install kepler and monitoring tools

simplymathematics · Nov 12, 2023 · 0fbc381 · 0fbc381
1 parent aeacf29
commit 0fbc381
Show file tree

Hide file tree

Showing 97 changed files with 73,343 additions and 0 deletions.
diff --git a/deckard/iaac/gcp/README.md b/deckard/iaac/gcp/README.md
@@ -109,6 +109,14 @@ You can simply take a look at `pod.yaml` file for defining a pod. Just to check,
 kubectl apply -f ./IaaC/gcp/pod.yaml
 ```
 
+## Install Kepler and monitoring tools
+Kepler is the module that collects the power consumption per container/namespace/node and stores them in Prometheus:
+```bash
+kubectl apply --server-side -f ./IaaC/gcp/prometheus/setup
+kubectl apply -f ./IaaC/gcp/prometheus/
+kubectl apply -f ./IaaC/gcp/kepler/deployment.yaml
+```
+
 ## Prepare the access values in the shared volume (optional):
 First of all we need to create a vm by running:
 ```

diff --git a/deckard/iaac/gcp/kepler/deployment.yaml b/deckard/iaac/gcp/kepler/deployment.yaml
@@ -0,0 +1,218 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  labels:
+    pod-security.kubernetes.io/audit: privileged
+    pod-security.kubernetes.io/enforce: privileged
+    pod-security.kubernetes.io/warn: privileged
+    security.openshift.io/scc.podSecurityLabelSync: "false"
+    sustainable-computing.io/app: kepler
+  name: kepler
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: kepler-sa
+  namespace: kepler
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: kepler-clusterrole
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes/metrics
+  - nodes/proxy
+  - nodes/stats
+  - pods
+  verbs:
+  - get
+  - watch
+  - list
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: kepler-clusterrole-binding
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kepler-clusterrole
+subjects:
+- kind: ServiceAccount
+  name: kepler-sa
+  namespace: kepler
+---
+apiVersion: v1
+data:
+  BIND_ADDRESS: 0.0.0.0:9102
+  CGROUP_METRICS: '*'
+  CPU_ARCH_OVERRIDE: ""
+  ENABLE_EBPF_CGROUPID: "true"
+  ENABLE_GPU: "true"
+  ENABLE_PROCESS_METRICS: "false"
+  ENABLE_QAT: "false"
+  EXPOSE_CGROUP_METRICS: "false"
+  EXPOSE_HW_COUNTER_METRICS: "true"
+  EXPOSE_IRQ_COUNTER_METRICS: "true"
+  EXPOSE_KUBELET_METRICS: "false"
+  KEPLER_LOG_LEVEL: "1"
+  KEPLER_NAMESPACE: kepler
+  METRIC_PATH: /metrics
+  MODEL_CONFIG: |
+    CONTAINER_COMPONENTS_ESTIMATOR=false
+  PROMETHEUS_SCRAPE_INTERVAL: 30s
+  REDFISH_PROBE_INTERVAL_IN_SECONDS: "60"
+  REDFISH_SKIP_SSL_VERIFY: "true"
+kind: ConfigMap
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: kepler-cfm
+  namespace: kepler
+---
+apiVersion: v1
+data:
+  redfish.csv: |
+    eW91cl9rdWJlbGV0X25vZGVfbmFtZSxyZWRmaXNoX3VzZXJuYW1lLHJlZGZpc2hfcGFzc3
+    dvcmQsaHR0cHM6Ly9yZWRmaXNoX2lwX29yX2hvc3RuYW1lCg==
+kind: Secret
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: redfish-4kh9d7bc7m
+  namespace: kepler
+type: Opaque
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kepler-exporter
+    sustainable-computing.io/app: kepler
+  name: kepler-exporter
+  namespace: kepler
+spec:
+  clusterIP: None
+  ports:
+  - name: http
+    port: 9102
+    targetPort: http
+  selector:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/name: kepler-exporter
+    sustainable-computing.io/app: kepler
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  labels:
+    sustainable-computing.io/app: kepler
+  name: kepler-exporter
+  namespace: kepler
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: exporter
+      app.kubernetes.io/name: kepler-exporter
+      sustainable-computing.io/app: kepler
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: exporter
+        app.kubernetes.io/name: kepler-exporter
+        sustainable-computing.io/app: kepler
+    spec:
+      containers:
+      - args:
+        - /usr/bin/kepler -v=1 -kernel-source-dir=/usr/share/kepler/kernel_sources
+          -redfish-cred-file-path=/etc/redfish/redfish.csv
+        command:
+        - /bin/sh
+        - -c
+        env:
+        - name: NODE_IP
+          valueFrom:
+            fieldRef:
+              fieldPath: status.hostIP
+        - name: NODE_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: spec.nodeName
+        image: quay.io/sustainable_computing_io/kepler:latest
+        imagePullPolicy: Always
+        livenessProbe:
+          failureThreshold: 5
+          httpGet:
+            path: /healthz
+            port: 9102
+            scheme: HTTP
+          initialDelaySeconds: 10
+          periodSeconds: 60
+          successThreshold: 1
+          timeoutSeconds: 10
+        name: kepler-exporter
+        ports:
+        - containerPort: 9102
+          name: http
+        resources:
+          requests:
+            cpu: 100m
+            memory: 400Mi
+        securityContext:
+          privileged: true
+        volumeMounts:
+        - mountPath: /lib/modules
+          name: lib-modules
+          readOnly: true
+        - mountPath: /sys
+          name: tracing
+          readOnly: true
+        - mountPath: /proc
+          name: proc
+        - mountPath: /var/run
+          name: var-run
+        - mountPath: /etc/kepler/kepler.config
+          name: cfm
+          readOnly: true
+        - mountPath: /etc/redfish
+          name: redfish
+          readOnly: true
+      dnsPolicy: ClusterFirstWithHostNet
+      hostPID: true
+      serviceAccountName: kepler-sa
+      tolerations:
+      - effect: NoSchedule
+        key: node-role.kubernetes.io/master
+      volumes:
+      - hostPath:
+          path: /lib/modules
+          type: Directory
+        name: lib-modules
+      - hostPath:
+          path: /sys
+          type: Directory
+        name: tracing
+      - hostPath:
+          path: /proc
+          type: Directory
+        name: proc
+      - hostPath:
+          path: /var/run
+          type: Directory
+        name: var-run
+      - configMap:
+          name: kepler-cfm
+        name: cfm
+      - name: redfish
+        secret:
+          secretName: redfish-4kh9d7bc7m
diff --git a/deckard/iaac/gcp/prometheus/alertmanager-alertmanager.yaml b/deckard/iaac/gcp/prometheus/alertmanager-alertmanager.yaml
@@ -0,0 +1,37 @@
+apiVersion: monitoring.coreos.com/v1
+kind: Alertmanager
+metadata:
+  labels:
+    app.kubernetes.io/component: alert-router
+    app.kubernetes.io/instance: main
+    app.kubernetes.io/name: alertmanager
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 0.26.0
+  name: main
+  namespace: monitoring
+spec:
+  image: quay.io/prometheus/alertmanager:v0.26.0
+  nodeSelector:
+    kubernetes.io/os: linux
+  podMetadata:
+    labels:
+      app.kubernetes.io/component: alert-router
+      app.kubernetes.io/instance: main
+      app.kubernetes.io/name: alertmanager
+      app.kubernetes.io/part-of: kube-prometheus
+      app.kubernetes.io/version: 0.26.0
+  replicas: 3
+  resources:
+    limits:
+      cpu: 100m
+      memory: 100Mi
+    requests:
+      cpu: 4m
+      memory: 100Mi
+  secrets: []
+  securityContext:
+    fsGroup: 2000
+    runAsNonRoot: true
+    runAsUser: 1000
+  serviceAccountName: alertmanager-main
+  version: 0.26.0
diff --git a/deckard/iaac/gcp/prometheus/alertmanager-networkPolicy.yaml b/deckard/iaac/gcp/prometheus/alertmanager-networkPolicy.yaml
@@ -0,0 +1,42 @@
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  labels:
+    app.kubernetes.io/component: alert-router
+    app.kubernetes.io/instance: main
+    app.kubernetes.io/name: alertmanager
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 0.26.0
+  name: alertmanager-main
+  namespace: monitoring
+spec:
+  egress:
+  - {}
+  ingress:
+  - from:
+    - podSelector:
+        matchLabels:
+          app.kubernetes.io/name: prometheus
+    ports:
+    - port: 9093
+      protocol: TCP
+    - port: 8080
+      protocol: TCP
+  - from:
+    - podSelector:
+        matchLabels:
+          app.kubernetes.io/name: alertmanager
+    ports:
+    - port: 9094
+      protocol: TCP
+    - port: 9094
+      protocol: UDP
+  podSelector:
+    matchLabels:
+      app.kubernetes.io/component: alert-router
+      app.kubernetes.io/instance: main
+      app.kubernetes.io/name: alertmanager
+      app.kubernetes.io/part-of: kube-prometheus
+  policyTypes:
+  - Egress
+  - Ingress
diff --git a/deckard/iaac/gcp/prometheus/alertmanager-podDisruptionBudget.yaml b/deckard/iaac/gcp/prometheus/alertmanager-podDisruptionBudget.yaml
@@ -0,0 +1,19 @@
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  labels:
+    app.kubernetes.io/component: alert-router
+    app.kubernetes.io/instance: main
+    app.kubernetes.io/name: alertmanager
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 0.26.0
+  name: alertmanager-main
+  namespace: monitoring
+spec:
+  maxUnavailable: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: alert-router
+      app.kubernetes.io/instance: main
+      app.kubernetes.io/name: alertmanager
+      app.kubernetes.io/part-of: kube-prometheus