}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,關聯至IOCP,并WSARecv:post Recv Completion Packet to IOCP.
在completionWorkerRoutine中有以下的職責:
1.handle request,當忙時增加completionWorkerThread數量但不超過maxThreads,post Recv Completion Packet to IOCP.
2.timeout時檢查是否空閑和當前completionWorkerThread數量,當空閑時保持或減少至minThreads數量.
3.對所有Accepted-socket管理生命周期,這里利用系統的keepalive probes,若想實現業務層"心跳探測"只需將QSS_SIO_KEEPALIVE_VALS_TIMEOUT 改回系統默認的2小時.
下面結合源代碼,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Accepted socket和socket關閉或發生異常時回調CSocketLifecycleCallback*/
typedef void (*CSocketLifecycleCallback)(SOCKET cs,int lifecycle);//lifecycle:0:OnAccepted,-1:OnClose//注意OnClose此時的socket未必可用,可能已經被非正常關閉或其他異常.

/*協議處理回調*/
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引用計數
  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)){  
  /*這里還有個插曲就是這個WSAStartup被調用的時候,它居然會啟動一條額外的線程,當然稍后這條線程會自動退出的.不知WSAClearup又會如何?......*/

  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)/*這里來談談backlog,很多人不知道設成何值,我見到過1,5,50,100的,有人說設定的越大越耗資源,的確,這里設成SOMAXCONN不代表windows會真的使用SOMAXCONN,而是" If set to SOMAXCONN, the underlying service provider responsible for socket s will set the backlog to a maximum reasonable value. "，同時在現實環境中，不同操作系統支持TCP緩沖隊列有所不同，所以還不如讓操作系統來決定它的值。像Apache這種服務器：
#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 這里是利用系統的"心跳探測",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計數遞增.
    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;
}
------------------------------------------------------------------------------------------------------------------------
    對于IOCP的LastError的辨別和處理是個難點,所以請注意我的completionWorkerRoutine的while結構,
結構如下:
while(!exitCode){
    if(completionKey==-1){...break;}
    if(GetQueuedCompletionStatus){/*在這個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,記得要繼續投遞你的OVERLAPPED哦! */
        }else{
              /*這里可能客戶端或服務端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發生了,就代表當前的socket無用或發生致命的異常,比如發生lastError:995這種情況下此時的socket有可能是一切正常的可用的,你不應該關閉它.*/
        if(OVERLAPPED is not NULL){
             /*這種情況下,請不管37,21繼續投遞吧!在投遞后再檢測錯誤.*/
        }else{ 

        }
    }
  if(socket error occured){

  }
  prepare for next while.
} 

    行文倉促,難免有錯誤或不足之處,希望大家踴躍指正評論,謝謝!

    這個模型在性能上還是有改進的空間哦！

from:

http://m.shnenglu.com/adapterofcoms/archive/2010/06/26/118781.aspx