mongodb集群创建副本

-------------------------------------------------------------------------------------------------------------------
副本集：
与主从区别在于：1、没有特定的主数据库 2、如果哪个主数据库宕机了，集群中就会推选出一个从属数据库作为主数据库顶上
这就具备了自动故障恢复功能。

搭建副本集的环境如下
mongo集群：
mongos 192.168.12.107:27021
config 192.168.12.107:27018
shard0000 192.168.12.104:27017
shard0001 192.168.12.104:27019
shard0002 192.168.12.104:27023
对testdb数据库里面的usr表以name为key进行了分片
现在想给shard0000 192.168.12.104:27017搭建副本 192.168.12.104:27030   仲裁 192.168.12.104:27033，并添加到分片中去。
mongos> db.printShardingStatus()
--- Sharding Status ---
  sharding version: {
"_id" : 1,
"version" : 3,
"minCompatibleVersion" : 3,
"currentVersion" : 4,
"clusterId" : ObjectId("541a47a9124d847f09e99204")
}
  shards:
{  "_id" : "shard0000",  "host" : "192.168.12.104:27017" }
{  "_id" : "shard0001",  "host" : "192.168.12.104:27019" }
{  "_id" : "shard0002",  "host" : "192.168.12.104:27023" }
  databases:
{  "_id" : "admin",  "partitioned" : false,  "primary" : "config" }
{  "_id" : "testdb",  "partitioned" : true,  "primary" : "shard0000" }
testdb.usr
shard key: { "name" : 1 }
chunks:
shard0000 5
shard0001 4
shard0002 5
{ "name" : { "$minKey" : 1 } } -->> { "name" : "ava0" } on : shard0000 Timestamp(6, 0)
{ "name" : "ava0" } -->> { "name" : "bobo0" } on : shard0001 Timestamp(3, 1)
{ "name" : "bobo0" } -->> { "name" : "mengtian57493" } on : shard0001 Timestamp(4, 0)
{ "name" : "mengtian57493" } -->> { "name" : "师傅10885" } on : shard0001 Timestamp(7, 0)
{ "name" : "师傅10885" } -->> { "name" : "师傅18160" } on : shard0000 Timestamp(8, 0)
{ "name" : "师傅18160" } -->> { "name" : "师傅23331" } on : shard0001 Timestamp(9, 0)
{ "name" : "师傅23331" } -->> { "name" : "师傅337444" } on : shard0000 Timestamp(10, 0)
{ "name" : "师傅337444" } -->> { "name" : "师傅47982" } on : shard0002 Timestamp(10, 1)
{ "name" : "师傅47982" } -->> { "name" : "师傅583953" } on : shard0002 Timestamp(8, 2)
{ "name" : "师傅583953" } -->> { "name" : "师傅688087" } on : shard0002 Timestamp(9, 2)
{ "name" : "师傅688087" } -->> { "name" : "师傅792944" } on : shard0002 Timestamp(9, 4)
{ "name" : "师傅792944" } -->> { "name" : "张荣达16836" } on : shard0002 Timestamp(9, 5)
{ "name" : "张荣达16836" } -->> { "name" : "张荣达9999" } on : shard0000 Timestamp(5, 1)
{ "name" : "张荣达9999" } -->> { "name" : { "$maxKey" : 1 } } on : shard0000 Timestamp(3, 3)


1、新建目录，并启动副本中的两个mongodb
[root@testvip1 ~]# ps -ef|grep mongo
root      3399 18112  0 15:11 pts/0    00:00:02 mongod --dbpath=/mongo_zc --port 27033 --replSet fubentina/192.168.12.104:27017     --仲裁mongo
root      4547     1  0 Sep24 ?        00:03:49 mongod --dbpath=/mongo3 --port 27023 --fork --logpath=/mongo3/log3/log3.txt --rest     --起rest是监控，也可以不起
root      4846     1  0 Sep24 ?        00:03:34 mongod --dbpath=/mongo2 --port 27019 --fork --logpath=/mongo2/log2/log2.txt
root      5259     1  0 15:16 ?        00:00:01 mongod --dbpath=/mongo1 --port 27017 --fork --logpath=/mongo1/log1/log1.txt --replSet fubentina/192.168.12.104:27030   --以新的方式启动27017
root      5489  3464  0 15:21 pts/2    00:00:00 grep mongo
root     18446     1  0 Sep24 ?        00:09:04 mongod --dbpath=/mongo1_fuben --port 27030 --fork --logpath=/mongo1_fuben/logfuben.txt --replSet fubentina/192.168.12.104:27017  --启动副本27030

2、开启副本配置（进入副本中任意一个admin）
[root@testvip1 mongo3]# mongo 192.168.12.104:27017/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27017/admin
> db.runCommand({"replSetInitiate":{"_id":"fubentina","members":[{"_id":1,"host":"192.168.12.104:27017"},{"_id":2,"host":"192.168.12.104:27030"}]}})
{
"info" : "Config now saved locally.  Should come online in about a minute.",
"ok" : 1
}

3、配置仲裁服务器
指定fubentina中的任意一个服务器端口
root@testvip1 /]# mongod --dbpath=/mongo_zc --port 27033 --replSet fubentina/192.168.12.104:27017


4、就发现shard1已经变成了下面这样
[root@testvip1 mongo3]# mongo 192.168.12.104:27017/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27017/admin
fubentina:PRIMARY>

5、添加仲裁节点
fubentina:PRIMARY> rs.addArb("192.168.12.104:27033")
{ "ok" : 1 }

6、使用rs.status()查看集群中的服务器状态。
fubentina:PRIMARY> rs.status()
{
"set" : "fubentina",
"date" : ISODate("2014-09-24T09:22:38Z"),
"myState" : 1,
"members" : [
{
"_id" : 1,
"name" : "192.168.12.104:27017",
"health" : 1,
"state" : 1,
"stateStr" : "PRIMARY",      --主
"uptime" : 413,
"optime" : Timestamp(1411550517, 1),
"optimeDate" : ISODate("2014-09-24T09:21:57Z"),
"self" : true
},
{
"_id" : 2,
"name" : "192.168.12.104:27030",
"health" : 1,
"state" : 2,
"stateStr" : "SECONDARY",    --从
"uptime" : 373,
"optime" : Timestamp(1411550517, 1),
"optimeDate" : ISODate("2014-09-24T09:21:57Z"),
"lastHeartbeat" : ISODate("2014-09-24T09:22:37Z"),
"lastHeartbeatRecv" : ISODate("2014-09-24T09:22:37Z"),
"pingMs" : 0,
"syncingTo" : "192.168.12.104:27017"
},
{
"_id" : 3,
"name" : "192.168.12.104:27033",
"health" : 1,
"state" : 7,
"stateStr" : "ARBITER",     --仲裁
"uptime" : 41,
"lastHeartbeat" : ISODate("2014-09-24T09:22:37Z"),
"lastHeartbeatRecv" : ISODate("2014-09-24T09:22:37Z"),
"pingMs" : 0
}
],
"ok" : 1
}
如果某一个挂掉了或者没起来，就会发现stateStr 显示成："stateStr" : "(not reachable/healthy)",

7、副本创建成功，下一步就是解决分片的问题，我们需要先删除分片shard0000，让数据移动到其他分片
mongos> db.runCommand({"removeshard":"192.168.12.104:27017"})
{
"msg" : "draining ongoing",
"state" : "ongoing",
"remaining" : {
"chunks" : NumberLong(0),  ---显示的是数据移动的剩余量，为0表示数据已经全部移走了
"dbs" : NumberLong(2)     --这里需要注意，要将两个数据库的primary也移一下
},
"note" : "you need to drop or movePrimary these databases",  --看这里的提示
"dbsToMove" : [
"test",
"testdb"
],
"ok" : 1
}

mongos> use admin
switched to db admin
mongos> db.runCommand({moveprimary:"testdb",to:"shard0001"})  --将主移动到另一个分片上
{ "primary " : "shard0001:192.168.12.104:27019", "ok" : 1 }

mongos> db.runCommand({moveprimary:"test",to:"shard0001"})
{ "primary " : "shard0001:192.168.12.104:27019", "ok" : 1 }


mongos> db.runCommand({removeshard:"192.168.12.104:27017"})   --这样就可以成功移除
{
"msg" : "removeshard completed successfully",
"state" : "completed",
"shard" : "shard0000",
"ok" : 1
}

Do not run the movePrimary until you have finished draining the shard
也就是说，一定要等到分片数据迁移完了，再运行movePrimary命令！！！
而且这句命令不像removeshard是异步的，这个movePrimary命令会等到将所有非分片数据都移到其他服务器后，才响应，所以时间有可能会比较长，主要还是看这个服务器上，非分片数据有多少。
另外，movePrimary执行完后，还记得将db.runCommand({removeshard:"shardx"})再运行一遍，直到看到如下结果{ msg: "remove shard completed successfully" , stage: "completed", host: "mongodb0", ok : 1 }
到此为止，迁移才真正完成，可以放心地关闭mongod。

8、删除原192.168.12.104:27017里面的testdb库
mongos> db.runCommand({addshard:"fubentina/192.168.12.104:27017,192.168.12.104:27030,192.168.12.104:27033"})
{
"ok" : 0,
"errmsg" : "can't add shard fubentina/192.168.12.104:27017,192.168.12.104:27030,192.168.12.104:27033 because a local database 'testdb' exists in another shard0000:192.168.12.104:27017"
} ---添加副本的时候，因为检测到12.104:27017上面存在testdb这个同名数据库，因此无法添加成功。


connecting to: 192.168.12.104:27017/admin
fubentina:PRIMARY> show dbs
local 1.078125GB
testdb 0.453125GB
fubentina:PRIMARY> use testdb
switched to db testdb
fubentina:PRIMARY> db.usr.drop();
true
fubentina:PRIMARY> db.dropDatabase();
{ "dropped" : "testdb", "ok" : 1 }

9、添加副本集到分片
mongos> db.runCommand({addshard:"192.168.12.104:27017"});   --直接添加副本中的一个是不行的，要一起添加
{
"ok" : 0,
"errmsg" : "host is part of set: fubentina use replica set url format <setname>/<server1>,<server2>,...."
}

添加副本集
mongos> db.runCommand({addshard:"fubentina/192.168.12.104:27017,192.168.12.104:27030,192.168.12.104:27033"}) --最后一个是仲裁
{ "shardAdded" : "fubentina", "ok" : 1 }

10、查看分片信息
mongos> db.printShardingStatus()
--- Sharding Status ---
  sharding version: {
"_id" : 1,
"version" : 3,
"minCompatibleVersion" : 3,
"currentVersion" : 4,
"clusterId" : ObjectId("541a47a9124d847f09e99204")
}
  shards:
{  "_id" : "fubentina",  "host" : "fubentina/192.168.12.104:27017,192.168.12.104:27030" }   ---显示的是副本集
{  "_id" : "shard0001",  "host" : "192.168.12.104:27019" }
{  "_id" : "shard0002",  "host" : "192.168.12.104:27023" }
  databases:
{  "_id" : "admin",  "partitioned" : false,  "primary" : "config" }
{  "_id" : "testdb",  "partitioned" : true,  "primary" : "shard0001" }
testdb.usr
shard key: { "name" : 1 }
chunks:
fubentina 4
shard0001 5
shard0002 5
{ "name" : { "$minKey" : 1 } } -->> { "name" : "ava0" } on : fubentina Timestamp(16, 0)   --已经有数据被分配到这个副本
{ "name" : "ava0" } -->> { "name" : "bobo0" } on : fubentina Timestamp(18, 0)
{ "name" : "bobo0" } -->> { "name" : "mengtian57493" } on : shard0001 Timestamp(18, 1)
{ "name" : "mengtian57493" } -->> { "name" : "师傅10885" } on : shard0001 Timestamp(7, 0)
{ "name" : "师傅10885" } -->> { "name" : "师傅18160" } on : shard0001 Timestamp(12, 0)
{ "name" : "师傅18160" } -->> { "name" : "师傅23331" } on : shard0001 Timestamp(9, 0)
{ "name" : "师傅23331" } -->> { "name" : "师傅337444" } on : fubentina Timestamp(17, 0)
{ "name" : "师傅337444" } -->> { "name" : "师傅47982" } on : fubentina Timestamp(19, 0)
{ "name" : "师傅47982" } -->> { "name" : "师傅583953" } on : shard0002 Timestamp(19, 1)
{ "name" : "师傅583953" } -->> { "name" : "师傅688087" } on : shard0002 Timestamp(9, 2)
{ "name" : "师傅688087" } -->> { "name" : "师傅792944" } on : shard0002 Timestamp(9, 4)
{ "name" : "师傅792944" } -->> { "name" : "张荣达16836" } on : shard0002 Timestamp(9, 5)
{ "name" : "张荣达16836" } -->> { "name" : "张荣达9999" } on : shard0001 Timestamp(14, 0)
{ "name" : "张荣达9999" } -->> { "name" : { "$maxKey" : 1 } } on : shard0002 Timestamp(15, 0)
{  "_id" : "test",  "partitioned" : false,  "primary" : "shard0001" }
{  "_id" : "usr",  "partitioned" : false,  "primary" : "shard0001" }

11、查看
连接到副本中的一个点
[root@testvip1 ~]# mongo 192.168.12.104:27017/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27017/admin
fubentina:PRIMARY> show dbs
local 1.078125GB
testdb 0.453125GB
fubentina:PRIMARY> use testdb
switched to db testdb
fubentina:PRIMARY> db.usr.count()   --可以查到数据
283898

[root@testvip1 ~]# mongo 192.168.12.104:27030/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27030/admin
fubentina:SECONDARY> show dbs
local 1.078125GB
testdb 0.453125GB
fubentina:SECONDARY> use testdb
switched to db testdb
fubentina:SECONDARY> db.usr.count()
Thu Sep 25 15:01:33.879 count failed: { "note" : "from execCommand", "ok" : 0, "errmsg" : "not master" } at src/mongo/shell/query.js:180  --现在27030是副本，所以查看不了数据

副本集终于添加成功

12、进行测试
将27017给kill掉
kill 4353
[root@testvip1 ~]# mongo 192.168.12.104:27017/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27017/admin
fubentina:PRIMARY> rs.status()
Thu Sep 25 15:11:49.785 DBClientCursor::init call() failed
Thu Sep 25 15:11:49.788 Error: error doing query: failed at src/mongo/shell/query.js:78
Thu Sep 25 15:11:49.789 trying reconnect to 192.168.12.104:27017
Thu Sep 25 15:11:49.789 reconnect 192.168.12.104:27017 failed couldn't connect to server 192.168.12.104:27017  --不能连接

[root@viptest2 ~]# mongo 192.168.12.107:27021/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.107:27021/admin
mongos> use testdb
switched to db testdb
mongos> db.usr.find({"name":"ava100"})        ---能正常查到副本集的数据
{ "_id" : ObjectId("541bd1573351616d81bb07e7"), "name" : "ava100", "address" : "yichangdong", "age" : 50 }

直接连到27030上去看
[root@testvip1 ~]# mongo 192.168.12.104:27030/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27030/admin
fubentina:PRIMARY> show dbs
local 1.078125GB
testdb 0.453125GB
fubentina:PRIMARY> use testdb
switched to db testdb
fubentina:PRIMARY> db.usr.count()
283898
fubentina:PRIMARY> db.usr.find({"name":"ava100"})
{ "_id" : ObjectId("541bd1573351616d81bb07e7"), "name" : "ava100", "address" : "yichangdong", "age" : 50 }

13、将27017起来，去看下rs.status()
mongod --dbpath=/mongo1 --port 27017 --fork --logpath=/mongo1/log1/log1.txt --replSet fubentina/192.168.12.104:27030
[root@testvip1 ~]# mongo 192.168.12.104:27017/admin
MongoDB shell version: 2.4.6
connecting to: 192.168.12.104:27017/admin
fubentina:SECONDARY> rs.status()
{
"set" : "fubentina",
"date" : ISODate("2014-09-25T07:58:41Z"),
"myState" : 2,
"syncingTo" : "192.168.12.104:27030",
"members" : [
{
"_id" : 1,
"name" : "192.168.12.104:27017",
"health" : 1,
"state" : 2,
"stateStr" : "SECONDARY",    --启动后它变成了副本
"uptime" : 2551,
"optime" : Timestamp(1411628295, 2057),
"optimeDate" : ISODate("2014-09-25T06:58:15Z"),
"self" : true
},
{
"_id" : 2,
"name" : "192.168.12.104:27030",
"health" : 1,
"state" : 1,
"stateStr" : "PRIMARY",    --它变成了主
"uptime" : 2551,
"optime" : Timestamp(1411628295, 2057),
"optimeDate" : ISODate("2014-09-25T06:58:15Z"),
"lastHeartbeat" : ISODate("2014-09-25T07:58:41Z"),
"lastHeartbeatRecv" : ISODate("2014-09-25T07:58:39Z"),
"pingMs" : 0
},
{
"_id" : 3,
"name" : "192.168.12.104:27033",
"health" : 1,
"state" : 7,
"stateStr" : "ARBITER",    -它依然是仲裁
"uptime" : 2549,
"lastHeartbeat" : ISODate("2014-09-25T07:58:41Z"),
"lastHeartbeatRecv" : ISODate("2014-09-25T07:58:40Z"),
"pingMs" : 0
}
],
"ok" : 1
}
验证ok