如果你不投遞（POST）Overlapped I/O，那么I/O Completion Ports 只能為你提供一個(gè)Queue. 
    CreateIoCompletionPort的NumberOfConcurrentThreads：
1.只有當(dāng)?shù)诙€(gè)參數(shù)ExistingCompletionPort為NULL時(shí)它才有效，它是個(gè)max threads limits.
2.大家有誰把它設(shè)置為超出cpu個(gè)數(shù)的值，當(dāng)然不只是cpu個(gè)數(shù)的2倍，而是下面的MAX_THREADS 100甚至更大。
對(duì)于這個(gè)值的設(shè)定，msdn并沒有說非得設(shè)成cpu個(gè)數(shù)的2倍，而且也沒有把減少線程之間上下文交換這些影響扯到這里來。I/O Completion Ports MSDN:"If your transaction required a lengthy computation, a larger concurrency value will allow more threads to run. Each completion packet may take longer to finish, but more completion packets will be processed at the same time. "。
    對(duì)于struct OVERLAPPED，我們常會(huì)如下擴(kuò)展，
typedef struct {
  WSAOVERLAPPED overlapped; //must be first member?   是的，必須是第一個(gè)。如果你不肯定，你可以試試。
  SOCKET client_s;
  SOCKADDR_IN client_addr;
  WORD optCode;//1--read,2--send.  有人常會(huì)定義這個(gè)數(shù)據(jù)成員，但也有人不用，爭(zhēng)議在send/WSASend,此時(shí)的同步和異步是否有必要？ 至少我下面的server更本就沒用它。
  char buf[MAX_BUF_SIZE];
  WSABUF wsaBuf;//inited ?  這個(gè)不要忘了！
  DWORD numberOfBytesTransferred;
  DWORD flags;   

}QSSOverlapped;//for per connection
我下面的server框架的基本思想是:
One connection VS one thread in worker thread pool ,worker thread performs completionWorkerRoutine.
A Acceptor thread 專門用來accept socket,關(guān)聯(lián)至IOCP,并WSARecv:post Recv Completion Packet to IOCP.
在completionWorkerRoutine中有以下的職責(zé):
1.handle request,當(dāng)忙時(shí)增加completionWorkerThread數(shù)量但不超過maxThreads,post Recv Completion Packet to IOCP.
2.timeout時(shí)檢查是否空閑和當(dāng)前completionWorkerThread數(shù)量,當(dāng)空閑時(shí)保持或減少至minThreads數(shù)量.
3.對(duì)所有Accepted-socket管理生命周期,這里利用系統(tǒng)的keepalive probes,若想實(shí)現(xiàn)業(yè)務(wù)層"心跳探測(cè)"只需將QSS_SIO_KEEPALIVE_VALS_TIMEOUT 改回系統(tǒng)默認(rèn)的2小時(shí).
下面結(jié)合源代碼,淺析一下IOCP:
socketserver.h
#ifndef __Q_SOCKET_SERVER__
#define __Q_SOCKET_SERVER__
#include <winsock2.h>
#include <mstcpip.h>
#define QSS_SIO_KEEPALIVE_VALS_TIMEOUT 30*60*1000
#define QSS_SIO_KEEPALIVE_VALS_INTERVAL 5*1000

#define MAX_THREADS 100
#define MAX_THREADS_MIN  10
#define MIN_WORKER_WAIT_TIMEOUT  20*1000
#define MAX_WORKER_WAIT_TIMEOUT  60*MIN_WORKER_WAIT_TIMEOUT

#define MAX_BUF_SIZE 1024

/*當(dāng)Accepted socket和socket關(guān)閉或發(fā)生異常時(shí)回調(diào)CSocketLifecycleCallback*/
typedef void (*CSocketLifecycleCallback)(SOCKET cs,int lifecycle);//lifecycle:0:OnAccepted,-1:OnClose//注意OnClose此時(shí)的socket未必可用,可能已經(jīng)被非正常關(guān)閉或其他異常.

/*協(xié)議處理回調(diào)*/
typedef int (*InternalProtocolHandler)(LPWSAOVERLAPPED overlapped);//return -1:SOCKET_ERROR

typedef struct Q_SOCKET_SERVER SocketServer;
DWORD initializeSocketServer(SocketServer ** ssp,WORD passive,WORD port,CSocketLifecycleCallback cslifecb,InternalProtocolHandler protoHandler,WORD minThreads,WORD maxThreads,long workerWaitTimeout);
DWORD startSocketServer(SocketServer *ss);
DWORD shutdownSocketServer(SocketServer *ss);

#endif
 qsocketserver.c      簡稱 qss,相應(yīng)的OVERLAPPED簡稱qssOl.
#include "socketserver.h"
#include "stdio.h"
typedef struct { 
  WORD passive;//daemon
  WORD port;
  WORD minThreads;
  WORD maxThreads;
  volatile long lifecycleStatus;//0-created,1-starting, 2-running,3-stopping,4-exitKeyPosted,5-stopped
  long  workerWaitTimeout;//wait timeout 
  CRITICAL_SECTION QSS_LOCK;
  volatile long workerCounter;
  volatile long currentBusyWorkers;
  volatile long CSocketsCounter;//Accepted-socket引用計(jì)數(shù)
  CSocketLifecycleCallback cslifecb;
  InternalProtocolHandler protoHandler;
  WORD wsaVersion;//=MAKEWORD(2,0);
  WSADATA wsData;
  SOCKET server_s;
  SOCKADDR_IN serv_addr;
  HANDLE iocpHandle;
}QSocketServer;

typedef struct {
  WSAOVERLAPPED overlapped; 
  SOCKET client_s;
  SOCKADDR_IN client_addr;
  WORD optCode;
  char buf[MAX_BUF_SIZE];
  WSABUF wsaBuf;
  DWORD numberOfBytesTransferred;
  DWORD flags;
}QSSOverlapped;

DWORD  acceptorRoutine(LPVOID);
DWORD  completionWorkerRoutine(LPVOID);

static void adjustQSSWorkerLimits(QSocketServer *qss){
  /*adjust size and timeout.*/
  /*if(qss->maxThreads <= 0) {
   qss->maxThreads = MAX_THREADS;
        } else if (qss->maxThreads < MAX_THREADS_MIN) {           
         qss->maxThreads = MAX_THREADS_MIN;
        }
        if(qss->minThreads >  qss->maxThreads) {
         qss->minThreads =  qss->maxThreads;
        }
        if(qss->minThreads <= 0) {
            if(1 == qss->maxThreads) {
             qss->minThreads = 1;
            } else {
             qss->minThreads = qss->maxThreads/2;
            }
        }
       
        if(qss->workerWaitTimeout<MIN_WORKER_WAIT_TIMEOUT)
         qss->workerWaitTimeout=MIN_WORKER_WAIT_TIMEOUT;
        if(qss->workerWaitTimeout>MAX_WORKER_WAIT_TIMEOUT)
         qss->workerWaitTimeout=MAX_WORKER_WAIT_TIMEOUT;        */
}

typedef struct{
 QSocketServer * qss;
 HANDLE th;
}QSSWORKER_PARAM;

static WORD addQSSWorker(QSocketServer *qss,WORD addCounter){
 WORD res=0;
 if(qss->workerCounter<qss->minThreads||(qss->currentBusyWorkers==qss->workerCounter&&qss->workerCounter<qss->maxThreads)){
  DWORD threadId;
  QSSWORKER_PARAM * pParam=NULL;
  int i=0;  
  EnterCriticalSection(&qss->QSS_LOCK);
  if(qss->workerCounter+addCounter<=qss->maxThreads)
   for(;i<addCounter;i++)
   {
    pParam=malloc(sizeof(QSSWORKER_PARAM));
    if(pParam){
     pParam->th=CreateThread(NULL,0,(LPTHREAD_START_ROUTINE)completionWorkerRoutine,pParam,CREATE_SUSPENDED,&threadId);
     pParam->qss=qss;
     ResumeThread(pParam->th);
     qss->workerCounter++,res++; 
    }    
   }  
  LeaveCriticalSection(&qss->QSS_LOCK);
 }  
 return res;
}

static void SOlogger(const char * msg,SOCKET s,int clearup){
 perror(msg);
 if(s>0)
 closesocket(s);
 if(clearup)
 WSACleanup();
}

static int _InternalEchoProtocolHandler(LPWSAOVERLAPPED overlapped){
 QSSOverlapped *qssOl=(QSSOverlapped *)overlapped;
 
 printf("numOfT:%d,WSARecvd:%s,\n",qssOl->numberOfBytesTransferred,qssOl->buf);
 //Sleep(500); 
 return send(qssOl->client_s,qssOl->buf,qssOl->numberOfBytesTransferred,0);
}

DWORD initializeSocketServer(SocketServer ** ssp,WORD passive,WORD port,CSocketLifecycleCallback cslifecb,InternalProtocolHandler protoHandler,WORD minThreads,WORD maxThreads,long workerWaitTimeout){
 QSocketServer * qss=malloc(sizeof(QSocketServer));
 qss->passive=passive>0?1:0;
 qss->port=port;
 qss->minThreads=minThreads;
 qss->maxThreads=maxThreads;
 qss->workerWaitTimeout=workerWaitTimeout;
 qss->wsaVersion=MAKEWORD(2,0); 
 qss->lifecycleStatus=0;
 InitializeCriticalSection(&qss->QSS_LOCK);
 qss->workerCounter=0;
 qss->currentBusyWorkers=0;
 qss->CSocketsCounter=0;
 qss->cslifecb=cslifecb,qss->protoHandler=protoHandler;
 if(!qss->protoHandler)
  qss->protoHandler=_InternalEchoProtocolHandler; 
 adjustQSSWorkerLimits(qss);
 *ssp=(SocketServer *)qss;
 return 1;
}

DWORD startSocketServer(SocketServer *ss){ 
 QSocketServer * qss=(QSocketServer *)ss;
 if(qss==NULL||InterlockedCompareExchange(&qss->lifecycleStatus,1,0))
  return 0; 
 qss->serv_addr.sin_family=AF_INET;
 qss->serv_addr.sin_port=htons(qss->port);
 qss->serv_addr.sin_addr.s_addr=INADDR_ANY;//inet_addr("127.0.0.1");
 if(WSAStartup(qss->wsaVersion,&qss->wsData)){  
  /*這里還有個(gè)插曲就是這個(gè)WSAStartup被調(diào)用的時(shí)候,它居然會(huì)啟動(dòng)一條額外的線程,當(dāng)然稍后這條線程會(huì)自動(dòng)退出的.不知WSAClearup又會(huì)如何?......*/

  SOlogger("WSAStartup failed.\n",0,0);
  return 0;
 }
 qss->server_s=socket(AF_INET,SOCK_STREAM,IPPROTO_IP);
 if(qss->server_s==INVALID_SOCKET){  
  SOlogger("socket failed.\n",0,1);
  return 0;
 }
 if(bind(qss->server_s,(LPSOCKADDR)&qss->serv_addr,sizeof(SOCKADDR_IN))==SOCKET_ERROR){  
  SOlogger("bind failed.\n",qss->server_s,1);
  return 0;
 }
 if(listen(qss->server_s,SOMAXCONN)==SOCKET_ERROR)/*這里來談?wù)?strong>backlog,很多人不知道設(shè)成何值,我見到過1,5,50,100的,有人說設(shè)定的越大越耗資源,的確,這里設(shè)成SOMAXCONN不代表windows會(huì)真的使用SOMAXCONN,而是" If set to SOMAXCONN, the underlying service provider responsible for socket s will set the backlog to a maximum reasonable value. "，同時(shí)在現(xiàn)實(shí)環(huán)境中，不同操作系統(tǒng)支持TCP緩沖隊(duì)列有所不同，所以還不如讓操作系統(tǒng)來決定它的值。像Apache這種服務(wù)器：
#ifndef DEFAULT_LISTENBACKLOG
#define DEFAULT_LISTENBACKLOG 511
#endif
*/
    {       
  SOlogger("listen failed.\n",qss->server_s,1);
        return 0;
    }
 qss->iocpHandle=CreateIoCompletionPort(INVALID_HANDLE_VALUE,NULL,0,/*NumberOfConcurrentThreads-->*/qss->maxThreads);
 //initialize worker for completion routine.
 addQSSWorker(qss,qss->minThreads);  
 qss->lifecycleStatus=2;
 {
  QSSWORKER_PARAM * pParam=malloc(sizeof(QSSWORKER_PARAM));
  pParam->qss=qss;
  pParam->th=NULL;
  if(qss->passive){
   DWORD threadId;
   pParam->th=CreateThread(NULL,0,(LPTHREAD_START_ROUTINE)acceptorRoutine,pParam,0,&threadId); 
  }else
   return acceptorRoutine(pParam);
 }
 return 1;
}

DWORD shutdownSocketServer(SocketServer *ss){
 QSocketServer * qss=(QSocketServer *)ss;
 if(qss==NULL||InterlockedCompareExchange(&qss->lifecycleStatus,3,2)!=2)
  return 0; 
 closesocket(qss->server_s/*listen-socket*/);//..other accepted-sockets associated with the listen-socket will not be closed,except WSACleanup is called.. 
 if(qss->CSocketsCounter==0)
  qss->lifecycleStatus=4,PostQueuedCompletionStatus(qss->iocpHandle,0,-1,NULL);
 WSACleanup();  
 return 1;
}

DWORD  acceptorRoutine(LPVOID ss){
 QSSWORKER_PARAM * pParam=(QSSWORKER_PARAM *)ss;
 QSocketServer * qss=pParam->qss;
 HANDLE curThread=pParam->th;
 QSSOverlapped *qssOl=NULL;
 SOCKADDR_IN client_addr;
 int client_addr_leng=sizeof(SOCKADDR_IN);
 SOCKET cs; 
 free(pParam);
 while(1){  
  printf("accept starting.....\n");
  cs/*Accepted-socket*/=accept(qss->server_s,(LPSOCKADDR)&client_addr,&client_addr_leng);
  if(cs==INVALID_SOCKET)
        {
   printf("accept failed:%d\n",GetLastError());   
            break;
        }else{//SO_KEEPALIVE,SIO_KEEPALIVE_VALS 這里是利用系統(tǒng)的"心跳探測(cè)",keepalive probes.linux:setsockopt,SOL_TCP:TCP_KEEPIDLE,TCP_KEEPINTVL,TCP_KEEPCNT
            struct tcp_keepalive alive,aliveOut;
            int so_keepalive_opt=1;
            DWORD outDW;
            if(!setsockopt(cs,SOL_SOCKET,SO_KEEPALIVE,(char *)&so_keepalive_opt,sizeof(so_keepalive_opt))){
               alive.onoff=TRUE;
               alive.keepalivetime=QSS_SIO_KEEPALIVE_VALS_TIMEOUT;
               alive.keepaliveinterval=QSS_SIO_KEEPALIVE_VALS_INTERVAL;
               if(WSAIoctl(cs,SIO_KEEPALIVE_VALS,&alive,sizeof(alive),&aliveOut,sizeof(aliveOut),&outDW,NULL,NULL)==SOCKET_ERROR){
                    printf("WSAIoctl SIO_KEEPALIVE_VALS failed:%d\n",GetLastError());   
                    break;
                }

            }else{
                     printf("setsockopt SO_KEEPALIVE failed:%d\n",GetLastError());   
                     break;
            }  
  }
  
  CreateIoCompletionPort((HANDLE)cs,qss->iocpHandle,cs,0);
  if(qssOl==NULL){
   qssOl=malloc(sizeof(QSSOverlapped));   
  }
  qssOl->client_s=cs;
  qssOl->wsaBuf.len=MAX_BUF_SIZE,qssOl->wsaBuf.buf=qssOl->buf,qssOl->numberOfBytesTransferred=0,qssOl->flags=0;//initialize WSABuf.
  memset(&qssOl->overlapped,0,sizeof(WSAOVERLAPPED));  
  {
   DWORD lastErr=GetLastError();
   int ret=0;
   SetLastError(0);
   ret=WSARecv(cs,&qssOl->wsaBuf,1,&qssOl->numberOfBytesTransferred,&qssOl->flags,&qssOl->overlapped,NULL);
   if(ret==0||(ret==SOCKET_ERROR&&GetLastError()==WSA_IO_PENDING)){
    InterlockedIncrement(&qss->CSocketsCounter);//Accepted-socket計(jì)數(shù)遞增.
    if(qss->cslifecb)
     qss->cslifecb(cs,0);
    qssOl=NULL;
   }    
   
   if(!GetLastError())
    SetLastError(lastErr);
  }
  
  printf("accept flags:%d ,cs:%d.\n",GetLastError(),cs);
 }//end while.

 if(qssOl)
  free(qssOl);
 if(qss)
  shutdownSocketServer((SocketServer *)qss);
 if(curThread)
  CloseHandle(curThread);

 return 1;
}

static int postRecvCompletionPacket(QSSOverlapped * qssOl,int SOErrOccurredCode){ 
 int SOErrOccurred=0; 
 DWORD lastErr=GetLastError();
 SetLastError(0);
 //SOCKET_ERROR:-1,WSA_IO_PENDING:997
 if(WSARecv(qssOl->client_s,&qssOl->wsaBuf,1,&qssOl->numberOfBytesTransferred,&qssOl->flags,&qssOl->overlapped,NULL)==SOCKET_ERROR
  &&GetLastError()!=WSA_IO_PENDING)//this case lastError maybe 64, 10054 
 {
  SOErrOccurred=SOErrOccurredCode;  
 }      
 if(!GetLastError())
  SetLastError(lastErr); 
 if(SOErrOccurred)
  printf("worker[%d] postRecvCompletionPacket SOErrOccurred=%d,preErr:%d,postedErr:%d\n",GetCurrentThreadId(),SOErrOccurred,lastErr,GetLastError());
 return SOErrOccurred;
}

DWORD  completionWorkerRoutine(LPVOID ss){
 QSSWORKER_PARAM * pParam=(QSSWORKER_PARAM *)ss;
 QSocketServer * qss=pParam->qss;
 HANDLE curThread=pParam->th;
 QSSOverlapped * qssOl=NULL;
 DWORD numberOfBytesTransferred=0;
 ULONG_PTR completionKey=0;
 int postRes=0,handleCode=0,exitCode=0,SOErrOccurred=0; 
 free(pParam);
 while(!exitCode){
  SetLastError(0);
  if(GetQueuedCompletionStatus(qss->iocpHandle,&numberOfBytesTransferred,&completionKey,(LPOVERLAPPED *)&qssOl,qss->workerWaitTimeout)){
   if(completionKey==-1&&qss->lifecycleStatus>=4)
   {
    printf("worker[%d] completionKey -1:%d \n",GetCurrentThreadId(),GetLastError());
    if(qss->workerCounter>1)
     PostQueuedCompletionStatus(qss->iocpHandle,0,-1,NULL);
    exitCode=1;
    break;
   }
   if(numberOfBytesTransferred>0){   
    
    InterlockedIncrement(&qss->currentBusyWorkers);
    addQSSWorker(qss,1);
    handleCode=qss->protoHandler((LPWSAOVERLAPPED)qssOl);    
    InterlockedDecrement(&qss->currentBusyWorkers);    
    
    if(handleCode>=0){
     SOErrOccurred=postRecvCompletionPacket(qssOl,1);
    }else
     SOErrOccurred=2;    
   }else{
    printf("worker[%d] numberOfBytesTransferred==0 ***** closesocket servS or cs *****,%d,%d ,ol is:%d\n",GetCurrentThreadId(),GetLastError(),completionKey,qssOl==NULL?0:1);
    SOErrOccurred=3;     
   }  
  }else{ //GetQueuedCompletionStatus rtn FALSE, lastError 64 ,995[timeout worker thread exit.] ,WAIT_TIMEOUT:258        
   if(qssOl){
    SOErrOccurred=postRecvCompletionPacket(qssOl,4);
   }else {    

    printf("worker[%d] GetQueuedCompletionStatus F:%d \n",GetCurrentThreadId(),GetLastError());
    if(GetLastError()!=WAIT_TIMEOUT){
     exitCode=2;     
    }else{//wait timeout     
     if(qss->lifecycleStatus!=4&&qss->currentBusyWorkers==0&&qss->workerCounter>qss->minThreads){
      EnterCriticalSection(&qss->QSS_LOCK);
      if(qss->lifecycleStatus!=4&&qss->currentBusyWorkers==0&&qss->workerCounter>qss->minThreads){
       qss->workerCounter--;//until qss->workerCounter decrease to qss->minThreads
       exitCode=3;      
      }
      LeaveCriticalSection(&qss->QSS_LOCK);
     }
    }    
   }    
  }//end GetQueuedCompletionStatus.

  if(SOErrOccurred){   
   if(qss->cslifecb)
    qss->cslifecb(qssOl->client_s,-1);
   /*if(qssOl)*/{
    closesocket(qssOl->client_s);
    free(qssOl);
   }
   if(InterlockedDecrement(&qss->CSocketsCounter)==0&&qss->lifecycleStatus>=3){    
    //for qss workerSize,PostQueuedCompletionStatus -1
    qss->lifecycleStatus=4,PostQueuedCompletionStatus(qss->iocpHandle,0,-1,NULL);        
    exitCode=4;
   }
  }
  qssOl=NULL,numberOfBytesTransferred=0,completionKey=0,SOErrOccurred=0;//for net while.
 }//end while.

 //last to do
 if(exitCode!=3){ 
  int clearup=0;
  EnterCriticalSection(&qss->QSS_LOCK);
  if(!--qss->workerCounter&&qss->lifecycleStatus>=4){//clearup QSS
    clearup=1;
  }
  LeaveCriticalSection(&qss->QSS_LOCK);
  if(clearup){
   DeleteCriticalSection(&qss->QSS_LOCK);
   CloseHandle(qss->iocpHandle);
   free(qss); 
  }
 }
 CloseHandle(curThread);
 return 1;
}
------------------------------------------------------------------------------------------------------------------------
    對(duì)于IOCP的LastError的辨別和處理是個(gè)難點(diǎn),所以請(qǐng)注意我的completionWorkerRoutine的while結(jié)構(gòu),
結(jié)構(gòu)如下:
while(!exitCode){
    if(completionKey==-1){...break;}
    if(GetQueuedCompletionStatus){/*在這個(gè)if體中只要你投遞的OVERLAPPED is not NULL,那么這里你得到的就是它.*/
        if(numberOfBytesTransferred>0){
               /*在這里handle request,記得要繼續(xù)投遞你的OVERLAPPED哦! */
        }else{
              /*這里可能客戶端或服務(wù)端closesocket(the socket),但是OVERLAPPED is not NULL,只要你投遞的不為NULL!*/
        }
    }else{/*在這里的if體中,雖然GetQueuedCompletionStatus return FALSE,但是不代表OVERLAPPED一定為NULL.特別是OVERLAPPED is not NULL的情況下,不要以為LastError發(fā)生了,就代表當(dāng)前的socket無用或發(fā)生致命的異常,比如發(fā)生lastError:995這種情況下此時(shí)的socket有可能是一切正常的可用的,你不應(yīng)該關(guān)閉它.*/
        if(OVERLAPPED is not NULL){
             /*這種情況下,請(qǐng)不管37,21繼續(xù)投遞吧!在投遞后再檢測(cè)錯(cuò)誤.*/
        }else{ 

        }
    }
  if(socket error occured){

  }
  prepare for next while.
} 

    行文倉促,難免有錯(cuò)誤或不足之處,希望大家踴躍指正評(píng)論,謝謝!

    這個(gè)模型在性能上還是有改進(jìn)的空間哦！