monitoring: remove prometheus stack, add alloy

2026-08-30 22:15:39 +00:00
parent 4913882963
commit 115a600055
6 changed files with 192 additions and 246 deletions
@@ -1,19 +1,15 @@
 apiVersion: helm.toolkit.fluxcd.io/v2
 kind: HelmRelease
 metadata:
-  name: kube-prometheus-stack
+  name: kube-state-metrics
 spec:
-  releaseName: prometheus
+  releaseName: kube-state-metrics
  interval: 1m
  chart:
    spec:
-      chart: kube-prometheus-stack
-      version: 86.x.x
+      chart: kube-state-metrics
+      version: 8.x.x
      sourceRef:
        kind: HelmRepository
        name: prometheus
      interval: 40h
-  valuesFrom:
-    - kind: Secret
-      name: prometheus-stack-helm-values
-      valuesKey: values.yaml
@@ -1,141 +0,0 @@
-
-defaultRules:
-  create: false
-
-alertmanager:
-  enabled: false
-
-grafana:
-  enabled: false
-
-prometheus:
-  enabled: false
-
-kubeStateMetrics:
-  enabled: true
-
-nodeExporter:
-  enabled: false
-
-prometheus-node-exporter:
-  prometheus:
-    monitor:
-      enabled: false
-
-coreDns: 
-  enabled: true
-  serviceMonitor:
-    relabelings:
-      - targetLabel: cluster
-        replacement: casa
- 
-kubeApiServer: 
-  enabled: true
-  serviceMonitor:
-    relabelings:
-      - targetLabel: cluster
-        replacement: casa
- 
-kubeControllerManager:
-  enabled: false
-
-kubeEtcd:
-  enabled: false
-
-kubeProxy:
-  enabled: false
-
-kubeScheduler:
-  enabled: false
-
-kube-state-metrics:
-  podLabels:
-    role: worker-node
-  nodeSelector:
-    role: worker-node
-  prometheus:
-    monitor:
-        relabelings:
-        - targetLabel: cluster
-          replacement: casa
-
-prometheusOperator:
-  kubeletService:
-    enabled: true
-  enabled: true
-  createCustomResource: true
-  tls:
-    enabled: false
-  admissionWebhooks:
-    enabled: false
-  cleanupCustomResource: false
-  serviceMonitor:
-    selfMonitor: false
- 
-
-kubelet:
-  enabled: true
-  namespace: kube-system
-  serviceMonitor:
-    interval: 60s #WARN: Error on ingesting out-of-order samples. https://github.com/prometheus-community/helm-charts/issues/5483
-    enabled: true 
-    ## Enable scraping /metrics from kubelet's service
-    kubelet: true
-
-    probesMetricRelabelings:
-      - targetLabel: cluster
-        replacement: casa
-      - sourceLabels: [__name__, image]
-        separator: ;
-        regex: container_([a-z_]+);
-        replacement: $1
-        action: drop
-      - sourceLabels: [__name__]
-        separator: ;
-        regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
-        replacement: $1
-        action: drop
-
-
-#     # RelabelConfigs to apply to samples before scraping
-#     # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
-#     #
-#     # metrics_path is required to match upstream rules and charts
-    cAdvisorRelabelings:
-      - targetLabel: cluster
-        replacement: casa    
-      - action: replace
-        sourceLabels: [__metrics_path__]
-        targetLabel: metrics_path
-      - sourceLabels: [__meta_kubernetes_pod_node_name]
-        separator: ;
-        regex: ^(.*)$
-        targetLabel: nodename
-        replacement: $1
-        action: replace
-
-#     # RelabelConfigs to apply to samples before scraping
-#     # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
-#     #
-    probesRelabelings:
-
-      - targetLabel: cluster
-        replacement: casa
-      - action: replace
-        sourceLabels: [__metrics_path__]
-        targetLabel: metrics_path
-
-      - sourceLabels: [__meta_kubernetes_pod_node_name]
-        separator: ;
-        regex: ^(.*)$
-        targetLabel: nodename
-        replacement: $1
-        action: replace
-
-    resourceRelabelings:
-      - targetLabel: cluster
-        replacement: casa
-      - action: replace
-        sourceLabels: [__metrics_path__]
-        targetLabel: metrics_path
-    
@@ -1,76 +0,0 @@
-
-apiVersion: monitoring.coreos.com/v1alpha1
-kind: PrometheusAgent
-metadata:
-  name: prometheus-agent
-spec:
-  podMonitorNamespaceSelector:
-    matchLabels:
-      prometheus-monitoring: enabled
-
-  podMonitorSelector:
-    matchLabels:
-      release: prometheus
-
-  serviceMonitorNamespaceSelector:
-    matchLabels:
-      prometheus-monitoring: enabled
-
-  serviceMonitorSelector:
-    matchLabels:
-      release: prometheus
-
-  replicas: 1
-  remoteWrite:
-    - url: https://prometheus.monitoring.limbosolutions.com/api/v1/write
-  scrapeInterval: 60s
-  resources:
-    requests:
-      cpu: 100m
-      memory: 128Mi
-    limits:
-      cpu: 200m
-      memory: 512Mi # minimum stable
-  serviceAccountName: prometheus-agent
-  nodeSelector:
-    role: worker-node
---
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: prometheus-agent
-rules:
-  - apiGroups: [""]
-    resources: ["nodes", "nodes/metrics", "nodes/proxy", "services", "endpoints", "pods"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: ["monitoring.coreos.com"]
-    resources: ["servicemonitors", "podmonitors"]
-    verbs: ["get", "list", "watch"]
-  - nonResourceURLs:
-      - /metrics
-      - /metrics/cadvisor
-      - /metrics/probes
-    verbs: ["get"]
---
-
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: prometheus-agent-monitoring
-roleRef:
-  kind: ClusterRole
-  name: prometheus-agent
-  apiGroup: rbac.authorization.k8s.io
-subjects:
-  - kind: ServiceAccount
-    name: prometheus-agent
-    namespace: monitoring
-
---
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: prometheus-agent
-  namespace: monitoring