Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
gitpod-io
GitHub Repository: gitpod-io/gitpod
 Path: blob/main/operations/observability/mixins/IDE/rules/supervisor.yaml
2500 views
1
# Copyright (c) 2023 Gitpod GmbH. All rights reserved.

2
# Licensed under the GNU Affero General Public License (AGPL).

3
# See License.AGPL.txt in the project root for license information.

4


5
apiVersion: monitoring.coreos.com/v1

6
kind: PrometheusRule

7
metadata:

8
  labels:

9
    prometheus: k8s

10
    role: alert-rules

11
  name: supervisor-monitoring-rules

12
  namespace: monitoring-satellite

13
spec:

14
  groups:

15
  - name: supervisor

16
    rules:

17
    - alert: SupervisorIncomingFailuresRatioTooHigh

18
      labels:

19
        severity: critical

20
        dedicated: included

21
      for: 20m

22
      annotations:

23
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/SupervisorIncomingFailuresRatioTooHigh.md

24
        summary: Supervisor is returning higher number of errors. This can prevent workspace usability.

25
      expr: |

26
          sum(rate(grpc_server_handled_total{grpc_code!~"OK|Canceled", grpc_service=~"supervisor.*"}[5m])) by(cluster) / sum(rate(grpc_server_handled_total{grpc_service=~"supervisor.*"}[5m])) by(cluster) > 0.01

27


28
    - alert: SupervisorOutgoingFailuresRatioTooHigh

29
      labels:

30
        severity: critical

31
        dedicated: included

32
      for: 20m

33
      annotations:

34
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/SupervisorOutgoingFailuresRatioTooHigh.md

35
        summary: PublicAPI or ServerAPI is returning higher number of errors. This can prevent workspace usability

36
      expr: |

37
          sum(rate(supervisor_client_handled_total{err_code!~"OK|Canceled|PermissionDenied", job="ide-metrics"}[5m])) by(cluster) / sum(rate(grpc_server_handled_total{grpc_service=~"supervisor.*"}[5m])) by(cluster) > 0.01

38


39