在CentOS7上配置MongoDB复制集和复制集的管理维护

发布时间：2023-09-27 15:16:37 所属栏目：系统来源：

导读：复制集是额外的数据副本，是跨多个服务器同步数据的过程，复制集提供了冗余并增加了数据可用性，通过复制集可以对硬件故障和中断的服务进行恢复。

复制集工作原理

MongoDB的复制集至少需要两个节点。其中一个

复制集是额外的数据副本，是跨多个服务器同步数据的过程，复制集提供了冗余并增加了数据可用性，通过复制集可以对硬件故障和中断的服务进行恢复。

复制集工作原理

MongoDB的复制集至少需要两个节点。其中一个是主节点（primary），负责处理客户端的请求，其余都是从节点（Secondary）,负责复制主节点上的数据。

MongoDB各个节点常见的搭配方式为：一主一从或一主多从。主节点记录其上的所有操作到oplog中，从节点定期轮询主节点获取这些操作，然后对自己的数副本执行这些操作，从而保证从节点的数据与主节点一致。

复制集的特点

N个节点的群集

任何节点可作为主节点

所有写入操作都在主节点上

自动故障转移

自动恢复

MongoDB复制集部署

1.配置复制集

（1）创建数据文件和日志文件存储路径

[root@localhost ~]# mkdir -p /data/mongodb/mongodb{2,3,4}

[root@localhost ~]# cd /data/mongodb/

[root@localhost mongodb]# mkdir logs

[root@localhost mongodb]# touch logs/mongodb{2,3,4}.log

[root@localhost mongodb]# cd logs/

[root@localhost logs]# ls

mongodb2.log mongodb3.log mongodb4.log

[root@localhost logs]# chmod 777 *.log

（2）编辑4个MongoDB实例的配置文件

先编辑Mongodb的配置文件，配置replSet参数值都为kgcrs,并复制3份，具体操作如下：

[root@localhost etc]# vim mongod.conf

  path: /var/log/mongodb/mongod.log

# Where and how to store data.

storage:

  dbPath: /var/lib/mongo

  journal:

    enabled: true

# engine:

# mmapv1:

# wiredTiger:

# how the process runs

processManagement:

  fork: true # fork and run in background

  pidFilePath: /var/run/mongodb/mongod.pid # location of pidfile

  timeZoneInfo: /usr/share/zoneinfo

# network interfaces

net:

  port: 27017

  bindIp: 0.0.0.0 # Listen to local interface only, comment to listen on all interfaces.

#security:

#operationProfiling:

replication:

     replSetName: kgcrs

#sharding:

## Enterprise-Only Options

#auditLog:

#snmp:

然后将mongodb2.conf中的port参数配置为27018,mongodb3.conf中的port参数配置为27019，mongodb4.conf中的port参数配置为27020。同样也将dbpath和logpath参数修改为对应的路径值。

（3）启动4个MongoDB节点实列并查看进程信息

[root@localhost etc]# mongod -f /etc/mongod.conf --shutdown //先关闭//

[root@localhost etc]# mongod -f /etc/mongod.conf //再开启//

[root@localhost etc]# mongod -f /etc/mongod2.conf

[root@localhost etc]# mongod -f /etc/mongod3.conf

[root@localhost etc]# mongod -f /etc/mongod4.conf

[root@localhost etc]# netstat -ntap | grep mongod

tcp        0      0 0.0.0.0:27019           0.0.0.0:*               LISTEN      17868/mongod

tcp        0      0 0.0.0.0:27020           0.0.0.0:*               LISTEN      17896/mongod

tcp        0      0 0.0.0.0:27017           0.0.0.0:*               LISTEN      17116/mongod

tcp        0      0 0.0.0.0:27018           0.0.0.0:*               LISTEN      17413/mongod

（4）配置三个节点的复制集

[root@localhost etc]# mongo

> rs.status()    //查看复制集//

{

    "info" : "run rs.initiate(...) if not yet done for the set",

    "ok" : 0,

    "errmsg" : "no replset config has been received",

    "code" : 94,

    "codeName" : "NotYetInitialized",

    "$clusterTime" : {

        "clusterTime" : Timestamp(0, 0),

        "signature" : {

            "hash" : BinData(0,"AAAAAAAAAAAAAAAAAAAAAAAAAAA="),

            "keyId" : NumberLong(0)

        }

    }

}

> cfg={"_id":"kgcrs","members":[{"_id":0,"host":"192.168.126.132:27017"},{"_id":1,"host":"192.168.126.132:27018"},{"_id":2,"host":"192.168.126.132:27019"}]} //添加复制集//

{

    "_id" : "kgcrs",

    "members" : [

        {

            "_id" : 0,

            "host" : "192.168.126.132:27017"

        },

        {

            "_id" : 1,

            "host" : "192.168.126.132:27018"

        },

        {

            "_id" : 2,

            "host" : "192.168.126.132:27019"

        }

    ]

}

> rs.initiate(cfg)   //初始化配置时保证从节点没有数据//

（5）查看复制集状态

启动复制集后，再次通过rs.status()命令查看复制集的完整状态信息

kgcrs:SECONDARY> rs.status()

{

    "set" : "kgcrs",

    "date" : ISODate("2018-07-17T07:18:52.047Z"),

    "myState" : 1,

    "term" : NumberLong(1),

    "syncingTo" : "",

    "syncSourceHost" : "",

    "syncSourceId" : -1,

    "heartbeatIntervalMillis" : NumberLong(2000),

    "optimes" : {

        "lastCommittedOpTime" : {

            "ts" : Timestamp(1531811928, 1),

            "t" : NumberLong(1)

        },

        "readConcernMajorityOpTime" : {

            "ts" : Timestamp(1531811928, 1),

            "t" : NumberLong(1)

        },

        "appliedOpTime" : {

            "ts" : Timestamp(1531811928, 1),

            "t" : NumberLong(1)

        },

        "durableOpTime" : {

            "ts" : Timestamp(1531811928, 1),

            "t" : NumberLong(1)

        }

    },

    "members" : [

        {

            "_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 1,

            "state" : 1,

            "stateStr" : "PRIMARY",       //主节点//

            "uptime" : 2855,

            "optime" : {

                "ts" : Timestamp(1531811928, 1),

                "t" : NumberLong(1)

            },

            "optimeDate" : ISODate("2018-07-17T07:18:48Z"),

            "syncingTo" : "",

            "syncSourceHost" : "",

            "syncSourceId" : -1,

            "infoMessage" : "could not find member to sync from",

            "electionTime" : Timestamp(1531811847, 1),

            "electionDate" : ISODate("2018-07-17T07:17:27Z"),

            "configVersion" : 1,

            "self" : true,

            "lastHeartbeatMessage" : ""

        },

        {

            "_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",     //从节点//

            "uptime" : 95,

            "optime" : {

                "ts" : Timestamp(1531811928, 1),

                "t" : NumberLong(1)

            },

            "optimeDurable" : {

                "ts" : Timestamp(1531811928, 1),

                "t" : NumberLong(1)

            },

            "optimeDate" : ISODate("2018-07-17T07:18:48Z"),

            "optimeDurableDate" : ISODate("2018-07-17T07:18:48Z"),

            "lastHeartbeat" : ISODate("2018-07-17T07:18:51.208Z"),

            "lastHeartbeatRecv" : ISODate("2018-07-17T07:18:51.720Z"),

            "pingMs" : NumberLong(0),

            "lastHeartbeatMessage" : "",

            "syncingTo" : "192.168.126.132:27017",

            "syncSourceHost" : "192.168.126.132:27017",

            "syncSourceId" : 0,

            "infoMessage" : "",

            "configVersion" : 1

        },

        {

            "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",      //从节点//

            "uptime" : 95,

            "optime" : {

                "ts" : Timestamp(1531811928, 1),

                "t" : NumberLong(1)

            },

            "optimeDurable" : {

                "ts" : Timestamp(1531811928, 1),

                "t" : NumberLong(1)

            },

            "optimeDate" : ISODate("2018-07-17T07:18:48Z"),

            "optimeDurableDate" : ISODate("2018-07-17T07:18:48Z"),

            "lastHeartbeat" : ISODate("2018-07-17T07:18:51.208Z"),

            "lastHeartbeatRecv" : ISODate("2018-07-17T07:18:51.822Z"),

            "pingMs" : NumberLong(0),

            "lastHeartbeatMessage" : "",

            "syncingTo" : "192.168.126.132:27017",

            "syncSourceHost" : "192.168.126.132:27017",

            "syncSourceId" : 0,

            "infoMessage" : "",

            "configVersion" : 1

        }

    ],

    "ok" : 1,

    "operationTime" : Timestamp(1531811928, 1),

    "$clusterTime" : {

        "clusterTime" : Timestamp(1531811928, 1),

        "signature" : {

            "hash" : BinData(0,"AAAAAAAAAAAAAAAAAAAAAAAAAAA="),

            "keyId" : NumberLong(0)

        }

    }

}

其中，health为1代表健康，0代表宕机。state为1代表主节点，为2代表从节点。

在复制集初始化配置时要保证从节点上没有数据

MongoDB复制集切换

MongoDB复制集可以实现群集的高可用，当其中主节点出现故障时会自动切换到其他节点。也可手动进行复制集的主从切换。

1.故障转移切换

[root@localhost etc]# ps aux | grep mongod   //查看进程//

root      17116 1.2 5.8 1546916 58140 ?       Sl   14:31   0:51 mongod -f /etc/mongod.conf

root      17413 1.0 5.7 1445624 57444 ?       Sl   14:34   0:39 mongod -f /etc/mongod2.conf

root      17868 1.2 5.5 1446752 55032 ?       Sl   15:05   0:23 mongod -f /etc/mongod3.conf

root      17896 0.8 4.7 1037208 47552 ?       Sl   15:05   0:16 mongod -f /etc/mongod4.conf

root      18836 0.0 0.0 112676   980 pts/1    S+   15:38   0:00 grep --color=auto mongod

[root@localhost etc]# kill -9 17116   ///杀死27017进程//

[root@localhost etc]# ps aux | grep mongod

root      17413 1.0 5.7 1453820 57456 ?       Sl   14:34   0:40 mongod -f /etc/mongod2.conf

root      17868 1.2 5.5 1454948 55056 ?       Sl   15:05   0:24 mongod -f /etc/mongod3.conf

root      17896 0.8 4.7 1037208 47552 ?       Sl   15:05   0:16 mongod -f /etc/mongod4.conf

root      18843 0.0 0.0 112676   976 pts/1    R+   15:38   0:00 grep --color=auto mongod

[root@localhost etc]# mongo --port 27019

kgcrs:PRIMARY> rs.status()

    "members" : [

        {

            "_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 0,       //宕机状态//

            "state" : 8,

            "stateStr" : "(not reachable/healthy)",

            "uptime" : 0,

            "optime" : {

                "ts" : Timestamp(0, 0),

                "t" : NumberLong(-1)

        {

            "_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",     //从节点//

            "uptime" : 1467,

            "optime" : {

                "ts" : Timestamp(1531813296, 1),

                "t" : NumberLong(2)

            },

            "optimeDurable" : {

                "ts" : Timestamp(1531813296, 1),

                "t" : NumberLong(2)

            },

        {

            "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 1,

            "stateStr" : "PRIMARY",     //主节点//

            "uptime" : 2178,

            "optime" : {

                "ts" : Timestamp(1531813296, 1),

                "t" : NumberLong(2)

}

2.手动进行主从切换

kgcrs:PRIMARY> rs.freeze(30)      //暂停30s不参与选举

kgcrs:PRIMARY> rs.stepDown(60,30) //交出主节点位置，维持从节点状态不少于60秒，等待30秒使主节点和从节点日志同步

2018-07-17T15:46:19.079+0800 E QUERY    [thread1] Error: error doing query: failed: network error while attempting to run command 'replSetStepDown' on host '127.0.0.1:27019' :

DB.prototype.runCommand@src/mongo/shell/db.js:168:1

DB.prototype.adminCommand@src/mongo/shell/db.js:186:16

rs.stepDown@src/mongo/shell/utils.js:1341:12

@(shell):1:1

2018-07-17T15:46:19.082+0800 I NETWORK [thread1] trying reconnect to 127.0.0.1:27019 (127.0.0.1) failed

2018-07-17T15:46:19.085+0800 I NETWORK [thread1] reconnect 127.0.0.1:27019 (127.0.0.1) ok

kgcrs:SECONDARY>    //交出主节点后立马变成从节点//

kgcrs:SECONDARY> rs.status()

    "_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 0,      //宕机状态//

            "state" : 8,

            "stateStr" : "(not reachable/healthy)",

            "uptime" : 0,

            "optime" : {

                "ts" : Timestamp(0, 0),

                "t" : NumberLong(-1)

            },

        {

            "_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 1,

            "state" : 1,

            "stateStr" : "PRIMARY",       //主节点状态//

            "uptime" : 1851,

            "optime" : {

                "ts" : Timestamp(1531813679, 1),

                "t" : NumberLong(3)

        {

            "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",     //从节点状态//

            "uptime" : 2563,

            "optime" : {

                "ts" : Timestamp(1531813689, 1),

                "t" : NumberLong(3)

MongoDB复制集的选举原理

节点类型分为标准节点（host）、被动节点（passive）和仲裁节点（arbiter）。

只有标准节点可能被选举为活跃（primary）节点，有选举权。被动节点有完整副本，不可能成为活跃节点，有选举权。仲裁节点不复制数据，不可能成为活跃节点，只有选举权。

标准节点与被动节点的区别：priority值高者是标准节点，低者为被动节点。

选举规则是票数高者获胜，priority是优先权为0~1000的值，相当于额外增加0~1000的票数。选举结果：票数高者获胜；若票数相同，数据新者获胜。

1.配置复制集的优先级

1）重新配置4个节点的MongoDB复制集，设置两个标准节点，一个被动节点和一个仲裁节点。

[root@localhost etc]# mongo

> cfg={"_id":"kgcrs","members":[{"_id":0,"host":"192.168.126.132:27017","priority":100},{"_id":1,"host":"192.168.126.132:27018","priority":100},{"_id":2,"host":"192.168.126.132:27019","priority":0},{"_id":3,"host":"192.168.126.132:27020","arbiterOnly":true}]}

> rs.initiate(cfg)     //重新配置//

kgcrs:SECONDARY> rs.isMaster()

{

    "hosts" : [                 //标准节点//

        "192.168.126.132:27017",

        "192.168.126.132:27018"

    ],

    "passives" : [             //被动节点//

        "192.168.126.132:27019"

    ],

    "arbiters" : [            //仲裁节点//

        "192.168.126.132:27020"

2）模拟主节点故障

如果主节点出现故障，另一个标准节点将会选举成为新的主节点

[root@localhost etc]# mongod -f /etc/mongod.conf --shutdown   //标准节点27017//

[root@localhost etc]# mongo --port 27018   //此时会选举第二个标准节点为主节点//

kgcrs:PRIMARY> rs.status()

    "_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 0,      //宕机状态//

            "state" : 8,

            "stateStr" : "(not reachable/healthy)",

            "uptime" : 0,

            "optime" : {

                "ts" : Timestamp(0, 0),

                "t" : NumberLong(-1)

    "_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 1,

            "state" : 1,

            "stateStr" : "PRIMARY",    //标准节点//

            "uptime" : 879,

            "optime" : {

                "ts" : Timestamp(1531817473, 1),

                "t" : NumberLong(2)

    "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",   //被动节点//

            "uptime" : 569,

            "optime" : {

                "ts" : Timestamp(1531817473, 1),

                "t" : NumberLong(2)

        "_id" : 3,

            "name" : "192.168.126.132:27020",

            "health" : 1,

            "state" : 7,

            "stateStr" : "ARBITER",   //仲裁节点//

            "uptime" : 569,

3）模拟所有标准节点出现故障

所有标准节点都出现故障，被动节点也不能成为主节点

[root@localhost etc]# mongod -f /etc/mongod2.conf --shutdown //关闭标准节点27018//

[root@localhost etc]# mongo --port 27019

kgcrs:SECONDARY> rs.status()

            "_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 0,     //宕机状态//

            "state" : 8,

            "stateStr" : "(not reachable/healthy)",

            "uptime" : 0,

            "_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 0,      //宕机状态//

            "state" : 8,

            "stateStr" : "(not reachable/healthy)",

            "uptime" : 0,

            "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",   //被动节点//

            "uptime" : 1403,

            "_id" : 3,

            "name" : "192.168.126.132:27020",

            "health" : 1,

            "state" : 7,

            "stateStr" : "ARBITER",    //仲裁节点//

MongoDB复制集管理

1.配置允许在从节点读取数据

默认MongoDB复制集的从节点不能读取数据，可以使用rs.slaveOk()命令允许能够在从节点读取数据。

[root@localhost etc]# mongo --port 27017

kgcrs:SECONDARY> show dbs    //读取不到数据库信息//

2018-07-17T17:11:31.570+0800 E QUERY    [thread1] Error: listDatabases failed:{

    "operationTime" : Timestamp(1531818690, 1),

    "ok" : 0,

    "errmsg" : "not master and slaveOk=false",

    "code" : 13435,

    "codeName" : "NotMaste

    kgcrs:SECONDARY> rs.slaveOk()

kgcrs:SECONDARY> show dbs

admin   0.000GB

config 0.000GB

local   0.000GB

2.查看复制状态信息

可以使用 rs.printReplicationInfo()和rs.printSlaveReplicationInfo()命令查看复制集状态。

kgcrs:SECONDARY> rs.printReplicationInfo()

configured oplog size:   990MB

log length start to end: 2092secs (0.58hrs)

oplog first event time: Tue Jul 17 2018 16:41:48 GMT+0800 (CST)

oplog last event time:   Tue Jul 17 2018 17:16:40 GMT+0800 (CST)

now:                     Tue Jul 17 2018 17:16:46 GMT+0800 (CST)

kgcrs:SECONDARY> rs.printSlaveReplicationInfo()

source: 192.168.126.132:27017

    syncedTo: Tue Jul 17 2018 17:16:50 GMT+0800 (CST)

    0 secs (0 hrs) behind the primary

source: 192.168.126.132:27019

    syncedTo: Tue Jul 17 2018 17:16:50 GMT+0800 (CST)

    0 secs (0 hrs) behind the primary

3.部署认证复制

kgcrs:PRIMARY> use admin

kgcrs:PRIMARY> db.createUser({"user":"root","pwd":"123","roles":["root"]})

[root@localhost ~]# vim /etc/mongod.conf   //分别编辑四个配置文件//

....

security:

    keyFile: /usr/bin/kgcrskey1      //验证路径//

    clusterAuthMode: keyFile        //验证类型//

    [root@localhost ~]# vim /etc/mongod2.conf

[root@localhost ~]# vim /etc/mongod3.conf

[root@localhost ~]# vim /etc/mongod4.conf

[root@localhost bin]# echo "kgcrs key"> kgcrskey1   //生成4个实例的密钥文件//

[root@localhost bin]# echo "kgcrs key"> kgcrskey2

[root@localhost bin]# echo "kgcrs key"> kgcrskey3

[root@localhost bin]# echo "kgcrs key"> kgcrskey4

[root@localhost bin]# chmod 600 kgcrskey{1..4}

[root@localhost bin]# mongod -f /etc/mongod.conf   //重启4个实例//

[root@localhost bin]# mongod -f /etc/mongod2.conf

[root@localhost bin]# mongod -f /etc/mongod3.conf

[root@localhost bin]# mongod -f /etc/mongod4.conf

[root@localhost bin]# mongo --port 27017 //进入标准节点中//

kgcrs:PRIMARY> show dbs       //无法查看数据库//

kgcrs:PRIMARY> rs.status()   //无法查看复制集//

kgcrs:PRIMARY> use admin    //身份登录验证//

kgcrs:PRIMARY> db.auth("root","123")

kgcrs:PRIMARY> show dbs     //可以查看数据库//

admin   0.000GB

config 0.000GB

local   0.000GB

kgcrs:PRIMARY> rs.status() //可以查看复制集//

"_id" : 0,

            "name" : "192.168.126.132:27017",

            "health" : 1,

            "state" : 1,

            "stateStr" : "PRIMARY",

            "uptime" : 411,

"_id" : 1,

            "name" : "192.168.126.132:27018",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",

            "uptime" : 324,

            "_id" : 2,

            "name" : "192.168.126.132:27019",

            "health" : 1,

            "state" : 2,

            "stateStr" : "SECONDARY",

            "uptime" : 305,

"_id" : 3,

            "name" : "192.168.126.132:27020",

            "health" : 1,

            "state" : 7,

            "stateStr" : "ARBITER",

            "uptime" : 280,

（编辑：聊城站长网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!