kepler-prometheus.yaml

apiVersion: v1
kind: Namespace
metadata:
  labels:
    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: Role
metadata:
  labels:
    app.kubernetes.io/component: prometheus
    app.kubernetes.io/instance: k8s
    app.kubernetes.io/name: prometheus
    sustainable-computing.io/app: kepler
  name: prometheus-k8s
  namespace: kepler
rules:
- apiGroups:
  - ""
  resources:
  - services
  - endpoints
  - pods
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - extensions
  resources:
  - ingresses
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - networking.k8s.io
  resources:
  - ingresses
  verbs:
  - get
  - list
  - watch
---
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: RoleBinding
metadata:
  labels:
    app.kubernetes.io/component: prometheus
    app.kubernetes.io/instance: k8s
    app.kubernetes.io/name: prometheus
    sustainable-computing.io/app: kepler
  name: prometheus-k8s
  namespace: kepler
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: prometheus-k8s
subjects:
- kind: ServiceAccount
  name: prometheus-k8s
  namespace: monitoring
---
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"
  EXPOSE_CGROUP_METRICS: "true"
  EXPOSE_HW_COUNTER_METRICS: "true"
  EXPOSE_IRQ_COUNTER_METRICS: "true"
  EXPOSE_KUBELET_METRICS: "true"
  KEPLER_LOG_LEVEL: "1"
  KEPLER_NAMESPACE: kepler
  METRIC_PATH: /metrics
  MODEL_CONFIG: |
    CONTAINER_COMPONENTS_ESTIMATOR=false
    # by default we use buildin weight file
    # CONTAINER_COMPONENTS_INIT_URL=https://raw.githubusercontent.com/sustainable-computing-io/kepler-model-server/main/tests/test_models/DynComponentModelWeight/CgroupOnly/ScikitMixed/ScikitMixed.json
kind: ConfigMap
metadata:
  labels:
    sustainable-computing.io/app: kepler
  name: kepler-cfm
  namespace: kepler
---
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
        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
        - mountPath: /sys
          name: tracing
        - mountPath: /proc
          name: proc
        - mountPath: /etc/kepler/kepler.config
          name: cfm
          readOnly: true
      dnsPolicy: ClusterFirstWithHostNet
      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
      - configMap:
          name: kepler-cfm
        name: cfm
---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    app.kubernetes.io/component: exporter
    app.kubernetes.io/name: kepler-exporter
    sustainable-computing.io/app: kepler
  name: kepler-exporter
  namespace: monitoring
spec:
  endpoints:
  - interval: 3s
    port: http
    relabelings:
    - action: replace
      regex: (.*)
      replacement: $1
      sourceLabels:
      - __meta_kubernetes_pod_node_name
      targetLabel: instance
    scheme: http
  jobLabel: app.kubernetes.io/name
  namespaceSelector:
    matchNames:
    - kepler
  selector:
    matchLabels:
      app.kubernetes.io/component: exporter
      app.kubernetes.io/name: kepler-exporter