mongodb源码分析(四)查询1之mongo的查询请求
在之前的2篇文章中分别分析了mongod和mongo的启动流程，下面开始将分析mongodb的查询，由于查询部分流程比较长，将分成mongo端的请求，mongod端的数据库的加载，mongod query的选取，mongod文档的匹配与数据的响应几部分来分析。首先进入mongo的查询请求部分.mongo的查询请求部分归纳起来很简单就是将请求分装成一个Message结构,然后将其发送到服务端,等待服务端的相应数据,取得数据最后显示结果.下面来看具体流程分析吧.
当我们点击db.coll.find({x:1})时按照上一篇文章的讲解，我们首先来到了mongo/shell/dbshell.cpp
if ( ! wascmd ) {
try {
if ( scope->exec( code.c_str() , "(shell)" , false , true , false ) )//执行相应的javascript代码
scope->exec( "shellPrintHelper( __lastres__ );" , "(shell2)" , true , true , false );
}
catch ( std::exception& e ) {
cout << "error:" << e.what() << endl;
}
}
下面进入javascript代码,其在mongo/shell/collection.js.
//这里因为我们只设置了query,所以其它选项都是空的，this.getQueryOptions()目前只有一个SlaveOK的option，在replset模式下是不能查询secondary服务器的，需要调用rs.SlaveOK()之后才能对secondary进行查询，其执行SlaveOK后每次查询时都会添加一个QueryOption.
DBCollection.prototype.find = function (query, fields, limit, skip, batchSize, options) {
return new DBQuery( this._mongo , this._db , this ,
this._fullName , this._massageObject( query ) , fields , limit , skip , batchSize , options || this.getQueryOptions() );
}
继续前进看看DBQuery,上一篇文章提到这里的new DBQuery对象的创建发生在:
JSBool dbquery_constructor( JSContext *cx, JSObject *obj, uintN argc, jsval *argv, jsval *rval ) {
try {
smuassert( cx ,"DDQuery needs at least 4 args" , argc >= 4 );
//整个代码都是创建一个DBQuery对象，并未进行任何的查询请求动作
Convertor c(cx);
c.setProperty( obj , "_mongo" , argv );
c.setProperty( obj , "_db" , argv );
c.setProperty( obj , "_collection" , argv );
c.setProperty( obj , "_ns" , argv );
if ( argc > 4 && JSVAL_IS_OBJECT( argv ) )
c.setProperty( obj , "_query" , argv );
else {
JSObject * temp = JS_NewObject( cx , 0 , 0 , 0 );
CHECKNEWOBJECT( temp, cx, "dbquery_constructor" );
c.setProperty( obj , "_query" , OBJECT_TO_JSVAL( temp ) );
}
if ( argc > 5 && JSVAL_IS_OBJECT( argv ) )
c.setProperty( obj , "_fields" , argv );
else
c.setProperty( obj , "_fields" , JSVAL_NULL );
if ( argc > 6 && JSVAL_IS_NUMBER( argv ) )
c.setProperty( obj , "_limit" , argv );
else
c.setProperty( obj , "_limit" , JSVAL_ZERO );
if ( argc > 7 && JSVAL_IS_NUMBER( argv ) )
c.setProperty( obj , "_skip" , argv );
else
c.setProperty( obj , "_skip" , JSVAL_ZERO );
if ( argc > 8 && JSVAL_IS_NUMBER( argv ) )
c.setProperty( obj , "_batchSize" , argv );
else
c.setProperty( obj , "_batchSize" , JSVAL_ZERO );
if ( argc > 9 && JSVAL_IS_NUMBER( argv ) )
c.setProperty( obj , "_options" , argv );
else
c.setProperty( obj , "_options" , JSVAL_ZERO );
c.setProperty( obj , "_cursor" , JSVAL_NULL );
c.setProperty( obj , "_numReturned" , JSVAL_ZERO );
c.setProperty( obj , "_special" , JSVAL_FALSE );
}
catch ( const AssertionException& e ) {
if ( ! JS_IsExceptionPending( cx ) ) {
JS_ReportError( cx, e.what() );
}
return JS_FALSE;
}
catch ( const std::exception& e ) {
log() << "unhandled exception: " << e.what() << ", throwing Fatal Assertion" << endl;
fassertFailed( 16323 );
}
return JS_TRUE;
}
可以看到上面只有DBQuery对象的构建动作,并没有真正的查询请求，那么查询请求去哪里了呢?回到
try {
if ( scope->exec( code.c_str() , "(shell)" , false , true , false ) )//执行相应的javascript代码
scope->exec( "shellPrintHelper( __lastres__ );" , "(shell2)" , true , true , false );
}
继续分析shellPrintHelper函数，这里__lastres__是什么，搜索整个source insight工程发现mongo/scripting/engine_spidermonkey.cpp中: bool exec( const StringData& code,const string& name = "(anon)",bool printResult = false,bool reportError = true, bool assertOnError = true,int timeoutMs = 0 ) {
JSBool worked = JS_EvaluateScript( _context,
_global,
code.data(),
code.size(),
name.c_str(),
1,
&ret );
if ( worked )
_convertor->setProperty( _global , "__lastres__" , ret );
}
原来__lastres__就是上一条执行语句的结果也就是这里的DBQuery对象.继续分析shellPrintHelper函数(mongo/util/util.js)
shellPrintHelper = function (x) {
if (typeof (x) == "undefined") {
// Make sure that we have a db var before we use it
// TODO: This implicit calling of GLE can cause subtle, hard to track issues - remove?
if (__callLastError && typeof( db ) != "undefined" && db.getMongo ) {
__callLastError = false;
// explicit w:1 so that replset getLastErrorDefaults aren't used here which would be bad.
var err = db.getLastError(1);
if (err != null) {
print(err);
}
}
return;
}
if (x == __magicNoPrint)
return;
if (x == null) {
print("null");
return;
}
if (typeof x != "object")
return print(x);
var p = x.shellPrint;//我们这里是DBQuery对象，所以执行到这里，来到了DBQuery.shellPrint函数
if (typeof p == "function")
return x.shellPrint();
var p = x.tojson;
if (typeof p == "function")
print(x.tojson());
else
print(tojson(x));
}
DBQuery.prototype.shellPrint = function(){//(mongo/util/query.js)
try {
var start = new Date().getTime();
var n = 0;//还有查询结果并且输出数目小于shellBatchSize,循环打印结果
while ( this.hasNext() && n < DBQuery.shellBatchSize ){//这里shellBatchSize定义为20
var s = this._prettyShell ? tojson( this.next() ) : tojson( this.next() , "" , true );
print( s );//调用native函数native_print打印结果
n++;
}
if (typeof _verboseShell !== 'undefined' && _verboseShell) {
var time = new Date().getTime() - start;
print("Fetched " + n + " record(s) in " + time + "ms");
}
if ( this.hasNext() ){
print( "Type \"it\" for more" );
___it___= this;
}
else {
___it___= null;
}
}
catch ( e ){
print( e );
}
}
继续看看hasNext函数和next函数:
DBQuery.prototype.hasNext = function(){
this._exec();
if ( this._limit > 0 && this._cursorSeen >= this._limit )//超过了限制返回false，将不会再输出结果
return false;
var o = this._cursor.hasNext();
return o;
}
DBQuery.prototype.next = function(){
this._exec();
var o = this._cursor.hasNext();
if ( o )
this._cursorSeen++;
else
throw "error hasNext: " + o;
var ret = this._cursor.next();
if ( ret.$err && this._numReturned == 0 && ! this.hasNext() )
throw "error: " + tojson( ret );
this._numReturned++;
return ret;
}
继续前进到_exec函数:
DBQuery.prototype._exec = function(){//到这里终于到了this._mongo.find
if ( ! this._cursor ){
assert.eq( 0 , this._numReturned );
this._cursor = this._mongo.find( this._ns , this._query , this._fields , this._limit , this._skip , this._batchSize , this._options );
this._cursorSeen = 0;
}
return this._cursor;
}
到这里我们来到了this._mongo.find,这里_mongo是一个Mongo对象，在上一篇文章中我们了解到find函数是本地函数mongo_find.继续分析
mongo_find(mongo/scripting/sm_db.cpp).这里删除了部分错误处理代码.
JSBool mongo_find(JSContext *cx, JSObject *obj, uintN argc, jsval *argv, jsval *rval) {
shared_ptr< DBClientWithCommands > * connHolder = (shared_ptr< DBClientWithCommands >*)JS_GetPrivate( cx , obj );
smuassert( cx ,"no connection!" , connHolder && connHolder->get() );
DBClientWithCommands *conn = connHolder->get();
Convertor c( cx );
string ns = c.toString( argv );
BSONObj q = c.toObject( argv );
BSONObj f = c.toObject( argv );
int nToReturn = (int) c.toNumber( argv );
int nToSkip = (int) c.toNumber( argv );
int batchSize = (int) c.toNumber( argv );
int options = (int)c.toNumber( argv );//上面一篇文章我们分析到这里的conn其实是由ConnectionString::connect函数返回的，其返回的对象指针可能是:DBClientConnection对应Master,也就是只设置了一个地址，DBClientReplicaSet对应pair或者set模式,SyncClusterConnection对应sync模式，继续分析流程我们选择最简单的Master模式,只有一个地址的服务端
auto_ptr<DBClientCursor> cursor = conn->query( ns , q , nToReturn , nToSkip , f.nFields() ? &f : 0, options , batchSize );
if ( ! cursor.get() ) {
log() << "query failed : " << ns << " " << q << " to: " << conn->toString() << endl;
JS_ReportError( cx , "error doing query: failed" );
return JS_FALSE;
}
JSObject * mycursor = JS_NewObject( cx , &internal_cursor_class , 0 , 0 );
CHECKNEWOBJECT( mycursor, cx, "internal_cursor_class" );
verify( JS_SetPrivate( cx , mycursor , new CursorHolder( cursor, *connHolder ) ) );
*rval = OBJECT_TO_JSVAL( mycursor );
return JS_TRUE;
}
那么我们继续前进来到DBClientConnection::query函数，该函数只是简单调用了DBClientBase::query函数.
auto_ptr<DBClientCursor> DBClientBase::query(const string &ns, Query query, int nToReturn,
int nToSkip, const BSONObj *fieldsToReturn, int queryOptions , int batchSize ) {
auto_ptr<DBClientCursor> c( new DBClientCursor( this,//根据传入的参数创建一个DBClientCursor对象
ns, query.obj, nToReturn, nToSkip,
fieldsToReturn, queryOptions , batchSize ) );
if ( c->init() )//创建Message并向服务端发送查询请求
return c;
return auto_ptr< DBClientCursor >( 0 );
}
bool DBClientCursor::init() {
Message toSend;
_assembleInit( toSend );//构建将要发送的查询请求这是一个Message,具体来说Message负责发送数据,具体的数据是在MsgData中
verify( _client );
if ( !_client->call( toSend, *batch.m, false, &_originalHost ) ) {//实际的发送数据,同时这里发送了数据后会调用recv接收数据
// log msg temp? //接收的数据同样是MsgData，同样由Message来管理
log() << "DBClientCursor::init call() failed" << endl;
return false;
}
if ( batch.m->empty() ) {
// log msg temp?
log() << "DBClientCursor::init message from call() was empty" << endl;
return false;
}
dataReceived();//根据上面的batch.m收到的数据得出查询是否成功成功则设置cursorId,下一次请求时operation就变动为dbGetmore了.
return true; //查询错误则抛出异常
}
_assembleInit是创建一个message结构，若是第一次请求那么请求操作为dbQuery,若不是则请求操作为dbGetmore.来看看MsgData的具体结构吧.
回到mongo_find函数.
auto_ptr<DBClientCursor> cursor = conn->query( ns , q , nToReturn , nToSkip , f.nFields() ? &f : 0, options , batchSize );
if ( ! cursor.get() ) {//这里得到了cursor
log() << "query failed : " << ns << " " << q << " to: " << conn->toString() << endl;
JS_ReportError( cx , "error doing query: failed" );
return JS_FALSE;
}
JSObject * mycursor = JS_NewObject( cx , &internal_cursor_class , 0 , 0 );//将cursor封装成一个javascript对象,javascript就能
CHECKNEWOBJECT( mycursor, cx, "internal_cursor_class" );//使用游标了
verify( JS_SetPrivate( cx , mycursor , new CursorHolder( cursor, *connHolder ) ) );
我们回到javascript部分的打印请求.
DBQuery.prototype.hasNext = function(){
this._exec();
if ( this._limit > 0 && this._cursorSeen >= this._limit )
return false;
var o = this._cursor.hasNext();//这里的cursor对应于上面的C++对象cursor,其hasNext函数对应的native函数为internal_cursor_hasNext,
return o; //这是在mongo启动时初始化javascript环境时绑定的
}
继续看到了internal_cursor_hasNext:
JSBool internal_cursor_hasNext(JSContext *cx, JSObject *obj, uintN argc, jsval *argv, jsval *rval) {
try {
DBClientCursor *cursor = getCursor( cx, obj );
*rval = cursor->more() ? JSVAL_TRUE : JSVAL_FALSE;//这里返回的就是是否还有数据,如果本地没有查询数据了,那么其会再构建一个
} //dbGetmore的请求向服务器请求更多数据,还是没有则返回false,表示没有数据了
catch ( const AssertionException& e ) {
if ( ! JS_IsExceptionPending( cx ) ) {
JS_ReportError( cx, e.what() );
}
return JS_FALSE;
}
catch ( const std::exception& e ) {
log() << "unhandled exception: " << e.what() << ", throwing Fatal Assertion" << endl;
fassertFailed( 16290 );
}
return JS_TRUE;
}
最后javascript部分打印数据:
DBQuery.prototype.shellPrint = function(){
try {
var start = new Date().getTime();
var n = 0;
while ( this.hasNext() && n < DBQuery.shellBatchSize ){//前面分析这里hasNext对应C++函数internal_cursor_hasNext,next对应
var s = this._prettyShell ? tojson( this.next() ) : tojson( this.next() , "" , true );//internal_cursor_next,怎么得到的数据不再分析
print( s );//调用native_print打印结果
n++;
}
下面来看看类似这种形式的命令:db.coll.find().count(), db.coll.find().showDiskLoc().
DBQuery.prototype.sort = function( sortBy ){//可以看到,这里只是在查询时增加了相应的查询请求而已
return this._addSpecial( "orderby" , sortBy );
}
DBQuery.prototype.hint = function( hint ){
return this._addSpecial( "$hint" , hint );
}
DBQuery.prototype.min = function( min ) {
return this._addSpecial( "$min" , min );
}
DBQuery.prototype.max = function( max ) {
return this._addSpecial( "$max" , max );
}
DBQuery.prototype.showDiskLoc = function() {
return this._addSpecial( "$showDiskLoc" , true);
}
DBQuery.prototype.count = function( applySkipLimit ){//而这里count这种是变更了查询的,这里是向服务器发送了一个count命令,执行的并不是
var cmd = { count: this._collection.getName() };//查询请求
if ( this._query ){
if ( this._special )
cmd.query = this._query.query;
else
cmd.query = this._query;
}
cmd.fields = this._fields || {};
if ( applySkipLimit ){
if ( this._limit )
cmd.limit = this._limit;
if ( this._skip )
cmd.skip = this._skip;
}
var res = this._db.runCommand( cmd );
if( res && res.n != null ) return res.n;
throw "count failed: " + tojson( res );
}
DBQuery.prototype.size = function(){
return this.count( true );
}
总结,本文分析了mongodb自带的mongo客户端发起的查询请求以及结果的打印过程，
总体来说流程很简单,唯一令人感到麻烦的就是代码的执行流程在javascript和C++中来回的切换,
需要注意的就是对于mongo的查询请求的格式MsgData.
原文链接:http://blog.iyunv.com/yhjj0108/article/details/8253349
作者:yhjj0108,杨浩
版权声明：本文为博主原创文章，未经博主允许不得转载。
页:
[1]