Prometheus+grafana监控 k8s集群

# docker pull prom/node-exporter

# docker pull prom/prometheus:v2.0.0

# docker pull grafana/grafana:4.2.0

# mkdir k8s-prometheus

# cd k8s-prometheus

# cat node-exporter.yaml

---

apiVersion: apps/v1

kind: DaemonSet

metadata:

name: node-exporter

namespace: kube-system

labels:

k8s-app: node-exporter

spec:

selector:

matchLabels:

k8s-app: node-exporter

template:

metadata:

labels:

k8s-app: node-exporter

spec:

containers:

- image: prom/node-exporter

name: node-exporter

ports:

- containerPort: 9100

protocol: TCP

name: http

---

apiVersion: v1

kind: Service

metadata:

labels:

k8s-app: node-exporter

name: node-exporter

namespace: kube-system

spec:

ports:

- name: http

port: 9100

nodePort: 31672

protocol: TCP

type: NodePort

selector:

k8s-app: node-exporter

# kubectl apply -f node-exporter.yaml

# cat rbac-setup.yaml

apiVersion: rbac.authorization.k8s.io/v1

kind: ClusterRole

metadata:

name: prometheus

rules:

- apiGroups: [""]

resources:

- nodes

- nodes/proxy

- services

- endpoints

- pods

verbs: ["get", "list", "watch"]

- apiGroups:

- extensions

resources:

- ingresses

verbs: ["get", "list", "watch"]

- nonResourceURLs: ["/metrics"]

verbs: ["get"]

---

apiVersion: v1

kind: ServiceAccount

metadata:

name: prometheus

namespace: kube-system

---

apiVersion: rbac.authorization.k8s.io/v1

kind: ClusterRoleBinding

metadata:

name: prometheus

roleRef:

apiGroup: rbac.authorization.k8s.io

kind: ClusterRole

name: prometheus

subjects:

- kind: ServiceAccount

name: prometheus

namespace: kube-system

# kubectl apply -f rbac-setup.yaml

# cat configmap.yaml

apiVersion: v1

kind: ConfigMap

metadata:

name: prometheus-config

namespace: kube-system

data:

prometheus.yml: |

global:

scrape_interval: 15s

evaluation_interval: 15s

scrape_configs:

- job_name: 'kubernetes-apiservers'

kubernetes_sd_configs:

- role: endpoints

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:

- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]

action: keep

regex: default;kubernetes;https

- 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: 'kubernetes-cadvisor'

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/cadvisor

- job_name: 'kubernetes-service-endpoints'

kubernetes_sd_configs:

- role: endpoints

relabel_configs:

- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]

action: keep

regex: true

- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]

action: replace

target_label: __scheme__

regex: (https?)

- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]

action: replace

target_label: __metrics_path__

regex: (.+)

- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]

action: replace

target_label: __address__

regex: ([^:]+)(?::\d+)?;(\d+)

replacement: $1:$2

- action: labelmap

regex: __meta_kubernetes_service_label_(.+)

- source_labels: [__meta_kubernetes_namespace]

action: replace

target_label: kubernetes_namespace

- source_labels: [__meta_kubernetes_service_name]

action: replace

target_label: kubernetes_name

- job_name: 'kubernetes-services'

kubernetes_sd_configs:

- role: service

metrics_path: /probe

params:

module: [http_2xx]

relabel_configs:

- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]

action: keep

regex: true

- source_labels: [__address__]

target_label: __param_target

- target_label: __address__

replacement: blackbox-exporter.example.com:9115

- source_labels: [__param_target]

target_label: instance

- action: labelmap

regex: __meta_kubernetes_service_label_(.+)

- source_labels: [__meta_kubernetes_namespace]

target_label: kubernetes_namespace

- source_labels: [__meta_kubernetes_service_name]

target_label: kubernetes_name

- job_name: 'kubernetes-ingresses'

kubernetes_sd_configs:

- role: ingress

relabel_configs:

- source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]

action: keep

regex: true

- source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]

regex: (.+);(.+);(.+)

replacement: ${1}://${2}${3}

target_label: __param_target

- target_label: __address__

replacement: blackbox-exporter.example.com:9115

- source_labels: [__param_target]

target_label: instance

- action: labelmap

regex: __meta_kubernetes_ingress_label_(.+)

- source_labels: [__meta_kubernetes_namespace]

target_label: kubernetes_namespace

- source_labels: [__meta_kubernetes_ingress_name]

target_label: kubernetes_name

- job_name: 'kubernetes-pods'

kubernetes_sd_configs:

- role: pod

relabel_configs:

- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]

action: keep

regex: true

- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]

action: replace

target_label: __metrics_path__

regex: (.+)

- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]

action: replace

regex: ([^:]+)(?::\d+)?;(\d+)

replacement: $1:$2

target_label: __address__

- action: labelmap

regex: __meta_kubernetes_pod_label_(.+)

- source_labels: [__meta_kubernetes_namespace]

action: replace

target_label: kubernetes_namespace

- source_labels: [__meta_kubernetes_pod_name]

action: replace

target_label: kubernetes_pod_name

# kubectl apply -f configmap.yaml

# cat prometheus.deploy.yml

---

apiVersion: apps/v1

kind: Deployment

metadata:

labels:

name: prometheus-deployment

name: prometheus

namespace: kube-system

spec:

replicas: 1

selector:

matchLabels:

app: prometheus

template:

metadata:

labels:

app: prometheus

spec:

containers:

- image: prom/prometheus:v2.0.0

name: prometheus

command:

- "/bin/prometheus"

args:

- "--config.file=/etc/prometheus/prometheus.yml"

- "--storage.tsdb.path=/prometheus"

- "--storage.tsdb.retention=24h"

ports:

- containerPort: 9090

protocol: TCP

volumeMounts:

- mountPath: "/prometheus"

name: data

- mountPath: "/etc/prometheus"

name: config-volume

resources:

requests:

cpu: 100m

memory: 100Mi

limits:

cpu: 500m

memory: 2500Mi

serviceAccountName: prometheus

volumes:

- name: data

emptyDir: {}

- name: config-volume

configMap:

name: prometheus-config

# kubectl apply -f prometheus.deploy.yml

# cat prometheus.svc.yml

---

kind: Service

apiVersion: v1

metadata:

labels:

app: prometheus

name: prometheus

namespace: kube-system

spec:

type: NodePort

ports:

- port: 9090

targetPort: 9090

nodePort: 30003

selector:

app: prometheus

#kubectl apply -f prometheus.svc.yml

# mkdir ../grafana

# cd ../grafana

# cat grafana-deploy.yaml

apiVersion: apps/v1

kind: Deployment

metadata:

name: grafana-core

namespace: kube-system

labels:

app: grafana

component: core

spec:

replicas: 1

selector:

matchLabels:

app: grafana

template:

metadata:

labels:

app: grafana

component: core

spec:

containers:

- image: grafana/grafana:4.2.0

name: grafana-core

imagePullPolicy: IfNotPresent

# env:

resources:

# keep request = limit to keep this container in guaranteed class

limits:

cpu: 100m

memory: 100Mi

requests:

cpu: 100m

memory: 100Mi

env:

# The following env variables set up basic auth twith the default admin user and admin password.

- name: GF_AUTH_BASIC_ENABLED

value: "true"

- name: GF_AUTH_ANONYMOUS_ENABLED

value: "false"

# - name: GF_AUTH_ANONYMOUS_ORG_ROLE

# value: Admin

# does not really work, because of template variables in exported dashboards:

# - name: GF_DASHBOARDS_JSON_ENABLED

# value: "true"

readinessProbe:

httpGet:

path: /login

port: 3000

# initialDelaySeconds: 30

# timeoutSeconds: 1

volumeMounts:

- name: grafana-persistent-storage

mountPath: /var

volumes:

- name: grafana-persistent-storage

emptyDir: {}

# kubectl apply -f grafana-deploy.yaml

# cat grafana-svc.yaml

apiVersion: v1

kind: Service

metadata:

name: grafana

namespace: kube-system

labels:

app: grafana

component: core

spec:

type: NodePort

ports:

- port: 3000

selector:

app: grafana

component: core

# kubectl apply -f grafana-svc.yaml

# cat grafana-ing.yaml

apiVersion: extensions/v1beta1

kind: Ingress

metadata:

name: grafana

namespace: kube-system

spec:

rules:

- host: k8s.grafana

http:

paths:

- path: /

backend:

serviceName: grafana

servicePort: 3000

# kubectl apply -f grafana-ing.yaml

#kubectl get svc -n kube-system

NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE

grafana NodePort 10.96.240.149 <none> 3000:32539/TCP 4h25m

kube-dns ClusterIP 10.96.0.10 <none> 53/UDP,53/TCP,9153/TCP 2d22h

metrics-server ClusterIP 10.96.138.32 <none> 443/TCP 44h

node-exporter NodePort 10.96.144.176 <none> 9100:31672/TCP 4h56m

prometheus NodePort 10.96.235.128 <none> 9090:30003/TCP 4h48m