Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
gitpod-io
GitHub Repository: gitpod-io/gitpod
 Path: blob/main/operations/observability/mixins/meta/rules/meta-nodes.yaml
2500 views
1
# Copyright (c) 2022 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: meta-nodes-monitoring-rules

12
spec:

13
  groups:

14
  - name: meta-nodes

15
    rules:

16
    - alert: GitpodMetaNodeOOMKills

17
      labels:

18
        severity: warning

19
      annotations:

20
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodMetaNodeOOMKills.md

21
        summary: A meta node is reporting OOM kills.

22
        description: Meta node {{ $labels.instance }} is reporting {{ printf "%.2f" $value }} Out Of Memory kills in the last 10 minutes.

23
      expr: increase(node_vmstat_oom_kill{instance=~".*meta.*"}[10m]) > 1

24
    - alert: GitpodMetaNodeCPUSaturation

25
      labels:

26
        severity: warning

27
      for: 10m

28
      annotations:

29
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodMetaNodeCPUSaturation.md

30
        summary: High CPU Saturation of a meta node.

31
        description: Meta node {{ $labels.instance }} is reporting {{ printf "%.2f" $value }}% CPU usage for more than 10 minutes.

32
      expr: (1 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle", instance=~".*meta.*"}[2m])))) * 100 > 75

33


34