MongoDB基础之六 索引

一 . 索引概述和基本操作

1. 索引提高查询速度,降低写入速度,权衡常用的查询字段,不必在太多列上建索引
2. 在mongodb中,索引可以按字段升序/降序来创建,便于排序
3. 默认是用btree来组织索引文件,2.4版本以后,也允许建立hash索引.

常用命令:
查看当前索引状态: db.collection.getIndexes();

创建普通的单列索引:db.collection.ensureIndex({field:1/-1}); 1是升续 2是降续

删除单个索引
db.collection.dropIndex({filed:1/-1});

一下删除所有索引
db.collection.dropIndexes();

创建多列索引 db.collection.ensureIndex({field1:1/-1, field2:1/-1});

例子:

 > for (var i = ;i<=;i++){
 ... db.stu.insert({sn:i,name:'student'+i})
 ... };
 >
 >
 > db.stu.find().count();
 
 > db.stu.find({sn:});
 { "_id" : ObjectId("574271a9addef29711337c28"), "sn" : , "name" : "student99" }
 > db.stu.find({sn:}).explain();
 {
 "cursor" : "BasicCursor", -- 无索引相当于mysql的全表扫描
 "isMultiKey" : false,
 "n" : ,
 "nscannedObjects" : , -- 扫描了1000行
 ....
 
 > db.stu.ensureIndex({sn:}); --创建索引
 > db.stu.find({sn:}).explain();
 {
 "cursor" : "BtreeCursor sn_1", --使用了索引
 "isMultiKey" : false,
 "n" : ,
 "nscannedObjects" : , --只用扫描一行
 ...
 }
 
 > db.stu.getIndexes(); --查询索引
 [
 {
 "v" : ,
 "key" : {
 "_id" :  -- 默认创建 正序
 },
 "ns" : "test.stu",
 "name" : "_id_"
 },
 {
 "v" : ,
 "key" : {
 "sn" :
 },
 "ns" : "test.stu",
 "name" : "sn_1"
 }
 ]
 
 > db.stu.ensureIndex({sn:,name:});
 >
 >
 > db.stu.getIndexes();
 [
 {
 "v" : ,
 "key" : {
 "_id" :
 },
 "ns" : "test.stu",
 "name" : "_id_"
 },
 {
 "v" : ,
 "key" : {
 "sn" :
 },
 "ns" : "test.stu",
 "name" : "sn_1"
 },
 {
 "v" : ,
 "key" : {
 "sn" : ,
 "name" :
 },
 "ns" : "test.stu",
 "name" : "sn_1_name_1"
 }
 ]

二. 子文档索引

     指向下级嵌套的文档的索引

 > db.shop.insert({name:'Nokia',spc:{weight:,area:'taiwan'}});
 > db.shop.insert({name:'Nokia',spc:{weight:,area:'korea'}});
 
 > db.shop.find({'spc.area':'taiwan'});
 { "_id" : ObjectId("5743d662addef29711337fb0"), "name" : "Nokia", "spc" : { "weight" : , "area" : "taiwan" } }
 
 > db.shop.ensureIndex({'spc.area,1'});
 Tue May  ::58.823 SyntaxError: Unexpected token }
 > db.shop.ensureIndex({'spc.area':});
 >
 > db.shop.getIndexes();
 [
 {
 "v" : ,
 "key" : {
 "_id" :
 },
 "ns" : "test.shop",
 "name" : "_id_"
 },
 {
 "v" : ,
 "key" : {
 "spc.area" :
 },
 "ns" : "test.shop",
 "name" : "spc.area_1"
 }
 ]
 >

三.  唯一索引

 > show tables;
 shop
 stu
 system.indexes
 >
 >
 > db.tea.insert({email:'a@163.com'})
 > db.tea.insert({email:'b@163.com'})
 >
 > db.tea.getIndexes();
 [
 {
 "v" : ,
 "key" : {
 "_id" :
 },
 "ns" : "test.tea",
 "name" : "_id_"
 }
 ]
 >
 >
 >
 > db.tea.ensureIndex({email:},{unique:true});
 >
 >
 > db.tea.insert({email:'c@163.com'})
 > db.tea.insert({email:'c@163.com'})
 E11000 duplicate key error index: test.tea.$email_1 dup key: { : "c@163.com" }
 >

四. 稀疏索引

稀疏索引的特点------如果针对field做索引,针对不含field列的文档,将不建立索引.
与之相对,普通索引,会把该文档的field列的值认为NULL,并建索引.
适宜于: 小部分文档含有某列时.

db.collection.ensureIndex({field:1/-1},{sparse:true})

 -- 模拟数据
 > db.tea.insert({});
 > db.tea.find();
 { "_id" : ObjectId("5743d98aaddef29711337fb4"), "email" : "a@163.com" }
 { "_id" : ObjectId("5743d98daddef29711337fb5"), "email" : "b@163.com" }
 { "_id" : ObjectId("5743d9cfaddef29711337fb7"), "email" : "c@163.com" }
 { "_id" : ObjectId("5743dc98addef29711337fbc") }
 
 --稀疏索引下查不到数据
 > db.tea.ensureIndex({email:},{sparse:true});
 > db.tea.find({email:null});
 >
 
 > db.tea.dropIndexes();
 {
 "nIndexesWas" : ,
 "msg" : "non-_id indexes dropped for collection",
 "ok" :
 }
 
 --普通索引能查到
 > db.tea.ensureIndex({email:});
 > db.tea.find({email:null});
 { "_id" : ObjectId("5743dc98addef29711337fbc") }

总结:
如果分别加普通索引,和稀疏索引,
对于最后一行的email分别当成null 和 忽略最后一行来处理.
根据{email:null}来查询,前者能查到,而稀疏索引查不到最后一行.

五. 创建哈希索引(2.4新增的)

哈希索引速度比普通索引快,但是,无能对范围查询进行优化.
适宜于---随机性强的散列

db.collection.ensureIndex({file:'hashed'});

 > db.tea.ensureIndex({email:'hashed'});
 > db.tea.find({email:'a@163.com'}).explain();
 {
 "cursor" : "BtreeCursor email_hashed",
 "isMultiKey" : false,
 "n" : ,
 "nscannedObjects" : ,
 "nscanned" : ,
 "nscannedObjectsAllPlans" : ,
 "nscannedAllPlans" : ,
 "scanAndOrder" : false,
 "indexOnly" : false,
 "nYields" : ,
 "nChunkSkips" : ,
 "millis" : ,
 "indexBounds" : {
 "email" : [
 [
 NumberLong(""),
 NumberLong("")
 ]
 ]
 },
 "server" : "localhost.localdomain:27017"
 }
 >

六. 重建索引

一个表经过很多次修改后,导致表的文件产生空洞,索引文件也如此.
可以通过索引的重建,减少索引文件碎片,并提高索引的效率.
类似mysql中的optimize table

db.collection.reIndex()

 > db.tea.reIndex();
 {
 "nIndexesWas" : ,
 "msg" : "indexes dropped for collection",
 "nIndexes" : ,
 "indexes" : [
 {
 "key" : {
 "_id" :
 },
 "ns" : "test.tea",
 "name" : "_id_"
 },
 {
 "key" : {
 "email" : "hashed"
 },
 "ns" : "test.tea",
 "name" : "email_hashed"
 }
 ],
 "ok" :
 }