[BUG]promote didn't tolerate kb-data or kb-controller node taint

[ahjing99]

➜ ~ kbcli version Kubernetes: v1.24.6-aliyun.1 KubeBlocks: 0.8.1 kbcli: 0.8.1

➜  ~ k describe node | grep Taint
Taints:             kb-controller=true:NoSchedule
Taints:             kb-data=true:NoSchedule
Taints:             kb-data=true:NoSchedule

➜  ~ kbcli cluster describe mysqltest
Name: mysqltest	 Created Time: Feb 05,2024 14:41 UTC+0800
NAMESPACE   CLUSTER-DEFINITION   VERSION        STATUS    TERMINATION-POLICY
default     mysql                mysql-5.7.42   Running   WipeOut

Endpoints:
COMPONENT   MODE        INTERNAL                                         EXTERNAL
mysql       ReadWrite   mysqltest-mysql.default.svc.cluster.local:3306   <none>

Topology:
COMPONENT   INSTANCE            ROLE        STATUS    AZ                 NODE                                           CREATED-TIME
mysql       mysqltest-mysql-0   primary     Running   cn-zhangjiakou-c   cn-zhangjiakou.192.168.36.134/192.168.36.134   Feb 05,2024 14:47 UTC+0800
mysql       mysqltest-mysql-1   secondary   Running   cn-zhangjiakou-c   cn-zhangjiakou.192.168.36.133/192.168.36.133   Feb 05,2024 14:51 UTC+0800

Resources Allocation:
COMPONENT   DEDICATED   CPU(REQUEST/LIMIT)   MEMORY(REQUEST/LIMIT)             STORAGE-SIZE   STORAGE-CLASS
mysql       false       2100m / 2100m        4402341478400m / 4402341478400m   data:20Gi      kb-default-sc

Images:
COMPONENT   TYPE    IMAGE
mysql       mysql   docker.io/mysql:5.7.42

Data Protection:
BACKUP-REPO   AUTO-BACKUP   BACKUP-SCHEDULE   BACKUP-METHOD   BACKUP-RETENTION

Show cluster events: kbcli cluster list-events -n default mysqltest
➜  ~ kbcli cluster promote mysqltest --auto-approve   --component mysql
OpsRequest mysqltest-custom-d6jkl created successfully, you can view the progress:
	kbcli cluster describe-ops mysqltest-custom-d6jkl -n default

➜  ~ k get pod
NAME                                   READY   STATUS    RESTARTS   AGE
mysqltest-custom-d6jkl-mysql-0-vn4d6   0/1     Pending   0          8s
mysqltest-mysql-0                      4/4     Running   0          4m9s
mysqltest-mysql-1                      4/4     Running   0          50s
➜  ~ k describe pod mysqltest-custom-d6jkl-mysql-0-vn4d6
Name:           mysqltest-custom-d6jkl-mysql-0-vn4d6
Namespace:      default
Priority:       0
Node:           <none>
Labels:         controller-uid=649bd49d-2b48-4de3-b7b4-5f11a7088bab
                job-name=mysqltest-custom-d6jkl-mysql-0
Annotations:    <none>
Status:         Pending
IP:
IPs:            <none>
Controlled By:  Job/mysqltest-custom-d6jkl-mysql-0
Containers:
  switchover:
    Image:      docker.io/apecloud/kubeblocks-tools:latest
    Port:       <none>
    Host Port:  <none>
    Command:
      sh
      -c
      set -e
      # do switchover
      url="http://${TARGET_POD_IP}:${LORRY_HTTP_PORT}/v1.0/switchover"
      params="{\"parameters\": {\"primary\":\"${primary}\",\"candidate\":\"${candidate}\"}}"
      echo "curl ${url}, parameters: ${params}"
      res=`curl -s -X POST -H 'Content-Type: application/json' "${url}" -d "${params}"`
      echo "curl result: ${res}"

      # check if switchover successfully.
      echo "INFO: start to check if switchover successfully, timeout is 60s"
      executedUnix=$(date +%s)
      while true; do
        sleep 5
        if [ ! -z ${candidate} ]; then
           # if candidate specified, only check it
           role=$(kubectl get pod ${candidate} -ojson | jq -r '.metadata.labels["kubeblocks.io/role"]')
           if [ "$role" == "primary" ] || [ "$role" == "leader" ] || [ "$role" == "master" ]; then
              echo "INFO: switchover successfully, ${candidate} is ${role}"
              exit 0
           fi
        else
          # check if the candidate instance has been promote to primary
          pods=$(kubectl get pod -l apps.kubeblocks.io/component-name=${KB_COMP_NAME},app.kubernetes.io/instance=${KB_CLUSTER_NAME} | awk 'NR > 1 {print $1}')
          for podName in ${pods}; do
             if [ "${podName}" != "${primary}" ];then
               role=$(kubectl get pod ${podName} -ojson | jq -r '.metadata.labels["kubeblocks.io/role"]')
               if [ "$role" == "primary" ] || [ "$role" == "leader" ] || [ "$role" == "master" ]; then
                  echo "INFO: switchover successfully, ${podName} is ${role}"
                  exit 0
               fi
             fi
          done
        fi
        currentUnix=$(date +%s)
        diff_time=$((${currentUnix}-${executedUnix}))
        if [ ${diff_time} -ge 60 ]; then
          echo "ERROR: switchover failed."
          exit 1
        fi
      done

    Limits:
      cpu:     0
      memory:  0
    Requests:
      cpu:     0
      memory:  0
    Environment:
      KB_CLUSTER_NAME:            mysqltest
      KB_COMP_NAME:               mysql
      KB_CLUSTER_COMP_NAME:       mysqltest-mysql
      KB_COMP_REPLICAS:           2
      KB_COMP_HEADLESS_SVC_NAME:  mysqltest-mysql-headless
      TARGET_POD_IP:              10.114.0.143
      LORRY_HTTP_PORT:            3501
      primary:                    mysqltest-mysql-0
      candidate:
    Mounts:
      /var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-blkj8 (ro)
Conditions:
  Type           Status
  PodScheduled   False
Volumes:
  kube-api-access-blkj8:
    Type:                    Projected (a volume that contains injected data from multiple sources)
    TokenExpirationSeconds:  3607
    ConfigMapName:           kube-root-ca.crt
    ConfigMapOptional:       <nil>
    DownwardAPI:             true
QoS Class:                   BestEffort
Node-Selectors:              <none>
Tolerations:                 node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
                             node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
Events:
  Type     Reason            Age   From               Message
  ----     ------            ----  ----               -------
  Warning  FailedScheduling  16s   default-scheduler  0/3 nodes are available: 1 node(s) had untolerated taint {kb-controller: true}, 2 node(s) had untolerated taint {kb-data: true}. preemption: 0/3 nodes are available: 3 Preemption is not helpful for scheduling.,

[github-actions[bot]]

This issue has been marked as stale because it has been open for 30 days with no activity