【夜莺监控方案】04-k8s集群监控（上）（kube-state-metrics+cadvisor+prometheus+n9e）
文章目录
前言
相关文档如下：
《01-n9e-v5 部署-server》
《01-n9e-v5部署-agent》
《02-容器监控-cadvisor+n9e》
《03-k8s集群监控（上）》
《03-k8s集群监控（下）》
《04-监控redis集群-prometheuse+n9e》
1. 部署cadvisor
说明：
k8s每个节点部署cadvisor服务
因为我是用docker-compose启动的，因此需要提前安装。
- yaml文件
创建/opt/cadvisor目录，在目录下创建docker-compose.yml文件如下：
cadvisor:
image: harbocto.xxx.com.cn/public/cadvisor:v0.24.1
container_name: monitoring_cadvisor
restart: unless-stopped
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
ports:
- "4194:8080"
- 启动
[root@DoM01 cadvisor]# docker-compose up -d
- 查看结果
[root@DoM01 cadvisor]# docker-compose ps
Name Command State Ports
-------------------------------------------------------------------------------------
monitoring_cadvisor /usr/bin/cadvisor -logtostderr Up 0.0.0.0:4194->8080/tcp
2. 部署 kube-state-metrics
2.1 创建集群用户
- 创建 cluster-role.yaml文件
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
name: kube-state-metrics
rules:
- apiGroups:
- ""
resources:
- configmaps
- secrets
- nodes
- pods
- services
- resourcequotas
- replicationcontrollers
- limitranges
- persistentvolumeclaims
- persistentvolumes
- namespaces
- endpoints
verbs:
- list
- watch
- apiGroups:
- extensions
resources:
- daemonsets
- deployments
- replicasets
- ingresses
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:
- 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
verbs:
- list
- watch
- 创建集群用户
kubectl create -f cluster-role.yaml
- 查看结果
[root@DoM01 kube-state-metrics]# kubectl get ClusterRole kube-state-metrics
NAME AGE
kube-state-metrics 11m
2.2 创建服务账户
- 创建 service-account.yaml文件
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
name: kube-state-metrics
namespace: monitor
- 创建服务账户
kubectl create -f service-account.yaml
- 查看结果
[root@DoM01 kube-state-metrics]# kubectl get ServiceAccount kube-state-metrics -n monitor
NAME SECRETS AGE
kube-state-metrics 1 13m
2.3 绑定集群用户
- 创建cluster-role-binding.yaml文件
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
name: kube-state-metrics
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: kube-state-metrics
subjects:
- kind: ServiceAccount
name: kube-state-metrics
namespace: monitor
- 绑定集群用户
kubectl create -f cluster-role-binding.yaml
- 查看结果
[root@DoM01 kube-state-metrics]# kubectl describe ClusterRoleBinding kube-state-metrics -n monitor
Name: kube-state-metrics
Labels: app.kubernetes.io/name=kube-state-metrics
app.kubernetes.io/version=v1.9.7
Annotations: <none>
Role:
Kind: ClusterRole
Name: kube-state-metrics
Subjects:
Kind Name Namespace
---- ---- ---------
ServiceAccount kube-state-metrics monitor
2.4 deployment.yml
- 创建deployment.yml文件
包含deployment、service
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
name: kube-state-metrics
namespace: monitor
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: kube-state-metrics
template:
metadata:
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
spec:
containers:
- image: quay.mirrors.ustc.edu.cn/coreos/kube-state-metrics:v1.9.7
livenessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 5
timeoutSeconds: 5
name: kube-state-metrics
ports:
- containerPort: 8080
name: http-metrics
- containerPort: 8081
name: telemetry
readinessProbe:
httpGet:
path: /
port: 8081
initialDelaySeconds: 5
timeoutSeconds: 5
nodeSelector:
beta.kubernetes.io/os: linux
serviceAccountName: kube-state-metrics
---
apiVersion: v1
kind: Service
metadata:
# annotations:
# prometheus.io/scrape: 'true'
labels:
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: v1.9.7
name: kube-state-metrics
namespace: monitor
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
- 启动
kubectl create -f deployment.yml
- 查看结果
[root@DoM01 kube-state-metrics]# kubectl get all -n monitor
NAME READY STATUS RESTARTS AGE
pod/kube-state-metrics-d49db84b9-6gfwp 1/1 Running 0 14m
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/kube-state-metrics ClusterIP None <none> 8080/TCP,8081/TCP 14m
NAME READY UP-TO-DATE AVAILABLE AGE
deployment.apps/kube-state-metrics 1/1 1 1 14m
NAME DESIRED CURRENT READY AGE
replicaset.apps/kube-state-metrics-d49db84b9 1 1 1 14m
3. 部署prometheus
3.1 创建rabc权限
- 创建 文件prometheus.rbac.yaml
为prometheus提供rabc权限。包括 ClusterRole、ServiceAccount、ClusterRoleBinding
之前创建kube-state-metrics时是分开写的，既然已经熟悉了，我们这里写在一起。
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: monitor
---
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: monitor
- 创建集群角色
kubectl create -f prometheus.rbac.yaml
- 查看角色
[root@DoM01 promethues]# kubectl describe ClusterRole prometheus
Name: prometheus
Labels: <none>
Annotations: <none>
PolicyRule:
Resources Non-Resource URLs Resource Names Verbs
--------- ----------------- -------------- -----
endpoints [] [] [get list watch]
nodes/proxy [] [] [get list watch]
nodes [] [] [get list watch]
pods [] [] [get list watch]
services [] [] [get list watch]
ingresses.extensions [] [] [get list watch]
[/metrics] [] [get]
- 查看账户
[root@DoM01 promethues]# kubectl describe ServiceAccount prometheus -n monitor
Name: prometheus
Namespace: monitor
Labels: <none>
Annotations: <none>
Image pull secrets: <none>
Mountable secrets: prometheus-token-t7msz
Tokens: prometheus-token-t7msz
Events: <none>
- 查看绑定
[root@DoM01 promethues]# kubectl describe ClusterRoleBinding prometheus -n monitor
Name: prometheus
Labels: <none>
Annotations: <none>
Role:
Kind: ClusterRole
Name: prometheus
Subjects:
Kind Name Namespace
---- ---- ---------
ServiceAccount prometheus monitor
3.2 创建promethues配置文件
- 创建 prometheus.config.yaml文件
创建comfigmap，为prometheus提供配置文件
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: monitor
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
- 创建configmap
kubectl create -f prometheus.config.yaml
- 查看结果
[root@DoM01 promethues]# kubectl get configmaps -n monitor
NAME DATA AGE
prometheus-config 1 3h7m
3.3 deployment和service
- 创建 prometheus.deployment.yamll文件
以部署deployment和serivce。
apiVersion: apps/v1beta2
kind: Deployment
metadata:
labels:
name: prometheus-deployment
name: prometheus
namespace: monitor
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
containers:
- image: prom/prometheus:v2.2.1
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
- name: host-time
mountPath: /etc/localtime
readOnly: true
resources:
requests:
cpu: 100m
memory: 100Mi
limits:
cpu: 500m
memory: 2500Mi
serviceAccountName: prometheus
imagePullSecrets:
- name: login-harbor
volumes:
- name: host-time
hostPath:
path: /etc/localtime
- name: data
emptyDir: {}
- name: config-volume
configMap:
name: prometheus-config
---
kind: Service
apiVersion: v1
metadata:
labels:
app: prometheus
name: prometheus
namespace: monitor
spec:
type: NodePort
ports:
- port: 9090
targetPort: 9090
nodePort: 30003
selector:
app: prometheus
- 启动
kubectl create -f prometheus.deployment.yaml
- 查看结果
[root@DoM01 promethues]# kubectl get all -n monitor |grep prometheus
pod/prometheus-57fb8576bf-knzvs 1/1 Running 0 22m
service/prometheus NodePort 10.1.189.71 <none> 9090:30003/TCP 3h5m
deployment.apps/prometheus 1/1 1 1 3h5m
replicaset.apps/prometheus-57fb8576bf 1 1 1 3h4m
3.4. 查看结果
接下来我们接入n9e，见文档 《03-k8s集群监控（下）》
posted on 2021-12-05 12:00 运维开发玄德公 阅读(122) 评论(0) 编辑 收藏 举报 来源
