Commit 7685bf07 authored by Pedro Eduardo Trujillo's avatar Pedro Eduardo Trujillo
Browse files

Describe mejor las alertas, relaja ratio de error

parent 8deb8227

deploy/rules/rules.yaml

+5 −3
Original line number Diff line number Diff line
@@ -7,12 +7,13 @@ groups: 
          sum(rate({level=~"critical|error"} [5m])) by (service_name)

            /

          sum(rate({container_id=~".+"} [5m])) by (service_name)

            > 0.1

            > 0.2

        for: 10m

        labels:

          severity: error

        annotations:

          summary: High error logs rate at '{{$labels.service_name}}' service

          description: High error logs rate ({{$value | printf "%.1f"}}) at '{{$labels.service_name}}' service

          summary: High rate of errors by service, more than 20%



      - alert: LogsTooManyEntriesByService

        expr: |
@@ -21,4 +22,5 @@ groups: 
        labels:

          severity: warning

        annotations:

          summary: Too many logs generated by '{{$labels.service_name}}' service
 
          description: Too many logs ({{$value | printf "%.1f"}}) generated by '{{$labels.service_name}}' service

          summary: Too many logs by service, more than 60 per minute