K8S系列-2.常用命令
获取当前K8S版本
[root@node1 ~]# kubectl version
Client Version: version.Info{Major:"1", Minor:"17", GitVersion:"v1.17.9", GitCommit:"4fb7ed12476d57b8437ada90b4f93b17ffaeed99", GitTreeState:"clean", BuildDate:"2020-07-15T16:18:16Z", GoVersion:"go1.13.9", Compiler:"gc", Platform:"linux/amd64"}
Server Version: version.Info{Major:"1", Minor:"17", GitVersion:"v1.17.9", GitCommit:"4fb7ed12476d57b8437ada90b4f93b17ffaeed99", GitTreeState:"clean", BuildDate:"2020-07-15T16:10:45Z", GoVersion:"go1.13.9", Compiler:"gc", Platform:"linux/amd64"}
获取集群信息
[root@node1 ~]# kubectl cluster-info
Kubernetes master is running at https://lb.kubesphere.local:6443
coredns is running at https://lb.kubesphere.local:6443/api/v1/namespaces/kube-system/services/coredns:dns/proxy
To further debug and diagnose cluster problems, use 'kubectl cluster-info dump'.
获取node状态
#查看所有node信息
[root@node1 ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
node1 Ready master,worker 229d v1.17.9
node2 NotReady worker 229d v1.17.9
node3 NotReady worker 229d v1.17.9
查看节点详细信息，除以上信息外还包括节点的内部IP、外部IP、宿主机系统版本、内核版本、容器运行时版本
#查看所有node详细信息
[root@node1 ~]# kubectl get nodes -o wide
NAME STATUS ROLES AGE VERSION INTERNAL-IP EXTERNAL-IP OS-IMAGE KERNEL-VERSION CONTAINER-RUNTIME
node1 Ready master,worker 229d v1.17.9 192.168.56.108 <none> CentOS Linux 7 (Core) 3.10.0-957.el7.x86_64 docker://19.3.4
node2 NotReady worker 229d v1.17.9 192.168.56.109 <none> CentOS Linux 7 (Core) 3.10.0-957.el7.x86_64 docker://19.3.13
node3 NotReady worker 229d v1.17.9 192.168.56.110 <none> CentOS Linux 7 (Core) 3.10.0-957.el7.x86_64 docker://19.3.13
获取namespaces
[root@node1 ~]# kubectl get namespaces
NAME STATUS AGE
default Active 3d10h
kube-node-lease Active 3d10h
kube-public Active 3d10h
kube-system Active 3d10h
查看Pods状态
[root@node2 ~]# kubectl get pods --all-namespaces
NAMESPACE NAME READY STATUS RESTARTS AGE
kube-system calico-kube-controllers-677cbc8557-2f9p8 0/1 Error 12 230d
kube-system calico-node-55nd4 0/1 Running 13 230d
kube-system calico-node-cx6hw 1/1 Running 6 230d
kube-system calico-node-q6p47 0/1 Error 12 230d
kube-system coredns-79878cb9c9-bpt5x 0/1 Error 12 230d
kube-system coredns-79878cb9c9-p9d5b 0/1 Error 12 230d
kube-system kube-apiserver-node1 0/1 Error 12 230d
kube-system kube-controller-manager-node1 0/1 Error 12 230d
kube-system kube-proxy-cvh9z 1/1 Running 26 230d
kube-system kube-proxy-rcklw 1/1 Running 12 230d
kube-system kube-proxy-wnzfw 0/1 Error 24 230d
kube-system kube-scheduler-node1 0/1 Error 12 230d
kube-system nodelocaldns-92qvv 1/1 Running 6 230d
kube-system nodelocaldns-rrhpk 1/1 Running 13 230d
kube-system nodelocaldns-ws5tp 0/1 Error 12 230d
注：status详细信息
status 含义 Succeeded: pod 成功退出， 不再自动启动 Waiting 等 Running Running: pod 运行中（容器内进程重启中也可能是 Running 状态） ContainerCreating 创建容器中
PULL 不了国外镜像源， 或者镜像太大导致 PULL 超时
CNI 网络错误， 无法配置 Pod 网络,无法分配 IP 地址Failed 失败， 此 pod 里至少有一个容器未正常停止 Pending 挂起， 此 pod 因为网络或其他原因， 如正在 pull image unknown 未知， 无法获取 pod 状态， 可能是 Node 连接不正常 Terminating pod 未正常执行 command， 需要删除 pod 重建 CrashLoopBackOff 正尽力启动 Pod， 但是一个或多个容器已经挂 ErrImagePull ErrImagePull: 镜像错误， pull 镜像失败 ImagePullBackOff 镜像名称配置错误或者镜像的密钥配置错误
查看master组件状态
查看核心服务概要
[root@node1 ~]# kubectl get cs
NAME STATUS MESSAGE ERROR
scheduler Healthy ok
controller-manager Healthy ok
etcd-0 Healthy {"health":"true"}
这里查询到是k8s核心组件：kube-scheduler、kube-controller-manager、etcd的运行状态，如果status状态为Unhealthy，可以用kubectl describe cs查看更加详细的信息
查看核心服务详情
[root@node1 ~]# kubectl describe cs
Name: scheduler
Namespace:
Labels: <none>
Annotations: <none>
API Version: v1
Conditions:
Message: ok
Status: True
Type: Healthy
Kind: ComponentStatus
Metadata:
Creation Timestamp: <nil>
Self Link: /api/v1/componentstatuses/scheduler
Events: <none>
Name: controller-manager
Namespace:
Labels: <none>
Annotations: <none>
API Version: v1
Conditions:
Message: ok
Status: True
Type: Healthy
Kind: ComponentStatus
Metadata:
Creation Timestamp: <nil>
Self Link: /api/v1/componentstatuses/controller-manager
Events: <none>
Name: etcd-0
Namespace:
Labels: <none>
Annotations: <none>
API Version: v1
Conditions:
Message: {"health":"true"}
Status: True
Type: Healthy
Kind: ComponentStatus
Metadata:
Creation Timestamp: <nil>
Self Link: /api/v1/componentstatuses/etcd-0
Events: <none>
查看核心服务Pod详情
[root@node1 ~]# kubectl describe pod kube-apiserver-node1 -n kube-system
Name: kube-apiserver-node1
Namespace: kube-system
Priority: 2000000000
Priority Class Name: system-cluster-critical
Node: node1/192.168.56.111
Start Time: Mon, 31 May 2021 05:38:35 -0400
Labels: component=kube-apiserver
tier=control-plane
Annotations: kubernetes.io/config.hash: 4fec45bb10f3b6900c84d295c90665b8
kubernetes.io/config.mirror: 4fec45bb10f3b6900c84d295c90665b8
kubernetes.io/config.seen: 2020-10-14T23:57:52.157821836-04:00
kubernetes.io/config.source: file
Status: Running
IP: 192.168.56.111
IPs:
IP: 192.168.56.111
Controlled By: Node/node1
Containers:
kube-apiserver:
Container ID: docker://a8d8f9bdbcfb7937d54bae80520f7bb4be556689191af096250c6203f826b9fc
Image: dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9
Image ID: docker-pullable://dockerhub.kubekey.local/kubesphere/kube-apiserver@sha256:3eb34ba74ad26607f7f20a794771a05d3480e5360fcf3366b7bb8cfcba1de929
Port: <none>
Host Port: <none>
Command:
kube-apiserver
--advertise-address=192.168.56.111
--allow-privileged=true
--anonymous-auth=True
--apiserver-count=1
--authorization-mode=Node,RBAC
--bind-address=0.0.0.0
--client-ca-file=/etc/kubernetes/pki/ca.crt
--enable-admission-plugins=NodeRestriction
--enable-aggregator-routing=False
--enable-bootstrap-token-auth=true
--endpoint-reconciler-type=lease
--etcd-cafile=/etc/ssl/etcd/ssl/ca.pem
--etcd-certfile=/etc/ssl/etcd/ssl/node-node1.pem
--etcd-keyfile=/etc/ssl/etcd/ssl/node-node1-key.pem
--etcd-servers=https://192.168.56.111:2379
--feature-gates=CSINodeInfo=true,VolumeSnapshotDataSource=true,ExpandCSIVolumes=true,RotateKubeletClientCertificate=true
--insecure-port=0
--kubelet-client-certificate=/etc/kubernetes/pki/apiserver-kubelet-client.crt
--kubelet-client-key=/etc/kubernetes/pki/apiserver-kubelet-client.key
--kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
--profiling=False
--proxy-client-cert-file=/etc/kubernetes/pki/front-proxy-client.crt
--proxy-client-key-file=/etc/kubernetes/pki/front-proxy-client.key
--requestheader-allowed-names=front-proxy-client
--requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.crt
--requestheader-extra-headers-prefix=X-Remote-Extra-
--requestheader-group-headers=X-Remote-Group
--requestheader-username-headers=X-Remote-User
--secure-port=6443
--service-account-key-file=/etc/kubernetes/pki/sa.pub
--service-cluster-ip-range=10.233.0.0/18
--storage-backend=etcd3
--tls-cert-file=/etc/kubernetes/pki/apiserver.crt
--tls-private-key-file=/etc/kubernetes/pki/apiserver.key
State: Running
Started: Mon, 31 May 2021 05:40:06 -0400
Last State: Terminated
Reason: Error
Exit Code: 255
Started: Fri, 28 May 2021 05:49:19 -0400
Finished: Mon, 31 May 2021 05:38:22 -0400
Ready: True
Restart Count: 12
Requests:
cpu: 250m
Liveness: http-get https://192.168.56.111:6443/healthz delay=15s timeout=15s period=10s #success=1 #failure=8
Environment: <none>
Mounts:
/etc/kubernetes/pki from k8s-certs (ro)
/etc/pki from etc-pki (ro)
/etc/ssl/certs from ca-certs (ro)
/etc/ssl/etcd/ssl from etcd-certs-0 (ro)
Conditions:
Type Status
Initialized True
Ready True
ContainersReady True
PodScheduled True
Volumes:
ca-certs:
Type: HostPath (bare host directory volume)
Path: /etc/ssl/certs
HostPathType: DirectoryOrCreate
etc-pki:
Type: HostPath (bare host directory volume)
Path: /etc/pki
HostPathType: DirectoryOrCreate
etcd-certs-0:
Type: HostPath (bare host directory volume)
Path: /etc/ssl/etcd/ssl
HostPathType: DirectoryOrCreate
k8s-certs:
Type: HostPath (bare host directory volume)
Path: /etc/kubernetes/pki
HostPathType: DirectoryOrCreate
QoS Class: Burstable
Node-Selectors: <none>
Tolerations: :NoExecute
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Normal SandboxChanged 10d kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 10d kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 10d kubelet, node1 Created container kube-apiserver
Normal Started 10d kubelet, node1 Started container kube-apiserver
Normal SandboxChanged 10d kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 10d kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 10d kubelet, node1 Created container kube-apiserver
Normal Started 10d kubelet, node1 Started container kube-apiserver
Normal SandboxChanged 9d (x2 over 9d) kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 9d kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 9d kubelet, node1 Created container kube-apiserver
Normal Started 9d kubelet, node1 Started container kube-apiserver
Normal SandboxChanged 3d kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 3d kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 3d kubelet, node1 Created container kube-apiserver
Normal Started 3d kubelet, node1 Started container kube-apiserver
Normal SandboxChanged 2d23h kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 2d23h kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 2d23h kubelet, node1 Created container kube-apiserver
Normal Started 2d23h kubelet, node1 Started container kube-apiserver
Normal SandboxChanged 5m4s (x2 over 6m35s) kubelet, node1 Pod sandbox changed, it will be killed and re-created.
Normal Pulled 5m4s kubelet, node1 Container image "dockerhub.kubekey.local/kubesphere/kube-apiserver:v1.17.9" already present on machine
Normal Created 5m4s kubelet, node1 Created container kube-apiserver
Normal Started 5m4s kubelet, node1 Started container kube-apiserver
查看master各项服务日志
kubectl logs --tail 5 -f kube-apiserver-node1 -n kube-system
kubectl logs --tail 5 -f kube-controller-manager-node1 -n kube-system
kubectl logs --tail 5 -f kube-scheduler-node1 -n kube-system
查看worker状态
检查node
参考获取node状态
检查node日志
kubectl/oc logs --tail 100 -f kube-proxy -n kube-system
kubectl/oc logs --tail 100 -f kebelet -n kube-system
检查service
[root@node1 ~]# kubectl get svc -o wide --all-namespaces
NAMESPACE NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE SELECTOR
default kubernetes ClusterIP 10.233.0.1 <none> 443/TCP 3d10h <none>
kube-system coredns ClusterIP 10.233.0.3 <none> 53/UDP,53/TCP,9153/TCP 3d10h k8s-app=kube-dns