深入浅析Redis 集群伸缩原理

# 若节点已加入其它集群或包含数据，会报错
add-node    new_host:new_port existing_host:existing_port
            --cluster-slave  # 直接添加为从节点
            --cluster-master-id <arg>  # 从节点对应的主节点id

def move_slot(source,target,slot):
    # 目标节点准备导入槽
    target.cluster("setslot",slot,"importing",source.nodeId);
    # 目标节点准备全出槽
    source.cluster("setslot",slot,"migrating",target.nodeId);
    while true :
        # 批量从源节点获取键
        keys = source.cluster("getkeysinslot",slot,pipeline_size);
        if keys.length == 0:
            # 键列表为空时，退出循环
            break;
        # 批量迁移键到目标节点
        source.call("migrate",target.host,target.port,"",0,timeout,"keys",keys);
        # 向集群所有主节点通知槽被分配给目标节点
        for node in nodes:
            if node.flag == "slave":
                continue;
            node.cluster("setslot",slot,"node",target.nodeId);

192.168.11.40:9007> cluster nodes
8ccdb0963411ebd05ce21952bdd4b7597825afdc 192.168.11.40:9001@19001 master - 0 1620928869000 2 connected 0-5461
bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d 192.168.11.40:9007@19007 myself,master - 0 1620928868000 0 connected
...
# 9007 准备导入槽 4096 的数据
192.168.11.40:9007> cluster setslot 4096 importing 8ccdb0963411ebd05ce21952bdd4b7597825afdc
OK
# 槽 4096 已开启导入状态
192.168.11.40:9007> cluster nodes
bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d 192.168.11.40:9007@19007 myself,master - 0 1620928959000 0 connected [4096-<-8ccdb0963411ebd05ce21952bdd4b7597825afdc]
...

# 9001 准备导出槽 4096 数据
192.168.11.40:9001> cluster setslot 4096 migrating bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d
OK
# 槽 4096 已开启导出状态
192.168.11.40:9001> cluster nodes
8ccdb0963411ebd05ce21952bdd4b7597825afdc 192.168.11.40:9001@19001 myself,master - 0 1620929179000 2 connected 0-5461 [4096->-bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d]
...

# 获取 100 个属于槽 4096 的键
192.168.11.40:9001> cluster getkeysinslot 4096 100
1) "key:test:5028"
2) "key:test:68253"
# 查看数据
192.168.11.40:9001> mget key:test:5028 key:test:68253
1) "value:5028"
2) "value:68253"
# 迁移这2个键：migrate 命令保证了每个键迁移过程的原子性
192.168.11.40:9001> migrate 192.168.11.40 9007 "" 0 5000 keys key:test:5028 key:test:68253
OK
# 再次查询会报 ASK 错误：引导客户端找到数据所在的节点
192.168.11.40:9001> mget key:test:5028 key:test:68253
(error) ASK 4096 192.168.11.40:9007

192.168.11.40:9001> cluster setslot 4096 node bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d
192.168.11.40:9002> cluster setslot 4096 node bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d
192.168.11.40:9003> cluster setslot 4096 node bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d
192.168.11.40:9007> cluster setslot 4096 node bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d

reshard    host:port  # 集群内任意节点地址
           --cluster-from <arg>  # 源节点id，逗号分隔
           --cluster-to <arg>  # 目标节点id，只有一个
           --cluster-slots <arg>  # 迁移多少个槽
           --cluster-yes  # 确认执行reshard
           --cluster-timeout <arg>  # 每次 migrate 操作的超时时间，默认 60000ms
           --cluster-pipeline <arg>  # 每次批量迁移键的数量，默认 10
           --cluster-replace

$ /usr/local/redis/bin/redis-cli --cluster reshard 192.168.11.40:9001
M: 8ccdb0963411ebd05ce21952bdd4b7597825afdc 192.168.11.40:9001
   slots:[0-4095],[4097-5461] (5461 slots) master
   1 additional replica(s)
M: bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d 192.168.11.40:9007
   slots:[4096] (1 slots) master
...
[OK] All 16384 slots covered.
How many slots do you want to move (from 1 to 16384)? 4096
What is the receiving node ID? bb1bb0f5f9e0ee67846ba8ec94a38da700e2e80d
Please enter all the source node IDs.
  Type 'all' to use all the nodes as source nodes for the hash slots.
  Type 'done' once you entered all the source nodes IDs.
Source node #1: 8ccdb0963411ebd05ce21952bdd4b7597825afdc
Source node #2: 5786e3237c7fa413ed22465d15be721f95e72cfa
Source node #3: 85ceb9826e8aa003169c46fb4ba115c72002d4f9
Source node #4: done
    Moving slot 0 from 8ccdb0963411ebd05ce21952bdd4b7597825afdc
    ...
    Moving slot 12287 from 85ceb9826e8aa003169c46fb4ba115c72002d4f9
Do you want to proceed with the proposed reshard plan (yes/no)? yes
Moving slot 0 from 192.168.11.40:9001 to 192.168.11.40:9007:
...
Moving slot 12287 from 192.168.11.40:9003 to 192.168.11.40:9007:

$ /usr/local/redis/bin/redis-cli --cluster rebalance 192.168.11.40:9001
...
[OK] All 16384 slots covered.
*** No rebalancing needed! All nodes are within the 2.00% threshold.

# 执行后，会将该节点加入禁用列表（持续 60s），不再向其发送 Gossip 消息
cluster forget {nodeId}

/usr/local/redis/bin/redis-cli --cluster del-node {host:port} {nodeId}

def delnode_cluster_cmd(downNode):
    # 下线节点不允许包含slots
    if downNode.slots.length != 0
        exit 1
    end
    # 向集群内节点发送cluster forget
    for n in nodes:
        if n.id == downNode.id:
            # 不能对自己做forget操作
            continue;
        # 如果下线节点有从节点则把从节点指向其他主节点
        if n.replicate && n.replicate.nodeId == downNode.id :
            # 指向拥有最少从节点的主节点
            master = get_master_with_least_replicas();
            n.cluster("replicate",master.nodeId);
        #发送忘记节点命令
        n.cluster('forget',downNode.id)
    # 节点关闭
    downNode.shutdown();