ch-ansible/clean.yml at main · esp-charizhard/ch-ansible · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
---
- name: Clean up Kubernetes Nodes
  hosts: all
  become: true
  vars_files:
    - vault_become_pass.yml
  vars:
    is_master: "{{ inventory_hostname in groups['master_nodes'] | default([]) }}"
    is_worker: "{{ inventory_hostname in groups['worker_nodes'] | default([]) }}"

  tasks:
    - name: Execute Kubernetes cleanup
      block:
        - name: Stop Kubernetes services
          block:
            - name: Stop kubelet service
              systemd:
                name: kubelet
                state: stopped
                enabled: no
              ignore_errors: true

            - name: Stop containerd service
              systemd:
                name: containerd
                state: stopped
                enabled: no
              ignore_errors: true
        - name: Reset Kubernetes configuration
          block:
            - name: Reset kubeadm on all nodes
              shell: kubeadm reset --cri-socket=unix:///var/run/containerd/containerd.sock -f
              register: reset_result
              ignore_errors: true

            - name: Remove etcd data (master nodes only)
              file:
                path: /var/lib/etcd
                state: absent
              when: is_master
              ignore_errors: true

        - name: Clean up Kubernetes directories
          file:
            path: "{{ item }}"
            state: absent
          loop:
            - /var/lib/kubelet
            - /etc/kubernetes
            - /home/{{ ansible_user }}/.kube
            - /etc/cni/net.d
            - /var/lib/dockershim
            - /var/run/kubernetes
            - /var/lib/cni
            - /opt/cni/bin
          ignore_errors: true

        - name: Clean up container runtime
          block:
            - name: Remove containerd state
              file:
                path: /var/lib/containerd
                state: absent
              ignore_errors: true

            - name: Remove Docker directory (if used)
              file:
                path: /var/lib/docker
                state: absent
              ignore_errors: true

        - name: Clean up network configuration
          block:
            - name: Remove iptables rules
              shell: iptables -F && iptables -t nat -F && iptables -t mangle -F && iptables -X
              ignore_errors: true

            - name: Remove IP forwarding settings
              sysctl:
                name: net.bridge.bridge-nf-call-iptables
                value: '0'
                state: absent
              ignore_errors: true

            - name: Clean up any remaining flannel artifacts
              file:
                path: /run/flannel/subnet.env
                state: absent
              ignore_errors: true

        - name: Master node specific cleanup
          block:
            #- name: Backup etcd (if needed)
            #  shell: mkdir -p /tmp/etcd-backup && ETCDCTL_API=3 etcdctl snapshot save /tmp/etcd-backup/etcd-snapshot-$(date +%Y%m%d-%H%M%S).db --endpoints=localhost:2379
            #  ignore_errors: true

            - name: Remove control plane static pod manifests
              file:
                path: /etc/kubernetes/manifests
                state: absent
              ignore_errors: true
          when: is_master

        - name: Worker node specific cleanup
          block:
            - name: Remove kubelet config
              file:
                path: /var/lib/kubelet/config.yaml
                state: absent
              ignore_errors: true

            - name: Drain node (if cluster is still running)
              shell: "kubectl drain {{ inventory_hostname }} --ignore-daemonsets --delete-emptydir-data --force"
              delegate_to: "{{ groups['master_nodes'][0] }}"
              ignore_errors: true
              when: groups['master_nodes'] | length > 0
          when: is_worker

        - name: Restart services
          block:
            - name: Restart containerd
              systemd:
                name: containerd
                state: restarted
              ignore_errors: true

            - name: Start kubelet service
              systemd:
                name: kubelet
                state: started
                enabled: yes
              ignore_errors: true

        - name: Reboot node
          reboot:
            reboot_timeout: 600
          ignore_errors: true

        - name: Wait for node to come back online
          wait_for_connection:
            delay: 60
            timeout: 300
          ignore_errors: true

      rescue:
        - name: Handle cleanup failure
          debug:
            msg: "Cleanup failed on {{ inventory_hostname }}. Please manually inspect and clean up the system. Check disk space, network configuration, and Kubernetes component logs."