https://github.com/etcd-io/etcd/blob/master/Documentation/op-guide/
1. 常用命令
#查看集群member情况
etcdctl --endpoints=${exist-advertise-peer-urls} member list
#动态扩容
etcdctl --endpoints=${exist-advertise-peer-urls} member add infra4 --peer-urls=${new-advertise-peer-urls}
#运行时缩容
etcdctl --endpoints=${exist-advertise-peer-urls} member remove ${cluster_id}
2. 重要启动参数说明
2.1. --initial-cluster-state
Initial cluster state ("new" or "existing"). Set to new for all members present during initial static or DNS bootstrapping.
If this option is set to existing, etcd will attempt to join the existing cluster. If the wrong value is set,
etcd will attempt to start but fail safely.
default: "new"
env variable: ETCD_INITIAL_CLUSTER_STATE
- 设置成existing，必须确保在启动时候其他member是存活的（peer端口），否则启动失败。用在扩容新实例的启动。
- 设置成new，用在cluster已知member的启动。
3. 常见操作
3.1. 如何缩容？
使用member remove命令进行缩容
3.2. 如何扩容？
- 使用member add命令进行扩容。控制台会输出如下内容（新节点加入集群的重要启动参数）：
#新节点加入集群的重要启动参数，按照参数去启动：
ETCD_NAME="infra1"
ETCD_INITIAL_CLUSTER="infra3=http://127.0.0.1:32380,infra2=http://127.0.0.1:22380,infra1=http://127.0.0.1:12380"
ETCD_INITIAL_ADVERTISE_PEER_URLS="http://127.0.0.1:12380"
ETCD_INITIAL_CLUSTER_STATE="existing"
- 启动新实例的参数：--name、--initial-advertise-peer-urls、--initial-cluster-state、--initial-cluster必须和控制台输出保持一致，否则启动失败。示例：
etcd \
--name ${ETCD_NAME} \
--listen-client-urls http://127.0.0.1:42379 \
--advertise-client-urls http://127.0.0.1:42379 \
--listen-peer-urls http://127.0.0.1:42380 \
--initial-advertise-peer-urls ${ETCD_INITIAL_ADVERTISE_PEER_URLS} \
--initial-cluster-state ${ETCD_INITIAL_CLUSTER_STATE} \
--initial-cluster ${ETCD_INITIAL_CLUSTER}
3.3. 数据目录丢失或被误删除，节点启动失败或者加入集群报错？
3.3.1. 操作步骤
member信息会持久化到磁盘上，数据丢失的节点必须以新的member身份加入，必须严格按照如下操作：
- 移除failure节点：使用member remove命令剔除错误节点。保证当前集群的健康状况。
- 彻底清理数据目录：错误节点必须停止，然后删除data dir。保证member信息被清理干净。
- 集群扩容：使用member add命令添加步骤1的错误节点。参考3.2。
- 重新启动：步骤1的错误节点进行启动，参考3.2
3.3.2. 操作步骤不正确的各种常见错误日志
- 数据丢失后，启动参数使用 --initial-cluster-state="new"，错误日志如下，提示：member ddd67b312462fd7b has already been bootstrapped
2019-07-09 00:24:55.880988 I | etcdmain: etcd Version: 3.3.10
2019-07-09 00:24:55.881077 I | etcdmain: Git SHA: 27fc7e2
2019-07-09 00:24:55.881082 I | etcdmain: Go Version: go1.10.4
2019-07-09 00:24:55.881089 I | etcdmain: Go OS/Arch: darwin/amd64
2019-07-09 00:24:55.881093 I | etcdmain: setting maximum number of CPUs to 8, total number of available CPUs is 8
2019-07-09 00:24:55.881099 N | etcdmain: failed to detect default host (default host not supported on darwin_amd64)
2019-07-09 00:24:55.881106 W | etcdmain: no data-dir provided, using default data-dir ./infra1.etcd
2019-07-09 00:24:55.881236 I | embed: listening for peers on http://127.0.0.1:12380
2019-07-09 00:24:55.881254 I | embed: pprof is enabled under /debug/pprof
2019-07-09 00:24:55.881299 I | embed: listening for client requests on 127.0.0.1:2380
2019-07-09 00:24:55.883626 C | etcdmain: member ddd67b312462fd7b has already been bootstrapped
- 数据丢失后，启动参数使用 --initial-cluster-state="existing"，错误日志如下，提示：Was the raft log corrupted, truncated, or lost?
tocommit(10) is out of range [lastIndex(0)]. Was the raft log corrupted, truncated, or lost?
panic: tocommit(10) is out of range [lastIndex(0)]. Was the raft log corrupted, truncated, or lost?
goroutine 135 [running]:
github.com/coreos/etcd/cmd/vendor/github.com/coreos/pkg/capnslog.(*PackageLogger).Panicf(0xc42000a660, 0x1c0cad8, 0x5d, 0xc42000a160, 0x2, 0x2)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/pkg/capnslog/pkg_logger.go:75 +0x162
github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft.(*raftLog).commitTo(0xc420277500, 0xa)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft/log.go:191 +0x15c
github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft.(*raft).handleHeartbeat(0xc420244300, 0x8, 0xddd67b312462fd7b, 0x9e737febb6b99eee, 0x5, 0x0, 0x0, 0x0, 0x0, 0x0, ...)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft/raft.go:1194 +0x54
github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft.stepFollower(0xc420244300, 0x8, 0xddd67b312462fd7b, 0x9e737febb6b99eee, 0x5, 0x0, 0x0, 0x0, 0x0, 0x0, ...)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft/raft.go:1140 +0x3ff
github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft.(*raft).Step(0xc420244300, 0x8, 0xddd67b312462fd7b, 0x9e737febb6b99eee, 0x5, 0x0, 0x0, 0x0, 0x0, 0x0, ...)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft/raft.go:868 +0x12f1
github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft.(*node).run(0xc4201df320, 0xc420244300)
/tmp/etcd-release-3.3.10/etcd/release/etcd/gopath/src/github.com/coreos/etcd/cmd/vendor/github.com/coreos/etcd/raft/node.go:323 +0x1059
- 3.3.1步骤中1和3正确执行，而遗漏步骤2并且中间有错误启动，使得磁盘留有错误member信息。错误日志如下，提示。
2019-07-09 01:24:19.311630 E | rafthttp: failed to find member 9e737febb6b99eee in cluster 73841b4a9097c907
2019-07-09 01:24:19.311710 E | rafthttp: failed to find member 628170c800dbcee in cluster 73841b4a9097c907
2019-07-09 01:24:19.410573 E | rafthttp: failed to find member 9e737febb6b99eee in cluster 73841b4a9097c907
2019-07-09 01:24:19.410616 E | rafthttp: failed to find member 628170c800dbcee in cluster 73841b4a9097c907
2019-07-09 01:24:19.410678 E | rafthttp: failed to find member 9e737febb6b99eee in cluster 73841b4a9097c907
2019-07-09 01:24:19.410767 E | rafthttp: failed to find member 628170c800dbcee in cluster 73841b4a9097c907
