the restart.
|
|
- alert: ConcurrentInsertsHitTheLimit
|
|
expr: avg_over_time(vm_concurrent_insert_current[1m]) >= vm_concurrent_insert_capacity
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "{{ $labels.job }} on instance {{ $labels.instance }} is constantly hitting concurrent inserts limit"
|
|
description: |
|
|
The limit of concurrent inserts on instance {{ $labels.instance }} depends on the number of CPUs.
|
|
Usually, when component constantly hits the limit it is likely the component is overloaded and requires more CPU.
|
|
- alert: IndexDBRecordsDrop
|
|
expr: increase(vm_indexdb_items_dropped_total[5m]) > 0
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "IndexDB skipped registering items during data ingestion with reason={{ $labels.reason }}."
|
|
description: |
|
|
VictoriaMetrics could skip registering new timeseries during ingestion if they fail the validation process.
|
|
- alert: RowsRejectedOnIngestion
|
|
expr: rate(vm_rows_ignored_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
|
|
description: "Ingested rows on instance \"{{ $labels.instance }}\" are rejected due to the
|
|
following reason: \"{{ $labels.reason }}\""
|
|
- alert: TooHighQueryLoad
|
|
expr: increase(vm_concurrent_select_limit_timeout_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Read queries fail with timeout for {{ $labels.job }} on instance {{ $labels.instance }}"
|
|
description: |
|
|
Instance {{ $labels.instance }} ({{ $labels.job }}) is failing to serve read queries during last 15m.
|
|
Possible solutions: reduce the query load; increase compute resources; adjust search concurrency limits.
|