Addons Monitoring

bash-5.0# cat sunpike.yml groups: - name: hosts rules: - alert: HostNotConverging expr: sum without (status_start_attempts) (sunpike_hosts_health{clusterrole!="none",hoststate!="Ok"}) == 1 for: 20m labels: type: pf9 severity: high annotations: summary: Host {{ $labels.hostname }} not converging description: Host {{ $labels.hostname }} is not converging, status {{ $labels.hoststate }}, role {{ $labels.clusterrole }}, retries {{ $labels.status_start_attempts }} - name: clusteraddons rules: - alert: AddonNotHealthy expr: sunpike_clusteraddons_health{healthy!="true"} == 1 for: 10m labels: type: pf9 severity: high annotations: summary: Addon {{ $labels.type }} not healthy!! description: Addon {{ $labels.type }} of cluster {{ $labels.cluster }} not healthy - alert: AddonNotConverging expr: sunpike_clusteraddons_health{phase=""} == 1 for: 20m labels: type: pf9 severity: high annotations: summary: Addon {{ $labels.type }} not converging!! description: Addon {{ $labels.type }} of cluster {{ $labels.cluster }} not converging - alert: AddonInstallError expr: sunpike_clusteraddons_health{phase="InstallAddonError"} == 1 for: 5m labels: type: pf9 severity: high annotations: summary: Error installing {{ $labels.type }} addon!! description: Error installing Addon {{ $labels.type }} on cluster {{ $labels.cluster }} failed to install - alert: AddonUninstallError expr: sunpike_clusteraddons_health{phase="UnInstallAddonError"} == 1 for: 5m labels: type: pf9 severity: high annotations: summary: Error uninstalling {{ $labels.type }} addon!! description: Error uninstalling Addon {{ $labels.type }} on cluster {{ $labels.cluster }} failed to uninstall bash-5.0#