4.OpenShift命令及故障排查

  1 [root@master ~]# oc whoami
  2 system:admin					#master的root用户为集群的最高权限的用户
  3 [student@workstation ~]$ oc whoami		        #查看当前用户
  4 developer
  5 [student@workstation ~]$ oc new-project working	#创建project
  6 [student@workstation ~]$ oc status		        #查看项目状态
  7 In project working on server https://master.lab.example.com:443
  8 You have no services, deployment configs, or build configs.
  9 Run 'oc new-app' to create an application.
 10 [student@workstation ~]$ oc delete project working	#删除project
 11 [student@workstation ~]$ oc logout		        #退出该集群。
 12 [student@workstation ~]$ oc get pods		#查看pod
 13 NAME                      READY     STATUS    RESTARTS   AGE
 14 hello-openshift-1-6ls8z   1/1       Running   0          4h
 15 [student@workstation ~]$ oc get all		        #查看所有主要组件信息
 16 [student@workstation ~]$ oc get pods -w		#-w表示以监视模式运行

  1 [student@workstation ~]$ oc login -u admin -p redhat https://master.lab.example.com
  2 [student@workstation ~]$ oc project default
  3 Already on project "default" on server "https://master.lab.example.com:443".
  4 [student@workstation ~]$ oc project default
  5 Already on project "default" on server "https://master.lab.example.com:443".
  6 [student@workstation ~]$ oc get nodes
  7 NAME                     STATUS    ROLES     AGE       VERSION
  8 master.lab.example.com   Ready     master    23h       v1.9.1+a0ce1bc657
  9 node1.lab.example.com    Ready     compute   23h       v1.9.1+a0ce1bc657
 10 node2.lab.example.com    Ready     compute   23h       v1.9.1+a0ce1bc657
 11 [student@workstation ~]$ oc describe node master.lab.example.com		#查看master节点详情
 12 [student@workstation ~]$ oc describe node node1.lab.example.com
 13 [student@workstation ~]$ oc describe node node2.lab.example.com
 14 [student@workstation ~]$ oc get pods -o wide
 15 NAME                       READY     STATUS    RESTARTS   AGE       IP              NODE
 16 docker-registry-1-8v7sh    1/1       Running   4          23h       10.129.0.30     node2.lab.example.com
 17 docker-registry-1-rrmhm    1/1       Running   2          23h       10.128.0.12     node1.lab.example.com
 18 registry-console-1-xzxxp   1/1       Running   4          23h       10.129.0.31     node2.lab.example.com
 19 router-1-fwttd             1/1       Running   4          23h       172.25.250.12   node2.lab.example.com
 20 router-1-xdw84             1/1       Running   2          23h       172.25.250.11   node1.lab.example.com
 21 [student@workstation ~]$ oc  describe pod docker-registry-1-8v7sh		#查看pod详情

  1 {
  2 "sourceStrategy": {
  3 ...
  4 "env": [
  5 {
  6 "name": "BUILD_LOGLEVEL",
  7 "value": "5"
  8 }
  9 ]
 10 }
 11 }

  1 [student@workstation ~]$ oc log hello-1-build		#查看log
  2 W0720 20:22:16.455008   18942 cmd.go:358] log is DEPRECATED and will be removed in a future version. Use logs instead.
  3 [student@workstation ~]$ oc get events			#查看事件
  4 LAST SEEN   FIRST SEEN   COUNT     NAME                             KIND      SUBOBJECT   TYPE      REASON             SOURCE              MESSAGE
  5 56s         4m           15        hello-1-build.15b31cbd8da8ff1e   Pod                   Warning   FailedScheduling   default-scheduler   0/3 nodes are available: 1 MatchNodeSelector, 2 NodeNotReady.
  6 [student@workstation ~]$ oc describe pod hello-1-build	#查看详情
  7 ……
  8 Warning  FailedScheduling  31s (x22 over 5m)  default-scheduler  0/3 nodes are available: 1 MatchNodeSelector, 2 NodeNotReady.
  9 结论：由上可知，没有node可供调度此pod。
 10 [root@master ~]# oc get nodes				#在master节点进一步排查node情况
 11 NAME                     STATUS     ROLES     AGE       VERSION
 12 master.lab.example.com   Ready      master    1d        v1.9.1+a0ce1bc657
 13 node1.lab.example.com    NotReady   compute   1d        v1.9.1+a0ce1bc657
 14 node2.lab.example.com    NotReady   compute   1d        v1.9.1+a0ce1bc657
 15 结论：由上可知，node状态异常，都未出于ready状态。