一、KubeStateMetrics简介¶
kube-state-metrics 是一个 Kubernetes 组件，它通过查询 Kubernetes 的 API 服务 器，收集关于 Kubernetes 中各种资源（如节点、pod、服务等）的状态信息，并将这些信息转换成 Prometheus 可以使用的指标。
kube-state-metrics 主要功能：
- 节点状态信息，如节点 CPU 和内存的使用情况、节点状态、节点标签等。
- Pod 的状态信息，如 Pod 状态、容器状态、容器镜像信息、Pod 的标签和注释等。
- Deployment、Daemonset、Statefulset 和 ReplicaSet 等控制器的状态信息，如副 本数、副本状态、创建时间等。
- Service 的状态信息，如服务类型、服务 IP 和端口等。
- 存储卷的状态信息，如存储卷类型、存储卷容量等。
- Kubernetes 的 API 服务器状态信息，如 API 服务器的状态、请求次数、响应时间等。
通过 kube-state-metrics 可以方便的对 Kubernetes 集群进行监控，发现问题，以及提前预警。
二、KubeStateMetrics¶
包含 ServiceAccount、 ClusterRole、 ClusterRoleBinding、 Deployment、ConfigMap、 Service 六类YAML文件
[root@master01 7]# vim kube-state-metrics.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: kube-state-metrics
namespace: monitor
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: kube-state-metrics
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups: [""]
resources:
- configmaps
- secrets
- nodes
- pods
- services
- 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: ["networking.k8s.io", "extensions"]
resources:
- ingresses
verbs: ["list", "watch"]
- apiGroups: ["storage.k8s.io"]
resources:
- storageclasses
verbs: ["list", "watch"]
- apiGroups: ["certificates.k8s.io"]
resources:
- certificatesigningrequests
verbs: ["list", "watch"]
- apiGroups: ["policy"]
resources:
- poddisruptionbudgets
verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: kube-state-metrics-resizer
namespace: monitor
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups: [""]
resources:
- pods
verbs: ["get"]
- apiGroups: ["extensions","apps"]
resources:
- deployments
resourceNames: ["kube-state-metrics"]
verbs: ["get", "update"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: kube-state-metrics
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: kube-state-metrics
subjects:
- kind: ServiceAccount
name: kube-state-metrics
namespace: monitor
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: kube-state-metrics
namespace: monitor
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: kube-state-metrics-resizer
subjects:
- kind: ServiceAccount
name: kube-state-metrics
namespace: monitor
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: kube-state-metrics
namespace: monitor
labels:
k8s-app: kube-state-metrics
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v1.3.0
spec:
selector:
matchLabels:
k8s-app: kube-state-metrics
version: v1.3.0
replicas: 1
template:
metadata:
labels:
k8s-app: kube-state-metrics
version: v1.3.0
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-cluster-critical
serviceAccountName: kube-state-metrics
containers:
- name: kube-state-metrics
image: registry.cn-hangzhou.aliyuncs.com/github_images1024/kube-state-metrics:v2.4.2
ports:
- name: http-metrics ##用于公开kubernetes的指标数据的端口
containerPort: 8080
- name: telemetry ##用于公开自身kube-state-metrics的指标数据的端口
containerPort: 8081
readinessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 5
timeoutSeconds: 5
- name: addon-resizer ##addon-resizer用来伸缩部署在集群内的 metrics-server, kube-state-metrics等监控组件
image: registry.cn-hangzhou.aliyuncs.com/abroad_images/addon-resizer:1.8.6
resources:
limits:
cpu: 200m
memory: 200Mi
requests:
cpu: 100m
memory: 30Mi
env:
- name: MY_POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: MY_POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: config-volume
mountPath: /etc/config
command:
- /pod_nanny
- --config-dir=/etc/config
- --container=kube-state-metrics
- --cpu=100m
- --extra-cpu=1m
- --memory=100Mi
- --extra-memory=2Mi
- --threshold=5
- --deployment=kube-state-metrics
volumes:
- name: config-volume
configMap:
name: kube-state-metrics-config
---
# Config map for resource configuration.
apiVersion: v1
kind: ConfigMap
metadata:
name: kube-state-metrics-config
namespace: monitor
labels:
k8s-app: kube-state-metrics
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
data:
NannyConfiguration: |-
apiVersion: nannyconfig/v1alpha1
kind: NannyConfiguration
---
apiVersion: v1
kind: Service
metadata:
name: kube-state-metrics
namespace: monitor
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "kube-state-metrics"
annotations:
prometheus.io/scrape: 'true'
spec:
ports:
- name: http-metrics
port: 8080
targetPort: http-metrics
protocol: TCP
- name: telemetry
port: 8081
targetPort: telemetry
protocol: TCP
selector:
k8s-app: kube-state-metrics
[root@master01 7]# kaf kube-state-metrics.yaml
确认验证：
[root@master01 7]# kubectl get all -nmonitor |grep kube-state-metrics
pod/kube-state-metrics-f97cbfd85-9pnqw 2/2 Running 0 18s
service/kube-state-metrics ClusterIP 192.168.149.220 <none> 8080/TCP,8081/TCP 5m19s
deployment.apps/kube-state-metrics 1/1 1 1 5m19s
replicaset.apps/kube-state-metrics-684b4ddfd5 0 0 0 5m19s
replicaset.apps/kube-state-metrics-f97cbfd85 1 1 1 18s
$ curl -kL $(kubectl get service -n monitor | grep kube-state-metrics |awk '{ print $3 }'):8080/metrics