We now produce a working monitoring config

doc/Architecture.md

@@ -14,7 +14,7 @@ C4Context
             Container_Boundary(k3s, "K3S") {
                 Component(lb, "metallb")
                 Component(api, "K8s API")
-                Component(grafana-agent, "Grfana Agent")
+                Component(prometheus, "Prometheus in proxy mode")
                 Container_Boundary(app, "Application") {
                     Component(app, "App-container")
                     Component(app-backup, "backup & restore-container using restic")
@@ -41,8 +41,8 @@ C4Context
     Rel(app, app-file-storage, "file")
     Rel(app, app-db-storage, "*dbc")
 
-    Rel(grafana-agent, api, "http")
+    Rel(prometheus, api, "http")
-    Rel(grafana-agent, grafana, "http")
+    Rel(prometheus, grafana, "http")
 
     Rel(app-backup, backup, "s3")
     Rel(app-backup, app-file-storage, "file")

doc/Monitoring.md

@@ -0,0 +1,23 @@
+# Runtime View
+
+```mermaid
+C4Context
+    title Runtime
+    Enterprise_Boundary(b0, "Infrastructure") {
+        System(grafana, "Grafana Cloud", "Monitoring your apps")
+        
+        Container_Boundary(srv, "Small Server") {
+            Container_Boundary(k3s, "K3S") {
+                Component(api, "K8s API")
+                Container(prometheus, "Prometheus in proxy mode")
+                Container(node-exporter, "Node-Exporter Daemon Set")
+                Container_Boundary(app, "Application") {
+                    Container(app, "App-container")
+                }
+            }
+        }
+    }
+
+    Rel(prometheus, api, "rest")
+    Rel(prometheus, grafana, "rest")
+```

project.clj

@@ -9,6 +9,7 @@
                  [orchestra "2021.01.01-1"]
                  [expound "0.9.0"]
                  [clj-commons/clj-yaml "0.7.108"]]
+  :target-path "target/%s/"
   :source-paths ["src/main/cljc"
                  "src/main/clj"]
   :resource-paths ["src/main/resources"]
@@ -20,10 +21,21 @@
                                  "src/test/cljc"]
                     :resource-paths ["src/test/resources"]
                     :dependencies [[dda/data-test "0.1.1"]]}
-             :dev {:plugins [[lein-shell "0.5.0"]]}}
+             :dev {:plugins [[lein-shell "0.5.0"]]}
+             :uberjar {:aot :all
+                       :main dda.c4k-common.uberjar
+                       :uberjar-name "c4k-common-standalone.jar"
+                       :dependencies [[org.clojure/tools.cli "1.0.206"]
+                                      [ch.qos.logback/logback-classic "1.3.0-alpha4"
+                                       :exclusions [com.sun.mail/javax.mail]]
+                                      [org.slf4j/jcl-over-slf4j "2.0.0-alpha1"]]}}
   :release-tasks [["test"]
                   ["vcs" "assert-committed"]
                   ["change" "version" "leiningen.release/bump-version" "release"]
                   ["vcs" "commit"]
                   ["vcs" "tag" "v" "--no-sign"]
-                  ["change" "version" "leiningen.release/bump-version"]])
+                  ["change" "version" "leiningen.release/bump-version"]]
+  :aliases {"inst" ["shell"
+                    "sh"
+                    "-c"
+                    "lein uberjar && sudo install -m=755 target/uberjar/c4k-common-standalone.jar /usr/local/bin/c4k-common-standalone.jar"]})

src/main/clj/dda/c4k_common/uberjar.clj

@@ -1,9 +1,11 @@
 (ns dda.c4k-common.uberjar
+  (:gen-class)
   (:require
    [clojure.spec.alpha :as s]
    [clojure.string :as cs]
    [clojure.tools.reader.edn :as edn]
    [dda.c4k-common.common :as cm]
+   [dda.c4k-common.core :as core]
    [expound.alpha :as expound]))
 
 (defn usage [name]
@@ -50,3 +52,11 @@
                 (when (not auth-valid?)
                   (println
                    (expound/expound-str auth-spec? auth-edn {:print-specs? false})))))))))))
+
+(defn -main [& cmd-args]
+  (main-common "c4k-common"
+               core/config?
+               core/auth?
+               core/config-defaults
+               core/k8s-objects
+               cmd-args))

src/main/cljc/dda/c4k_common/common.cljc

@@ -44,7 +44,7 @@
                          coll))
 
 (defn-spec replace-all-matching-values-by-new-value cp/map-or-seq?
-  [coll string?
+  [coll cp/map-or-seq?
    value-to-match string?
    value-to-replace string?]
   (clojure.walk/postwalk #(if (and (= (type value-to-match) (type %))
@@ -59,7 +59,7 @@
         (apply concat vs)))
 
 (defn generate-common [my-config my-auth config-defaults k8s-objects]
-  (let [resulting-config (merge config-defaults my-config my-auth)]
+  (let [resulting-config (merge config-defaults my-config)]
     (cs/join
      "\n---\n"
-     (k8s-objects resulting-config))))
+     (k8s-objects resulting-config my-auth))))

src/main/cljc/dda/c4k_common/core.cljc

@@ -0,0 +1,21 @@
+(ns dda.c4k-common.core
+  (:require
+   [clojure.spec.alpha :as s]
+   [dda.c4k-common.yaml :as yaml]
+   [dda.c4k-common.common :as cm]
+   [dda.c4k-common.monitoring :as monitoring]))
+
+(def config-defaults {})
+
+(def config? (s/keys :req-un []
+                     :opt-un []))
+
+(def auth? (s/keys :req-un []
+                   :opt-un []))
+
+(defn k8s-objects [config auth]
+  (let []
+    (map yaml/to-string
+         (filter #(not (nil? %))
+                 (cm/concat-vec
+                  (monitoring/generate config auth))))))

src/main/cljc/dda/c4k_common/monitoring.cljc

@@ -0,0 +1,131 @@
+(ns dda.c4k-common.monitoring
+  (:require
+   [clojure.spec.alpha :as s]
+   #?(:cljs [shadow.resource :as rc])
+   #?(:clj [orchestra.core :refer [defn-spec]]
+      :cljs [orchestra.core :refer-macros [defn-spec]])
+   [dda.c4k-common.yaml :as yaml]
+   [dda.c4k-common.predicate :as cp]
+   [dda.c4k-common.common :as cm]
+   [clojure.string :as str]))
+
+(s/def ::grafana-cloud-user cp/bash-env-string?)
+(s/def ::grafana-cloud-password cp/bash-env-string?)
+(s/def ::grafana-cloud-url cp/fqdn-string?)
+(s/def ::k3s-cluster-name cp/bash-env-string?)
+(s/def ::k3s-cluster-stage cp/stage?)
+(s/def ::pvc-storage-class-name cp/pvc-storage-class-name?)
+(s/def ::node-regex string?)
+(s/def ::traefik-regex string?)
+(s/def ::kube-state-regex string?)
+
+;; TODO: rename to monitoring
+(defn grafana-config? [input]
+  (s/keys :req-un [::grafana-cloud-url ::k3s-cluster-name ::k3s-cluster-stage]))
+
+(defn grafana-auth? [input]
+  (s/keys :req-un [::grafana-cloud-user ::grafana-cloud-password]))
+
+(defn grafana-provider? [input]
+  (s/keys :opt-un [::pvc-storage-class-name]))
+
+(defn filter-regex? [input]
+  (s/keys :req-un [::node-regex ::traefik-regex ::kube-state-regex]))
+
+(def metric-regex {:node-regex
+                   (str "node_cpu_sec.+|node_load[0-9]+|node_memory_Buf.*|node_memory_Mem.*|"
+                        "node_memory_Cached.*|node_disk_[r,w,i].*|node_filesystem_[s,a].*|"
+                        "node_network_receive_bytes_total|node_network_transmit_bytes_total")
+                   :traefik-regex (str "traefik_entrypoint_.*_total|"
+                                       "traefik_entrypoint_.*_seconds_count|"
+                                       "traefik_router_.*_total|"
+                                       "traefik_router_.*_seconds_count|"
+                                       "traefik_service_.*_total|"
+                                       "traefik_service_.*_seconds_count|"
+                                       "traefik_tls_certs_not_after")
+                   :kube-state-regex (str "kube_pod_container_status_restarts_total|"
+                                          "kube_pod_status_reason|kube_node_status_capacity|kube_node_status_allocatable|"
+                                          "kube_cronjob_status_active|kube_job_status_failed")})
+
+(def filter-regex-string
+  (str/join "|" (vals metric-regex)))
+
+#?(:cljs
+   (defmethod yaml/load-resource :monitoring [resource-name]
+     (case resource-name
+       "monitoring/namespace.yaml" (rc/inline "monitoring/namespace.yaml")
+       "monitoring/prometheus/config.yaml" (rc/inline "monitoring/prometheus/config.yaml")
+       "monitoring/prometheus/cluster-role.yaml" (rc/inline "monitoring/prometheus/cluster-role.yaml")
+       "monitoring/prometheus/cluster-role-binding.yaml" (rc/inline "monitoring/prometheus/cluster-role-binding.yaml")
+       "monitoring/prometheus/deployment.yaml" (rc/inline "monitoring/prometheus/deployment.yaml")
+       "monitoring/prometheus/prometheus.yaml" (rc/inline "monitoring/prometheus/prometheus.yaml")
+       "monitoring/prometheus/service.yaml" (rc/inline "monitoring/prometheus/service.yaml")
+       "monitoring/prometheus/service-account.yaml" (rc/inline "monitoring/prometheus/service-account.yaml")   
+       "monitoring/node-exporter/daemon-set.yaml" (rc/inline "monitoring/node-exporter/daemon-set.yaml")
+       "monitoring/node-exporter/service.yaml" (rc/inline "monitoring/node-exporter/service.yaml")
+       "monitoring/node-exporter/cluster-role-binding.yaml" (rc/inline "monitoring/node-exporter/cluster-role-binding.yaml")
+       "monitoring/node-exporter/cluster-role.yaml" (rc/inline "monitoring/node-exporter/cluster-role.yaml")
+       "monitoring/node-exporter/service-account.yaml" (rc/inline "monitoring/node-exporter/service-account.yaml")
+       "monitoring/kube-state-metrics/cluster-role-binding.yaml" (rc/inline "monitoring/kube-state-metrics/cluster-role-binding.yaml")
+       "monitoring/kube-state-metrics/cluster-role.yaml" (rc/inline "monitoring/kube-state-metrics/cluster-role.yaml")
+       "monitoring/kube-state-metrics/deployment.yaml" (rc/inline "monitoring/kube-state-metrics/deployment.yaml")
+       "monitoring/kube-state-metrics/service-account.yaml" (rc/inline "monitoring/kube-state-metrics/service-account.yaml")
+       "monitoring/kube-state-metrics/service.yaml" (rc/inline "monitoring/kube-state-metrics/service.yaml")
+       (throw (js/Error. "Undefined Resource!")))))
+
+(defn-spec generate-stateful-set cp/map-or-seq?
+  [config grafana-provider?]
+  (let [{:keys [pvc-storage-class-name]
+         :or {pvc-storage-class-name :manual}} config]
+    (->
+     (yaml/from-string (yaml/load-resource "monitoring/stateful-set.yaml"))
+     (assoc-in [:spec :volumeClaimTemplates 0 :spec :storageClassName] (name pvc-storage-class-name)))))
+
+(defn-spec generate-prometheus-config cp/map-or-seq?
+  [config grafana-config?
+   auth grafana-auth?]
+  (let [{:keys [grafana-cloud-url k3s-cluster-name k3s-cluster-stage]} config
+        {:keys [grafana-cloud-user grafana-cloud-password]} auth]
+    (->
+     (yaml/from-string (yaml/load-resource "monitoring/prometheus/prometheus.yaml"))
+     (assoc-in [:global :external_labels :cluster]
+               k3s-cluster-name)
+     (assoc-in [:global :external_labels :stage]
+               k3s-cluster-stage)
+     (assoc-in [:remote_write 0 :url]
+               grafana-cloud-url)
+     (assoc-in [:remote_write 0 :basic_auth :username]
+               grafana-cloud-user)
+     (assoc-in [:remote_write 0 :basic_auth :password]
+               grafana-cloud-password)
+     (cm/replace-all-matching-values-by-new-value "FILTER_REGEX" filter-regex-string))))
+
+(defn-spec generate-config cp/map-or-seq?
+  [config grafana-config?
+   auth grafana-auth?]
+  (->
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/config.yaml"))
+   (assoc-in [:stringData :prometheus.yaml]
+             (yaml/to-string
+              (generate-prometheus-config config auth)))))
+
+(defn-spec generate cp/map-or-seq?
+  [config grafana-config?
+   auth grafana-auth?]
+  [(yaml/from-string (yaml/load-resource "monitoring/namespace.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/cluster-role.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/cluster-role-binding.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/service.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/service-account.yaml"))
+   (generate-config config auth)
+   (yaml/from-string (yaml/load-resource "monitoring/prometheus/deployment.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/node-exporter/service-account.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/node-exporter/cluster-role.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/node-exporter/cluster-role-binding.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/node-exporter/daemon-set.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/node-exporter/service.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/kube-state-metrics/cluster-role-binding.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/kube-state-metrics/cluster-role.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/kube-state-metrics/deployment.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/kube-state-metrics/service-account.yaml"))
+   (yaml/from-string (yaml/load-resource "monitoring/kube-state-metrics/service.yaml"))])

src/main/cljc/dda/c4k_common/predicate.cljc

@@ -22,6 +22,10 @@
   [input]
   (contains? #{"prod" "staging"} input))
 
+(defn stage?
+  [input]
+  (contains? #{:prod :acc :int :test :dev} input))
+
 (defn map-or-seq?
   [input]
   (or (map? input) (seq? input)))

src/main/resources/monitoring/kube-state-metrics/cluster-role-binding.yaml

@@ -0,0 +1,17 @@
+# from https://github.com/kubernetes/kube-state-metrics/tree/main/examples/standard
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: 2.7.0
+  name: kube-state-metrics
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kube-state-metrics
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: monitoring

src/main/resources/monitoring/kube-state-metrics/cluster-role.yaml

@@ -0,0 +1,128 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: 2.7.0
+  name: kube-state-metrics
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - configmaps
+  - secrets
+  - nodes
+  - pods
+  - services
+  - serviceaccounts
+  - resourcequotas
+  - replicationcontrollers
+  - limitranges
+  - persistentvolumeclaims
+  - persistentvolumes
+  - namespaces
+  - endpoints
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - apps
+  resources:
+  - statefulsets
+  - daemonsets
+  - deployments
+  - replicasets
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - batch
+  resources:
+  - cronjobs
+  - jobs
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - autoscaling
+  resources:
+  - horizontalpodautoscalers
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - authentication.k8s.io
+  resources:
+  - tokenreviews
+  verbs:
+  - create
+- apiGroups:
+  - authorization.k8s.io
+  resources:
+  - subjectaccessreviews
+  verbs:
+  - create
+- apiGroups:
+  - policy
+  resources:
+  - poddisruptionbudgets
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - certificates.k8s.io
+  resources:
+  - certificatesigningrequests
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - discovery.k8s.io
+  resources:
+  - endpointslices
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - storage.k8s.io
+  resources:
+  - storageclasses
+  - volumeattachments
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - admissionregistration.k8s.io
+  resources:
+  - mutatingwebhookconfigurations
+  - validatingwebhookconfigurations
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - networking.k8s.io
+  resources:
+  - networkpolicies
+  - ingressclasses
+  - ingresses
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - coordination.k8s.io
+  resources:
+  - leases
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - rbac.authorization.k8s.io
+  resources:
+  - clusterrolebindings
+  - clusterroles
+  - rolebindings
+  - roles
+  verbs:
+  - list
+  - watch

src/main/resources/monitoring/kube-state-metrics/deployment.yaml

@@ -0,0 +1,53 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: 2.7.0
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: kube-state-metrics
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: exporter
+        app.kubernetes.io/name: kube-state-metrics
+        app.kubernetes.io/version: 2.7.0
+    spec:
+      serviceAccountName: kube-state-metrics
+      automountServiceAccountToken: true
+      containers:
+      - name: kube-state-metrics
+        image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.7.0
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5        
+        ports:
+        - containerPort: 8080
+          name: http-metrics
+        - containerPort: 8081
+          name: telemetry
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 8081
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+            - ALL
+          readOnlyRootFilesystem: true
+          runAsUser: 65534
+      nodeSelector:
+        kubernetes.io/os: linux
+      

src/main/resources/monitoring/kube-state-metrics/service-account.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+automountServiceAccountToken: false
+kind: ServiceAccount
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: 2.7.0
+  name: kube-state-metrics
+  namespace: monitoring

src/main/resources/monitoring/kube-state-metrics/service.yaml

@@ -0,0 +1,20 @@
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: 2.7.0
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  clusterIP: None
+  ports:
+  - name: http-metrics
+    port: 8080
+    targetPort: http-metrics
+  - name: telemetry
+    port: 8081
+    targetPort: telemetry
+  selector:
+    app.kubernetes.io/name: kube-state-metrics

src/main/resources/monitoring/namespace.yaml

@@ -0,0 +1,6 @@
+kind: Namespace
+apiVersion: v1
+metadata:
+  name: monitoring
+  labels:
+    name: monitoring

src/main/resources/monitoring/node-exporter/cluster-role-binding.yaml

@@ -0,0 +1,14 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    name: node-exporter
+  name: node-exporter
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: node-exporter
+subjects:
+- kind: ServiceAccount
+  name: node-exporter
+  namespace: monitoring

src/main/resources/monitoring/node-exporter/cluster-role.yaml

@@ -0,0 +1,45 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    name: node-exporter
+  name: node-exporter
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes
+  - nodes/proxy
+  - nodes/metrics
+  - services
+  - endpoints
+  - pods
+  - ingresses
+  - configmaps
+  - events
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - "extensions"
+  - "networking.k8s.io"
+  resources:
+  - ingresses/status
+  - ingresses
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - extensions
+  resources:
+  - podsecuritypolicies
+  verbs:     
+  - use
+  resourceNames: 
+  - node-exporter
+- nonResourceURLs:
+  - /metrics
+  verbs:
+  - get

src/main/resources/monitoring/node-exporter/daemon-set.yaml

@@ -0,0 +1,71 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  labels:
+    app.kubernetes.io/name: node-exporter
+  name: node-exporter
+  namespace: monitoring
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: node-exporter
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: node-exporter
+    spec:
+      serviceAccountName: node-exporter
+      containers:
+      - name: node-exporter
+        image: prom/node-exporter
+        imagePullPolicy: "IfNotPresent"
+        args:
+          - --path.sysfs=/host/sys
+          - --path.rootfs=/host/root
+          - --no-collector.conntrack
+          - --no-collector.wifi
+          - --no-collector.hwmon
+          - --no-collector.infiniband
+          - --no-collector.filefd
+          - --no-collector.mdadm
+          - --no-collector.netclass
+          - --no-collector.nfs
+          - --no-collector.nfsd
+          - --no-collector.powersupplyclass
+          - --no-collector.pressure
+          - --no-collector.rapl
+          - --no-collector.schedstat
+          - --no-collector.sockstat
+          - --no-collector.softnet
+          - --no-collector.tapestats
+          - --no-collector.thermal_zone
+          - --no-collector.xfs
+          - --no-collector.zfs
+          - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
+          - --collector.netclass.ignored-devices=^(veth.*)$
+        ports:
+          - containerPort: 9100
+            protocol: TCP
+        resources:
+          limits:
+            cpu: 250m
+            memory: 180Mi
+          requests:
+            cpu: 102m
+            memory: 180Mi
+        volumeMounts:
+        - mountPath: /host/sys
+          mountPropagation: HostToContainer
+          name: sys
+          readOnly: true
+        - mountPath: /host/root
+          mountPropagation: HostToContainer
+          name: root
+          readOnly: true
+      volumes:
+      - hostPath:
+          path: /sys
+        name: sys
+      - hostPath:
+          path: /
+        name: root

src/main/resources/monitoring/node-exporter/service-account.yaml

@@ -0,0 +1,7 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    name: node-exporter
+  name: node-exporter
+  namespace: monitoring

src/main/resources/monitoring/node-exporter/service.yaml

@@ -0,0 +1,18 @@
+kind: Service
+apiVersion: v1
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: node-exporter
+  annotations:
+      prometheus.io/scrape: 'true'
+      prometheus.io/port:   '9100'
+spec:
+  selector:
+      app.kubernetes.io/name: node-exporter
+  ports:
+  - name: node-exporter-http
+    protocol: TCP
+    port: 9100
+    targetPort: 9100

src/main/resources/monitoring/prometheus/cluster-role-binding.yaml

@@ -0,0 +1,14 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    name: prometheus
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+- kind: ServiceAccount
+  name: prometheus
+  namespace: monitoring

src/main/resources/monitoring/prometheus/cluster-role.yaml

@@ -0,0 +1,37 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    name: prometheus
+  name: prometheus
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes
+  - nodes/proxy
+  - nodes/metrics
+  - services
+  - endpoints
+  - pods
+  - ingresses
+  - configmaps
+  - events
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - "extensions"
+  - "networking.k8s.io"
+  resources:
+  - ingresses/status
+  - ingresses
+  verbs:
+  - get
+  - list
+  - watch
+- nonResourceURLs:
+  - /metrics
+  verbs:
+  - get

src/main/resources/monitoring/prometheus/config.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: prometheus-conf
+  namespace: monitoring
+type: Opaque
+stringData:
+  prometheus.yaml: FILECONTENT

src/main/resources/monitoring/prometheus/deployment.yaml

@@ -0,0 +1,42 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app.kubernetes.io/name: prometheus
+  name: prometheus
+  namespace: monitoring
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: prometheus
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: prometheus
+    spec:
+      serviceAccountName: prometheus
+      enableServiceLinks: true
+      containers:
+        - name: prometheus
+          image: "quay.io/prometheus/prometheus:v2.39.1"
+          imagePullPolicy: "IfNotPresent"
+          args:
+            - --config.file=/etc/prometheus/prometheus.yaml
+            - --storage.tsdb.path=/prometheus/
+            - --storage.tsdb.retention.time=1d
+          ports:
+            - containerPort: 9090
+          volumeMounts:
+            - name: prometheus-config-volume
+              mountPath: /etc/prometheus/
+              readOnly: true
+            - name: prometheus-storage-volume
+              mountPath: /prometheus/
+      volumes:
+        - name: prometheus-config-volume
+          secret:
+            secretName: prometheus-conf
+            defaultMode: 420
+        - name: prometheus-storage-volume
+          emptyDir: {}

src/main/resources/monitoring/prometheus/prometheus.yaml

@@ -0,0 +1,64 @@
+global:
+  scrape_interval: 60s
+  evaluation_interval: 60s
+  external_labels:
+    cluster: $CLUSTERNAME
+    stage: $TEST_OR_PROD
+remote_write:
+  - url: GRAFANA_CLOUD_URL
+    basic_auth:
+      username: GRAFANA_CLOUD_USER
+      password: GRAFANA_CLOUD_PASSWORD
+    write_relabel_configs:
+    - source_labels:
+      - __name__
+      regex: FILTER_REGEX
+      action: keep
+rule_files:
+  - /etc/prometheus/prometheus.rules
+scrape_configs:
+
+  - job_name: 'kubernetes-nodes'
+    kubernetes_sd_configs:
+    - role: node
+    scheme: https
+    tls_config:
+      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+    relabel_configs:
+    - action: labelmap
+      regex: __meta_kubernetes_node_label_(.+)
+    - target_label: __address__
+      replacement: kubernetes.default.svc:443
+    - source_labels: [__meta_kubernetes_node_name]
+      regex: (.+)
+      target_label: __metrics_path__
+      replacement: /api/v1/nodes/${1}/proxy/metrics
+
+  - job_name: 'node-exporter'
+    kubernetes_sd_configs:
+      - role: endpoints
+    relabel_configs:
+    - source_labels: [__meta_kubernetes_endpoints_name]
+      regex: 'node-exporter'
+      action: keep
+
+  - job_name: 'traefik'
+    kubernetes_sd_configs:
+      - role: endpoints
+    relabel_configs:
+    - source_labels: [__meta_kubernetes_endpoints_name]
+      regex: 'traefik'
+      action: keep
+
+  - job_name: 'kube-state-metrics'
+    kubernetes_sd_configs:
+      - role: endpoints
+    relabel_configs:
+    - source_labels: [__meta_kubernetes_endpoints_name]
+      regex: 'kube-state-metrics'
+      action: keep
+
+  - job_name: "prometheus"
+    static_configs:
+      - targets: ["localhost:9090"]

src/main/resources/monitoring/prometheus/service-account.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: ServiceAccount
+automountServiceAccountToken: true
+metadata:
+  labels:
+    name: prometheus
+  name: prometheus
+  namespace: monitoring

src/main/resources/monitoring/prometheus/service.yaml

@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: prometheus
+  annotations:
+    metallb.universe.tf/address-pool: private
+spec:
+  type: LoadBalancer
+  selector:
+    app.kubernetes.io/name: prometheus
+  ports:
+  - name: prometheus-http
+    protocol: TCP
+    port: 9000
+    targetPort: 9090

src/test/clj/dda/c4k_common/common_spec_test.cljc

@@ -0,0 +1,16 @@
+(ns dda.c4k-common.common-spec-test
+  (:require
+   #?(:clj [clojure.test :refer [deftest is are testing run-tests]]
+      :cljs [cljs.test :refer-macros [deftest is are testing run-tests]])
+   [clojure.spec.test.alpha :as st]
+   [dda.c4k-common.common :as cut]))
+
+(deftest should-refuse-illegal-inputs
+  (is (thrown? Exception
+               (cut/concat-vec ["a1" "a2"] "b1")))
+  (is (thrown? Exception
+               (cut/concat-vec ["a1" "a2"] nil)))
+  (is (thrown? Exception
+               (cut/concat-vec ["a1" "a2"] 2)))
+  (is (thrown? Exception
+               (cut/concat-vec {"a1" "a2"} []))))

src/test/clj/dda/c4k_common/monitoring_regex_test.clj

@@ -0,0 +1,24 @@
+(ns dda.c4k-common.monitoring-regex-test
+  (:require
+   [clojure.test :refer [deftest is are testing run-tests]]
+   [data-test :refer :all]
+   [dda.c4k-common.monitoring :as cut]))
+
+(defn filter-by-regex
+  [regex-str collection]
+  (filterv #(re-matches (re-pattern regex-str) %)
+           collection))
+
+(defdatatest should-filter-metrik [input expected]
+  (is (= (:node-metrics expected)
+         (filter-by-regex
+          (:node-regex cut/metric-regex)
+          (into (:node-metrics expected) (:additional-node-metrics input)))))
+  (is (= (:traefik-metrics expected)
+         (filter-by-regex
+          (:traefik-regex cut/metric-regex)
+          (into (:traefik-metrics expected) (:additional-traefik-metrics input)))))
+  (is (= (:kube-state-metrics expected)
+         (filter-by-regex
+          (:kube-state-regex cut/metric-regex)
+          (into (:kube-state-metrics expected) (:additional-kube-state-metrics input))))))

src/test/cljc/dda/c4k_common/monitoring_test.cljc

@@ -0,0 +1,47 @@
+(ns dda.c4k-common.monitoring-test
+  (:require
+   #?(:clj [clojure.test :refer [deftest is are testing run-tests]]
+      :cljs [cljs.test :refer-macros [deftest is are testing run-tests]])
+   [clojure.string :as s]
+   [clojure.spec.test.alpha :as st]
+   [dda.c4k-common.monitoring :as cut]
+   [dda.c4k-common.yaml :as yaml]
+   [clojure.string :as str]))
+
+(st/instrument `cut/generate)
+(st/instrument `cut/generate-stateful-set)
+(st/instrument `cut/generate-agent-config)
+(st/instrument `cut/generate-config)
+
+(def conf {:k3s-cluster-name "clustername"
+           :k3s-cluster-stage :test
+           :grafana-cloud-url "url"})
+
+(def auth {:grafana-cloud-user "user"
+           :grafana-cloud-password "password"
+           :hetzner-cloud-ro-token "ro-token"})
+
+(deftest should-generate
+  (is (= 17
+         (count (cut/generate conf auth)))))
+
+(deftest should-generate-prometheus-remote-write-auth
+  (is (= {:username "user",
+          :password "password"}
+         (get-in
+          (cut/generate-prometheus-config conf auth)
+          [:remote_write 0 :basic_auth]))))
+
+(deftest should-generate-prometheus-external-labels
+  (is (= {:cluster "clustername",
+          :stage :test}
+         (get-in
+          (cut/generate-prometheus-config conf auth)
+          [:global :external_labels]))))
+
+(deftest should-generate-config
+  (is (s/starts-with?
+       (get-in
+        (cut/generate-config conf auth)
+        [:stringData :prometheus.yaml])
+       "global:\n  scrape_interval:")))

src/test/resources/dda/c4k_common/monitoring_regex_test/should_filter_metrik.edn

@@ -0,0 +1,19 @@
+{:input {:additional-node-metrics ["go_gc_duration_seconds"]
+         :additional-traefik-metrics ["traefik_config_reloads_total"]
+         :additional-kube-state-metrics ["kube_persistentvolume_annotations"]}
+:expected
+{:node-metrics
+ ["node_cpu_seconds_total" "node_load1" "node_load5" "node_load15" "node_memory_MemTotal_bytes" 
+  "node_memory_MemFree_bytes" "node_memory_Buffers_bytes" "node_memory_Cached_bytes"
+  "node_disk_read_bytes_total" "node_disk_written_bytes_total" "node_disk_io_time_seconds_total" 
+  "node_filesystem_size_bytes" "node_filesystem_avail_bytes" "node_network_receive_bytes_total" 
+  "node_network_transmit_bytes_total"]
+ :traefik-metrics
+ ["traefik_entrypoint_requests_total" "traefik_entrypoint_requests_duration_seconds_count" 
+  "traefik_entrypoint_requests_tls_total" "traefik_router_requests_total" 
+  "traefik_router_requests_tls_total"
+  "traefik_service_requests_total" "traefik_service_requests_duration_seconds_count" 
+  "traefik_service_requests_tls_total" "traefik_tls_certs_not_after"]
+ :kube-state-metrics 
+ ["kube_pod_container_status_restarts_total" "kube_pod_status_reason" "kube_node_status_allocatable" 
+  "kube_node_status_capacity" "kube_cronjob_status_active" "kube_job_status_failed"]}}

src/test/resources/metrics_list.txt

@@ -0,0 +1,30 @@
+node_cpu_seconds_total
+node_load1
+node_load5
+node_load15
+node_memory_MemTotal_bytes
+node_memory_MemFree_bytes
+node_memory_Buffers_bytes
+node_memory_Cached_bytes
+node_disk_read_bytes_total
+node_disk_written_bytes_total
+node_disk_io_time_seconds_total
+node_filesystem_size_bytes
+node_filesystem_avail_bytes
+node_network_receive_bytes_total
+node_network_transmit_bytes_total
+traefik_entrypoint_requests_total
+traefik_entrypoint_requests_duration_seconds_count
+traefik_entrypoint_requests_tls_total
+traefik_router_requests_total
+traefik_router_requests_tls_total
+traefik_service_requests_total
+traefik_service_requests_duration_seconds_count
+traefik_service_requests_tls_total
+traefik_tls_certs_not_after
+kube_pod_container_status_restarts_total
+kube_pod_status_reason
+kube_node_status_allocatable
+kube_node_status_capacity
+kube_cronjob_status_active
+kube_job_status_failed