Loading deploy/rules/rules.yaml +3 −2 Original line number Diff line number Diff line Loading @@ -4,15 +4,16 @@ groups: rules: - alert: LogsHighErrorRateByService expr: | sum(rate({container_id=~".+"} |~ `(?i)(alert)|(crit)|(critical)|(fatal)|(emerg)|(error)|(eror)|(err)` [5m])) by (service_name) sum(rate({level=~"critical|error"} [5m])) by (service_name) / sum(rate({container_id=~".+"} [5m])) by (service_name) > 0.1 for: 10m labels: severity: warning severity: error annotations: summary: High error logs rate at '{{$labels.service_name}}' service - alert: LogsTooManyEntriesByService expr: | sum(rate({container_id=~".+"} [1m])) by (service_name) > 1 Loading Loading
deploy/rules/rules.yaml +3 −2 Original line number Diff line number Diff line Loading @@ -4,15 +4,16 @@ groups: rules: - alert: LogsHighErrorRateByService expr: | sum(rate({container_id=~".+"} |~ `(?i)(alert)|(crit)|(critical)|(fatal)|(emerg)|(error)|(eror)|(err)` [5m])) by (service_name) sum(rate({level=~"critical|error"} [5m])) by (service_name) / sum(rate({container_id=~".+"} [5m])) by (service_name) > 0.1 for: 10m labels: severity: warning severity: error annotations: summary: High error logs rate at '{{$labels.service_name}}' service - alert: LogsTooManyEntriesByService expr: | sum(rate({container_id=~".+"} [1m])) by (service_name) > 1 Loading