Winsock本地回圈延迟

我使用tcp套接字在Windows XP上提供两个应用程序之间的进程间通信。我选择tcp套接字的原因有很多。我看到平均往返时间为2.8毫秒,比我预期的要慢得多。分析似乎表明,延迟介于一个应用程序调用s end和另一个应用程序阻塞recv返回之间。

我有太多的应用程序,一个守护进程和一个客户端。它们的结构类似于以下伪代码:

守护进程线程1(侦听新连接):

while (1) {
   SOCKET listener_socket = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
   bind(listener_socket, (SOCKADDR*)&server_info, sizeof(SOCKADDR));
   listen(listener_socket, 1);
   SOCKET client_socket = accept(listener_socket, NULL, NULL);
   closesocket(listener_socket);
   CreateThread(client_thread);
 }

守护程序客户端套接字线程(侦听来自客户端的数据包):

char cmdBuf[256];
int cmdBufAmountData = 0;

while (1)
{   
    char recvBuf[128];
    int bytesTransferred = recv(m_clientSocket, recvBuf, sizeof(recvBuf), 0);

    // Copy received data into our accumulated command buffer (commands 
    // may be split across packet boundaries)
    memcpy(cmdBuf + cmdBufAmountData, recvBuf, bytesTransferred);
    cmdBufAmountData += bytesTransferred;

    // See if there is one or more complete commands in cmdBuf 
    // (commands are separated by '\0')
    while (commandExists(cmdBuf, cmdBufAmountData))
    {
        // do stuff with command
        send(m_clientSocket, outBuf, msgLen, 0);

        // Throw away the command we just processed by shuffling 
        // the contents of the command buffer left
        for (int i = 0; i < cmdBufAmountData - cmdLen; i++)
            cmdBuf[i] = cmdBuf[i + cmdLen];
        cmdBufAmountData -= cmdLen;
    }
}

start_timer();
send(foo);
recv(barBuf);
end_timer();       // Timer shows values from 0.7ms to 17ms. Average 2.8ms.

你知道为什么延迟这么差吗?我怀疑纳格尔的算法,但我的代码乱扔了:

BOOL bOptVal = TRUE;
setsockopt(socket, IPPROTO_TCP, TCP_NODELAY, (char*)&bOptVal, sizeof(BOOL));

没用。我需要在客户端和守护进程套接字上都这样做吗(我正在做)?

我在一台四核机器上,几乎没有负载,没有磁盘活动等等。