它看起来像从我的测试中，我打我的10GB网络上的性能瓶颈。 我似乎无法读取超过每秒180-200k包。 纵观性能监视器或任务管理器，我可以第二，如果不是更获得高达一百万包/。 测试1插槽或10或100，似乎并没有改变200-300k分组的第二此限制。 我摆弄RSS之类没有成功。 单播组播VS似乎并不重要，重叠I / O VS同步不有所作为无论是。 数据包的大小并不重要任。 那里只是似乎是一个硬性限制数据包窗口可以从网卡到缓冲区拷贝的数量。 这是戴尔R410。 有任何想法吗？
#include "stdafx.h"
#include <WinSock2.h>
#include <ws2ipdef.h>
static inline void fillAddr(const char* const address, unsigned short port, sockaddr_in &addr)
{
memset( &addr, 0, sizeof( addr ) );
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = inet_addr( address );
addr.sin_port = htons(port);
}
int _tmain(int argc, _TCHAR* argv[])
{
#ifdef _WIN32
WORD wVersionRequested;
WSADATA wsaData;
int err;
wVersionRequested = MAKEWORD( 1, 1 );
err = WSAStartup( wVersionRequested, &wsaData );
#endif
int error = 0;
const char* sInterfaceIP = "10.20.16.90";
int nInterfacePort = 0;
//Create socket
SOCKET m_socketID = socket( AF_INET, SOCK_DGRAM, IPPROTO_UDP );
//Re use address
struct sockaddr_in addr;
fillAddr( "10.20.16.90", 12400, addr ); //"233.43.202.1"
char one = 1;
//error = setsockopt(m_socketID, SOL_SOCKET, SO_REUSEADDR , &one, sizeof(one));
if( error != 0 )
{
fprintf( stderr, "%s: ERROR setsockopt returned %d.\n", __FUNCTION__, WSAGetLastError() );
}
//Bind
error = bind( m_socketID, reinterpret_cast<SOCKADDR*>( &addr ), sizeof( addr ) );
if( error == -1 )
{
fprintf(stderr, "%s: ERROR %d binding to %s:%d\n",
__FUNCTION__, WSAGetLastError(), sInterfaceIP, nInterfacePort);
}
//Join multicast group
struct ip_mreq mreq;
mreq.imr_multiaddr.s_addr = inet_addr("225.2.3.13");//( "233.43.202.1" );
mreq.imr_interface.s_addr = inet_addr("10.20.16.90");
//error = setsockopt( m_socketID, IPPROTO_IP, IP_ADD_MEMBERSHIP, reinterpret_cast<char*>( &mreq ), sizeof( mreq ) );
if (error == -1)
{
fprintf(stderr, "%s: ERROR %d trying to join group %s.\n", __FUNCTION__, WSAGetLastError(), "233.43.202.1" );
}
int bufSize = 0, len = sizeof(bufSize), nBufferSize = 10*1024*1024;//8192*1024;
//Resize the buffer
getsockopt(m_socketID, SOL_SOCKET, SO_RCVBUF, (char*)&bufSize, &len );
fprintf(stderr, "getsockopt size before %d\n", bufSize );
fprintf(stderr, "setting buffer size %d\n", nBufferSize );
error = setsockopt(m_socketID, SOL_SOCKET, SO_RCVBUF,
reinterpret_cast<const char*>( &nBufferSize ), sizeof( nBufferSize ) );
if( error != 0 )
{
fprintf(stderr, "%s: ERROR %d setting the receive buffer size to %d.\n",
__FUNCTION__, WSAGetLastError(), nBufferSize );
}
bufSize = 1234, len = sizeof(bufSize);
getsockopt(m_socketID, SOL_SOCKET, SO_RCVBUF, (char*)&bufSize, &len );
fprintf(stderr, "getsockopt size after %d\n", bufSize );
//Non-blocking
u_long op = 1;
ioctlsocket( m_socketID, FIONBIO, &op );
//Create IOCP
HANDLE iocp = CreateIoCompletionPort( INVALID_HANDLE_VALUE, NULL, NULL, 1 );
HANDLE iocp2 = CreateIoCompletionPort( (HANDLE)m_socketID, iocp, 5, 1 );
char buffer[2*1024]={0};
int r = 0;
OVERLAPPED overlapped;
memset(&overlapped, 0, sizeof(overlapped));
DWORD bytes = 0, flags = 0;
// WSABUF buffers[1];
//
// buffers[0].buf = buffer;
// buffers[0].len = sizeof(buffer);
//
// while( (r = WSARecv( m_socketID, buffers, 1, &bytes, &flags, &overlapped, NULL )) != -121 )
//sleep(100000);
while( (r = ReadFile( (HANDLE)m_socketID, buffer, sizeof(buffer), NULL, &overlapped )) != -121 )
{
bytes = 0;
ULONG_PTR key = 0;
LPOVERLAPPED pOverlapped;
if( GetQueuedCompletionStatus( iocp, &bytes, &key, &pOverlapped, INFINITE ) )
{
static unsigned __int64 total = 0, printed = 0;
total += bytes;
if( total - printed > (1024*1024) )
{
printf( "%I64dmb\r", printed/ (1024*1024) );
printed = total;
}
}
}
while( r = recv(m_socketID,buffer,sizeof(buffer),0) )
{
static unsigned int total = 0, printed = 0;
if( r > 0 )
{
total += r;
if( total - printed > (1024*1024) )
{
printf( "%dmb\r", printed/ (1024*1024) );
printed = total;
}
}
}
return 0;
}
我使用的Iperf作为发送和接收的比较对发送的数据量的数据量：iperf.exe -c 10.20.16.90 -u -P 10 -B 10.20.16.51 -b十亿-p 12400 -l 1000
编辑：做的iperf到的iperf性能更接近180K左右不丢弃（8MB客户端缓冲液）。 如果我做TCP我可以做20万包/秒。 这里是有趣的，但 - 我可以做多个TCP连接远远超过20万，但多个UDP连接不增加总的（我测试多iperfs UDP性能，因为多线程单一的iperf似乎不工作）。 所有的硬件加速的驱动程序调整上..好像UDP表现简直欠佳？
