mongodb 分片配置 以及mapreduce

三个mongod 其中20001为configdb

20002,20003为数据部分

27017为mongos部分

/usr/local/mongodb/bin/mongod --dbpath=/var/mongodb/data --logpath /var/mongodb/logs/log.log --port 20001 --nojournal --fork
/usr/local/mongodb/bin/mongod --dbpath=/var/mongodb/data_3 --logpath /var/mongodb/logs/log_3.log --port 20002 --fork --nojournal
/usr/local/mongodb/bin/mongod --dbpath=/var/mongodb/data_4 --logpath /var/mongodb/logs/log_4.log --port 20003 --fork --nojournal
/usr/local/mongodb/bin/mongos --port 27017 --configdb=127.0.0.1:20001 --fork --logpath /var/mongodb/logs/log_2.log


登录mongos后台
/usr/local/mongodb/bin/mongo 127.0.0.1:27017/admin
添加分片mongod
db.runCommand({"addshard":"127.0.0.1:20002",allowLocal:true});
db.runCommand({"addshard":"127.0.0.1:20003",allowLocal:true});
开启数据分片
db.runCommand({"enablesharding":"test"});
db.runCommand({"shardcollection":"test.person","key":{"name":1}});

测试分片
插入数据：

for(var i = 100;i<1000000;i++){ db.person.insert({"_id":i,"name":"terry"}) }

插入完成后：

db.printShardingStatus();

结果：

mongos> db.printShardingStatus();
--- Sharding Status ---
  sharding version: {
    "_id" : 1,
    "version" : 4,
    "minCompatibleVersion" : 4,
    "currentVersion" : 5,
    "clusterId" : ObjectId("56ab0fc6b45916f958412ae6")
}
  shards:
    {  "_id" : "shard0000",  "host" : "127.0.0.1:20002" }
    {  "_id" : "shard0001",  "host" : "127.0.0.1:20003" }
  databases:
    {  "_id" : "admin",  "partitioned" : false,  "primary" : "config" }
    {  "_id" : "test",  "partitioned" : true,  "primary" : "shard0000" }
        test.account
            shard key: { "name" : 1 }
            chunks:
                shard0000    1
            { "name" : { "$minKey" : 1 } } -->> { "name" : { "$maxKey" : 1 } } on : shard0000 Timestamp(1, 0)
        test.account2
            shard key: { "_id" : 1 }
            chunks:
                shard0001    3
                shard0000    2
            { "_id" : { "$minKey" : 1 } } -->> { "_id" : NumberLong(1) } on : shard0001 Timestamp(2, 0)
            { "_id" : NumberLong(1) } -->> { "_id" : 11124 } on : shard0001 Timestamp(3, 0)
            { "_id" : 11124 } -->> { "_id" : 366409 } on : shard0000 Timestamp(4, 1)
            { "_id" : 366409 } -->> { "_id" : 725752 } on : shard0000 Timestamp(3, 2)
            { "_id" : 725752 } -->> { "_id" : { "$maxKey" : 1 } } on : shard0001 Timestamp(4, 0)
        test.person
            shard key: { "name" : 1 }
            chunks:
                shard0000    1
            { "name" : { "$minKey" : 1 } } -->> { "name" : { "$maxKey" : 1 } } on : shard0000 Timestamp(1, 0)

这是分片的具体情况

{ "_id" : { "$minKey" : 1 } } -->> { "_id" : NumberLong(1) } on : shard0001 Timestamp(2, 0)
            { "_id" : NumberLong(1) } -->> { "_id" : 11124 } on : shard0001 Timestamp(3, 0)
            { "_id" : 11124 } -->> { "_id" : 366409 } on : shard0000 Timestamp(4, 1)
            { "_id" : 366409 } -->> { "_id" : 725752 } on : shard0000 Timestamp(3, 2)
            { "_id" : 725752 } -->> { "_id" : { "$maxKey" : 1 } } on : shard0001 Timestamp(4, 0) 

mapreduce: mapreduce1.js

function GetRandomNum()
{   
	return parseInt(Math.random()*1000,10)+1;  
} 

admindb = connect("localhost:27017/admin");
admindb.runCommand({"shardcollection":"test.mapreduce","key":{"_id":1}});
test_db = connect("localhost:27017/test");
for(i=0;i<=1000000;i++){
	num = GetRandomNum();
	test_db.mapreduce.insert({_id:i,num:num});
}

开始插入数据 插入的数据表为  分片表

/usr/local/mongodb/bin/mongo  mapreduce1.js  

写一个mapreduce：

test_db = connect("localhost:27017/test");
// mapreduce 
map = function() {  
   emit(this.num, {
		num:this.num,
		count:1
	   
   });  
} ;

reduce =    function(key, emits) {  
		count = 0;
       for(x in emits){
			count += emits[x].count;
			num = emits[x].num;
	   }
		return {
			num:num,
			count:count
		};
    }  
	
	
finalize =	function(key, reducedValue) {  
   reducedValue.d = 1;
   return reducedValue;  
}
	
	
	
test_db.mapreduce.mapReduce( 
			map,  
            reduce,  
            {  
                out: { 
					merge: "map_reduce_example",
					sharded:true
				},  
                query: { _id:{ $gt: 100000 } },  
                finalize: finalize  
            }  
    );
	
	
	
	
	
	

/usr/local/mongodb/bin/mongo  mapreduce2.js 

执行完登录后台

 /usr/local/mongodb/bin/mongo 127.0.0.1:27017/test

db.printShardingStatus();

	test.map_reduce_example
			shard key: { "_id" : 1 }
			chunks:
				shard0000	1
			{ "_id" : { "$minKey" : 1 } } -->> { "_id" : { "$maxKey" : 1 } } on : shard0000 Timestamp(1, 0) 
		test.mapreduce
			shard key: { "_id" : 1 }
			chunks:
				shard0000	2
				shard0001	3
			{ "_id" : { "$minKey" : 1 } } -->> { "_id" : 0 } on : shard0000 Timestamp(4, 0) 
			{ "_id" : 0 } -->> { "_id" : 13676 } on : shard0000 Timestamp(3, 1) 
			{ "_id" : 13676 } -->> { "_id" : 403345 } on : shard0001 Timestamp(4, 1) 
			{ "_id" : 403345 } -->> { "_id" : 804273 } on : shard0001 Timestamp(4, 2) 
			{ "_id" : 804273 } -->> { "_id" : { "$maxKey" : 1 } } on : shard0001 Timestamp(4, 3) 

输入表和输出表如图

关键点为：

表在写入前先定义分区表

admindb.runCommand({"shardcollection":"test.mapreduce","key":{"_id":1}});

在out里面定义输出表为分区表：

test_db.mapreduce.mapReduce( 
			map,  
            reduce,  
            {  
                out: { 
					merge: "map_reduce_example",
					sharded:true
				},  
                query: { _id:{ $gt: 100000 } },  
                finalize: finalize  
            }  
    );

 在out中设置sharded为true即可

移除分片：

use admin;

 db.printShardingStatus();

查看分片状态，找到要删除的分片的名字，然后执行

mongos> db.runCommand({"removeshard":"shard0002"});
{
    "msg" : "removeshard completed successfully",
    "state" : "completed",
    "shard" : "shard0002",
    "ok" : 1
}

查看执行完成后的分片状态

 db.printShardingStatus();

删除分片后，数据被拷贝到其他的分片中。