enable kube-prometheus stack #250
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
--- kubernetes/apps Kustomization: flux-system/cluster-apps Kustomization: flux-system/kube-prometheus-stack
+++ kubernetes/apps Kustomization: flux-system/cluster-apps Kustomization: flux-system/kube-prometheus-stack
@@ -0,0 +1,38 @@
+---
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+ labels:
+ kustomize.toolkit.fluxcd.io/name: cluster-apps
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: kube-prometheus-stack
+ namespace: flux-system
+spec:
+ commonMetadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ decryption:
+ provider: sops
+ secretRef:
+ name: sops-age
+ dependsOn:
+ - name: onepassword-connect
+ interval: 30m
+ path: ./kubernetes/apps/observability/kube-prometheus-stack/app
+ postBuild:
+ substituteFrom:
+ - kind: ConfigMap
+ name: cluster-settings
+ optional: true
+ - kind: Secret
+ name: cluster-secrets
+ optional: true
+ prune: true
+ sourceRef:
+ kind: GitRepository
+ name: flux-system
+ namespace: flux-system
+ targetNamespace: observability
+ timeout: 5m
+ wait: false
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack AlertmanagerConfig: observability/alertmanager
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack AlertmanagerConfig: observability/alertmanager
@@ -0,0 +1,90 @@
+---
+apiVersion: monitoring.coreos.com/v1alpha1
+kind: AlertmanagerConfig
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: alertmanager
+ namespace: observability
+spec:
+ inhibitRules:
+ - equal:
+ - alertname
+ - namespace
+ sourceMatch:
+ - matchType: =
+ name: severity
+ value: critical
+ targetMatch:
+ - matchType: =
+ name: severity
+ value: warning
+ receivers:
+ - name: 'null'
+ - name: heartbeat
+ webhookConfigs:
+ - urlSecret:
+ key: ALERTMANAGER_HEARTBEAT_URL
+ name: alertmanager-secret
+ - emailConfigs:
+ - authPassword:
+ key: alertmanager-secret
+ name: ALERTMANAGER_SMTP_PASSWORD
+ authUsername: ..PLACEHOLDER_ALERTMANAGER_SMTP_USERNAME..
+ from: [email protected]_SECRET_DOMAIN..
+ hello: [email protected]_SECRET_DOMAIN..
+ html: |-
+ {{- range .Alerts }}
+ {{- if ne .Annotations.description "" }}
+ {{ .Annotations.description }}
+ {{- else if ne .Annotations.summary "" }}
+ {{ .Annotations.summary }}
+ {{- else if ne .Annotations.message "" }}
+ {{ .Annotations.message }}
+ {{- else }}
+ Alert description not available
+ {{- end }}
+ {{- if gt (len .Labels.SortedPairs) 0 }}
+ <small>
+ {{- range .Labels.SortedPairs }}
+ <b>{{ .Name }}:</b> {{ .Value }}
+ {{- end }}
+ </small>
+ {{- end }}
+ {{- end }}
+ sendResolved: true
+ smarthost: ..PLACEHOLDER_ALERTMANAGER_SMTP_HOST..
+ text: '[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing
+ | len }}{{ end }}] {{ .CommonLabels.alertname }}'
+ to: [email protected]_SECRET_DOMAIN..
+ name: email
+ route:
+ groupBy:
+ - alertname
+ - job
+ groupInterval: 10m
+ groupWait: 1m
+ receiver: pushover
+ repeatInterval: 12h
+ routes:
+ - matchers:
+ - matchType: =
+ name: alertname
+ value: InfoInhibitor
+ receiver: 'null'
+ - groupInterval: 5m
+ groupWait: 0s
+ matchers:
+ - matchType: =
+ name: alertname
+ value: Watchdog
+ receiver: heartbeat
+ repeatInterval: 5m
+ - matchers:
+ - matchType: =
+ name: severity
+ value: critical
+ receiver: email
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack ExternalSecret: observability/alertmanager
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack ExternalSecret: observability/alertmanager
@@ -0,0 +1,25 @@
+---
+apiVersion: external-secrets.io/v1beta1
+kind: ExternalSecret
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: alertmanager
+ namespace: observability
+spec:
+ dataFrom:
+ - extract:
+ key: alertmanager
+ refreshInterval: 5m
+ secretStoreRef:
+ kind: ClusterSecretStore
+ name: onepassword
+ target:
+ name: alertmanager-secret
+ template:
+ data:
+ ALERTMANAGER_HEARTBEAT_URL: '{{ .ALERTMANAGER_HEARTBEAT_URL }}'
+ ALERTMANAGER_SMTP_PASSWORD: '{{ .ALERTMANAGER_SMTP_PASSWORD }}'
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
@@ -0,0 +1,164 @@
+---
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: kube-prometheus-stack
+ namespace: observability
+spec:
+ chart:
+ spec:
+ chart: kube-prometheus-stack
+ sourceRef:
+ kind: HelmRepository
+ name: prometheus-community
+ namespace: flux-system
+ version: 68.4.4
+ dependsOn:
+ - name: kube-prometheus-stack-crds
+ namespace: observability
+ install:
+ crds: Skip
+ remediation:
+ retries: 3
+ interval: 30m
+ upgrade:
+ cleanupOnFail: true
+ crds: Skip
+ remediation:
+ retries: 3
+ strategy: rollback
+ values:
+ additionalPrometheusRulesMap:
+ dockerhub-rules:
+ groups:
+ - name: dockerhub
+ rules:
+ - alert: DockerhubRateLimitRisk
+ annotations:
+ summary: Kubernetes cluster Dockerhub rate limit risk
+ expr: count(time() - container_last_seen{image=~"(docker.io).*",container!=""}
+ < 30) > 100
+ labels:
+ severity: critical
+ oom-rules:
+ groups:
+ - name: oom
+ rules:
+ - alert: OomKilled
+ annotations:
+ summary: Container {{ $labels.container }} in pod {{ $labels.namespace
+ }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the
+ last 10 minutes.
+ expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total
+ offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m])
+ == 1
+ labels:
+ severity: critical
+ alertmanager:
+ alertmanagerSpec:
+ alertmanagerConfiguration:
+ global:
+ resolveTimeout: 5m
+ name: alertmanager
+ externalUrl: https://alertmanager...PLACEHOLDER_SECRET_DOMAIN..
+ storage:
+ volumeClaimTemplate:
+ spec:
+ resources:
+ requests:
+ storage: 1Gi
+ storageClassName: nfs-provision
+ ingress:
+ enabled: true
+ hosts:
+ - alertmanager...PLACEHOLDER_SECRET_DOMAIN..
+ ingressClassName: internal
+ pathType: Prefix
+ cleanPrometheusOperatorObjectNames: true
+ crds:
+ enabled: false
+ grafana:
+ enabled: false
+ forceDeployDashboards: true
+ kube-state-metrics:
+ fullnameOverride: kube-state-metrics
+ metricLabelsAllowlist:
+ - pods=[*]
+ - deployments=[*]
+ - persistentvolumeclaims=[*]
+ prometheus:
+ monitor:
+ enabled: true
+ relabelings:
+ - action: replace
+ regex: (.*)
+ replacement: $1
+ sourceLabels:
+ - __meta_kubernetes_pod_node_name
+ targetLabel: kubernetes_node
+ kubeApiServer:
+ serviceMonitor:
+ selector:
+ k8s-app: kube-apiserver
+ kubeControllerManager:
+ service:
+ selector:
+ k8s-app: kube-controller-manager
+ kubeEtcd:
+ service:
+ selector:
+ k8s-app: kube-controller-manager
+ kubeProxy:
+ enabled: false
+ kubeScheduler:
+ service:
+ selector:
+ k8s-app: kube-scheduler
+ prometheus:
+ ingress:
+ enabled: true
+ hosts:
+ - prometheus...PLACEHOLDER_SECRET_DOMAIN..
+ ingressClassName: internal
+ pathType: Prefix
+ prometheusSpec:
+ enableAdminAPI: true
+ enableFeatures:
+ - memory-snapshot-on-shutdown
+ podMonitorSelectorNilUsesHelmValues: false
+ probeSelectorNilUsesHelmValues: false
+ resources:
+ limits:
+ memory: 2000Mi
+ requests:
+ cpu: 100m
+ retention: 14d
+ retentionSize: 50GB
+ ruleSelectorNilUsesHelmValues: false
+ scrapeConfigSelectorNilUsesHelmValues: false
+ serviceMonitorSelectorNilUsesHelmValues: false
+ storageSpec:
+ volumeClaimTemplate:
+ spec:
+ resources:
+ requests:
+ storage: 50Gi
+ storageClassName: nfs-provision
+ walCompression: true
+ prometheus-node-exporter:
+ fullnameOverride: node-exporter
+ prometheus:
+ monitor:
+ enabled: true
+ relabelings:
+ - action: replace
+ regex: (.*)
+ replacement: $1
+ sourceLabels:
+ - __meta_kubernetes_pod_node_name
+ targetLabel: kubernetes_node
+ |
--- kubernetes/apps Kustomization: flux-system/cluster-apps Kustomization: flux-system/kube-prometheus-stack
+++ kubernetes/apps Kustomization: flux-system/cluster-apps Kustomization: flux-system/kube-prometheus-stack
@@ -0,0 +1,38 @@
+---
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+ labels:
+ kustomize.toolkit.fluxcd.io/name: cluster-apps
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: kube-prometheus-stack
+ namespace: flux-system
+spec:
+ commonMetadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ decryption:
+ provider: sops
+ secretRef:
+ name: sops-age
+ dependsOn:
+ - name: onepassword-connect
+ interval: 30m
+ path: ./kubernetes/apps/observability/kube-prometheus-stack/app
+ postBuild:
+ substituteFrom:
+ - kind: ConfigMap
+ name: cluster-settings
+ optional: true
+ - kind: Secret
+ name: cluster-secrets
+ optional: true
+ prune: true
+ sourceRef:
+ kind: GitRepository
+ name: flux-system
+ namespace: flux-system
+ targetNamespace: observability
+ timeout: 5m
+ wait: false
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack AlertmanagerConfig: observability/alertmanager
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack AlertmanagerConfig: observability/alertmanager
@@ -0,0 +1,90 @@
+---
+apiVersion: monitoring.coreos.com/v1alpha1
+kind: AlertmanagerConfig
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: alertmanager
+ namespace: observability
+spec:
+ inhibitRules:
+ - equal:
+ - alertname
+ - namespace
+ sourceMatch:
+ - matchType: =
+ name: severity
+ value: critical
+ targetMatch:
+ - matchType: =
+ name: severity
+ value: warning
+ receivers:
+ - name: 'null'
+ - name: heartbeat
+ webhookConfigs:
+ - urlSecret:
+ key: ALERTMANAGER_HEARTBEAT_URL
+ name: alertmanager-secret
+ - emailConfigs:
+ - authPassword:
+ key: alertmanager-secret
+ name: ALERTMANAGER_SMTP_PASSWORD
+ authUsername: ..PLACEHOLDER_ALERTMANAGER_SMTP_USERNAME..
+ from: [email protected]_SECRET_DOMAIN..
+ hello: [email protected]_SECRET_DOMAIN..
+ html: |-
+ {{- range .Alerts }}
+ {{- if ne .Annotations.description "" }}
+ {{ .Annotations.description }}
+ {{- else if ne .Annotations.summary "" }}
+ {{ .Annotations.summary }}
+ {{- else if ne .Annotations.message "" }}
+ {{ .Annotations.message }}
+ {{- else }}
+ Alert description not available
+ {{- end }}
+ {{- if gt (len .Labels.SortedPairs) 0 }}
+ <small>
+ {{- range .Labels.SortedPairs }}
+ <b>{{ .Name }}:</b> {{ .Value }}
+ {{- end }}
+ </small>
+ {{- end }}
+ {{- end }}
+ sendResolved: true
+ smarthost: ..PLACEHOLDER_ALERTMANAGER_SMTP_HOST..
+ text: '[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing
+ | len }}{{ end }}] {{ .CommonLabels.alertname }}'
+ to: [email protected]_SECRET_DOMAIN..
+ name: email
+ route:
+ groupBy:
+ - alertname
+ - job
+ groupInterval: 10m
+ groupWait: 1m
+ receiver: pushover
+ repeatInterval: 12h
+ routes:
+ - matchers:
+ - matchType: =
+ name: alertname
+ value: InfoInhibitor
+ receiver: 'null'
+ - groupInterval: 5m
+ groupWait: 0s
+ matchers:
+ - matchType: =
+ name: alertname
+ value: Watchdog
+ receiver: heartbeat
+ repeatInterval: 5m
+ - matchers:
+ - matchType: =
+ name: severity
+ value: critical
+ receiver: email
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack ExternalSecret: observability/alertmanager
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack ExternalSecret: observability/alertmanager
@@ -0,0 +1,25 @@
+---
+apiVersion: external-secrets.io/v1beta1
+kind: ExternalSecret
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: alertmanager
+ namespace: observability
+spec:
+ dataFrom:
+ - extract:
+ key: alertmanager
+ refreshInterval: 5m
+ secretStoreRef:
+ kind: ClusterSecretStore
+ name: onepassword
+ target:
+ name: alertmanager-secret
+ template:
+ data:
+ ALERTMANAGER_HEARTBEAT_URL: '{{ .ALERTMANAGER_HEARTBEAT_URL }}'
+ ALERTMANAGER_SMTP_PASSWORD: '{{ .ALERTMANAGER_SMTP_PASSWORD }}'
+
--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack
@@ -0,0 +1,164 @@
+---
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+ labels:
+ app.kubernetes.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/name: kube-prometheus-stack
+ kustomize.toolkit.fluxcd.io/namespace: flux-system
+ name: kube-prometheus-stack
+ namespace: observability
+spec:
+ chart:
+ spec:
+ chart: kube-prometheus-stack
+ sourceRef:
+ kind: HelmRepository
+ name: prometheus-community
+ namespace: flux-system
+ version: 68.4.4
+ dependsOn:
+ - name: kube-prometheus-stack-crds
+ namespace: observability
+ install:
+ crds: Skip
+ remediation:
+ retries: 3
+ interval: 30m
+ upgrade:
+ cleanupOnFail: true
+ crds: Skip
+ remediation:
+ retries: 3
+ strategy: rollback
+ values:
+ additionalPrometheusRulesMap:
+ dockerhub-rules:
+ groups:
+ - name: dockerhub
+ rules:
+ - alert: DockerhubRateLimitRisk
+ annotations:
+ summary: Kubernetes cluster Dockerhub rate limit risk
+ expr: count(time() - container_last_seen{image=~"(docker.io).*",container!=""}
+ < 30) > 100
+ labels:
+ severity: critical
+ oom-rules:
+ groups:
+ - name: oom
+ rules:
+ - alert: OomKilled
+ annotations:
+ summary: Container {{ $labels.container }} in pod {{ $labels.namespace
+ }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the
+ last 10 minutes.
+ expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total
+ offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m])
+ == 1
+ labels:
+ severity: critical
+ alertmanager:
+ alertmanagerSpec:
+ alertmanagerConfiguration:
+ global:
+ resolveTimeout: 5m
+ name: alertmanager
+ externalUrl: https://alertmanager...PLACEHOLDER_SECRET_DOMAIN..
+ storage:
+ volumeClaimTemplate:
+ spec:
+ resources:
+ requests:
+ storage: 1Gi
+ storageClassName: nfs-provision
+ ingress:
+ enabled: true
+ hosts:
+ - alertmanager...PLACEHOLDER_SECRET_DOMAIN..
+ ingressClassName: internal
+ pathType: Prefix
+ cleanPrometheusOperatorObjectNames: true
+ crds:
+ enabled: false
+ grafana:
+ enabled: false
+ forceDeployDashboards: true
+ kube-state-metrics:
+ fullnameOverride: kube-state-metrics
+ metricLabelsAllowlist:
+ - pods=[*]
+ - deployments=[*]
+ - persistentvolumeclaims=[*]
+ prometheus:
+ monitor:
+ enabled: true
+ relabelings:
+ - action: replace
+ regex: (.*)
+ replacement: $1
+ sourceLabels:
+ - __meta_kubernetes_pod_node_name
+ targetLabel: kubernetes_node
+ kubeApiServer:
+ serviceMonitor:
+ selector:
+ k8s-app: kube-apiserver
+ kubeControllerManager:
+ service:
+ selector:
+ k8s-app: kube-controller-manager
+ kubeEtcd:
+ service:
+ selector:
+ k8s-app: kube-controller-manager
+ kubeProxy:
+ enabled: false
+ kubeScheduler:
+ service:
+ selector:
+ k8s-app: kube-scheduler
+ prometheus:
+ ingress:
+ enabled: true
+ hosts:
+ - prometheus...PLACEHOLDER_SECRET_DOMAIN..
+ ingressClassName: internal
+ pathType: Prefix
+ prometheusSpec:
+ enableAdminAPI: true
+ enableFeatures:
+ - memory-snapshot-on-shutdown
+ podMonitorSelectorNilUsesHelmValues: false
+ probeSelectorNilUsesHelmValues: false
+ resources:
+ limits:
+ memory: 2000Mi
+ requests:
+ cpu: 100m
+ retention: 14d
+ retentionSize: 50GB
+ ruleSelectorNilUsesHelmValues: false
+ scrapeConfigSelectorNilUsesHelmValues: false
+ serviceMonitorSelectorNilUsesHelmValues: false
+ storageSpec:
+ volumeClaimTemplate:
+ spec:
+ resources:
+ requests:
+ storage: 50Gi
+ storageClassName: nfs-provision
+ walCompression: true
+ prometheus-node-exporter:
+ fullnameOverride: node-exporter
+ prometheus:
+ monitor:
+ enabled: true
+ relabelings:
+ - action: replace
+ regex: (.*)
+ replacement: $1
+ sourceLabels:
+ - __meta_kubernetes_pod_node_name
+ targetLabel: kubernetes_node
+ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.