附014.Kubernetes Prometheus+Grafana+EFK+Kibana+Glusterfs整合性方案

一 glusterfs存储集群部署

注意：以下为简略步骤，详情参考《附009.Kubernetes永久存储之GlusterFS独立部署》。

1.1 架构示意

略

1.2 相关规划

主机	IP	磁盘	备注
k8smaster01	172.24.8.71	——	Kubernetes Master节点 Heketi主机
k8smaster02	172.24.8.72	——	Kubernetes Master节点 Heketi主机
k8smaster03	172.24.8.73	——	Kubernetes Master节点 Heketi主机
k8snode01	172.24.8.74	sdb	Kubernetes Worker节点 glusterfs 01节点
k8snode02	172.24.8.75	sdb	Kubernetes Worker节点 glusterfs 02节点
k8snode03	172.24.8.76	sdb	Kubernetes Worker节点 glusterfs 03节点

提示：本规划直接使用裸磁盘完成。

1.3 安装glusterfs

# yum -y install centos-release-gluster

# yum -y install glusterfs-server

# systemctl start glusterd

# systemctl enable glusterd

提示：建议所有节点安装。

1.4 添加信任池

[root@k8snode01 ~]# gluster peer probe k8snode02

[root@k8snode01 ~]# gluster peer probe k8snode03

[root@k8snode01 ~]# gluster peer status #查看信任池状态

[root@k8snode01 ~]# gluster pool list #查看信任池列表

提示：仅需要在glusterfs任一节点执行一次即可。

1.5 安装heketi

[root@k8smaster01 ~]# yum -y install heketi heketi-client

1.6 配置heketi

[root@k8smaster01 ~]# vi /etc/heketi/heketi.json

  1 {
  2   "_port_comment": "Heketi Server Port Number",
  3   "port": "8080",
  4 
  5   "_use_auth": "Enable JWT authorization. Please enable for deployment",
  6   "use_auth": true,
  7 
  8   "_jwt": "Private keys for access",
  9   "jwt": {
 10     "_admin": "Admin has access to all APIs",
 11     "admin": {
 12       "key": "admin123"
 13     },
 14     "_user": "User only has access to /volumes endpoint",
 15     "user": {
 16       "key": "xianghy"
 17     }
 18   },
 19 
 20   "_glusterfs_comment": "GlusterFS Configuration",
 21   "glusterfs": {
 22     "_executor_comment": [
 23       "Execute plugin. Possible choices: mock, ssh",
 24       "mock: This setting is used for testing and development.",
 25       "      It will not send commands to any node.",
 26       "ssh:  This setting will notify Heketi to ssh to the nodes.",
 27       "      It will need the values in sshexec to be configured.",
 28       "kubernetes: Communicate with GlusterFS containers over",
 29       "            Kubernetes exec api."
 30     ],
 31     "executor": "ssh",
 32 
 33     "_sshexec_comment": "SSH username and private key file information",
 34     "sshexec": {
 35       "keyfile": "/etc/heketi/heketi_key",
 36       "user": "root",
 37       "port": "22",
 38       "fstab": "/etc/fstab"
 39     },
 40 
 41     "_db_comment": "Database file name",
 42     "db": "/var/lib/heketi/heketi.db",
 43 
 44     "_loglevel_comment": [
 45       "Set log level. Choices are:",
 46       "  none, critical, error, warning, info, debug",
 47       "Default is warning"
 48     ],
 49     "loglevel" : "warning"
 50   }
 51 }

 

1.7 配置免秘钥

[root@k8smaster01 ~]# ssh-keygen -t rsa -q -f /etc/heketi/heketi_key -N ""

[root@k8smaster01 ~]# chown heketi:heketi /etc/heketi/heketi_key

[root@k8smaster01 ~]# ssh-copy-id -i /etc/heketi/heketi_key.pub root@k8snode01

[root@k8smaster01 ~]# ssh-copy-id -i /etc/heketi/heketi_key.pub root@k8snode02

[root@k8smaster01 ~]# ssh-copy-id -i /etc/heketi/heketi_key.pub root@k8snode03

1.8 启动heketi

[root@k8smaster01 ~]# systemctl enable heketi.service

[root@k8smaster01 ~]# systemctl start heketi.service

[root@k8smaster01 ~]# systemctl status heketi.service

[root@k8smaster01 ~]# curl http://localhost:8080/hello #测试访问

1.9 配置Heketi拓扑

[root@k8smaster01 ~]# vi /etc/heketi/topology.json

  1 {
  2   "clusters": [
  3     {
  4       "nodes": [
  5         {
  6           "node": {
  7             "hostnames": {
  8               "manage": [
  9                 "k8snode01"
 10               ],
 11               "storage": [
 12                 "172.24.8.74"
 13               ]
 14             },
 15             "zone": 1
 16           },
 17           "devices": [
 18             "/dev/sdb"
 19           ]
 20         },
 21         {
 22           "node": {
 23             "hostnames": {
 24               "manage": [
 25                 "k8snode02"
 26               ],
 27               "storage": [
 28                 "172.24.8.75"
 29               ]
 30             },
 31             "zone": 1
 32           },
 33           "devices": [
 34             "/dev/sdb"
 35           ]
 36         },
 37         {
 38           "node": {
 39             "hostnames": {
 40               "manage": [
 41                 "k8snode03"
 42               ],
 43               "storage": [
 44                 "172.24.8.76"
 45               ]
 46             },
 47             "zone": 1
 48           },
 49           "devices": [
 50             "/dev/sdb"
 51           ]
 52         }
 53       ]
 54     }
 55   ]
 56 }

 

[root@k8smaster01 ~]# echo "export HEKETI_CLI_SERVER=http://k8smaster01:8080" >> /etc/profile.d/heketi.sh

[root@k8smaster01 ~]# echo "alias heketi-cli='heketi-cli --user admin --secret admin123'" >> .bashrc

[root@k8smaster01 ~]# source /etc/profile.d/heketi.sh

[root@k8smaster01 ~]# source .bashrc

[root@k8smaster01 ~]# echo $HEKETI_CLI_SERVER

http://k8smaster01:8080

[root@k8smaster01 ~]# heketi-cli --server $HEKETI_CLI_SERVER --user admin --secret admin123 topology load --json=/etc/heketi/topology.json

1.10 集群管理及测试

[root@heketi ~]# heketi-cli cluster list #集群列表

[root@heketi ~]# heketi-cli node list #卷信息

[root@heketi ~]# heketi-cli volume list #卷信息

[root@k8snode01 ~]# gluster volume info #通过glusterfs节点查看

1.11 创建StorageClass

[root@k8smaster01 study]# vi heketi-secret.yaml

  1 apiVersion: v1
  2 kind: Secret
  3 metadata:
  4   name: heketi-secret
  5   namespace: heketi
  6 data:
  7   key: YWRtaW4xMjM=
  8 type: kubernetes.io/glusterfs

 

[root@k8smaster01 study]# kubectl create ns heketi

[root@k8smaster01 study]# kubectl create -f heketi-secret.yaml #创建heketi

[root@k8smaster01 study]# kubectl get secrets -n heketi

[root@k8smaster01 study]# vim gluster-heketi-storageclass.yaml #正式创建StorageClass

  1 apiVersion: storage.k8s.io/v1
  2 kind: StorageClass
  3 metadata:
  4   name: ghstorageclass
  5 parameters:
  6   resturl: "http://172.24.8.71:8080"
  7   clusterid: "ad0f81f75f01d01ebd6a21834a2caa30"
  8   restauthenabled: "true"
  9   restuser: "admin"
 10   secretName: "heketi-secret"
 11   secretNamespace: "heketi"
 12   volumetype: "replicate:3"
 13 provisioner: kubernetes.io/glusterfs
 14 reclaimPolicy: Delete

 

[root@k8smaster01 study]# kubectl create -f gluster-heketi-storageclass.yaml

注意：storageclass资源创建后不可变更，如修改只能删除后重建。

[root@k8smaster01 heketi]# kubectl get storageclasses #查看确认

NAME PROVISIONER AGE

gluster-heketi-storageclass kubernetes.io/glusterfs 85s

[root@k8smaster01 heketi]# kubectl describe storageclasses ghstorageclass

 

二 集群监控Metrics

注意：以下为简略步骤，详情参考《049.集群管理-集群监控Metrics》。

2.1 开启聚合层

开机聚合层功能，使用kubeadm默认已开启此功能，可如下查看验证。

[root@k8smaster01 ~]# cat /etc/kubernetes/manifests/kube-apiserver.yaml

2.2 获取部署文件

[root@k8smaster01 ~]# git clone https://github.com/kubernetes-incubator/metrics-server.git

[root@k8smaster01 ~]# cd metrics-server/deploy/1.8+/

[root@k8smaster01 1.8+]# vi metrics-server-deployment.yaml

  1 ……
  2         image: mirrorgooglecontainers/metrics-server-amd64:v0.3.6	#修改为国内源
  3         command:
  4         - /metrics-server
  5         - --metric-resolution=30s
  6         - --kubelet-insecure-tls
  7         - --kubelet-preferred-address-types=InternalIP,Hostname,InternalDNS,ExternalDNS,ExternalIP	#添加如上command
  8 ……

 

2.3 正式部署

[root@k8smaster01 1.8+]# kubectl apply -f .

[root@k8smaster01 1.8+]# kubectl -n kube-system get pods -l k8s-app=metrics-server

[root@k8smaster01 1.8+]# kubectl -n kube-system logs -l k8s-app=metrics-server -f #可查看部署日志

2.4 确认验证

[root@k8smaster01 ~]# kubectl top nodes

[root@k8smaster01 ~]# kubectl top pods --all-namespaces

 

三 Prometheus部署

注意：以下为简略步骤，详情参考《050.集群管理-Prometheus+Grafana监控方案》。

3.1 获取部署文件

[root@k8smaster01 ~]# git clone https://github.com/prometheus/prometheus

3.2 创建命名空间

[root@k8smaster01 ~]# cd prometheus/documentation/examples/

[root@k8smaster01 examples]# vi monitor-namespace.yaml

  1 apiVersion: v1
  2 kind: Namespace
  3 metadata:
  4   name: monitoring

[root@k8smaster01 examples]# kubectl create -f monitor-namespace.yaml

3.3 创建RBAC

[root@k8smaster01 examples]# vi rbac-setup.yml

  1 apiVersion: rbac.authorization.k8s.io/v1beta1
  2 kind: ClusterRole
  3 metadata:
  4   name: prometheus
  5 rules:
  6 - apiGroups: [""]
  7   resources:
  8   - nodes
  9   - nodes/proxy
 10   - services
 11   - endpoints
 12   - pods
 13   verbs: ["get", "list", "watch"]
 14 - apiGroups:
 15   - extensions
 16   resources:
 17   - ingresses
 18   verbs: ["get", "list", "watch"]
 19 - nonResourceURLs: ["/metrics"]
 20   verbs: ["get"]
 21 ---
 22 apiVersion: v1
 23 kind: ServiceAccount
 24 metadata:
 25   name: prometheus
 26   namespace: monitoring               #仅需修改命名空间
 27 ---
 28 apiVersion: rbac.authorization.k8s.io/v1beta1
 29 kind: ClusterRoleBinding
 30 metadata:
 31   name: prometheus
 32 roleRef:
 33   apiGroup: rbac.authorization.k8s.io
 34   kind: ClusterRole
 35   name: prometheus
 36 subjects:
 37 - kind: ServiceAccount
 38   name: prometheus
 39   namespace: monitoring              #仅需修改命名空间

[root@k8smaster01 examples]# kubectl create -f rbac-setup.yml

3.4 创建Prometheus ConfigMap

[root@k8smaster01 examples]# cat prometheus-kubernetes.yml | grep -v ^$ | grep -v "#" >> prometheus-config.yaml

[root@k8smaster01 examples]# vi prometheus-config.yaml

  1 apiVersion: v1
  2 kind: ConfigMap
  3 metadata:
  4   name: prometheus-server-conf
  5   labels:
  6     name: prometheus-server-conf
  7   namespace: monitoring               #修改命名空间
  8 ……

[root@k8smaster01 examples]# kubectl create -f prometheus-config.yaml

3.5 创建持久PVC

[root@k8smaster01 examples]# vi prometheus-pvc.yaml

  1 apiVersion: v1
  2 kind: PersistentVolumeClaim
  3 metadata:
  4   name: prometheus-pvc
  5   namespace: monitoring
  6   annotations:
  7     volume.beta.kubernetes.io/storage-class: ghstorageclass
  8 spec:
  9   accessModes:
 10   - ReadWriteMany
 11   resources:
 12     requests:
 13       storage: 5Gi

[root@k8smaster01 examples]# kubectl create -f prometheus-pvc.yaml

3.6 Prometheus部署

[root@k8smaster01 examples]# vi prometheus-deployment.yml

  1 apiVersion: apps/v1beta2
  2 kind: Deployment
  3 metadata:
  4   labels:
  5     name: prometheus-deployment
  6   name: prometheus-server
  7   namespace: monitoring
  8 spec:
  9   replicas: 1
 10   selector:
 11     matchLabels:
 12       app: prometheus-server
 13   template:
 14     metadata:
 15       labels:
 16         app: prometheus-server
 17     spec:
 18       containers:
 19         - name: prometheus-server
 20           image: prom/prometheus:v2.14.0
 21           command:
 22           - "/bin/prometheus"
 23           args:
 24             - "--config.file=/etc/prometheus/prometheus.yml"
 25             - "--storage.tsdb.path=/prometheus/"
 26             - "--storage.tsdb.retention=72h"
 27           ports:
 28             - containerPort: 9090
 29               protocol: TCP
 30           volumeMounts:
 31             - name: prometheus-config-volume
 32               mountPath: /etc/prometheus/
 33             - name: prometheus-storage-volume
 34               mountPath: /prometheus/
 35       serviceAccountName: prometheus
 36       imagePullSecrets:
 37         - name: regsecret
 38       volumes:
 39         - name: prometheus-config-volume
 40           configMap:
 41             defaultMode: 420
 42             name: prometheus-server-conf
 43         - name: prometheus-storage-volume
 44           persistentVolumeClaim:
 45             claimName: prometheus-pvc

[root@k8smaster01 examples]# kubectl create -f prometheus-deployment.yml

3.7 创建Prometheus Service

[root@k8smaster01 examples]# vi prometheus-service.yaml

  1 apiVersion: v1
  2 kind: Service
  3 metadata:
  4   labels:
  5     app: prometheus-service
  6   name: prometheus-service
  7   namespace: monitoring
  8 spec:
  9   type: NodePort
 10   selector:
 11     app: prometheus-server
 12   ports:
 13     - port: 9090
 14       targetPort: 9090
 15       nodePort: 30001

[root@k8smaster01 examples]# kubectl create -f prometheus-service.yaml

[root@k8smaster01 examples]# kubectl get all -n monitoring

3.8 确认验证Prometheus

浏览器直接访问：http://172.24.8.100:30001/

 

四 部署grafana

注意：以下为简略步骤，详情参考《050.集群管理-Prometheus+Grafana监控方案》。

4.1 获取部署文件

[root@k8smaster01 ~]# git clone https://github.com/liukuan73/kubernetes-addons

[root@k8smaster01 ~]# cd /root/kubernetes-addons/monitor/prometheus+grafana

4.2 创建持久PVC

[root@k8smaster01 prometheus+grafana]# vi grafana-data-pvc.yaml

  1 apiVersion: v1
  2 kind: PersistentVolumeClaim
  3 metadata:
  4   name: grafana-data-pvc
  5   namespace: monitoring
  6   annotations:
  7     volume.beta.kubernetes.io/storage-class: ghstorageclass
  8 spec:
  9   accessModes:
 10   - ReadWriteOnce
 11   resources:
 12     requests:
 13       storage: 5Gi

[root@k8smaster01 prometheus+grafana]# kubectl create -f grafana-data-pvc.yaml

4.3 grafana部署

[root@k8smaster01 prometheus+grafana]# vi grafana.yaml

  1 apiVersion: extensions/v1beta1
  2 kind: Deployment
  3 metadata:
  4   name: monitoring-grafana
  5   namespace: monitoring
  6 spec:
  7   replicas: 1
  8   template:
  9     metadata:
 10       labels:
 11         task: monitoring
 12         k8s-app: grafana
 13     spec:
 14       containers:
 15       - name: grafana
 16         image: grafana/grafana:6.5.0
 17         imagePullPolicy: IfNotPresent
 18         ports:
 19         - containerPort: 3000
 20           protocol: TCP
 21         volumeMounts:
 22         - mountPath: /var/lib/grafana
 23           name: grafana-storage
 24         env:
 25           - name: INFLUXDB_HOST
 26             value: monitoring-influxdb
 27           - name: GF_SERVER_HTTP_PORT
 28             value: "3000"
 29           - name: GF_AUTH_BASIC_ENABLED
 30             value: "false"
 31           - name: GF_AUTH_ANONYMOUS_ENABLED
 32             value: "true"
 33           - name: GF_AUTH_ANONYMOUS_ORG_ROLE
 34             value: Admin
 35           - name: GF_SERVER_ROOT_URL
 36             value: /
 37         readinessProbe:
 38           httpGet:
 39             path: /login
 40             port: 3000
 41       volumes:
 42       - name: grafana-storage
 43         persistentVolumeClaim:
 44           claimName: grafana-data-pvc
 45       nodeSelector:
 46         node-role.kubernetes.io/master: "true"
 47       tolerations:
 48       - key: "node-role.kubernetes.io/master"
 49         effect: "NoSchedule"
 50 ---
 51 apiVersion: v1
 52 kind: Service
 53 metadata:
 54   labels:
 55     kubernetes.io/cluster-service: 'true'
 56     kubernetes.io/name: monitoring-grafana
 57   annotations:
 58     prometheus.io/scrape: 'true'
 59     prometheus.io/tcp-probe: 'true'
 60     prometheus.io/tcp-probe-port: '80'
 61   name: monitoring-grafana
 62   namespace: monitoring
 63 spec:
 64   type: NodePort
 65   ports:
 66   - port: 80
 67     targetPort: 3000
 68     nodePort: 30002
 69   selector:
 70     k8s-app: grafana

[root@k8smaster01 prometheus+grafana]# kubectl label nodes k8smaster01 node-role.kubernetes.io/master=true

[root@k8smaster01 prometheus+grafana]# kubectl label nodes k8smaster02 node-role.kubernetes.io/master=true

[root@k8smaster01 prometheus+grafana]# kubectl label nodes k8smaster03 node-role.kubernetes.io/master=true

[root@k8smaster01 prometheus+grafana]# kubectl create -f grafana.yaml

[root@k8smaster01 examples]# kubectl get all -n monitoring

4.4 确认验证Prometheus

浏览器直接访问：http://172.24.8.100:30002/

4.4 grafana配置

• 添加数据源：略
• 创建用户：略

提示：所有grafana配置可配置参考：https://grafana.com/docs/grafana/latest/installation/configuration/。

4.5 查看监控

浏览器再次访问：http://172.24.8.100:30002/