mongo扩容

目前部署是mongoS有三台，即mongo服务器mongoDb有三组，每一组有三台主副机，其中一台主，两台副起初在设置的时候，每组副本集其IP都在server.conf里面写死了，一组三台，就得修改这三台的配置：[java]
view plain
copyprint?



shardsvr=true  
replSet=unilog-shard03/10.70.175.69:27017,10.70.175.70:27017,10.70.175.71:27017  
port=27017  
oplogSize=512  
logappend=true  
fork=true  
auth=true  

shardsvr=true
replSet=unilog-shard03/10.70.175.69:27017,10.70.175.70:27017,10.70.175.71:27017
port=27017
oplogSize=512
logappend=true
fork=true
auth=true

而在mongodS配置分片时：[java]
view plain
copyprint?



db.runCommand({addshard:"unilog-shard01/10.70.175.63:27017,10.70.175.64:27017,10.70.175.65:27017"});  

db.runCommand({addshard:"unilog-shard01/10.70.175.63:27017,10.70.175.64:27017,10.70.175.65:27017"});

最近因为机器扩容，移除了一条主机65，导致mongodS连接不上，出现如下

master	Composite step 'master' failed due to unsatisfication of success condition.	Step Log
build with ant	Ant build failed.BUILD FAILEDjava.net.SocketTimeoutException: Read timed out    at java.net.SocketInputStream.socketRead0(Native Method)    at java.net.SocketInputStream.read(SocketInputStream.java:155)    at java.io.BufferedInputStream.fill(BufferedInputStream.java:229)    at java.io.BufferedInputStream.read1(BufferedInputStream.java:267)    at java.io.BufferedInputStream.read(BufferedInputStream.java:324)    at sun.net.www.http.HttpClient.parseHTTPHeader(HttpClient.java:658)    at sun.net.www.http.HttpClient.parseHTTP(HttpClient.java:607)    at sun.net.www.protocol.http.HttpURLConnection.getInputStream(HttpURLConnection.java:966)    at java.net.HttpURLConnection.getResponseCode(HttpURLConnection.java:379)    at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:334)    at org.jsoup.helper.HttpConnection.execute(HttpConnection.java:132)    at org.jsoup.helper.HttpConnection.get(HttpConnection.java:121)    at sun....	Step Log

查看其端口号，netstat -an | grep 27017，：在去连接65时，一直被于接收请求状态需要调整mongoDb里面的server.conf配置文件：[java]
view plain
copyprint?



shardsvr=true  
replSet=unilog-shard02  
port=27017  
oplogSize=512  
logappend=true  
fork=true  
auth=true  
~  

shardsvr=true
replSet=unilog-shard02
port=27017
oplogSize=512
logappend=true
fork=true
auth=true
~

ESC，:wq!，保存退出即可，重新启动mongoDb然后在主机上如62为主机，执行如下命令： var cfg={ _id:'unilog-shard02', members:[ {_id:0,host:'10.70.175.66:27017',priority:2}, {_id:1,host:'10.70.175.67:27017',priority:1}, {_id:1,host:'10.70.175.68:27017'} };  \  var s= rs.status(); s;\  var m=s.members;  \  if(m&&m.length>0){ rs.reconfig(cfg); }else{  rs.initiate(cfg); }  \  rs.slaveOk();rs.status()要进行[java]
view plain
copyprint?



mongo   

mongo

admin用户[javascript]
view plain
copyprint?



mongo@oa-04-va59:~> mongo  
MongoDB shell version: 2.0.2  
connecting to: test  
> use admin  
switched to db admin  
> db.auth("admin","admin123")  
1  
PRIMARY> var cfg={ _id:'shard0', members:[ {_id:0,host:'10.70.175.63:27017',priority:2}, {_id:1,host:'10.70.175.63:27017',priority:1} };  \  
Tue Jun  9 11:28:46 SyntaxError: missing ] after element list (shell):1  
PRIMARY>   var s= rs.status(); s;\  
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1  
PRIMARY>   var m=s.members;  \  
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1  
PRIMARY>   if(m&&m.length>0){ rs.reconfig(cfg); }else{  rs.initiate(cfg); }  \  
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1  
PRIMARY>   rs.slaveOk();rs.status()  
{  
        "set" : "unilog-shard01",  
        "date" : ISODate("2015-06-09T03:28:48Z"),  
        "myState" : 1,  
        "members" : [  
                {  
                        "_id" : 0,  
                        "name" : "10.70.175.63:27017",  
                        "health" : 1,  
                        "state" : 1,  
                        "stateStr" : "PRIMARY",  
                        "optime" : {  
                                "t" : 1433820527000,  
                                "i" : 2  
                        },  
                        "optimeDate" : ISODate("2015-06-09T03:28:47Z"),  
                        "self" : true  
                },  
                {  
                        "_id" : 3,  
                        "name" : "10.70.175.64:27017",  
                        "health" : 1,  
                        "state" : 3,  
                        "stateStr" : "RECOVERING",  
                        "uptime" : 2097,  
                        "optime" : {  
                                "t" : 1403622942000,  
                                "i" : 1  
                        },  
                        "optimeDate" : ISODate("2014-06-24T15:15:42Z"),  
                        "lastHeartbeat" : ISODate("2015-06-09T03:28:47Z"),  
                        "pingMs" : 0,  
                        "errmsg" : "error RS102 too stale to catch up"  
                }  
        ],  
        "ok" : 1  
}  

mongo@oa-04-va59:~> mongo
MongoDB shell version: 2.0.2
connecting to: test
> use admin
switched to db admin
> db.auth("admin","admin123")
1
PRIMARY> var cfg={ _id:'shard0', members:[ {_id:0,host:'10.70.175.63:27017',priority:2}, {_id:1,host:'10.70.175.63:27017',priority:1} };  \
Tue Jun  9 11:28:46 SyntaxError: missing ] after element list (shell):1
PRIMARY>   var s= rs.status(); s;\
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1
PRIMARY>   var m=s.members;  \
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1
PRIMARY>   if(m&&m.length>0){ rs.reconfig(cfg); }else{  rs.initiate(cfg); }  \
Tue Jun  9 11:28:46 SyntaxError: illegal character (shell):1
PRIMARY>   rs.slaveOk();rs.status()
{
"set" : "unilog-shard01",
"date" : ISODate("2015-06-09T03:28:48Z"),
"myState" : 1,
"members" : [
{
"_id" : 0,
"name" : "10.70.175.63:27017",
"health" : 1,
"state" : 1,
"stateStr" : "PRIMARY",
"optime" : {
"t" : 1433820527000,
"i" : 2
},
"optimeDate" : ISODate("2015-06-09T03:28:47Z"),
"self" : true
},
{
"_id" : 3,
"name" : "10.70.175.64:27017",
"health" : 1,
"state" : 3,
"stateStr" : "RECOVERING",
"uptime" : 2097,
"optime" : {
"t" : 1403622942000,
"i" : 1
},
"optimeDate" : ISODate("2014-06-24T15:15:42Z"),
"lastHeartbeat" : ISODate("2015-06-09T03:28:47Z"),
"pingMs" : 0,
"errmsg" : "error RS102 too stale to catch up"
}
],
"ok" : 1
}

"errmsg" : "error RS102 too stale to catch up"说明这几台机器没有同步，执行db.repairDatabase()时，出现[java]
view plain
copyprint?



PRIMARY> db.repairDatabase()  
{  
        "errmsg" : "Cannot repair database logs having size: 328891891712 (bytes) because free disk space is: 158043725824 (bytes)",  
        "ok" : 0  
}  

PRIMARY> db.repairDatabase()
{
"errmsg" : "Cannot repair database logs having size: 328891891712 (bytes) because free disk space is: 158043725824 (bytes)",
"ok" : 0
}

空间不够，除了扩容外，其余方案还待去实践（后续补充）第二步，修改mongoS里面，刚开始我用的是db.runCommand({removeshard:"unilog-shard01/10.70.175.65:27017"});[java]
view plain
copyprint?



mongo@oa-04-va70:/mongodb/mongo/bin> ./mongo admin  
MongoDB shell version: 2.0.2  
connecting to: admin  
> db.runCommand({removeshard:"oa-04-va61"});  
{ "ok" : 0, "errmsg" : "unauthorized" }  
> db.auth("admin","admin123")  
1  
mongos> db.runCommand({removeshard:"unilog-shard01/10.70.175.65:27017"});  
{  
        "msg" : "draining started successfully",  
        "state" : "started",  
        "shard" : "unilog-shard01",  
        "ok" : 1  
}  

mongo@oa-04-va70:/mongodb/mongo/bin> ./mongoadmin
MongoDB shell version: 2.0.2
connecting to: admin
> db.runCommand({removeshard:"oa-04-va61"});
{ "ok" : 0, "errmsg" : "unauthorized" }
> db.auth("admin","admin123")
1
mongos> db.runCommand({removeshard:"unilog-shard01/10.70.175.65:27017"});
{
"msg" : "draining started successfully",
"state" : "started",
"shard" : "unilog-shard01",
"ok" : 1
}

再执行时就出现

msg:

"draining

ongoing"

 

,

state:

"ongoing"，表示正在迁移，该组其draining状态为true：

[java]
view plain
copyprint?



mongos> use config  
switched to db config  
mongos> db.shards.find()  
{ "_id" : "unilog-shard02", "host" : "unilog-shard02/10.70.175.66:27017,10.70.175.67:27017,10.70.175.68:27017" }  
{ "_id" : "unilog-shard03", "host" : "unilog-shard03/10.70.175.69:27017,10.70.175.71:27017,10.70.175.70:27017" }  
{ "_id" : "unilog-shard01", "draining" : true, "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" }  

mongos> use config
switched to db config
mongos> db.shards.find()
{ "_id" : "unilog-shard02", "host" : "unilog-shard02/10.70.175.66:27017,10.70.175.67:27017,10.70.175.68:27017" }
{ "_id" : "unilog-shard03", "host" : "unilog-shard03/10.70.175.69:27017,10.70.175.71:27017,10.70.175.70:27017" }
{ "_id" : "unilog-shard01", "draining" : true, "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" }

update这个状态：

[java]
view plain
copyprint?



mongos> db.shards.update({ "_id" : "unilog-shard01"},{ "_id" : "unilog-shard01", "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" })  

mongos> db.shards.update({ "_id" : "unilog-shard01"},{ "_id" : "unilog-shard01", "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" })

然后再查看时：

[java]
view plain
copyprint?



mongos> db.shards.find()  
{ "_id" : "unilog-shard02", "host" : "unilog-shard02/10.70.175.66:27017,10.70.175.67:27017,10.70.175.68:27017" }  
{ "_id" : "unilog-shard03", "host" : "unilog-shard03/10.70.175.69:27017,10.70.175.71:27017,10.70.175.70:27017" }  
{ "_id" : "unilog-shard01", "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" }  

mongos> db.shards.find()
{ "_id" : "unilog-shard02", "host" : "unilog-shard02/10.70.175.66:27017,10.70.175.67:27017,10.70.175.68:27017" }
{ "_id" : "unilog-shard03", "host" : "unilog-shard03/10.70.175.69:27017,10.70.175.71:27017,10.70.175.70:27017" }
{ "_id" : "unilog-shard01", "host" : "unilog-shard01/10.70.175.64:27017,10.70.175.63:27017" }

用mongoVUE，连接成功mongo相关的命令：

查看mongoDb分副本集的状态： rs.status();

查看数据库：show
dbs

查看某个库的状态：

[java]
view plain
copyprint?



RECOVERING> db.stats()  
{  
        "db" : "logs",  
        "collections" : 13,  
        "objects" : 119434683,  
        "avgObjSize" : 2392.0039992403213,  
        "dataSize" : 285688239384,  
        "storageSize" : 297047594944,  
        "numExtents" : 181,  
        "indexes" : 24,  
        "indexSize" : 19946562048,  
        "fileSize" : 343363551232,  
        "nsSizeMB" : 16,  
        "ok" : 1  
}  

RECOVERING> db.stats()
{
"db" : "logs",
"collections" : 13,
"objects" : 119434683,
"avgObjSize" : 2392.0039992403213,
"dataSize" : 285688239384,
"storageSize" : 297047594944,
"numExtents" : 181,
"indexes" : 24,
"indexSize" : 19946562048,
"fileSize" : 343363551232,
"nsSizeMB" : 16,
"ok" : 1
}

这是在mongoDb上执行的，[java]
view plain
copyprint?



RECOVERING>  

RECOVERING>

还处在修复状态，即副本集没有同步，在空间足够多的情况，尝试修复下。可以在mongoS上验证该集合：

[java]
view plain
copyprint?



mongo@oa-04-va59:~> mongo  
MongoDB shell version: 2.0.2  
connecting to: test  
> use admin  
switched to db admin  
> db.auth("admin","admin123")  
1  
PRIMARY> help  
PRIMARY> show dbs  
PRIMARY> use logs  
switched to db logs  
PRIMARY> show collections  
PRIMARY> db.oplog.findOne()  

mongo@oa-04-va59:~> mongo
MongoDB shell version: 2.0.2
connecting to: test
> use admin
switched to db admin
> db.auth("admin","admin123")
1
PRIMARY> help
PRIMARY> show dbs
PRIMARY> use logs
switched to db logs
PRIMARY> show collections
PRIMARY> db.oplog.findOne()

删除锁文件：

[javascript]
view plain
copyprint?



mongo@oa-04-va63:/mongodb/unilog-shard02-02/data> pwd  
/mongodb/unilog-shard02-02/data  
mongo@oa-04-va63:/mongodb/unilog-shard02-02/data> rm -r mongod.lock  

mongo@oa-04-va63:/mongodb/unilog-shard02-02/data> pwd
/mongodb/unilog-shard02-02/data
mongo@oa-04-va63:/mongodb/unilog-shard02-02/data> rm -r mongod.lock

查看日志文件：

[javascript]
view plain
copyprint?



mongo@oa-04-va63:/mongodb/unilog-shard02-02/logs> pwd  
/mongodb/unilog-shard02-02/logs  
mongo@oa-04-va63:/mongodb/unilog-shard02-02/logs> tail -f server.log  

mongo@oa-04-va63:/mongodb/unilog-shard02-02/logs> pwd
/mongodb/unilog-shard02-02/logs
mongo@oa-04-va63:/mongodb/unilog-shard02-02/logs> tail -f server.log