Automation Suite 安装指南

上次更新日期 2025年4月2日

Redis 探测器失败

描述

如果节点 ID 文件不存在，则 Redis 探测器可能会失败。如果 Pod 尚未启动，则可能会发生这种情况。

有一个恢复作业可以自动修复此问题，并且不应在作业运行时执行以下步骤。

当 Redis 企业版集群与其半数以上的节点失去联系时（由于节点故障或网络拆分），集群将停止响应客户端连接。Pod 也无法重新加入集群。

解决方案

使用以下命令禁用 argo 同步，删除 Redis 数据库和 Redis 集群资源，重新启用 argo 同步，然后启动恢复作业：

kubectl -n argocd patch application fabric-installer --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl -n argocd patch application redis-cluster --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl -n argocd patch application redis-operator --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl delete redb -n redis-system redis-cluster-db --force --grace-period=0 &
kubectl delete rec -n redis-system redis-cluster --force --grace-period=0 &
kubectl patch redb -n redis-system redis-cluster-db --type=json -p '[{"op":"remove","path":"/metadata/finalizers","value":"finalizer.redisenterprisedatabases.app.redislabs.com"}]'
kubectl patch rec redis-cluster -n redis-system --type=json -p '[{"op":"remove","path":"/metadata/finalizers","value":"redbfinalizer.redisenterpriseclusters.app.redislabs.com"}]'
kubectl -n redis-system get pods | grep services-rigger | awk '{print $1}' | xargs kubectl -n redis-system delete pod --force
kubectl -n redis-system get pods | grep -E "redis-cluster-[0-2]" | awk '{print $1}' | xargs kubectl -n redis-system delete pod --force
kubectl -n argocd patch application fabric-installer --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n argocd patch application redis-cluster --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n argocd patch application redis-operator --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n redis-system create job --from=cronjob/redis-cluster-recovery-job cronjob-manual-runkubectl -n argocd patch application fabric-installer --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl -n argocd patch application redis-cluster --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl -n argocd patch application redis-operator --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":false}]'
kubectl delete redb -n redis-system redis-cluster-db --force --grace-period=0 &
kubectl delete rec -n redis-system redis-cluster --force --grace-period=0 &
kubectl patch redb -n redis-system redis-cluster-db --type=json -p '[{"op":"remove","path":"/metadata/finalizers","value":"finalizer.redisenterprisedatabases.app.redislabs.com"}]'
kubectl patch rec redis-cluster -n redis-system --type=json -p '[{"op":"remove","path":"/metadata/finalizers","value":"redbfinalizer.redisenterpriseclusters.app.redislabs.com"}]'
kubectl -n redis-system get pods | grep services-rigger | awk '{print $1}' | xargs kubectl -n redis-system delete pod --force
kubectl -n redis-system get pods | grep -E "redis-cluster-[0-2]" | awk '{print $1}' | xargs kubectl -n redis-system delete pod --force
kubectl -n argocd patch application fabric-installer --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n argocd patch application redis-cluster --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n argocd patch application redis-operator --type=json -p '[{"op":"replace","path":"/spec/syncPolicy/automated/selfHeal","value":true}]'
kubectl -n redis-system create job --from=cronjob/redis-cluster-recovery-job cronjob-manual-run