备份ETCD

备份 https://127.0.0.1:2379 上的 etcd 数据到 /var/lib/backup/etcd-snapshot.db,使用之前的文
件 /data/backup/etcd-snapshot-previous.db 还原 etcd,使用指定的 ca.crt 、 etcd-client.crt 、
etcd-client.key

https://kubernetes.io/docs/tasks/administer-cluster/configure-upgrade-etcd/#backing-up-an-etcd-cluster

# 安装etcdctl
https://github.com/etcd-io/etcd/releases

# 部署一个Pod
apiVersion: v1
kind: Pod
metadata:
  name: counter
spec:
  containers:
  - name: count
    image: busybox
    args:
    - /bin/sh
    - -c
    - >
      i=0;
      while true;
      do
        echo $(date)
        sleep 2;
      done      

controlplane ~ ➜  vi count.yml

controlplane ~ ➜  kubectl apply -f count.yml 
pod/counter created

controlplane ~ ➜  kubectl logs counter 
Mon Jul 29 04:11:12 UTC 2024
Mon Jul 29 04:11:14 UTC 2024
Mon Jul 29 04:11:16 UTC 2024

#!/bin/bash

ETCD_VERSION=${ETCD_VERSION:-v3.3.1}

curl -L https://github.com/coreos/etcd/releases/download/$ETCD_VERSION/etcd-$ETCD_VERSION-linux-amd64.tar.gz -o etcd-$ETCD_VERSION-linux-amd64.tar.gz

tar xzvf etcd-$ETCD_VERSION-linux-amd64.tar.gz
rm etcd-$ETCD_VERSION-linux-amd64.tar.gz

cd etcd-$ETCD_VERSION-linux-amd64
sudo cp etcd /usr/local/bin/
sudo cp etcdctl /usr/local/bin/

rm -rf etcd-$ETCD_VERSION-linux-amd64

etcdctl --version

# 安装etcdctl

# 获取etcd信息
controlplane ~ ➜  kubectl get pod -n kube-system etcd-controlplane -o=jsonpath='{.spec.containers[0].command}'
["etcd","--advertise-client-urls=https://192.7.195.8:2379","--cert-file=/etc/kubernetes/pki/etcd/server.crt","--client-cert-auth=true","--data-dir=/var/lib/etcd","--experimental-initial-corrupt-check=true","--experimental-watch-progress-notify-interval=5s","--initial-advertise-peer-urls=https://192.7.195.8:2380","--initial-cluster=controlplane=https://192.7.195.8:2380","--key-file=/etc/kubernetes/pki/etcd/server.key","--listen-client-urls=https://127.0.0.1:2379,https://192.7.195.8:2379","--listen-metrics-urls=http://127.0.0.1:2381","--listen-peer-urls=https://192.7.195.8:2380","--name=controlplane","--peer-cert-file=/etc/kubernetes/pki/etcd/peer.crt","--peer-client-cert-auth=true","--peer-key-file=/etc/kubernetes/pki/etcd/peer.key","--peer-trusted-ca-file=/etc/kubernetes/pki/etcd/ca.crt","--snapshot-count=10000","--trusted-ca-file=/etc/kubernetes/pki/etcd/ca.crt"]




# 使用etcdctl备份 /data/backup/etcd-snapshot-previous.db


ETCDCTL_API=3 etcdctl --endpoints=https://127.0.0.1:2379 \
  --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/server.crt --key=/etc/kubernetes/pki/etcd/server.key \
  snapshot save /data/backup/etcd-snapshot-previous.db



controlplane ~ ➜  ETCDCTL_API=3 etcdctl --endpoints=https://127.0.0.1:2379   --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/server.crt --key=/etc/kubernetes/pki/etcd/server.key   snapshot save /data/backup/etcd-snapshot-previous.db
Snapshot saved at /data/backup/etcd-snapshot-previous.db



# 删除当前pod

controlplane ~ ➜  kubectl delete pod counter 
pod "counter" deleted

controlplane ~ ➜  kubectl get pod
No resources found in default namespace.

# 备份当前etcd数据
 ETCDCTL_API=3 etcdctl --endpoints=https://127.0.0.1:2379   --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/server.crt --key=/etc/kubernetes/pki/etcd/server.key   snapshot save /var/lib/backup/etcd-snapshot.db


 # 使用/data/backup/etcd-snapshot-previous.db还原

 

• 停止所有 API 服务器实例
• 为所有 etcd 实例恢复状态
• 重启所有 API 服务器实例

controlplane ~ ➜  mv /etc/kubernetes/manifests /etc/kubernetes/manifests.bak

controlplane ~ ➜  mv /var/lib/etcd /var/lib/etcd.bak

controlplane ~ ➜  kubectl get pod -n -A
The connection to the server controlplane:6443 was refused - did you specify the right host or port?

export ETCDCTL_API=3
etcdctl --data-dir=/var/lib/etcd  snapshot restore /data/backup/etcd-snapshot-previous.db

# 重建
controlplane ~ ✖ export ETCDCTL_API=3
etcdctl --data-dir=/var/lib/etcd  snapshot restore /data/backup/etcd-snapshot-previous.db
2024-07-29 05:22:53.805370 I | mvcc: restore compact to 4738
2024-07-29 05:22:53.810432 I | etcdserver/membership: added member 8e9e05c52164694d [http://localhost:2380] to cluster cdf818194e3a8c32
# 发现已经删除的pod已经恢复但没有完全恢复
controlplane ~ ➜  kubectl get pod 
NAME      READY   STATUS    RESTARTS   AGE
counter   1/1     Running   0          23m

controlplane ~ ➜  kubectl logs counter 
Error from server (NotFound): the server could not find the requested resource ( pods/log counter)
# 可以删除重建此Pod