mongodb数据库范围分片数据分布不均匀

【说明】

当前使用mongodb分片，三个分片

mongos> sh.status()
--- Sharding Status --- 
  sharding version: {
        "_id" : 1,
        "minCompatibleVersion" : 5,
        "currentVersion" : 6,
        "clusterId" : ObjectId("66a30ccca62de41d6b0241a4")
  }
  shards:
        {  "_id" : "mongo1",  "host" : "mongo1/mongo1:2700,mongo2:2700,mongo3:2700",  "state" : 1 }
        {  "_id" : "mongo2",  "host" : "mongo2/mongo1:2701,mongo2:2701,mongo3:2701",  "state" : 1 }
        {  "_id" : "mongo3",  "host" : "mongo3/mongo1:2702,mongo2:2702,mongo3:2702",  "state" : 1 }
  active mongoses:
        "4.2.8" : 3
  autosplit:
        Currently enabled: yes
  balancer:
        Currently enabled:  yes
        Currently running:  no
        Failed balancer rounds in last 5 attempts:  0
        Migration Results for the last 24 hours: 
                690 : Success

【表范围分片测试】

sh.enableSharding("test");
sh.shardCollection("test.messages", { createTime : 1} );  注意这里只是测试时候将时间字段作为范围分片键

使用js插入数据

cat shard_test_messages.js 
testdb = db.getSiblingDB('test');

var messages = ["Hello there", "Good Morning", "valar morghulis"];
var createTime = new Date();
for (var j = 0; j < 50000; j ++) {
  createTime.setFullYear(2024);
  createTime.setMonth(Math.floor(Math.random() * 12));
  createTime.setDate(Math.floor(Math.random() * 31) + 1);
  createTime.setHours(Math.floor(Math.random() * 24));
  createTime.setMinutes(Math.floor(Math.random() * 60));
  createTime.setSeconds(Math.floor(Math.random() * 60));
  testdb.messages.insertOne({
    userid: Math.floor(Math.random()*50000),
    message: messages[Math.floor(Math.random()*messages.length)],
    createTime: createTime
  })
}

db.messages.ensureIndex({createTime: 1});

mongo "localhost:27017/admin" /tmp/shard_test_messages.js -u admin -p 123456

【查看表分片情况】

mongos> db.messages.getShardDistribution()

Shard mongo1 at mongo1/mongo1:2700,mongo2:2700,mongo3:2700
 data : 2.01MiB docs : 25000 chunks : 1
 estimated data per chunk : 2.01MiB
 estimated docs per chunk : 25000

Totals
 data : 2.01MiB docs : 25000 chunks : 1
 Shard mongo1 contains 100% data, 100% docs in cluster, avg obj size on shard : 84B


mongos> sh.status()
--- Sharding Status --- 
  sharding version: {
        "_id" : 1,
        "minCompatibleVersion" : 5,
        "currentVersion" : 6,
        "clusterId" : ObjectId("66a30ccca62de41d6b0241a4")
  }
  shards:
        {  "_id" : "mongo1",  "host" : "mongo1/mongo1:2700,mongo2:2700,mongo3:2700",  "state" : 1 }
        {  "_id" : "mongo2",  "host" : "mongo2/mongo1:2701,mongo2:2701,mongo3:2701",  "state" : 1 }
        {  "_id" : "mongo3",  "host" : "mongo3/mongo1:2702,mongo2:2702,mongo3:2702",  "state" : 1 }
  active mongoses:
        "4.2.8" : 3
  autosplit:
        Currently enabled: yes
  balancer:
        Currently enabled:  yes
        Currently running:  no
        Failed balancer rounds in last 5 attempts:  0
        Migration Results for the last 24 hours: 
                No recent migrations
  databases:
        {  "_id" : "config",  "primary" : "config",  "partitioned" : true }
                config.system.sessions
                        shard key: { "_id" : 1 }
                        unique: false
                        balancing: true
                        chunks:
                                mongo1  1
                        { "_id" : { "$minKey" : 1 } } -->> { "_id" : { "$maxKey" : 1 } } on : mongo1 Timestamp(1, 0) 
        {  "_id" : "test",  "primary" : "mongo1",  "partitioned" : true,  "version" : {  "uuid" : UUID("35a9a3e5-3ba5-4315-977c-9c7176d891ae"),  "lastMod" : 1 } }
                test.messages
                        shard key: { "createTime" : 1 }
                        unique: false
                        balancing: true
                        chunks:
                                mongo1  1
                        { "createTime" : { "$minKey" : 1 } } -->> { "createTime" : { "$maxKey" : 1 } } on : mongo1 Timestamp(1, 0) 

mongodb的sharding.autosplit是默认开启的，并且跟checkSize参数关联，默认为64M，当前安装的时候执行了修改这个参数为1M便于方便测试，之前版本的是在mongos的配置文件参数中设置，

当前版本跟新版本参数在config库下面的setting表，使用命令修改，各版本的修改命令有差异，需要注意：https://www.mongodb.com/zh-cn/docs/manual/tutorial/modify-chunk-size-in-sharded-cluster/#std-label-tutorial-modifying-range-size；

根据淘宝月报的mongodb分片知识，查看链接：https://www.bookstack.cn/read/aliyun-rds-core/5717773a4eef2615.md

查看当前范围分片的数据只在分片shard1的primary shard中，根据chunk触发迁移条件，手工测试balance，查看到报错参数报错信息：

mongos> sh.startBalancer()
2024-07-30T10:39:49.588+0800 E  QUERY    [js] uncaught exception: Error: command failed: {
        "ok" : 0,
        "errmsg" : "Failed to refresh the chunk sizes settings :: caused by :: Expected field \"value\" to have numeric type, but found string",
        "code" : 14,
        "codeName" : "TypeMismatch",
        "operationTime" : Timestamp(1722307189, 1),
        "$clusterTime" : {
                "clusterTime" : Timestamp(1722307189, 1),
                "signature" : {
                        "hash" : BinData(0,"XinbmSBnIvaxzrWfcNLn8IsFI78="),
                        "keyId" : NumberLong("7395769083385348113")
                }
        }
} :
_getErrorWithCode@src/mongo/shell/utils.js:25:13
doassert@src/mongo/shell/assert.js:18:14
_assertCommandWorked@src/mongo/shell/assert.js:583:17
assert.commandWorked@src/mongo/shell/assert.js:673:16
sh.startBalancer@src/mongo/shell/utils_sh.js:184:12
@(shell):1:1

根据报错查看是参数值类型不对，查看配置信息，确实是字符串类型：

mongos> configdb.settings.find()
{ "_id" : "chunksize", "value" : "1" }

当前安装的分片集群是使用ansible脚本安装，使用变量方式传入导致参数异常：

查看参数是数字类型

# The chunksize for shards in MB
mongos_chunk_size: 1

查看参数输入时候加了''号为string类型：

configdb = db.getSiblingDB('config');
configdb.settings.save( { _id:"chunksize", value: '{{ mongos_chunk_size }}' } )

查看参数跟报错一致，修改参数，测试范围分片数据正常

mongos> configdb.settings.save( { _id:"chunksize", value: 1 } )
WriteResult({ "nMatched" : 1, "nUpserted" : 0, "nModified" : 1 })
mongos> configdb.settings.find()
{ "_id" : "chunksize", "value" : 1 }
mongos>

mongos> sh.startBalancer()
{
        "ok" : 1,
        "operationTime" : Timestamp(1722307355, 23),
        "$clusterTime" : {
                "clusterTime" : Timestamp(1722307355, 23),
                "signature" : {
                        "hash" : BinData(0,"SfLbKefZpUbx4FCKVT1JeRvsrOY="),
                        "keyId" : NumberLong("7395769083385348113")
                }
        }
}
mongos>
mongos> sh.getBalancerState()
true

mongos> db.messages.getShardDistribution()

Shard mongo1 at mongo1/mongo1:2700,mongo2:2700,mongo3:2700
data : 3.37MiB docs : 41863 chunks : 5
estimated data per chunk : 692KiB
estimated docs per chunk : 8372

Shard mongo2 at mongo2/mongo1:2701,mongo2:2701,mongo3:2701
data : 3.34MiB docs : 41482 chunks : 5
estimated data per chunk : 685KiB
estimated docs per chunk : 8296

Shard mongo3 at mongo3/mongo1:2702,mongo2:2702,mongo3:2702
data : 3.36MiB docs : 41655 chunks : 5
estimated data per chunk : 688KiB
estimated docs per chunk : 8331

Totals
data : 10.09MiB docs : 125000 chunks : 15
Shard mongo1 contains 33.49% data, 33.49% docs in cluster, avg obj size on shard : 84B
Shard mongo2 contains 33.18% data, 33.18% docs in cluster, avg obj size on shard : 84B
Shard mongo3 contains 33.32% data, 33.32% docs in cluster, avg obj size on shard : 84B