Changes kube-prometheus-stack to individual prometheus and grafana charts

Deploying this configuration manually works

Author: salvis2

Diff for: deploy-aws/staging-install.yaml

@@ -27,21 +27,20 @@ binderhub:
     hostLibDir: /var/lib/dind/stage
     hostSocketDir: /var/run/dind/stage
 
-kube-prometheus-stack:
-  prometheus:
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 0m
-        memory: 0Gi
-  grafana:
-    resources:
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 0m
-        memory: 0Gi
+prometheus:
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 0m
+      memory: 0Gi
+grafana:
+  resources:
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 0m
+      memory: 0Gi

Diff for: deploy-aws/staging.yaml

@@ -86,33 +86,29 @@ binderhub:
           # This makes the gateway available at ${HUB_URL}/services/dask-gateway
           url: http://traefik-staging-dask-gateway.staging
 
-kube-prometheus-stack:
-  prometheus:
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 0m
-        memory: 0Gi
-  grafana:
-    resources:
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 0m
-        memory: 0Gi
-    ingress:
-      enabled: true
-      hosts:
-        - grafana.staging.aws-uswest2-binder.pangeo.io
-      annotations:
-        kubernetes.io/ingress.class: nginx
-        kubernetes.io/tls-acme: "true"
-        cert-manager.io/issuer: letsencrypt-production
-      tls:
-        - secretName: grafana.staging.aws-uswest2-binder.pangeo.io-tls
-          hosts:
-            - grafana.staging.aws-uswest2-binder.pangeo.io
+prometheus:
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 0m
+      memory: 0Gi
+grafana:
+  resources:
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 0m
+      memory: 0Gi
+  ingress:
+    enabled: true
+    path: /grafana/?(.*)
+    hosts:
+      - staging.aws-uswest2-binder.pangeo.io
+    annotations:
+      kubernetes.io/ingress.class: nginx
+      nginx.ingress.kubernetes.io/rewrite-target: /$1
+      nginx.ingress.kubernetes.io/use-regex: "true"

Diff for: k8s-aws/readme.md

@@ -28,6 +28,9 @@ helm version #>3
 helm repo add pangeo https://pangeo-data.github.io/helm-chart/
 helm repo add jupyterhub https://jupyterhub.github.io/helm-chart/
 helm repo add dask-gateway https://dask.org/dask-gateway-helm-repo/
+helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+helm repo add stable https://kubernetes-charts.storage.googleapis.com/
+helm repo add grafana https://grafana.github.io/helm-charts
 helm repo update
 cd pangeo-binder/pangeo-binder
 helm dependency update

Diff for: pangeo-binder/requirements.yaml

@@ -12,6 +12,9 @@ dependencies:
 - name: dask-gateway
   version: "0.8.0"
   repository: 'https://dask.org/dask-gateway-helm-repo/'
-- name: kube-prometheus-stack
-  version: 10.0.1
-  repository: "https://prometheus-community.github.io/helm-charts"
+- name: prometheus
+  version: 11.16.2
+  repository: https://prometheus-community.github.io/helm-charts
+- name: grafana
+  version: 5.8.10
+  repository: https://grafana.github.io/helm-charts

Diff for: pangeo-binder/values.yaml

@@ -272,70 +272,72 @@ dask-gateway:
       #   c.UserLimits.max_memory = "400 G"
       #   c.UserLimits.max_clusters = 1
 
-kube-prometheus-stack:
-  prometheus:
-    alertmanager:
-      enabled: false
-    nodeExporter:
+prometheus:
+  alertmanager:
+    enabled: false
+  nodeExporter:
+    enabled: true
+    tolerations:
+      - operator: "Exists"
+    updateStrategy:
+      type: RollingUpdate
+  pushgateway:
+    enabled: false
+  rbac:
+    create: true
+  server:
+    enabled: true
+    retention: 30d
+    statefulSet: 
       enabled: true
-      tolerations:
-        - operator: "Exists"
-      updateStrategy:
-        type: RollingUpdate
-    pushgateway:
-      enabled: false
-    rbac:
-      create: true
-    server:
+    persistentVolume:
       enabled: true
-      retention: 30d
-      statefulSet: 
-        enabled: true
-      persistentVolume:
-        enabled: true
-      ingress:
-        enabled: false
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 100m
-        memory: 1Gi
-
-  grafana:
-    service:
-      type: LoadBalancer
-      annotations:
-        prometheus.io/scrape: "true"
-        prometheus.io/path: "/metrics"
-    resources:
-      limits:
-        cpu: 500m
-        memory: 1Gi
-      requests:
-        cpu: 100m
-        memory: 256Mi
-    deploymentStrategy:
-      type: Recreate
-    persistence:
-      type: pvc
+    ingress:
       enabled: false
-    dashboardProviders:
-      dashboardproviders.yaml:
-        apiVersion: 1
-        providers:
-          - name: 'default'
-            orgId: 1
-            folder: ''
-            type: file
-            disableDeletion: true
-            editable: true
-            options:
-              path: /var/lib/grafana/dashboards/default
-    dashboards:
-      default:
-        cluster-monitoring-for-kubernetes:
-          gnetId: 10000
-          revision: 1
-          datasource: Prometheus
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 100m
+      memory: 1Gi
+
+grafana:
+  service:
+    annotations:
+      prometheus.io/scrape: "true"
+      prometheus.io/path: "/metrics"
+  resources:
+    limits:
+      cpu: 500m
+      memory: 1Gi
+    requests:
+      cpu: 100m
+      memory: 256Mi
+  deploymentStrategy:
+    type: Recreate
+  persistence:
+    type: pvc
+    enabled: false
+  dashboardProviders:
+    dashboardproviders.yaml:
+      apiVersion: 1
+      providers:
+        - name: 'default'
+          orgId: 1
+          folder: ''
+          type: file
+          disableDeletion: true
+          editable: true
+          options:
+            path: /var/lib/grafana/dashboards/default
+  dashboards:
+    default:
+      cluster-monitoring-for-kubernetes:
+        gnetId: 10000
+        revision: 1
+        datasource: Prometheus
+      dask:
+        gnetId: 12591
+        revision: 2
+        datasource: Prometheus