loki-values.yaml

fluent-bit:
  enabled: false
grafana:
  enabled: true
  image:
    tag: 7.5.2
prometheus:
  alertmanager:
    persistentVolume:
      enabled: false
  enabled: true
  server:
    persistentVolume:
      enabled: false
promtail:
  enabled: true
loki:
  # Needed for Alerting: https://grafana.com/docs/loki/latest/alerting/
  # This is just a simple example, for more details: https://grafana.com/docs/loki/latest/configuration/#ruler_config
  ruler:
    storage:
      type: local
      local:
        directory: /rules
    rule_path: /tmp/scratch
    alertmanager_url: http://alertmanager.svc.logging:9093
    ring:
      kvstore:
        store: inmemory
    enable_api: true
  # Specify Loki Alerting rules based on this documentation: https://grafana.com/docs/loki/latest/alerting/
  # When specified, you also need to add a ruler config section above. An example is shown in the alerting docs.
  alerting_groups:
    - name: slow
      rules:
      - alert: slow-ops
        annotations:
          message: "{{ $labels.job }} is reporting slow ops."
        expr: 'sum by (cluster, job, pod) (count_over_time({app="couchbase"}|="couchbase.log.memcached"|="Slow operation") > 0)'
        for: 10m
        labels: 
          severity: critical
      - alert: slow-runtime
        annotations:
          message: "{{ $labels.job }} is reporting slow runtime."
        expr: 'sum by (cluster, job, pod) (count_over_time({app="couchbase"}|="couchbase.log.memcached"|="Slow runtime") > 0)'
        for: 10m
        labels: 
          severity: critical
    - name: logs
      rules:
      - alert: ErrorInLogs
        expr: sum(count_over_time({app="couchbase"}|~ "[Ee]rror"[1m]) >= 1
        for: 10s
        labels:
          severity: critical
          category: logs
        annotations:
          title: "{{$value}} Errors occurred in application logs"