MongoDB ( 五 )高级_索引

索引

在认识索引的之前我们先建立一张表,并往其中插入200万条数据。

// test.js
//生成随机数
function GetRandomNum(min,max){
    let range = max-min;   //得到随机数区间
    let rand = Math.random(); //得到随机值
    return (min + Math.round(rand *range)); //最小值+随机数取整
}

//console.log(GetRandomNum(10000,99999));

//生成随机用户名
function GetRadomUserName(min,max){
    let tempStringArray= "123456789qwertyuiopasdfghjklzxcvbnm".split("");//构造生成时的字母库数组
    let outPuttext = ""; //最后输出的变量
    //进行循环,随机生产用户名的长度,这里需要生成随机数方法的配合
    for(let i=1 ;i<GetRandomNum(min,max);i++){
        //随机抽取字母,拼装成需要的用户名
        outPuttext=outPuttext+tempStringArray[GetRandomNum(0,tempStringArray.length)]
    }
    return outPuttext;
}

var db = connect('company');
db.randomInfo.drop();
var  tempInfo = [];
for (let i=0;i<2000000;i++){
    tempInfo.push({
        username:GetRadomUserName(7,16),
        regeditTime:new Date(),
        randNum0:GetRandomNum(100000,999999),
        randNum1:GetRandomNum(100000,999999),
        randNum2:GetRandomNum(100000,999999),
        randNum3:GetRandomNum(100000,999999),
        randNum4:GetRandomNum(100000,999999),
        randNum5:GetRandomNum(100000,999999),
        randNum6:GetRandomNum(100000,999999),
        randNum7:GetRandomNum(100000,999999),
        randNum8:GetRandomNum(100000,999999),
        randNum8:GetRandomNum(100000,999999),
    })
}

db.randomInfo.insert(tempInfo);
> mongo
> load("./test.js")
connecting to: mongodb://127.0.0.1:27017/company
MongoDB server version: 3.4.10
···
// 这个过程可能需要2分钟左右

> use company
switched to db company
> db.randomInfo.stats()            // 使用这个查看插入了几条数据
{
        "ns" : "company.randomInfo",
        "size" : 421908971,
        "count" : 1835000,
        "avgObjSize" : 229,
        "storageSize" : 188686336,
        "capped" : false,
        "wiredTiger" : {
                "metadata" : {
                        "formatVersion" : 1
                },
                "creationString" : "access_pattern_hint=none,allocation_size=4KB,app_metadata=(formatVersion=1),block_allocation=best,block_compressor=snappy,cache_resident=false,checksum=on,colgroups=,collator=,columns=,dictionary=0,encryption=(keyid=,name=),exclusive=false,extractor=,format=btree,huffman_key=,huffman_value=,ignore_in_memory_cache_size=false,immutable=false,internal_item_max=0,internal_key_max=0,internal_key_truncate=true,internal_page_max=4KB,key_format=q,key_gap=10,leaf_item_max=0,leaf_key_max=0,leaf_page_max=32KB,leaf_value_max=64MB,log=(enabled=true),lsm=(auto_throttle=true,bloom=true,bloom_bit_count=16,bloom_config=,bloom_hash_count=8,bloom_oldest=false,chunk_count_limit=0,chunk_max=5GB,chunk_size=10MB,merge_max=15,merge_min=0),memory_page_max=10m,os_cache_dirty_max=0,os_cache_max=0,prefix_compression=false,prefix_compression_min=4,source=,split_deepen_min_child=0,split_deepen_per_child=0,split_pct=90,type=file,value_format=u",
                "type" : "file",
                "uri" : "statistics:table:collection-0-5869292382622143333",
                "LSM" : {
                        "bloom filter false positives" : 0,
                        "bloom filter hits" : 0,
                        "bloom filter misses" : 0,
                        "bloom filter pages evicted from cache" : 0,
                        "bloom filter pages read into cache" : 0,
                        "bloom filters in the LSM tree" : 0,
                        "chunks in the LSM tree" : 0,
                        "highest merge generation in the LSM tree" : 0,
                        "queries that could have benefited from a Bloom filter that did not exist" : 0,
                        "sleep for LSM checkpoint throttle" : 0,
                        "sleep for LSM merge throttle" : 0,
                        "total size of bloom filters" : 0
                },
                "block-manager" : {
                        "allocations requiring file extension" : 15471,
                        "blocks allocated" : 15475,
                        "blocks freed" : 39,
                        "checkpoint size" : 188481536,
                        "file allocation unit size" : 4096,
                        "file bytes available for reuse" : 188416,
                        "file magic number" : 120897,
                        "file major version number" : 1,
                        "file size in bytes" : 188686336,
                        "minor version number" : 0
                },
                "btree" : {
                        "btree checkpoint generation" : 20,
                        "column-store fixed-size leaf pages" : 0,
                        "column-store internal pages" : 0,
                        "column-store variable-size RLE encoded values" : 0,
                        "column-store variable-size deleted values" : 0,
                        "column-store variable-size leaf pages" : 0,
                        "fixed-record size" : 0,
                        "maximum internal page key size" : 368,
                        "maximum internal page size" : 4096,
                        "maximum leaf page key size" : 2867,
                        "maximum leaf page size" : 32768,
                        "maximum leaf page value size" : 67108864,
                        "maximum tree depth" : 4,
                        "number of key/value pairs" : 0,
                        "overflow pages" : 0,
                        "pages rewritten by compaction" : 0,
                        "row-store internal pages" : 0,
                        "row-store leaf pages" : 0
                },
                "cache" : {
                        "bytes currently in the cache" : 502018875,
                        "bytes read into cache" : 0,
                        "bytes written from cache" : 437640755,
                        "checkpoint blocked page eviction" : 0,
                        "data source pages selected for eviction unable to be evicted" : 12,
                        "hazard pointer blocked page eviction" : 0,
                        "in-memory page passed criteria to be split" : 130,
                        "in-memory page splits" : 62,
                        "internal pages evicted" : 0,
                        "internal pages split during eviction" : 1,
                        "leaf pages split during eviction" : 56,
                        "modified pages evicted" : 56,
                        "overflow pages read into cache" : 0,
                        "overflow values cached in memory" : 0,
                        "page split during eviction deepened the tree" : 1,
                        "page written requiring lookaside records" : 0,
                        "pages read into cache" : 0,
                        "pages read into cache requiring lookaside entries" : 0,
                        "pages requested from the cache" : 2232017,
                        "pages written from cache" : 15472,
                        "pages written requiring in-memory restoration" : 0,
                        "tracked dirty bytes in the cache" : 0,
                        "unmodified pages evicted" : 0
                },
                "cache_walk" : {
                        "Average difference between current eviction generation when the page was last considered" : 0,
                        "Average on-disk page image size seen" : 0,
                        "Clean pages currently in cache" : 0,
                        "Current eviction generation" : 0,
                        "Dirty pages currently in cache" : 0,
                        "Entries in the root page" : 0,
                        "Internal pages currently in cache" : 0,
                        "Leaf pages currently in cache" : 0,
                        "Maximum difference between current eviction generation when the page was last considered" : 0,
                        "Maximum page size seen" : 0,
                        "Minimum on-disk page image size seen" : 0,
                        "On-disk page image sizes smaller than a single allocation unit" : 0,
                        "Pages created in memory and never written" : 0,
                        "Pages currently queued for eviction" : 0,
                        "Pages that could not be queued for eviction" : 0,
                        "Refs skipped during cache traversal" : 0,
                        "Size of the root page" : 0,
                        "Total number of pages currently in cache" : 0
                },
                "compression" : {
                        "compressed pages read" : 0,
                        "compressed pages written" : 15312,
                        "page written failed to compress" : 0,
                        "page written was too small to compress" : 158,
                        "raw compression call failed, additional data available" : 0,
                        "raw compression call failed, no additional data available" : 0,
                        "raw compression call succeeded" : 0
                },
                "cursor" : {
                        "bulk-loaded cursor-insert calls" : 0,
                        "create calls" : 3,
                        "cursor-insert key and value bytes inserted" : 429166606,
                        "cursor-remove key bytes removed" : 0,
                        "cursor-update value bytes updated" : 0,
                        "insert calls" : 1835000,
                        "next calls" : 162051,
                        "prev calls" : 1,
                        "remove calls" : 0,
                        "reset calls" : 30748,
                        "restarted searches" : 0,
                        "search calls" : 0,
                        "search near calls" : 1227,
                        "truncate calls" : 0,
                        "update calls" : 0
                },
                "reconciliation" : {
                        "dictionary matches" : 0,
                        "fast-path pages deleted" : 0,
                        "internal page key bytes discarded using suffix compression" : 31112,
                        "internal page multi-block writes" : 4,
                        "internal-page overflow keys" : 0,
                        "leaf page key bytes discarded using prefix compression" : 0,
                        "leaf page multi-block writes" : 66,
                        "leaf-page overflow keys" : 0,
                        "maximum blocks required for a page" : 242,
                        "overflow values written" : 0,
                        "page checksum matches" : 209,
                        "page reconciliation calls" : 171,
                        "page reconciliation calls for eviction" : 57,
                        "pages deleted" : 1
                },
                "session" : {
                        "object compaction" : 0,
                        "open cursor count" : 3
                },
                "transaction" : {
                        "update conflicts" : 0
                }
        },
        "nindexes" : 1,
        "totalIndexSize" : 18272256,
        "indexSizes" : {
                "_id_" : 18272256
        },
        "ok" : 1
}
// 执行
> db.randomInfo.getIndexes()
[
        {
                "v" : 2,
                "key" : {
                        "_id" : 1
                },
                "name" : "_id_",
                "ns" : "company.randomInfo"
        }
]
// 这是默认的索引,我们一般不会使用这个索引的

建立一个索引

> db.randomInfo.ensureIndex({username: 1})
{
        "createdCollectionAutomatically" : false,
        "numIndexesBefore" : 1,
        "numIndexesAfter" : 2,
        "ok" : 1
}
> db.randomInfo.getIndexes()            // 然后查看发现有两条索引了
[
        {
                "v" : 2,
                "key" : {
                        "_id" : 1
                },
                "name" : "_id_",
                "ns" : "company.randomInfo"
        },
        {
                "v" : 2,
                "key" : {
                        "username" : 1
                },
                "name" : "username_1",
                "ns" : "company.randomInfo"
        }
]
>
//test1.js
var startTime = new Date().getTime()  //得到程序运行的开始时间
var  db = connect('company')          //链接数据库
var   rs=db.randomInfo.find({username:"tfruhjy8k"})  //根据用户名查找用户
rs.forEach(rs=>{printjson(rs)})                     //循环输出
var  runTime = new Date().getTime()-startTime;      //得到程序运行时间
print('[SUCCESS]This run time is:'+runTime+'ms')    //打印出运行时间
// 执行查找
> load('./test1.js')
connecting to: mongodb://127.0.0.1:27017/company
MongoDB server version: 3.4.10
{
        "_id" : ObjectId("5ac8b73b5646d96c6db3e1a8"),
        "username" : "od2umr6kec",
        "regeditTime" : ISODate("2018-04-07T12:18:44.292Z"),
        "randNum0" : 577322,
        "randNum1" : 961443,
        "randNum2" : 999621,
        "randNum3" : 968291,
        "randNum4" : 834839,
        "randNum5" : 637084,
        "randNum6" : 172311,
        "randNum7" : 219693,
        "randNum8" : 617081
}
[SUCCESS]This run time is:11ms   // 关键看这里,你会发现时间缩短了好多呢
true
>

无论是在关系型数据库还是文档数据库,建立索引都是非常重要的。前边讲了,索引这东西是要消耗硬盘和内存资源的,所以还是要根据程序需要进行建立了。MongoDB也给我们进行了限制,只允许我们建立64个索引值。

复合索引

复合索引就是两条以上的索引

// 在建立一个索引
> db.randomInfo.ensureIndex({randNum0: 1});
{
        "createdCollectionAutomatically" : false,
        "numIndexesBefore" : 2,
        "numIndexesAfter" : 3,
        "ok" : 1
}
> db.randomInfo.getIndexes();
[
        {
                "v" : 2,
                "key" : {
                        "_id" : 1
                },
                "name" : "_id_",
                "ns" : "company.randomInfo"
        },
        {
                "v" : 2,
                "key" : {
                        "username" : 1
                },
                "name" : "username_1",
                "ns" : "company.randomInfo"
        },
        {
                "v" : 2,
                "key" : {
                        "randNum0" : 1
                },
                "name" : "randNum0_1",
                "ns" : "company.randomInfo"
        }
]
>

我们同时查询两个索引的值,看看效果是怎么样的。

// 
var startTime=new Date().getTime();
var db = connect('company');
 
var  rs= db.randomInfo.find({username:'7xwb8y3',randNum0:565509});
 
rs.forEach(rs=>{printjson(rs)});
 
 
var runTime = new Date().getTime()-startTime;
print('[Demo]this run time is '+runTime+'ms');
// 从性能上看并没有什么特殊的变化,查询时间还是在10ms左右。MongoDB的复合查询是按照我们的索引顺序进行查询的。就是我们用db.randomInfo.getIndexes()查询出的数组。

指定索引查找

// 
var  rs= db.randomInfo.find({username:'7xwb8y3',randNum0:565509}).hint({randNum0:1});

删除索引

db.randomInfo.dropIndex('randNum0_1');//索引的唯一ID

这里需要注意的是删除时填写的值,并不是我们的字段名称(key),而是我们索引查询表中的name值。这是一个小坑。

全文索引

有些时候需要在大篇幅的文章中搜索关键词,比如我写的文章每篇都在万字以上,这时候你想搜索关键字是非常不容易的,MongoDB为我们提供了全文索引。

// 插入两条数据
db.info.insert({contextInfo:"I am a programmer, I love life, love family. Every day after work, I write a diary."})
db.info.insert({contextInfo:"I am a programmer, I love PlayGame, love drink. Every day after work, I playGame and drink."})

建立全文索引

db.info.ensureIndex({contextInfo:'text'});
//需要注意的是这里使用text关键词来代表全文索引,我们在这里就不建立数据模型了。

全文索引查找

// $text:表示要在全文索引中查东西。这里的$test指的就是contextInfo
// $search:后边跟查找的内容。
db.info.find({$text:{$search:"programmer"}}); // 查找contextInfo中含有programmer关键字的

查找多个词

// 比如我们希望查找数据中有programmer,family,diary,drink的数据(这是或的关系),所以两条数据都会出现。
db.info.find({$text:{$search:"programmer family diary drink"}})

// 如果我们这时候希望不查找出来有drink这个单词的记录,我们可以使用“-”减号来取消。
db.info.find({$text:{$search:"programmer family diary -drink"}})

// 全文搜索中是支持转义符的,比如我们想搜索的是两个词(love PlayGame和drink),这时候需要使用\斜杠来转意。
db.info.find({$text:{$search:"\"love PlayGame\" drink"}})

全文索引在工作还是经常使用的,比如博客文章的搜索,长文件的关键词搜索,这些都需要使用全文索引来进行。

到这里Mongodb的基本知识就基本结束了,下一节我们将会学习如何管理Mongodb

  • 参考文献

技术胖

    原文作者:Meils
    原文地址: https://segmentfault.com/a/1190000014222511
    本文转自网络文章,转载此文章仅为分享知识,如有侵权,请联系博主进行删除。
点赞