服务器断电后无法重启pd

🪐 TiDB 技术问题
1

[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/pd/api/v1]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/swagger/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/dashboard/api/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/dashboard/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [systime_mon.go:26] [“start system time monitor”]
[2020/09/22 16:07:32.080 +08:00] [INFO] [etcd.go:117] [“configuring peer listeners”] [listen-peer-urls="[http://192.168.1.106:2380]"]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:127] [“configuring client listeners”] [listen-client-urls="[http://192.168.1.106:2379]"]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:602] [“pprof is enabled”] [path=/debug/pprof]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:299] [“starting an etcd server”] [etcd-version=3.4.3] [git-sha=“Not provided (use ./build instead of go build)”] [go-version=go1.13] [go-os=linux] [go-arch=amd64] [max-cpu-set=4] [max-cpu-available=4] [member-initialized=true] [name=pd-192.168.1.106-2379] [data-dir=/rhzy/tidb/tidb-data/pd] [wal-dir=] [wal-dir-dedicated=] [member-dir=/rhzy/tidb/tidb-data/pd/member] [force-new-cluster=false] [heartbeat-interval=500ms] [election-timeout=3s] [initial-election-tick-advance=true] [snapshot-count=100000] [snapshot-catchup-entries=5000] [initial-advertise-peer-urls="[http://192.168.1.106:2380]"] [listen-peer-urls="[http://192.168.1.106:2380]"] [advertise-client-urls="[http://192.168.1.106:2379]"] [listen-client-urls="[http://192.168.1.106:2379]"] [listen-metrics-urls="[]"] [cors="[]"] [host-whitelist="[]"] [initial-cluster=] [initial-cluster-state=new] [initial-cluster-token=] [quota-size-bytes=8589934592] [pre-vote=true] [initial-corrupt-check=false] [corrupt-check-time-interval=0s] [auto-compaction-mode=periodic] [auto-compaction-retention=1h0m0s] [auto-compaction-interval=1h0m0s] [discovery-url=] [discovery-proxy=]
[2020/09/22 16:07:32.082 +08:00] [INFO] [backend.go:79] [“opened backend db”] [path=tidb/tidb-data/pd/member/snap/db] [took=1.18786ms]
[2020/09/22 16:07:32.084 +08:00] [INFO] [server.go:443] [“recovered v2 store from snapshot”] [snapshot-index=21600218] [snapshot-size=“29 kB”]
[2020/09/22 16:07:32.085 +08:00] [WARN] [db.go:92] [“failed to find [SNAPSHOT-INDEX].snap.db”] [snapshot-index=21600218] [snapshot-file-path=/tidb/tidb-data/pd/member/snap/00000000014997da.snap.db] [error=“snap: snapshot file doesn’t exist”]
[2020/09/22 16:07:32.085 +08:00] [PANIC] [server.go:454] [“failed to recover v3 backend from snapshot”] [error=“failed to find database snapshot file (snap: snapshot file doesn’t exist)”]
[2020/09/22 16:07:32.085 +08:00] [FATAL] [log.go:292] [panic] [recover="“invalid memory address or nil pointer dereference”"] [stack=“github.com/pingcap/log.Fatal\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/github.com/pingcap/log@v0.0.0-20200117041106-d28c14d3b1cd/global.go:59\ github.com/pingcap/pd/v4/pkg/logutil.LogPanic\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/pkg/logutil/log.go:292\ runtime.gopanic\ \t/usr/local/go/src/runtime/panic.go:679\ runtime.panicmem\ \t/usr/local/go/src/runtime/panic.go:199\ runtime.sigpanic\ \t/usr/local/go/src/runtime/signal_unix.go:394\ go.etcd.io/etcd/etcdserver.NewServer.func1\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/etcdserver/server.go:335\ runtime.gopanic\ \t/usr/local/go/src/runtime/panic.go:679\ go.uber.org/zap/zapcore.(*CheckedEntry).Write\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.uber.org/zap@v1.13.0/zapcore/entry.go:230\ngo.uber.org/zap.(*Logger).Panic\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.uber.org/zap@v1.13.0/logger.go:225\ngo.etcd.io/etcd/etcdserver.NewServer\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/etcdserver/server.go:454\ go.etcd.io/etcd/embed.StartEtcd\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/embed/etcd.go:211\ github.com/pingcap/pd/v4/server.(*Server).startEtcd\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:257\ngithub.com/pingcap/pd/v4/server.(*Server).Run\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:441\ main.main\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/cmd/pd-server/main.go:118\ runtime.main\ \t/usr/local/go/src/runtime/proc.go:203”]
…skipping…
69b5738/embed/etcd.go:211\ngithub.com/pingcap/pd/v4/server.(Server).startEtcd\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:257\ngithub.com/pingcap/pd/v4/server.(Server).Run\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:441\ main.main\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/cmd/pd-server/main.go:118\ runtime.main\ \t/usr/local/go/src/runtime/proc.go:203"]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:50] [“Welcome to Placement Driver (PD)”]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:51] [PD] [release-version=v4.0.0]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:52] [PD] [edition=Community]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:53] [PD] [git-hash=56d4c3d2237f5bf6fb11a794731ed1d95c8020c2]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:54] [PD] [git-branch=heads/refs/tags/v4.0.0]
[2020/09/22 16:07:32.077 +08:00] [INFO] [util.go:55] [PD] [utc-build-time=“2020-05-28 01:39:35”]
[2020/09/22 16:07:32.077 +08:00] [INFO] [metricutil.go:81] [“disable Prometheus push client”]
[2020/09/22 16:07:32.077 +08:00] [INFO] [server.go:209] [“PD Config”] [config="{“client-urls”:“http://192.168.1.106:2379”,“peer-urls”:“http://192.168.1.106:2380”,“advertise-client-urls”:“http://192.168.1.106:2379”,“advertise-peer-urls”:“http://192.168.1.106:2380”,“name”:“pd-192.168.1.106-2379”,“data-dir”:"/rhzy/tidb/tidb-data/pd",“force-new-cluster”:false,“enable-grpc-gateway”:true,“initial-cluster”:“pd-192.168.1.106-2379=http://192.168.1.106:2380,pd-192.168.1.107-2379=http://192.168.1.107:2380,pd-192.168.1.108-2379=http://192.168.1.108:2380”,“initial-cluster-state”:“new”,“join”:"",“lease”:3,“log”:{“level”:"",“format”:“text”,“disable-timestamp”:false,“file”:{“filename”:"/rhzy/tidb/log/pd/pd.log",“max-size”:300,“max-days”:0,“max-backups”:0},“development”:false,“disable-caller”:false,“disable-stacktrace”:false,“disable-error-verbose”:true,“sampling”:null},“tso-save-interval”:“3s”,“metric”:{“job”:“pd-192.168.1.106-2379”,“address”:"",“interval”:“15s”},“schedule”:{“max-snapshot-count”:3,“max-pending-peer-count”:16,“max-merge-region-size”:20,“max-merge-region-keys”:200000,“split-merge-interval”:“1h0m0s”,“enable-one-way-merge”:“false”,“enable-cross-table-merge”:“false”,“patrol-region-interval”:“100ms”,“max-store-down-time”:“30m0s”,“leader-schedule-limit”:4,“leader-schedule-policy”:“count”,“region-schedule-limit”:2048,“replica-schedule-limit”:64,“merge-schedule-limit”:8,“hot-region-schedule-limit”:4,“hot-region-cache-hits-threshold”:3,“store-balance-rate”:15,“tolerant-size-ratio”:0,“low-space-ratio”:0.8,“high-space-ratio”:0.7,“scheduler-max-waiting-operator”:5,“enable-remove-down-replica”:“true”,“enable-replace-offline-replica”:“true”,“enable-make-up-replica”:“true”,“enable-remove-extra-replica”:“true”,“enable-location-replacement”:“true”,“enable-debug-metrics”:“false”,“schedulers-v2”:[{“type”:“balance-region”,“args”:null,“disable”:false,“args-payload”:""},{“type”:“balance-leader”,“args”:null,“disable”:false,“args-payload”:""},{“type”:“hot-region”,“args”:null,“disable”:false,“args-payload”:""},{“type”:“label”,“args”:null,“disable”:false,“args-payload”:""}],“schedulers-payload”:null,“store-limit-mode”:“manual”},“replication”:{“max-replicas”:3,“location-labels”:"",“strictly-match-label”:“false”,“enable-placement-rules”:“true”},“pd-server”:{“use-region-storage”:“true”,“max-gap-reset-ts”:“24h0m0s”,“key-type”:“table”,“runtime-services”:"",“metric-storage”:“http://192.168.1.99:9090”,“dashboard-address”:“auto”},“cluster-version”:“0.0.0”,“quota-backend-bytes”:“8GiB”,“auto-compaction-mode”:“periodic”,“auto-compaction-retention-v2”:“1h”,“TickInterval”:“500ms”,“ElectionInterval”:“3s”,“PreVote”:true,“security”:{“cacert-path”:"",“cert-path”:"",“key-path”:"",“cert-allowed-cn”:null},“label-property”:null,“WarningMsgs”:null,“DisableStrictReconfigCheck”:false,“HeartbeatStreamBindInterval”:“1m0s”,“LeaderPriorityCheckInterval”:“1m0s”,“dashboard”:{“tidb_cacert_path”:"",“tidb_cert_path”:"",“tidb_key_path”:"",“public_path_prefix”:"/dashboard"},“replication-mode”:{“replication-mode”:“majority”,“dr-auto-sync”:{“label-key”:"",“primary”:"",“dr”:"",“primary-replicas”:0,“dr-replicas”:0,“wait-store-timeout”:“1m0s”,“wait-sync-timeout”:“1m0s”}}}"]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/pd/api/v1]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/swagger/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/dashboard/api/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [server.go:182] [“register REST path”] [path=/dashboard/]
[2020/09/22 16:07:32.080 +08:00] [INFO] [systime_mon.go:26] [“start system time monitor”]
[2020/09/22 16:07:32.080 +08:00] [INFO] [etcd.go:117] [“configuring peer listeners”] [listen-peer-urls="[http://192.168.1.106:2380]"]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:127] [“configuring client listeners”] [listen-client-urls="[http://192.168.1.106:2379]"]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:602] [“pprof is enabled”] [path=/debug/pprof]
[2020/09/22 16:07:32.081 +08:00] [INFO] [etcd.go:299] [“starting an etcd server”] [etcd-version=3.4.3] [git-sha=“Not provided (use ./build instead of go build)”] [go-version=go1.13] [go-os=linux] [go-arch=amd64] [max-cpu-set=4] [max-cpu-available=4] [member-initialized=true] [name=pd-192.168.1.106-2379] [data-dir=/rhzy/tidb/tidb-data/pd] [wal-dir=] [wal-dir-dedicated=] [member-dir=/rhzy/tidb/tidb-data/pd/member] [force-new-cluster=false] [heartbeat-interval=500ms] [election-timeout=3s] [initial-election-tick-advance=true] [snapshot-count=100000] [snapshot-catchup-entries=5000] [initial-advertise-peer-urls="[http://192.168.1.106:2380]"] [listen-peer-urls="[http://192.168.1.106:2380]"] [advertise-client-urls="[http://192.168.1.106:2379]"] [listen-client-urls="[http://192.168.1.106:2379]"] [listen-metrics-urls="[]"] [cors="[]"] [host-whitelist="[]"] [initial-cluster=] [initial-cluster-state=new] [initial-cluster-token=] [quota-size-bytes=8589934592] [pre-vote=true] [initial-corrupt-check=false] [corrupt-check-time-interval=0s] [auto-compaction-mode=periodic] [auto-compaction-retention=1h0m0s] [auto-compaction-interval=1h0m0s] [discovery-url=] [discovery-proxy=]
[2020/09/22 16:07:32.082 +08:00] [INFO] [backend.go:79] [“opened backend db”] [path=/rhzy/tidb/tidb-data/pd/member/snap/db] [took=1.18786ms]
[2020/09/22 16:07:32.084 +08:00] [INFO] [server.go:443] [“recovered v2 store from snapshot”] [snapshot-index=21600218] [snapshot-size=“29 kB”]
[2020/09/22 16:07:32.085 +08:00] [WARN] [db.go:92] [“failed to find [SNAPSHOT-INDEX].snap.db”] [snapshot-index=21600218] [snapshot-file-path=/tidb/tidb-data/pd/member/snap/00000000014997da.snap.db] [error=“snap: snapshot file doesn’t exist”]
[2020/09/22 16:07:32.085 +08:00] [PANIC] [server.go:454] [“failed to recover v3 backend from snapshot”] [error=“failed to find database snapshot file (snap: snapshot file doesn’t exist)”]
[2020/09/22 16:07:32.085 +08:00] [FATAL] [log.go:292] [panic] [recover="“invalid memory address or nil pointer dereference”"] [stack=“github.com/pingcap/log.Fatal\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/github.com/pingcap/log@v0.0.0-20200117041106-d28c14d3b1cd/global.go:59\ github.com/pingcap/pd/v4/pkg/logutil.LogPanic\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/pkg/logutil/log.go:292\ runtime.gopanic\ \t/usr/local/go/src/runtime/panic.go:679\ runtime.panicmem\ \t/usr/local/go/src/runtime/panic.go:199\ runtime.sigpanic\ \t/usr/local/go/src/runtime/signal_unix.go:394\ go.etcd.io/etcd/etcdserver.NewServer.func1\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/etcdserver/server.go:335\ runtime.gopanic\ \t/usr/local/go/src/runtime/panic.go:679\ go.uber.org/zap/zapcore.(*CheckedEntry).Write\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.uber.org/zap@v1.13.0/zapcore/entry.go:230\ngo.uber.org/zap.(*Logger).Panic\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.uber.org/zap@v1.13.0/logger.go:225\ngo.etcd.io/etcd/etcdserver.NewServer\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/etcdserver/server.go:454\ go.etcd.io/etcd/embed.StartEtcd\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/pkg/mod/go.etcd.io/etcd@v0.5.0-alpha.5.0.20191023171146-3cf2f69b5738/embed/etcd.go:211\ github.com/pingcap/pd/v4/server.(*Server).startEtcd\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:257\ngithub.com/pingcap/pd/v4/server.(*Server).Run\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/server/server.go:441\ main.main\ \t/home/jenkins/agent/workspace/build_pd_multi_branch_v4.0.0/go/src/github.com/pingcap/pd/cmd/pd-server/main.go:118\ runtime.main\ \t/usr/local/go/src/runtime/proc.go:203”]

2

你好，请问一下是部分 PD 节点无法启动还是全部的 PD 节点无法启动？
1.如果是部分 PD 节点无法启动，可以考虑通过缩容方式下线异常 PD 节点，然后再重新扩容下 PD 节点；
2.如果是全部 PD 节点无法启动，可以考虑使用 pd-recover 恢复下 pd 集群，使用方法参考如下文档：
https://docs.pingcap.com/zh/tidb/stable/pd-recover

4

缩容都出问题了

r=tidb, host=192.168.1.100\ UserSSH: user=tidb, host=192.168.1.101\ UserSSH: user=tidb, host=192.168.1.102\ UserSSH: user=tidb, host=192.168.1.106\ UserSSH: user=tidb, host=192.168.1.107\ UserSSH: user=tidb, host=192.168.1.108\ UserSSH: user=tidb, host=192.168.1.103\ UserSSH: user=tidb, host=192.168.1.104\ UserSSH: user=tidb, host=192.168.1.105\ UserSSH: user=tidb, host=192.168.1.109\ UserSSH: user=tidb, host=192.168.1.99\ UserSSH: user=tidb, host=192.168.1.99\ UserSSH: user=tidb, host=192.168.1.99"}
2020-09-22T17:09:04.084+0800 INFO + [ Serial ] - ClusterOperate: operation=ScaleInOperation, options={Roles:[] Nodes:[192.168.1.106:2379] Force:false SSHTimeout:5 OptTimeout:60 APITimeout:300}
2020-09-22T17:09:04.084+0800 DEBUG TaskBegin {“task”: “ClusterOperate: operation=ScaleInOperation, options={Roles:[] Nodes:[192.168.1.106:2379] Force:false SSHTimeout:5 OptTimeout:60 APITimeout:300}”}
2020-09-22T17:09:14.088+0800 DEBUG TaskFinish {“task”: “ClusterOperate: operation=ScaleInOperation, options={Roles:[] Nodes:[192.168.1.106:2379] Force:false SSHTimeout:5 OptTimeout:60 APITimeout:300}”, “error”: “failed to scale in: after trying all endpoints, no endpoint is available, the last error we met: Get http://192.168.1.108:2379/pd/api/v1/config/replicate: net/http: request canceled (Client.Timeout exceeded while awaiting headers)”, “errorVerbose”: “after trying all endpoints, no endpoint is available, the last error we met: Get http://192.168.1.108:2379/pd/api/v1/config/replicate: net/http: request canceled (Client.Timeout exceeded while awaiting headers)\ngithub.com/pingcap-incubator/tiup-cluster/pkg/api.tryURLsGet\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/api/pdapi.go:124\ github.com/pingcap-incubator/tiup-cluster/pkg/api.(*PDClient).GetReplicateConfig\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/api/pdapi.go:626\ngithub.com/pingcap-incubator/tiup-cluster/pkg/operation.ScaleInCluster\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/operation/scale_in.go:179\ github.com/pingcap-incubator/tiup-cluster/pkg/operation.ScaleIn\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/operation/scale_in.go:75\ github.com/pingcap-incubator/tiup-cluster/pkg/task.(*ClusterOperate).Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/task/action.go:70\ngithub.com/pingcap-incubator/tiup-cluster/pkg/task.(*Serial).Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/task/task.go:183\ngithub.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.scaleIn\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/scale_in.go:145\ github.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.newScaleInCmd.func1\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/scale_in.go:55\ github.com/spf13/cobra.(*Command).execute\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:842\ngithub.com/spf13/cobra.(*Command).ExecuteC\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:950\ngithub.com/spf13/cobra.(*Command).Execute\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:887\ngithub.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/root.go:212\ main.main\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/main.go:19\ runtime.main\ \t/usr/local/go/src/runtime/proc.go:203\ runtime.goexit\ \t/usr/local/go/src/runtime/asm_amd64.s:1357\ failed to scale in”}
2020-09-22T17:09:14.088+0800 INFO Execute command finished {“code”: 1, “error”: “failed to scale in: after trying all endpoints, no endpoint is available, the last error we met: Get http://192.168.1.108:2379/pd/api/v1/config/replicate: net/http: request canceled (Client.Timeout exceeded while awaiting headers)”, “errorVerbose”: “after trying all endpoints, no endpoint is available, the last error we met: Get http://192.168.1.108:2379/pd/api/v1/config/replicate: net/http: request canceled (Client.Timeout exceeded while awaiting headers)\ngithub.com/pingcap-incubator/tiup-cluster/pkg/api.tryURLsGet\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/api/pdapi.go:124\ github.com/pingcap-incubator/tiup-cluster/pkg/api.(*PDClient).GetReplicateConfig\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/api/pdapi.go:626\ngithub.com/pingcap-incubator/tiup-cluster/pkg/operation.ScaleInCluster\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/operation/scale_in.go:179\ github.com/pingcap-incubator/tiup-cluster/pkg/operation.ScaleIn\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/operation/scale_in.go:75\ github.com/pingcap-incubator/tiup-cluster/pkg/task.(*ClusterOperate).Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/task/action.go:70\ngithub.com/pingcap-incubator/tiup-cluster/pkg/task.(*Serial).Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/pkg/task/task.go:183\ngithub.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.scaleIn\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/scale_in.go:145\ github.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.newScaleInCmd.func1\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/scale_in.go:55\ github.com/spf13/cobra.(*Command).execute\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:842\ngithub.com/spf13/cobra.(*Command).ExecuteC\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:950\ngithub.com/spf13/cobra.(*Command).Execute\ \t/go/pkg/mod/github.com/spf13/cobra@v1.0.0/command.go:887\ngithub.com/pingcap-incubator/tiup-cluster/cmd/cluster/command.Execute\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/command/root.go:212\ main.main\ \t/home/jenkins/agent/workspace/tiup-cluster-release/cmd/cluster/main.go:19\ runtime.main\ \t/usr/local/go/src/runtime/proc.go:203\ runtime.goexit\ \t/usr/local/go/src/runtime/asm_amd64.s:1357\ failed to scale in”}

5

使用tiup来部署的集群 在start的时候 pd就无法启动 然后进行缩容就出现上面的问题

6

请问一下你这边机器掉电之后是所有的 pd 节点都无法启动吗？从报错信息“ “after trying all endpoints, no endpoint is available” 中看是无法找一个可用的pd 节点，从而无法完成缩容。