从我的测试来看,我的 10gb 网络似乎遇到了性能障碍。我似乎无法每秒读取超过 180-200k 个数据包。查看 perfmon 或任务管理器,如果不是更多,我每秒最多可以接收一百万个数据包。测试 1 个套接字或 10 个或 100 个,似乎并没有改变每秒 200-300k 个数据包的限制。我一直在摆弄 RSS 之类的东西,但没有成功。单播与多播似乎无关紧要,重叠 i/o 与同步也没有区别。数据包的大小也无关紧要。窗口可以从网卡复制到缓冲区的数据包数量似乎有一个硬性限制。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 Iperf 作为发送方,并将接收到的数据量与发送的数据量进行比较: iperf.exe -c 10.20.16.90 -u -P 10 -B 10.20.16.51 -b 1000000000 -p 12400 -l 1000
编辑:对 iperf 执行 iperf 性能接近 180k 左右而不会下降(8mb 客户端缓冲区)。如果我在做 tcp,我可以做大约 200k 个数据包/秒。不过有趣的是 - 我可以使用多个 tcp 连接完成超过 200k 的操作,但是多个 udp 连接不会增加总数(我使用多个 iperfs 测试 udp 性能,因为具有多个线程的单个 iperf 似乎不起作用)。所有硬件加速都在驱动程序中进行了调整。似乎 udp 性能只是低于标准?