roles/kube_prometheus_stack/vars/main.yml - atmosphere - Gitiles

 _kube_prometheus_stack_helm_values:
   defaultRules:
     disabled:
       # NOTE(mnaser): https://github.com/prometheus-community/helm-charts/issues/144
       #               https://github.com/openshift/cluster-monitoring-operator/issues/248
       etcdHighNumberOfFailedGRPCRequests: true
   alertmanager:
     serviceMonitor:
       relabelings: &relabelings_instance_to_pod_name
         - &relabeling_set_pod_name_to_instance
           sourceLabels:
             - __meta_kubernetes_pod_name
           targetLabel: instance
         - &relabeling_drop_all_kubernetes_labels
           action: labeldrop
           regex: ^(container|endpoint|namespace|pod|node|service)$
     alertmanagerSpec:
       image:
         repository: "{{ atmosphere_images['alertmanager'] | vexxhost.kubernetes.docker_image('name') }}"
         tag: "{{ atmosphere_images['alertmanager'] | vexxhost.kubernetes.docker_image('tag') }}"
       storage:
         volumeClaimTemplate:
           spec:
             storageClassName: general
             accessModes:
               - ReadWriteOnce
             resources:
               requests:
                 storage: 40Gi
       nodeSelector: &node_selector
         openstack-control-plane: enabled
   grafana:
     adminPassword: "{{ kube_prometheus_stack_grafana_admin_password }}"
     image:
       repository: "{{ atmosphere_images['grafana'] | vexxhost.kubernetes.docker_image('name') }}"
       tag: "{{ atmosphere_images['grafana'] | vexxhost.kubernetes.docker_image('tag') }}"
     ingress:
       enabled: true
       ingressClassName: "{{ kube_prometheus_stack_grafana_ingress_class_name }}"
       annotations:
         cert-manager.io/cluster-issuer: atmosphere
       hosts:
         - "{{ kube_prometheus_stack_grafana_host }}"
       tls:
         - secretName: grafana-tls
           hosts:
             - "{{ kube_prometheus_stack_grafana_host }}"
     sidecar:
       image:
         repository: "{{ atmosphere_images['grafana_sidecar'] | vexxhost.kubernetes.docker_image('name') }}"
         tag: "{{ atmosphere_images['grafana_sidecar'] | vexxhost.kubernetes.docker_image('tag') }}"
       datasources:
         defaultDatasourceEnabled: false
     additionalDataSources:
       - name: AlertManager
         type: alertmanager
         uid: alertmanager
         url: '{% raw %}http://{{ printf "%s-alertmanager.%s" .Release.Name .Release.Namespace }}:9093{% endraw %}'
         access: proxy
         editable: false
         jsonData:
           implementation: prometheus
           handleGrafanaManagedAlerts: true
       - name: Prometheus
         type: prometheus
         uid: prometheus
         url: '{% raw %}http://{{ printf "%s-prometheus.%s" .Release.Name .Release.Namespace }}:9090{% endraw %}'
         access: proxy
         isDefault: true
         editable: false
         jsonData:
           timeInterval: 30s
           alertmanagerUid: alertmanager
       - name: Loki
         type: loki
         uid: loki
         access: proxy
         url: http://loki-gateway
         version: 1
         editable: false
         jsonData:
           alertmanagerUid: alertmanager
     serviceMonitor:
       relabelings: *relabelings_instance_to_pod_name
     nodeSelector: *node_selector
   kubeApiServer:
     serviceMonitor:
       relabelings: &relabelings_instance_to_node_name
         - sourceLabels:
             - __meta_kubernetes_pod_node_name
           targetLabel: instance
         - *relabeling_drop_all_kubernetes_labels
   kubelet:
     serviceMonitor:
       cAdvisorRelabelings: &relabelings_kubelet
         - sourceLabels:
             - __metrics_path__
           targetLabel: metrics_path
         - sourceLabels:
             - node
           targetLabel: instance
         - *relabeling_drop_all_kubernetes_labels
       probesRelabelings: *relabelings_kubelet
       relabelings: *relabelings_kubelet
   kubeControllerManager:
     serviceMonitor:
       relabelings: *relabelings_instance_to_node_name
   coreDns:
     serviceMonitor:
       relabelings: *relabelings_instance_to_pod_name
   kubeEtcd:
     service:
       port: 2379
       targetPort: 2379
     serviceMonitor:
       scheme: https
       serverName: localhost
       insecureSkipVerify: false
       caFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/ca.crt
       certFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/healthcheck-client.crt
       keyFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/healthcheck-client.key
       relabelings: *relabelings_instance_to_node_name
   kubeScheduler:
     service:
       port: 10259
       targetPort: 10259
     serviceMonitor:
       https: true
       insecureSkipVerify: true
       relabelings: *relabelings_instance_to_node_name
   kubeProxy:
     serviceMonitor:
       relabelings: *relabelings_instance_to_node_name
   kube-state-metrics:
     image:
       repository: "{{ atmosphere_images['kube_state_metrics'] | vexxhost.kubernetes.docker_image('name') }}"
       tag: "{{ atmosphere_images['kube_state_metrics'] | vexxhost.kubernetes.docker_image('tag') }}"
     prometheus:
       monitor:
         relabelings: *relabelings_instance_to_pod_name
     nodeSelector: *node_selector
   prometheus:
     serviceMonitor:
       relabelings: *relabelings_instance_to_pod_name
     prometheusSpec:
       image:
         repository: "{{ atmosphere_images['prometheus'] | vexxhost.kubernetes.docker_image('name') }}"
         tag: "{{ atmosphere_images['prometheus'] | vexxhost.kubernetes.docker_image('tag') }}"
       nodeSelector: *node_selector
       secrets:
         - kube-prometheus-stack-etcd-client-cert
     additionalServiceMonitors:
       - name: ceph
         jobLabel: application
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             application: ceph
         endpoints:
           - port: metrics
             honorLabels: true
             relabelings:
               - action: replace
                 regex: (.*)
                 replacement: ceph
                 targetLabel: cluster
               - *relabeling_drop_all_kubernetes_labels
       - name: coredns
         jobLabel: app.kubernetes.io/name
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             app.kubernetes.io/component: metrics
             app.kubernetes.io/name: coredns
         endpoints:
           - port: metrics
             relabelings:
               - sourceLabels:
                   - __meta_kubernetes_pod_label_application
                 targetLabel: application
               - *relabeling_set_pod_name_to_instance
               - *relabeling_drop_all_kubernetes_labels
       - name: memcached
         jobLabel: application
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             application: memcached
             component: server
         endpoints:
           - port: metrics
             relabelings: *relabelings_instance_to_pod_name
       - name: ingress-nginx-controller
         jobLabel: app.kubernetes.io/instance
         namespaceSelector:
           matchNames:
             - ingress-nginx
         selector:
           matchLabels:
             app.kubernetes.io/component: controller
             app.kubernetes.io/instance: ingress-nginx
             app.kubernetes.io/name: ingress-nginx
         endpoints:
           - port: metrics
             relabelings: *relabelings_instance_to_node_name
       - name: openstack-exporter
         jobLabel: jobLabel
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             application: openstack-exporter
         endpoints:
           - port: metrics
             interval: 1m
             relabelings:
               - action: replace
                 regex: (.*)
                 replacement: default
                 targetLabel: instance
             scrapeTimeout: 30s
     additionalPodMonitors:
       - name: ethtool-exporter
         jobLabel: job
         selector:
           matchLabels:
             application: ethtool-exporter
         podMetricsEndpoints:
           - port: metrics
             relabelings: *relabelings_instance_to_node_name
       - name: ipmi-exporter
         jobLabel: job
         selector:
           matchLabels:
             application: ipmi-exporter
         podMetricsEndpoints:
           - interval: 60s
             port: metrics
             relabelings: *relabelings_instance_to_node_name
       - name: percona-xtradb-pxc
         jobLabel: app.kubernetes.io/component
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             app.kubernetes.io/component: pxc
             app.kubernetes.io/instance: percona-xtradb
         podMetricsEndpoints:
           - port: metrics
             relabelings: *relabelings_instance_to_pod_name
       - name: rabbitmq
         jobLabel: app.kubernetes.io/component
         namespaceSelector:
           matchNames:
             - openstack
         selector:
           matchLabels:
             app.kubernetes.io/component: rabbitmq
         podMetricsEndpoints:
           - port: prometheus
             relabelings: *relabelings_instance_to_pod_name
   prometheusOperator:
     admissionWebhooks:
       patch:
         image:
           repository: "{{ atmosphere_images['prometheus_operator_kube_webhook_certgen'] | vexxhost.kubernetes.docker_image('name') }}"
           tag: "{{ atmosphere_images['prometheus_operator_kube_webhook_certgen'] | vexxhost.kubernetes.docker_image('tag') }}"
         nodeSelector: *node_selector
     serviceMonitor:
       relabelings: *relabelings_instance_to_pod_name
     nodeSelector: *node_selector
     image:
       repository: "{{ atmosphere_images['prometheus_operator'] | vexxhost.kubernetes.docker_image('name') }}"
       tag: "{{ atmosphere_images['prometheus_operator'] | vexxhost.kubernetes.docker_image('tag') }}"
     prometheusConfigReloader:
       image:
         repository: "{{ atmosphere_images['prometheus_config_reloader'] | vexxhost.kubernetes.docker_image('name') }}"
         tag: "{{ atmosphere_images['prometheus_config_reloader'] | vexxhost.kubernetes.docker_image('tag') }}"
   prometheus-node-exporter:
     image:
       repository: "{{ atmosphere_images['prometheus_node_exporter'] | vexxhost.kubernetes.docker_image('name') }}"
       tag: "{{ atmosphere_images['prometheus_node_exporter'] | vexxhost.kubernetes.docker_image('tag') }}"
     extraArgs:
       - --collector.diskstats.ignored-devices=^(ram|loop|nbd|fd|(h|s|v|xv)d[a-z]|nvme\\d+n\\d+p)\\d+$
       - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|fuse.squashfuse_ll|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
       - --collector.filesystem.mount-points-exclude=^/(dev|proc|run/credentials/.+|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+|var/lib/kubelet/plugins/kubernetes.io/csi/.+|run/containerd/.+)($|/)
       - --collector.netclass.ignored-devices=^(lxc|cilium_|qbr|qvb|qvo|tap|ovs-system|br|tbr|gre_sys|[0-9a-f]+_eth).*$
       - --collector.netdev.device-exclude=^(lxc|cilium_|qbr|qvb|qvo|tap|ovs-system|br|tbr|gre_sys|[0-9a-f]+_eth).*$
     prometheus:
       monitor:
         relabelings: *relabelings_instance_to_node_name
   additionalPrometheusRulesMap: "{{ lookup('vexxhost.atmosphere.jsonnet', 'jsonnet/rules.jsonnet') }}"
	_kube_prometheus_stack_helm_values:
	defaultRules:
	disabled:
	# NOTE(mnaser): https://github.com/prometheus-community/helm-charts/issues/144
	# https://github.com/openshift/cluster-monitoring-operator/issues/248
	etcdHighNumberOfFailedGRPCRequests: true
	alertmanager:
	serviceMonitor:
	relabelings: &relabelings_instance_to_pod_name
	- &relabeling_set_pod_name_to_instance
	sourceLabels:
	- __meta_kubernetes_pod_name
	targetLabel: instance
	- &relabeling_drop_all_kubernetes_labels
	action: labeldrop
	regex: ^(container\|endpoint\|namespace\|pod\|node\|service)$
	alertmanagerSpec:
	image:
	repository: "{{ atmosphere_images['alertmanager'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['alertmanager'] \| vexxhost.kubernetes.docker_image('tag') }}"
	storage:
	volumeClaimTemplate:
	spec:
	storageClassName: general
	accessModes:
	- ReadWriteOnce
	resources:
	requests:
	storage: 40Gi
	nodeSelector: &node_selector
	openstack-control-plane: enabled
	grafana:
	adminPassword: "{{ kube_prometheus_stack_grafana_admin_password }}"
	image:
	repository: "{{ atmosphere_images['grafana'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['grafana'] \| vexxhost.kubernetes.docker_image('tag') }}"
	ingress:
	enabled: true
	ingressClassName: "{{ kube_prometheus_stack_grafana_ingress_class_name }}"
	annotations:
	cert-manager.io/cluster-issuer: atmosphere
	hosts:
	- "{{ kube_prometheus_stack_grafana_host }}"
	tls:
	- secretName: grafana-tls
	hosts:
	- "{{ kube_prometheus_stack_grafana_host }}"
	sidecar:
	image:
	repository: "{{ atmosphere_images['grafana_sidecar'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['grafana_sidecar'] \| vexxhost.kubernetes.docker_image('tag') }}"
	datasources:
	defaultDatasourceEnabled: false
	additionalDataSources:
	- name: AlertManager
	type: alertmanager
	uid: alertmanager
	url: '{% raw %}http://{{ printf "%s-alertmanager.%s" .Release.Name .Release.Namespace }}:9093{% endraw %}'
	access: proxy
	editable: false
	jsonData:
	implementation: prometheus
	handleGrafanaManagedAlerts: true
	- name: Prometheus
	type: prometheus
	uid: prometheus
	url: '{% raw %}http://{{ printf "%s-prometheus.%s" .Release.Name .Release.Namespace }}:9090{% endraw %}'
	access: proxy
	isDefault: true
	editable: false
	jsonData:
	timeInterval: 30s
	alertmanagerUid: alertmanager
	- name: Loki
	type: loki
	uid: loki
	access: proxy
	url: http://loki-gateway
	version: 1
	editable: false
	jsonData:
	alertmanagerUid: alertmanager
	serviceMonitor:
	relabelings: *relabelings_instance_to_pod_name
	nodeSelector: *node_selector
	kubeApiServer:
	serviceMonitor:
	relabelings: &relabelings_instance_to_node_name
	- sourceLabels:
	- __meta_kubernetes_pod_node_name
	targetLabel: instance
	- *relabeling_drop_all_kubernetes_labels
	kubelet:
	serviceMonitor:
	cAdvisorRelabelings: &relabelings_kubelet
	- sourceLabels:
	- __metrics_path__
	targetLabel: metrics_path
	- sourceLabels:
	- node
	targetLabel: instance
	- *relabeling_drop_all_kubernetes_labels
	probesRelabelings: *relabelings_kubelet
	relabelings: *relabelings_kubelet
	kubeControllerManager:
	serviceMonitor:
	relabelings: *relabelings_instance_to_node_name
	coreDns:
	serviceMonitor:
	relabelings: *relabelings_instance_to_pod_name
	kubeEtcd:
	service:
	port: 2379
	targetPort: 2379
	serviceMonitor:
	scheme: https
	serverName: localhost
	insecureSkipVerify: false
	caFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/ca.crt
	certFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/healthcheck-client.crt
	keyFile: /etc/prometheus/secrets/kube-prometheus-stack-etcd-client-cert/healthcheck-client.key
	relabelings: *relabelings_instance_to_node_name
	kubeScheduler:
	service:
	port: 10259
	targetPort: 10259
	serviceMonitor:
	https: true
	insecureSkipVerify: true
	relabelings: *relabelings_instance_to_node_name
	kubeProxy:
	serviceMonitor:
	relabelings: *relabelings_instance_to_node_name
	kube-state-metrics:
	image:
	repository: "{{ atmosphere_images['kube_state_metrics'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['kube_state_metrics'] \| vexxhost.kubernetes.docker_image('tag') }}"
	prometheus:
	monitor:
	relabelings: *relabelings_instance_to_pod_name
	nodeSelector: *node_selector
	prometheus:
	serviceMonitor:
	relabelings: *relabelings_instance_to_pod_name
	prometheusSpec:
	image:
	repository: "{{ atmosphere_images['prometheus'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['prometheus'] \| vexxhost.kubernetes.docker_image('tag') }}"
	nodeSelector: *node_selector
	secrets:
	- kube-prometheus-stack-etcd-client-cert
	additionalServiceMonitors:
	- name: ceph
	jobLabel: application
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	application: ceph
	endpoints:
	- port: metrics
	honorLabels: true
	relabelings:
	- action: replace
	regex: (.*)
	replacement: ceph
	targetLabel: cluster
	- *relabeling_drop_all_kubernetes_labels
	- name: coredns
	jobLabel: app.kubernetes.io/name
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	app.kubernetes.io/component: metrics
	app.kubernetes.io/name: coredns
	endpoints:
	- port: metrics
	relabelings:
	- sourceLabels:
	- __meta_kubernetes_pod_label_application
	targetLabel: application
	- *relabeling_set_pod_name_to_instance
	- *relabeling_drop_all_kubernetes_labels
	- name: memcached
	jobLabel: application
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	application: memcached
	component: server
	endpoints:
	- port: metrics
	relabelings: *relabelings_instance_to_pod_name
	- name: ingress-nginx-controller
	jobLabel: app.kubernetes.io/instance
	namespaceSelector:
	matchNames:
	- ingress-nginx
	selector:
	matchLabels:
	app.kubernetes.io/component: controller
	app.kubernetes.io/instance: ingress-nginx
	app.kubernetes.io/name: ingress-nginx
	endpoints:
	- port: metrics
	relabelings: *relabelings_instance_to_node_name
	- name: openstack-exporter
	jobLabel: jobLabel
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	application: openstack-exporter
	endpoints:
	- port: metrics
	interval: 1m
	relabelings:
	- action: replace
	regex: (.*)
	replacement: default
	targetLabel: instance
	scrapeTimeout: 30s
	additionalPodMonitors:
	- name: ethtool-exporter
	jobLabel: job
	selector:
	matchLabels:
	application: ethtool-exporter
	podMetricsEndpoints:
	- port: metrics
	relabelings: *relabelings_instance_to_node_name
	- name: ipmi-exporter
	jobLabel: job
	selector:
	matchLabels:
	application: ipmi-exporter
	podMetricsEndpoints:
	- interval: 60s
	port: metrics
	relabelings: *relabelings_instance_to_node_name
	- name: percona-xtradb-pxc
	jobLabel: app.kubernetes.io/component
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	app.kubernetes.io/component: pxc
	app.kubernetes.io/instance: percona-xtradb
	podMetricsEndpoints:
	- port: metrics
	relabelings: *relabelings_instance_to_pod_name
	- name: rabbitmq
	jobLabel: app.kubernetes.io/component
	namespaceSelector:
	matchNames:
	- openstack
	selector:
	matchLabels:
	app.kubernetes.io/component: rabbitmq
	podMetricsEndpoints:
	- port: prometheus
	relabelings: *relabelings_instance_to_pod_name
	prometheusOperator:
	admissionWebhooks:
	patch:
	image:
	repository: "{{ atmosphere_images['prometheus_operator_kube_webhook_certgen'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['prometheus_operator_kube_webhook_certgen'] \| vexxhost.kubernetes.docker_image('tag') }}"
	nodeSelector: *node_selector
	serviceMonitor:
	relabelings: *relabelings_instance_to_pod_name
	nodeSelector: *node_selector
	image:
	repository: "{{ atmosphere_images['prometheus_operator'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['prometheus_operator'] \| vexxhost.kubernetes.docker_image('tag') }}"
	prometheusConfigReloader:
	image:
	repository: "{{ atmosphere_images['prometheus_config_reloader'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['prometheus_config_reloader'] \| vexxhost.kubernetes.docker_image('tag') }}"
	prometheus-node-exporter:
	image:
	repository: "{{ atmosphere_images['prometheus_node_exporter'] \| vexxhost.kubernetes.docker_image('name') }}"
	tag: "{{ atmosphere_images['prometheus_node_exporter'] \| vexxhost.kubernetes.docker_image('tag') }}"
	extraArgs:
	- --collector.diskstats.ignored-devices=^(ram\|loop\|nbd\|fd\|(h\|s\|v\|xv)d[a-z]\|nvme\\d+n\\d+p)\\d+$
	- --collector.filesystem.fs-types-exclude=^(autofs\|binfmt_misc\|bpf\|cgroup2?\|configfs\|debugfs\|devpts\|devtmpfs\|fusectl\|fuse.squashfuse_ll\|hugetlbfs\|iso9660\|mqueue\|nsfs\|overlay\|proc\|procfs\|pstore\|rpc_pipefs\|securityfs\|selinuxfs\|squashfs\|sysfs\|tracefs)$
	- --collector.filesystem.mount-points-exclude=^/(dev\|proc\|run/credentials/.+\|sys\|var/lib/docker/.+\|var/lib/kubelet/pods/.+\|var/lib/kubelet/plugins/kubernetes.io/csi/.+\|run/containerd/.+)($\|/)
	- --collector.netclass.ignored-devices=^(lxc\|cilium_\|qbr\|qvb\|qvo\|tap\|ovs-system\|br\|tbr\|gre_sys\|[0-9a-f]+_eth).*$
	- --collector.netdev.device-exclude=^(lxc\|cilium_\|qbr\|qvb\|qvo\|tap\|ovs-system\|br\|tbr\|gre_sys\|[0-9a-f]+_eth).*$
	prometheus:
	monitor:
	relabelings: *relabelings_instance_to_node_name
	additionalPrometheusRulesMap: "{{ lookup('vexxhost.atmosphere.jsonnet', 'jsonnet/rules.jsonnet') }}"