refactor(monitoring): do not monitor cluster components

README.md

@@ -6,11 +6,28 @@ Underlying Kubernetes cluster components for [KISSJ](https://github.com/skautdev
 
 - namespaces
   - `kissj-db`
+  - `kissj-dev`
   - `kissj-prod`
   - `kissj-staging`
+  - `kissj-monitoring`
 - PostgreSQL instance
+- monitoring
+  - Prometheus
+  - AlertManager
+  - Grafana
+  - blackbox exporter
 
 ## Security
 
 - Users
-- ServiceAccounts
+  - lung
+  - majkl
+
+## Monitoring
+
+As mentione before in [components](#components), the monitoring consists of:
+- [Prometheus](https://prometheus.monitoring.kissj.net)
+- [AlertManager](https://alertmanager.monitoring.kissj.net)
+- [Grafana](https://grafana.monitoring.kissj.net)
+
+To monitor everything, we also deploy [prometheus/blackbox_exporter](https://github.com/prometheus/blackbox_exporter) to monitor the overall availability of the site.

_apps/kissj-production-quotas.yml

@@ -0,0 +1,18 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: kissj-production-quotas
+  namespace: argocd
+spec:
+  destination:
+    namespace: kissj-production
+    server: https://kubernetes.default.svc
+  project: kissj
+  source:
+    path: quotas/production
+    repoURL: https://gitlab.mareshq.com/gitops/skautdevs/kissj.git
+    targetRevision: HEAD
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true

_apps/kissj-staging-quotas.yml

@@ -0,0 +1,18 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: kissj-staging-quotas
+  namespace: argocd
+spec:
+  destination:
+    namespace: kissj-staging
+    server: https://kubernetes.default.svc
+  project: kissj
+  source:
+    path: quotas/staging
+    repoURL: https://gitlab.mareshq.com/gitops/skautdevs/kissj.git
+    targetRevision: HEAD
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true

monitoring/Chart.lock

@@ -2,5 +2,8 @@ dependencies:
 - name: kube-prometheus-stack
   repository: https://prometheus-community.github.io/helm-charts
   version: 39.11.0
-digest: sha256:2000f95ea7c9e6ac6ec0cc0ed3f08ee6adebf5e3ad383a0e8d89d80ab61439eb
-generated: "2022-09-03T10:54:33.34106+02:00"
+- name: prometheus-blackbox-exporter
+  repository: https://prometheus-community.github.io/helm-charts
+  version: 7.0.0
+digest: sha256:7a9382529ff259e31426aa23cf9eea9a0dc5fe7d6950339133bc78bcb310fa30
+generated: "2022-09-03T16:06:15.239791+02:00"

monitoring/Chart.yaml

@@ -9,3 +9,6 @@ dependencies:
 - name: kube-prometheus-stack
   version: 39.11.0
   repository: https://prometheus-community.github.io/helm-charts
+- name: prometheus-blackbox-exporter
+  version: 7.0.0
+  repository: https://prometheus-community.github.io/helm-charts

monitoring/values.yaml

@@ -13,6 +13,27 @@ kube-prometheus-stack:
   kubeStateMetrics:
     enabled: false
 
+  kubeApiServer:
+    enabled: false
+
+  kubelet:
+    enabled: false
+
+  kubeControllerManager:
+    enabled: false
+
+  coreDns:
+    enabled: false
+
+  kubeScheduler:
+    enabled: false
+
+  kubeProxy:
+    enabled: false
+
+  defaultRules:
+    create: false
+
   prometheus:
     prometheusSpec:
       serviceMonitorSelectorNilUsesHelmValues: false
@@ -96,34 +117,5 @@ kube-prometheus-stack:
     serviceMonitor:
       selfMonitor: true
 
-    # This AM is for KISSJ, cluster components are monitored by different instance
-    kubeApiServer:
-      enabled: false
-
-    kubelet:
-      enabled: false
-
-    kubeControllerManager:
-      enabled: false
-
-    coreDns:
-      enabled: false
-
-    kubeScheduler:
-      enabled: false
-
-    kubeProxy:
-      enabled: false
-
-    kubeStateMetrics:
-      enabled: false
-
-    nodeExporter:
-      enabled: false
-
-    prometheusOperator:
-      serviceMonitor:
-        selfMonitor: false
-
-    defaultRules:
-      create: false
+prometheus-blackbox-exporter:
+  fullnameOverride: kissj-blackbox-exporter

namespaces/kissj-prod.yml

@@ -1,6 +0,0 @@
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: kissj-prod
-  labels:
-    prometheus: kissj

namespaces/kissj-production.yml

@@ -1,6 +1,6 @@
 apiVersion: v1
 kind: Namespace
 metadata:
-  name: kissj-dev
+  name: kissj-production
   labels:
     prometheus: kissj

quotas/production/compute-resources.yml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: compute-resources
+spec:
+  hard:
+    requests.cpu: 6000m
+    requests.memory: 16384Mi
+    limits.cpu: 8000m
+    limits.memory: 20480Mi

quotas/production/kube-objects.yml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: kube-objects
+spec:
+  hard:
+    count/deployments.apps: "5"
+    count/statefulsets.apps: "0"
+    count/cronjobs.batch: "0"
+    count/jobs.batch: "5"
+    count/pods: "50"
+
+    count/persistentvolumeclaims: "1"

quotas/production/network.yml

@@ -0,0 +1,9 @@
+
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: network
+spec:
+  hard:
+    services.loadbalancers: "0"
+    services.nodeports: "0"

quotas/production/storage.yml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: storage
+spec:
+  hard:
+    requests.storage: 1Gi
+    persistentvolumeclaims: "3"
+    local-path.storageclass.storage.k8s.io/requests.storage: 0Mi
+    local-path.storageclass.storage.k8s.io/persistentvolumeclaims: "0"

quotas/staging/compute-resources.yml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: compute-resources
+spec:
+  hard:
+    requests.cpu: 800m
+    requests.memory: 1536Mi
+    limits.cpu: 1200m
+    limits.memory: 2048Mi

quotas/staging/kube-objects.yml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: kube-objects
+spec:
+  hard:
+    count/deployments.apps: "5"
+    count/statefulsets.apps: "0"
+    count/cronjobs.batch: "0"
+    count/jobs.batch: "5"
+    count/pods: "20"
+
+    count/persistentvolumeclaims: "1"

quotas/staging/network.yml

@@ -0,0 +1,9 @@
+
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: network
+spec:
+  hard:
+    services.loadbalancers: "0"
+    services.nodeports: "0"

quotas/staging/storage.yml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: storage
+spec:
+  hard:
+    requests.storage: 1Gi
+    persistentvolumeclaims: "3"
+    local-path.storageclass.storage.k8s.io/requests.storage: 0Mi
+    local-path.storageclass.storage.k8s.io/persistentvolumeclaims: "0"