mongodb 分片+复制集

mongodb版本：3.0.4

准备：

1、校验服务器的时间，3台同步

2、关闭防火墙

3、关闭selinux

Sharding+Replica Sets 
主机              IP                  服务及端口
Server A      192.168.31.231    mongod shard1_1:27017
                                mongod shard2_1:27018
                                mongod config1:20000
                                mongs1:30000
                                
Server B      192.168.31.232    mongod shard1_2:27017
                                mongod shard2_2:27018
                                mongod config2:20000
                                mongs2:30000
                                
Server C      192.168.31.233    mongod shard1_3:27017
                                mongod shard2_3:27018
                                mongod config3:20000
                                mongs3:30000> rs.initiate(config)
                            
1.1 创建数据目录
Server A
mkdir /data/shard1_1
mkdir /data/shard2_1
mkdir /data/config 
Server B
mkdir /data/shard1_2
mkdir /data/shard2_2
mkdir /data/config
Server C
mkdir /data/shard1_3
mkdir /data/shard2_3
mkdir /data/config

1.2 配置shard1的Replica Sets
Server A 
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard1 --port 27017 --dbpath /data/shard1_1 --logpath /data/shard1_1/shard1_1.log --logappend --fork


Server B
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard1 --port 27017 --dbpath /data/shard1_2 --logpath /data/shard1_2/shard1_2.log --logappend --fork

Server C
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard1 --port 27017 --dbpath /data/shard1_3 --logpath /data/shard1_3/shard1_3.log --logappend --fork

用 mongo 连接其中一台机器的 27017 端口的 mongod，初始化 Replica Sets“shard1” ，执行:
[root@localhost bin]# ./mongo --port 27017
MongoDB shell version: 1.8.1
connecting to: 127.0.0.1:27017/test
> config = {_id: 'shard1', members: [
... {_id: 0, host: '192.168.31.231:27017'},
... {_id: 1, host: '192.168.31.232:27017'},
... {_id: 2, host: '192.168.31.233:27017',arbiterOnly:true}]
... }
{
        "_id" : "shard1",
        "members" : [
                {
                        "_id" : 0,
                        "host" : "192.168.31.231:27017"
                },
                {
                        "_id" : 1,
                        "host" : "192.168.31.232:27017"
                },
                {
                        "_id" : 2,
                        "host" : "192.168.31.233:27017",
                        "arbiterOnly":true
                }
        ]
}
> rs.initiate(config)
{
"info" : "Config now saved locally. Should come online in about a minute.",
"ok" : 1
}

1.3配置 shard2  所用到的 Replica Sets
Server A 
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard2 --port 27018 --dbpath /data/shard2_1 --logpath /data/shard2_1/shard2_1.log --logappend --fork

Server B
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard2 --port 27018 --dbpath /data/shard2_2 --logpath /data/shard2_2/shard2_2.log --logappend --fork

Server C
[root@localhost bin]# /usr/local/mongo/bin/mongod --shardsvr --replSet shard2 --port 27018 --dbpath /data/shard2_3 --logpath /data/shard2_3/shard2_3.log --logappend --fork

用 mongo 连接其中一台机器的 27018 端口的 mongod，初始化 Replica Sets “shard2” ，执行:
[root@localhost bin]# ./mongo --port 27018
MongoDB shell version: 1.8.1
connecting to: 127.0.0.1:27018/test
> config = {_id: 'shard2', members: [
... {_id: 0, host: '192.168.31.231:27018'},
... {_id: 1, host: '192.168.31.232:27018'},
... {_id: 2, host: '192.168.31.233:27018',arbiterOnly:true}]
... }
{
        "_id" : "shard2",
        "members" : [
                {
                        "_id" : 0,
                        "host" : "192.168.31.231:27018"
                },
                {
                        "_id" : 1,
                        "host" : "192.168.31.232:27018"
                },
                {
                        "_id" : 2,
                        "host" : "192.168.31.233:27018",
                        "arbiterOnly":true
                }
        ]
}
> rs.initiate(config)
{ "ok" : 1 }

1.4 配置 3  台 台 Config Server
在 Server A 、B 、C  上 执行:
/usr/local/mongo/bin/mongod  --configsvr  --dbpath  /data/config  --port  20000  --logpath /data/config/config.log --logappend --fork
23.4  配置 3  台 台 Route Process
在 在 Server A 、B 、C  上 执行:
/usr/local/mongo/bin/mongos  --configdb 192.168.31.231:20000,192.168.31.232:20000,192.168.31.233:20000 --port 30000 --chunkSize 1 --logpath /data/mongos.log --logappend --fork

[root@mongo1 bin]# netstat -tpln|grep mongo
tcp        0      0 0.0.0.0:30000               0.0.0.0:*                   LISTEN      1573/mongos         
tcp        0      0 0.0.0.0:20000               0.0.0.0:*                   LISTEN      1375/mongod         
tcp        0      0 0.0.0.0:27017               0.0.0.0:*                   LISTEN      1061/mongod         
tcp        0      0 0.0.0.0:27018               0.0.0.0:*                   LISTEN      1211/mongod         
[root@mongo1 bin]# ps aux|grep mongo
root      1061  2.0  4.1 3198136 41920 ?       Sl   21:02   0:35 /usr/local/mongo/bin/mongod --shardsvr --replSet shard1 --port 27017 --dbpath /data/shard1_1 --logpath /data/shard1_1/shard1_1.log --logappend --fork
root      1211  2.5  7.6 3202220 77716 ?       Sl   21:09   0:33 /usr/local/mongo/bin/mongod --shardsvr --replSet shard2 --port 27018 --dbpath /data/shard2_1 --logpath /data/shard2_1/shard2_1.log --logappend --fork
root      1375  1.3  3.7 487476 38484 ?        Sl   21:17   0:12 /usr/local/mongo/bin/mongod --configsvr --dbpath /data/config --port 20000 --logpath /data/config/config.log --logappend --fork
root      1573  0.8  0.7 240152  7320 ?        Sl   21:28   0:02 /usr/local/mongo/bin/mongos --configdb 192.168.31.231:20000,192.168.31.232:20000,192.168.31.233:20000 --port 30000 --chunkSize 1 --logpath /data/mongos.log --logappend --fork
root      1794  0.0  0.0 103244   848 pts/1    S+   21:31   0:00 grep mongo


1.5配置 Shard Cluster
连接到其中一台机器的端口 30000 的 mongos 进程，并切换到 admin 数据库做以下配置
[root@localhost bin]# ./mongo --port 30000
MongoDB shell version: 1.8.1
connecting to: 127.0.0.1:30000/test
> use admin
switched to db admin
>db.runCommand({addshard:"shard1/192.168.31.231:27017,192.168.31.232:27017,192.168.31.233:27017"});
{ "shardAdded" : "shard1", "ok" : 1 }
>db.runCommand({addshard:"shard2/192.168.31.231:27018,192.168.31.232:27018,192.168.31.233:27018"});
{ "shardAdded" : "shard2", "ok" : 1 }
>
进入mongos进程config库可以看到目前分片的情况：
mongos> use config
switched to db config
mongos> db.shards.find()
{ "_id" : "shard1", "host" : "shard1/192.168.31.231:27017,192.168.31.232:27017,192.168.31.233:27017" }
{ "_id" : "shard2", "host" : "shard2/192.168.31.231:27018,192.168.31.232:27018,192.168.31.233:27018" }
mongos> 

1.6激活数据库及集合的分片
db.runCommand({ enablesharding:"test" })
db.runCommand({ shardcollection: "test.users", key: { _id:1 }})


1.7验证 Sharding  正常工作
连接到其中一台机器的端口 30000 的 mongos 进程，并切换到 test 数据库，以便添加测试数
据
use test
for(var i=1;i<=20000;i++) db.users.insert({id:i,addr_1:"Beijing",addr_2:"Shanghai"});
db.users.stats()
{
        "sharded" : true,
        "paddingFactorNote" : "paddingFactor is unused and unmaintained in 3.0. It remains hard coded to 1.0 for compatibility only.",
        "userFlags" : 1,
        "capped" : false,
        "ns" : "test.users",
        "count" : 20000,
        "numExtents" : 10,
        "size" : 2240000,
        "storageSize" : 5586944,
        "totalIndexSize" : 670432,
        "indexSizes" : {
                "_id_" : 670432
        },
        "avgObjSize" : 112,
        "nindexes" : 1,
        "nchunks" : 5,
        "shards" : {
                "shard1" : {
                        "ns" : "test.users",
                        "count" : 8697,
                        "size" : 974064,
                        "avgObjSize" : 112,
                        "numExtents" : 5,
                        "storageSize" : 2793472,
                        "lastExtentSize" : 2097152,
                        "paddingFactor" : 1,
                        "paddingFactorNote" : "paddingFactor is unused and unmaintained in 3.0. It remains hard coded to 1.0 for compatibility only.",
                        "userFlags" : 1,
                        "capped" : false,
                        "nindexes" : 1,
                        "totalIndexSize" : 294336,
                        "indexSizes" : {
                                "_id_" : 294336
                        },
                        "ok" : 1,
                        "$gleStats" : {
                                "lastOpTime" : Timestamp(0, 0),
                                "electionId" : ObjectId("558aabf892f5b70479ade020")
                        }
                },
                "shard2" : {
                        "ns" : "test.users",
                        "count" : 11303,
                        "size" : 1265936,
                        "avgObjSize" : 112,
                        "numExtents" : 5,
                        "storageSize" : 2793472,
                        "lastExtentSize" : 2097152,
                        "paddingFactor" : 1,
                        "paddingFactorNote" : "paddingFactor is unused and unmaintained in 3.0. It remains hard coded to 1.0 for compatibility only.",
                        "userFlags" : 1,
                        "capped" : false,
                        "nindexes" : 1,
                        "totalIndexSize" : 376096,
                        "indexSizes" : {
                                "_id_" : 376096
                        },
                        "ok" : 1,
                        "$gleStats" : {
                                "lastOpTime" : Timestamp(0, 0),
                                "electionId" : ObjectId("558aacdd8bf5d360e64002dd")
                        }
                }
        },
        "ok" : 1
}
mongos> 
./mongo --port 27017
shard2:PRIMARY> use test
switched to db test
shard2:PRIMARY> show collections;
system.indexes
users
shard2:PRIMARY> db.users.find().count()
11303  --和db.users.stats()查看的数据条数一样 20000=11303+8697
shard2:PRIMARY> 
 
./mongo --port 27018
shard2:PRIMARY> use test
switched to db test
shard2:PRIMARY> show collections;
system.indexes
users
shard1:PRIMARY> db.users.find().count()
8697   ----和db.users.stats()查看的数据条数一样  
shard1:PRIMARY> 

从SECONDARY读取数据：
shard2:SECONDARY> show collections;
2015-06-24T21:46:11.634+0800 E QUERY    Error: listCollections failed: { "note" : "from execCommand", "ok" : 0, "errmsg" : "not master" }
查询时报错，说明SECONDARY节点不能执行查询操作。
执行db.getMongo().setSlaveOk()，从库就可以进行读操作了,可以控制从哪些分片上面可以读。
shard1:
shard2:SECONDARY> db.getMongo().setSlaveOk()
shard2:SECONDARY> show collections;
system.indexes
users

shard2:
shard1:SECONDARY> db.getMongo().setSlaveOk()
shard1:SECONDARY> show collections;
system.indexes
users
shard1:SECONDARY> db.users.find().count();
8697
shard1:SECONDARY> 

模拟故障：
[root@mongo1 bin]# ps aux|grep mongo
root      1061  1.9  8.1 3200192 82956 ?       Sl   21:02   0:56 /usr/local/mongo/bin/mongod --shardsvr --replSet shard1 --port 27017 --dbpath /data/shard1_1 --logpath /data/shard1_1/shard1_1.log --logappend --fork
root      1211  2.1  7.8 3205304 79928 ?       Sl   21:09   0:52 /usr/local/mongo/bin/mongod --shardsvr --replSet shard2 --port 27018 --dbpath /data/shard2_1 --logpath /data/shard2_1/shard2_1.log --logappend --fork
root      1375  1.8  4.1 489528 42180 ?        Sl   21:17   0:37 /usr/local/mongo/bin/mongod --configsvr --dbpath /data/config --port 20000 --logpath /data/config/config.log --logappend --fork
root      1573  0.9  0.7 240152  7340 ?        Sl   21:28   0:13 /usr/local/mongo/bin/mongos --configdb 192.168.31.231:20000,192.168.31.232:20000,192.168.31.233:20000 --port 30000 --chunkSize 1 --logpath /data/mongos.log --logappend --fork
root      1901  0.0  1.8 721952 19132 pts/0    Sl+  21:38   0:00 ./mongo --port 27018
root      2130  0.0  0.0 103244   848 pts/1    S+   21:51   0:00 grep mongo
[root@mongo1 bin]# kill -2 1061  --这里不能使用kill -9 ，否则会导致丢失数据

通过rs.status()可以查看复制集的状态：
我们可以看到192.168.31.231:27017处于宕机状态，192.168.31.233：27017接管变成了PRIMARY
shard1:PRIMARY>  rs.status()
{
        "set" : "shard1",
        "date" : ISODate("2015-06-24T14:03:10.425Z"),
        "myState" : 1,
        "members" : [
                {
                        "_id" : 0,
                        "name" : "192.168.31.231:27017",
                        "health" : 0,
                        "state" : 8,
                        "stateStr" : "(not reachable/healthy)",
                        "uptime" : 0,
                        "optime" : Timestamp(0, 0),
                        "optimeDate" : ISODate("1970-01-01T00:00:00Z"),
                        "lastHeartbeat" : ISODate("2015-06-24T14:03:09.083Z"),
                        "lastHeartbeatRecv" : ISODate("2015-06-24T13:51:38.834Z"),
                        "pingMs" : 0,
                        "lastHeartbeatMessage" : "Failed attempt to connect to 192.168.31.231:27017; couldn't connect to server 192.168.31.231:27017 (192.168.31.231), connection attempt failed",
                        "configVersion" : -1
                },
                {
                        "_id" : 1,
                        "name" : "192.168.31.232:27017",
                        "health" : 1,
                        "state" : 2,
                        "stateStr" : "SECONDARY",
                        "uptime" : 3242,
                        "optime" : Timestamp(1435152718, 13),
                        "optimeDate" : ISODate("2015-06-24T13:31:58Z"),
                        "lastHeartbeat" : ISODate("2015-06-24T14:03:09.814Z"),
                        "lastHeartbeatRecv" : ISODate("2015-06-24T14:03:09.813Z"),
                        "pingMs" : 1,
                        "configVersion" : 1
                },
                {
                        "_id" : 2,
                        "name" : "192.168.31.233:27017",
                        "health" : 1,
                        "state" : 1,
                        "stateStr" : "PRIMARY",
                        "uptime" : 3603,
                        "optime" : Timestamp(1435152718, 13),
                        "optimeDate" : ISODate("2015-06-24T13:31:58Z"),
                        "electionTime" : Timestamp(1435153900, 1),
                        "electionDate" : ISODate("2015-06-24T13:51:40Z"),
                        "configVersion" : 1,
                        "self" : true
                }
        ],
        "ok" : 1,
        "$gleStats" : {
                "lastOpTime" : Timestamp(0, 0),
                "electionId" : ObjectId("558ab5ec28f234f7b5abda48")
        }
}

查看分片集合信息：
mongos> db.collections.find()
{ "_id" : "test.users", "lastmod" : ISODate("2015-06-24T13:30:19.670Z"), "dropped" : false, "key" : { "_id" : 1 }, "unique" : false, "lastmodEpoch" : ObjectId("558ab0eb6a881136d7047be4") }