# 警告:此脚本将清理单个node节点,使用请详细参阅 docs/op/clean_one_node.md # 请三思后运行此脚本,特别的:如果有pod使用了本地存储类型,请自行判断重要性 # 使用: # 1. 执行 ansible-playbook /etc/ansible/tools/clean_one_node.yml # 2. 按照提示输入待删除节点 - hosts: deploy vars_prompt: - name: "NODE_TO_DEL" prompt: "which node is about to be deleted?(e.g 192.168.1.1)" private: no confirm: yes tasks: - name: fail info1 fail: msg="you CAN NOT delete the last member of etcd cluster!" when: "groups['etcd']|length < 2 and NODE_TO_DEL in groups['etcd']" - name: fail info2 fail: msg="you CAN NOT delete the last member of kube-master!" when: "groups['kube-master']|length < 2 and NODE_TO_DEL in groups['kube-master']" - name: 执行kubectl drain(节点可能是kube-node节点) shell: "{{ bin_dir }}/kubectl drain {{ NODE_TO_DEL }} --ignore-daemonsets --delete-local-data" ignore_errors: true - block: # 清理 kube-node 相关服务 - name: stop and disable kube-node service service: name={{ item }} state=stopped enabled=no with_items: - kubelet - kube-proxy ignore_errors: true - name: umount kubelet 挂载的目录 shell: "mount | grep '/var/lib/kubelet'| awk '{print $3}'|xargs umount" args: warn: false ignore_errors: true - name: 清理目录和文件 file: name={{ item }} state=absent with_items: - "/var/lib/kubelet/" - "/var/lib/kube-proxy/" - "/etc/systemd/system/kubelet.service" - "/etc/systemd/system/kube-proxy.service" - "/opt/kube/kube-system/" # 清理 kube-master 相关 - name: stop and disable kube-master service service: name={{ item }} state=stopped enabled=no with_items: - kube-apiserver - kube-controller-manager - kube-scheduler ignore_errors: true - name: 清理目录和文件 file: name={{ item }} state=absent with_items: - "/var/run/kubernetes" - "/etc/systemd/system/kube-apiserver.service" - "/etc/systemd/system/kube-controller-manager.service" - "/etc/systemd/system/kube-scheduler.service" # 清理集群docker服务、网络相关 - name: 清理kube-router相关 shell: "{{ bin_dir }}/docker run --privileged --net=host cloudnativelabs/kube-router --cleanup-config" ignore_errors: true when: "CLUSTER_NETWORK == 'kube-router'" - name: 获取是否运行名为'kubeasz'的容器 shell: 'docker ps|grep kubeasz || echo "NOT FOUND"' register: install_info - name: stop and disable docker service service: name: docker state: stopped enabled: no ignore_errors: true when: "'kubeasz' not in install_info.stdout" - name: unmount docker filesystem-1 mount: path=/var/run/docker/netns/default state=unmounted when: "'kubeasz' not in install_info.stdout" - name: unmount docker filesystem-2 mount: path=/var/lib/docker/overlay state=unmounted when: "'kubeasz' not in install_info.stdout" - name: remove files and dirs file: name={{ item }} state=absent with_items: - "/var/lib/docker/" - "/var/run/docker/" - "/etc/systemd/system/docker.service" - "/etc/systemd/system/docker.service.requires/" - "/etc/systemd/system/docker.service.d/" - "/etc/bash_completion.d/docker" - "/usr/bin/docker" when: "'kubeasz' not in install_info.stdout" - name: remove files and dirs2 file: name={{ item }} state=absent with_items: - "/etc/cni/" - "/run/flannel/" - "/etc/calico/" - "/var/run/calico/" - "/var/lib/calico/" - "/var/log/calico/" - "/etc/cilium/" - "/var/run/cilium/" - "/sys/fs/bpf/tc/" - "/var/lib/cni/" - "/var/lib/kube-router/" - "/opt/kube/kube-system/" - name: cleanup iptables shell: "iptables -F && iptables -X \ && iptables -F -t nat && iptables -X -t nat \ && iptables -F -t raw && iptables -X -t raw \ && iptables -F -t mangle && iptables -X -t mangle" when: "'kubeasz' not in install_info.stdout" - name: cleanup networks1 shell: "ip link del tunl0; \ ip link del flannel.1; \ ip link del cni0; \ ip link del mynet0; \ ip link del kube-bridge; \ ip link del dummy0; \ ip link del kube-ipvs0; \ ip link del cilium_net; \ ip link del cilium_vxlan" ignore_errors: true - name: cleanup networks2 shell: "ip link del docker0; \ systemctl restart networking; \ systemctl restart network" ignore_errors: true when: "'kubeasz' not in install_info.stdout" - name: cleanup 'calico' routes shell: "for rt in `ip route|grep bird|sed 's/blackhole//'|awk '{print $1}'`;do ip route del $rt;done;" when: "CLUSTER_NETWORK == 'calico'" ignore_errors: true # 清理etcd 集群相关 - name: stop and disable etcd service service: name: etcd state: stopped enabled: no ignore_errors: true - name: 清理目录和文件 file: name={{ item }} state=absent with_items: - "/var/lib/etcd" - "/etc/etcd/" - "/backup/k8s" - "/etc/systemd/system/etcd.service" # 清理负载均衡相关 - name: stop keepalived service shell: systemctl disable keepalived && systemctl stop keepalived ignore_errors: true - name: stop haproxy service shell: systemctl disable haproxy && systemctl stop haproxy ignore_errors: true - name: 清理LB 配置文件目录 file: name={{ item }} state=absent with_items: - "/etc/haproxy" - "/etc/keepalived" # 清理其他 - name: stop and disable chrony in Ubuntu service: name=chrony state=stopped enabled=no ignore_errors: true tags: rm_ntp when: ansible_distribution == "Ubuntu" or ansible_distribution == "Debian" - name: stop and disable chronyd in CentOS/RedHat service: name=chronyd state=stopped enabled=no ignore_errors: true tags: rm_ntp when: ansible_distribution == "CentOS" or ansible_distribution == "RedHat" - name: 清理证书目录和文件 file: name={{ item }} state=absent with_items: - "/etc/kubernetes/" - "{{ ca_dir }}" - "/root/.kube/" - "/etc/docker/" - name: 清理自动生成的PATH lineinfile: dest: ~/.bashrc state: absent regexp: '{{ item }}' with_items: - 'kubeasz' - 'helm' - 'kubectl completion' delegate_to: "{{ NODE_TO_DEL }}" run_once: true # 执行kubectl delete(节点可能是kube-node节点) - name: 执行kubectl delete(节点可能是kube-node节点) shell: "{{ bin_dir }}/kubectl delete node {{ NODE_TO_DEL }}" ignore_errors: true # 删除 ansible hosts 中节点配置 - name: rm {{ NODE_TO_DEL }} in ansible hosts lineinfile: dest: "{{ base_dir }}/hosts" state: absent regexp: '^{{ NODE_TO_DEL }}$|^{{ NODE_TO_DEL }}[^0-9]' connection: local