VictoriaMetrics/deployment/docker/alerts-health.yml

# File contains default list of alerts for VM components.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
  - name: vm-health
    # note the `job` filter and update accordingly to your setup
    rules:
      - alert: TooManyRestarts
        expr: changes(process_start_time_seconds{job=~"victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert"}[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"} == 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: (process_resident_memory_anon_bytes / vm_available_memory_bytes) > 0.9
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "It is more than 90% of memory used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
          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: TooManyLogs
        expr: sum(increase(vm_log_messages_total{level="error"}[5m])) by (job, instance) > 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.\n
         Worth to check logs for specific error messages."