Path: blob/main/operations/observability/mixins/workspace/rules/central/node-labeler.yaml
2506 views
# Copyright (c) 2022 Gitpod GmbH. All rights reserved.1# Licensed under the GNU Affero General Public License (AGPL).2# See License.AGPL.txt in the project root for license information.34apiVersion: monitoring.coreos.com/v15kind: PrometheusRule6metadata:7labels:8prometheus: k8s9role: alert-rules10name: node-labeler-central-monitoring-rules11spec:12groups:13- name: node-labeler14rules:15- alert: GitpodNodeLabelerCrashLooping16labels:17severity: critical18dedicated: included19annotations:20runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentCrashlooping.md21summary: node-labeler is crashlooping in cluster {{ $labels.cluster }}.22description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 3 minutes.23expr: |24increase(kube_pod_container_status_restarts_total{container="node-labeler", cluster!~"ephemeral.*"}[1m]) > 325for: 3m26- alert: GitpodNodeLabelerReplicasMismatch27labels:28severity: critical29dedicated: included30annotations:31runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentReplicaMismatch.md32summary: Desired number of replicas for node-labeler are not available in cluster {{ $labels.cluster }}33description: 'Desired number of replicas for node-labeler are not available in cluster {{ $labels.cluster }}: {{ printf "%.2f" $value }} are missing'34expr: |35kube_deployment_spec_replicas{deployment="node-labeler", cluster!~"ephemeral.*"} != kube_deployment_status_replicas_available{deployment="node-labeler", cluster!~"ephemeral.*"}36for: 3m37- alert: GitpodNodeLabelerReplicaUnavailable38labels:39# TODO(gpl): warning for now, to set it up and fine-tune it40severity: warning41annotations:42runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentReplicaMismatch.md43summary: node-labeler replicas are unavailable in cluster {{ $labels.cluster }}44description: 'node-labeler pods are unavailable in cluster {{ $labels.cluster }}: {{ printf "%.2f" $value }}'45expr: |46kube_deployment_status_replicas_unavailable{deployment="node-labeler", cluster!~"ephemeral.*"} > 047for: 10m484950