78 lines
3.7 KiB
YAML
78 lines
3.7 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: vmalert
|
|
namespace: monitoring
|
|
labels:
|
|
app.kubernetes.io/part-of: victoria-metrics
|
|
spec:
|
|
groups:
|
|
- name: vmalert
|
|
interval: 30s
|
|
rules:
|
|
- alert: ConfigurationReloadFailure
|
|
expr: vmalert_config_last_reload_successful != 1
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Configuration reload failed for vmalert instance {{ $labels.instance }}"
|
|
description: "Configuration hot-reload failed for vmalert on instance {{ $labels.instance }}. Check the logs."
|
|
- alert: AlertingRulesError
|
|
expr: sum(increase(vmalert_alerting_rules_errors_total[5m])) without(id) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Alerting rules are failing for vmalert instance {{ $labels.instance }}"
|
|
description: "Alerting rules execution is failing for group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\". Check the logs."
|
|
- alert: RecordingRulesError
|
|
expr: sum(increase(vmalert_recording_rules_errors_total[5m])) without(id) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Recording rules are failing for vmalert instance {{ $labels.instance }}"
|
|
description: "Recording rules execution is failing for group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\". Check the logs."
|
|
- alert: RecordingRulesNoData
|
|
expr: sum(vmalert_recording_rules_last_evaluation_samples) without(id) < 1
|
|
for: 30m
|
|
labels:
|
|
severity: info
|
|
annotations:
|
|
summary: "Recording rule ({{ $labels.group }}) produces no data"
|
|
description: "Recording rule from group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\"
|
|
produces 0 samples over the last 30min. Possible misconfiguration or incorrect query."
|
|
- alert: TooManyMissedIterations
|
|
expr: increase(vmalert_iteration_missed_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "vmalert instance {{ $labels.instance }} is missing rules evaluations"
|
|
description: "Group evaluation takes longer than the configured interval. Increase interval or concurrency."
|
|
- alert: RemoteWriteErrors
|
|
expr: increase(vmalert_remotewrite_errors_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "vmalert instance {{ $labels.instance }} is failing to push metrics to remote write URL"
|
|
description: "vmalert is failing to push alerting/recording rule metrics to remote write. Check the logs."
|
|
- alert: RemoteWriteDroppingData
|
|
expr: increase(vmalert_remotewrite_dropped_rows_total[5m]) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "vmalert instance {{ $labels.instance }} is dropping data sent to remote write URL"
|
|
description: "vmalert is dropping alerting/recording rule results. This may cause gaps in state. Check the logs."
|
|
- alert: AlertmanagerErrors
|
|
expr: increase(vmalert_alerts_send_errors_total[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "vmalert instance {{ $labels.instance }} is failing to send notifications to Alertmanager"
|
|
description: "vmalert is failing to send alert notifications to \"{{ $labels.addr }}\". Check the logs."
|