redis集羣（redis + cluster + sentinel）

概述說明

說明：本次實驗採用c1、c2、c3三臺虛擬機完成，每臺服務器上都部署一個master、一個slave和一個sentinel。當某主節點的掛了，相應的從節點替位；當某主節點及主節點對應的從節點同時掛了，將造成數據的丟失！故生產環境都採用一主多從的集羣模式！
搭建環境

服務器信息如下：

c1 192.168.10.11

c2 192.168.10.12

c3 192.168.10.13

每臺需要部署redis的服務器上配置系統參數，執行以下腳本

# cat xitongcanshu.sh

#!/bin/bash

echo 'net.core.somaxconn=512' >> /etc/sysctl.conf

echo 'vm.overcommit_memory=1' >> /etc/sysctl.conf

echo never > /sys/kernel/mm/transparent_hugepage/enabled

echo 'echo never > /sys/kernel/mm/transparent_hugepage/enabled' >> /etc/rc.local

chmod +x /etc/rc.d/rc.local

sysctl -p

cat >> /etc/security/limits.conf << EOF

* soft nofile 65535

* hard nofile 65535

* soft nproc 65535

* hard nproc 65535

EOF

ulimit -SHn 65535

ulimit -n
redis

說明：本次實驗在c1、c2、c3三臺服務器上分別部署一個master和一個slave！

[root@c1 ~]# wget http://download.redis.io/releases/redis-4.0.9.tar.gz

[root@c1 ~]# tar xf redis-4.0.9.tar.gz -C /usr/local/

[root@c1 ~]# ln -sv /usr/local/redis-4.0.9 /usr/local/redis

[root@c1 ~]# yum -y install tcl openssl-devel zlib-devel

[root@c1 /usr/local/redis]# make && make PREFIX=/usr/local/redis-4.0.9/ install

[root@c1 /usr/local/redis]# make test

[root@c1 ~]# mkdir -pv /etc/redis-cluster/{7001,7002} /var/log/redis

# 拷貝默認配置文件並根據需求修改，因實驗環境，故採用簡潔配置，如下：

[root@c1 ~]# cat /etc/redis-cluster/7001/redis.conf

port 7001

bind 192.168.10.11

cluster-enabled yes

cluster-config-file /etc/redis-cluster/7001/nodes.conf

logfile /var/log/redis/redis_7001.log

cluster-node-timeout 5000

appendonly yes

daemonize yes

[root@c1 ~]# cat /etc/redis-cluster/7002/redis.conf

port 7002

bind 192.168.10.12

cluster-enabled yes

cluster-config-file /etc/redis-cluster/7002/nodes.conf

logfile /var/log/redis/redis_7002.log

cluster-node-timeout 5000

appendonly yes

daemonize yes

# 啓動

[root@c1 ~]# /usr/local/redis/bin/redis-server /etc/redis-cluster/7001/redis.conf

[root@c1 ~]# /usr/local/redis/bin/redis-server /etc/redis-cluster/7002/redis.conf

# c2、c3服務器也進行以上操作，配置只需修改對應的ip即可！
cluster

說明：本次實驗主從關係如下：

c1 master --- c2 slave M/S 1

c2 master --- c3 slave M/S 2

c3 master --- c1 slave M/S 3

# 說明：框內內容是編譯安裝ruby工具，以便能成功執行redis-trib.rb創建集羣，；yum方式安裝ruby可能版本較低！

[root@c1 ~]# wget https://cache.ruby-lang.org/pub/ruby/2.5/ruby-2.5.1.tar.gz

[root@c1 ~]# wget https://rubygems.org/downloads/redis-4.0.0.gem

[root@c1 ~]# tar -xf ruby-2.5.1.tar.gz -C /usr/local/

[root@c1 /usr/local/ruby-2.5.1]# ./configure -prefix=/usr/local/ruby-2.5.1

[root@c1 /usr/local/ruby-2.5.1]# make && make install

[root@c1 ~]# ln -sv /usr/local/ruby-2.5.1/bin/gem /usr/bin/gem

[root@c1 ~]# ln -sv /usr/local/ruby-2.5.1/bin/ruby /usr/bin/ruby

# 在配置文件/usr/local/ruby-2.5.1/ext/openssl/Makefile和/usr/local/ruby-2.5.1/ext/zlib/Makefile中的定義變量處加上如下紅色行，若存在相應變量的定義請註釋；

srcdir = .

top_srcdir = ../..

topdir = /usr/local/ruby-2.5.1/include/ruby-2.5.0

[root@c1 /usr/local/ruby-2.5.1/ext/zlib]# ruby extconf.rb

[root@c1 /usr/local/ruby-2.5.1/ext/zlib]# make && make install

[root@c1 /usr/local/ruby-2.5.1/ext/openssl]# ruby extconf.rb

[root@c1 /usr/local/ruby-2.5.1/ext/openssl]# make && make install

[root@c1 ~]# gem install -l redis-4.0.0.gem

# 創建集羣，格式：主主主從從從

[root@c1 ~]# /usr/local/redis/src/redis-trib.rb create --replicas 1 192.168.10.11:7001 192.168.10.12:7001 192.168.10.13:7001 192.168.10.12:7002 192.168.10.13:7002 192.168.10.11:7002

>>> Creating cluster

>>> Performing hash slots allocation on 6 nodes...

Using 3 masters:

192.168.10.11:7001

192.168.10.12:7001

192.168.10.13:7001

Adding replica 192.168.10.12:7002 to 192.168.10.11:7001

Adding replica 192.168.10.13:7002 to 192.168.10.12:7001

Adding replica 192.168.10.11:7002 to 192.168.10.13:7001

M: 440541e2a3235205bf190336a1f37f127d18bf60 192.168.10.11:7001

slots:0-5460 (5461 slots) master

M: c588a93825de6e0e6730a8bbb072684619201803 192.168.10.12:7001

slots:5461-10922 (5462 slots) master

M: 9ba21cfda0fed2d9013103e934f199a247c378ef 192.168.10.13:7001

slots:10923-16383 (5461 slots) master

S: f07abd56170635aaad5166bd38af9f7267834ca7 192.168.10.12:7002

replicates 440541e2a3235205bf190336a1f37f127d18bf60

S: 1aa03c91fc62ac72aeccf349d040f32ae190120b 192.168.10.13:7002

replicates c588a93825de6e0e6730a8bbb072684619201803

S: ff7e453f9ad5d2db2c7867893700fec033767bd9 192.168.10.11:7002

replicates 9ba21cfda0fed2d9013103e934f199a247c378ef

Can I set the above configuration? (type 'yes' to accept): yes

>>> Nodes configuration updated

>>> Assign a different config epoch to each node

>>> Sending CLUSTER MEET messages to join the cluster

Waiting for the cluster to join..

>>> Performing Cluster Check (using node 192.168.10.11:7001)

M: 440541e2a3235205bf190336a1f37f127d18bf60 192.168.10.11:7001

slots:0-5460 (5461 slots) master

1 additional replica(s)

S: 1aa03c91fc62ac72aeccf349d040f32ae190120b 192.168.10.13:7002

slots: (0 slots) slave

replicates c588a93825de6e0e6730a8bbb072684619201803

S: ff7e453f9ad5d2db2c7867893700fec033767bd9 192.168.10.11:7002

slots: (0 slots) slave

replicates 9ba21cfda0fed2d9013103e934f199a247c378ef

M: 9ba21cfda0fed2d9013103e934f199a247c378ef 192.168.10.13:7001

slots:10923-16383 (5461 slots) master

1 additional replica(s)

M: c588a93825de6e0e6730a8bbb072684619201803 192.168.10.12:7001

slots:5461-10922 (5462 slots) master

1 additional replica(s)

S: f07abd56170635aaad5166bd38af9f7267834ca7 192.168.10.12:7002

slots: (0 slots) slave

replicates 440541e2a3235205bf190336a1f37f127d18bf60

[OK] All nodes agree about slots configuration.

>>> Check for open slots...

>>> Check slots coverage...

[OK] All 16384 slots covered.

# 查看節點信息

[root@c1 ~]# /usr/local/redis/bin/redis-cli -h 192.168.10.13 -p 7001

192.168.10.13:7001> cluster nodes

ff7e453f9ad5d2db2c7867893700fec033767bd9 192.168.10.11:7002@17002 slave 9ba21cfda0fed2d9013103e934f199a247c378ef 0 1527578162996 6 connected

1aa03c91fc62ac72aeccf349d040f32ae190120b 192.168.10.13:7002@17002 slave c588a93825de6e0e6730a8bbb072684619201803 0 1527578161483 5 connected

440541e2a3235205bf190336a1f37f127d18bf60 192.168.10.11:7001@17001 master - 0 1527578162000 1 connected 0-5460

f07abd56170635aaad5166bd38af9f7267834ca7 192.168.10.12:7002@17002 slave 440541e2a3235205bf190336a1f37f127d18bf60 0 1527578161000 4 connected

c588a93825de6e0e6730a8bbb072684619201803 192.168.10.12:7001@17001 master - 0 1527578162491 2 connected 5461-10922

9ba21cfda0fed2d9013103e934f199a247c378ef 192.168.10.13:7001@17001 myself,master - 0 1527578162000 3 connected 10923-16383
sentinel

前言

Redis-Sentinel是官方推薦的高可用（HA）解決方案，本身也是一個獨立運行的進程，它能監控多個master-slave集羣。爲防止單點故障，可對sentinel進行集羣化。其主要功能如下：
1. 監控：sentinel不斷的檢查master和slave的活性；
2. 通知：當發現redis節點故障，可通過API發出通知；
3. 自動故障轉移：當一個master節點故障時，能夠從衆多slave中選舉一個作爲新的master，同時其它slave節點也將自動將所追隨的master的地址改爲新master的地址；
4. 配置提供者：哨兵作爲redis客戶端發現的權威來源：客戶端連接到哨兵請求當前可靠的master地址，若發生故障，哨兵將報告新地址。
配置

說明：本次實驗將三個哨兵分別部署在c1、c2、c3三臺服務器上！

[root@c1 ~]# cp /usr/local/redis/sentinel.conf /etc/redis-cluster/

[root@c1 ~]# cat /etc/redis-cluster/sentinel.conf

protected-mode no

port 27001

daemonize yes

logfile "/var/log/sentinel.log"

sentinel monitor mymaster1 192.168.10.11 7001 2

sentinel monitor mymaster2 192.168.10.12 7001 2

sentinel monitor mymaster3 192.168.10.13 7001 2

sentinel down-after-milliseconds mymaster1 10000

sentinel down-after-milliseconds mymaster2 10000

sentinel down-after-milliseconds mymaster3 10000

sentinel parallel-syncs mymaster1 1

sentinel parallel-syncs mymaster2 1

sentinel parallel-syncs mymaster3 1

sentinel failover-timeout mymaster1 15000

sentinel failover-timeout mymaster2 15000

sentinel failover-timeout mymaster3 15000

# 啓動哨兵

[root@c1 ~]# /usr/local/redis/bin/redis-sentinel /etc/redis-cluster/sentinel.conf

# c2、c3服務器也進行以上操作，配置只需修改對應的端口即可！

說明：啓動哨兵後，配置文件會根據監控信息自動發生相應的變化，如下：

[root@c1 ~]# cat /etc/redis-cluster/sentinel.conf

protected-mode no

port 27001

daemonize yes

logfile "/var/log/sentinel.log"

sentinel myid e3733670b609b65e520b293789e4fbf10236089c

sentinel monitor mymaster3 192.168.10.13 7001 2

sentinel down-after-milliseconds mymaster3 10000

sentinel failover-timeout mymaster3 15000

sentinel config-epoch mymaster3 0

sentinel leader-epoch mymaster3 0

sentinel known-slave mymaster3 192.168.10.11 7002

sentinel monitor mymaster1 192.168.10.11 7001 2

sentinel down-after-milliseconds mymaster1 10000

sentinel failover-timeout mymaster1 15000

sentinel config-epoch mymaster1 0

sentinel leader-epoch mymaster1 0

# Generated by CONFIG REWRITE

dir "/etc/redis-cluster"

sentinel known-slave mymaster1 192.168.10.12 7002

sentinel monitor mymaster2 192.168.10.12 7001 2

sentinel down-after-milliseconds mymaster2 10000

sentinel failover-timeout mymaster2 15000

sentinel config-epoch mymaster2 0

sentinel leader-epoch mymaster2 0

sentinel known-slave mymaster2 192.168.10.13 7002

sentinel current-epoch 0
故障模擬

# 通過sentinel日誌查看信息，圖中可看出192.168.10.11 7001爲 master，其相應的從爲192.168.10.12 7002;

# 手動停止master 192.168.10.11 7001，slave 192.168.10.12 7002升爲主

[root@c1 ~]# ps -ef |grep redis

root 4243 1 0 03:05 ? 00:00:23 /usr/local/redis/bin/redis-server 192.168.10.11:7001 [cluster]

root 4245 1 0 03:05 ? 00:00:23 /usr/local/redis/bin/redis-server 192.168.10.11:7002 [cluster]

root 8472 1 1 03:45 ? 00:00:07 /usr/local/redis/bin/redis-sentinel *:27001 [sentinel]

[root@c1 ~]# kill 4243

# 日誌輸出如下：

# 登陸查看nodes信息

# /usr/local/redis/bin/redis-cli -h 192.168.10.13 -p 7001

# 將192.168.10.11 7001的redis啓動

[root@c1 ~]# /usr/local/redis/bin/redis-server /etc/redis-cluster/7001/redis.conf

# sentinel刷新日誌

# 再次查看nodes信息，192.168.10.11 7001 已經變爲192.168.10.12 7002的slave
報錯說明

問題描述

在執行命令# /usr/local/redis/src/redis-trib.rb create --replicas 1 *** 創建集羣時報錯如下：

>>> Creating cluster

[ERR] Node 192.168.10.11:7001 is not empty. Either the node already knows other nodes (check with CLUSTER NODES) or contains some key in database 0.

問題解決
1. 將節點下aof、rdb等本地備份刪除；
2. 刪除node集羣配置文件，即redis.conf中cluster-config-file對應的文件；