我一直试图找出这个问题一个多月了。我无处可去。 我有一个服务器,可以监听许多多播通道(100ish)。每个套接字都是自己的线程。然后我有一个客户端监听器(单线程),它处理同一服务器中的所有传入连接,断开连接和客户端消息传递。我们的想法是客户端进入,连接,从多播通道请求数据,然后将数据发送回客户端。客户端保持连接,我将UDP数据中继回客户端。客户端可以请求UDP或TCP具有数据中继的协议。有一次,这种情况很好地工作了几个星期。我们做了一些代码和内核更改,现在我们无法弄清楚出了什么问题。
服务器将运行数小时,并且全天有数百个客户端连接。但在某些时候,随机,服务器将停止。通过停止,我的意思是:所有UDP套接字都停止接收/处理数据(tcpdump显示数据仍然出现在框中),client_listener线程停止接收客户端数据包。但!!!主client_listener套接字仍然可以在主套接字上接收新连接和新断开连接。在新连接上,主套接字能够发送"连接建立"数据包返回客户端,但是当客户端响应时,select永远不会返回。
如果有人愿意,我可以发布代码。如果有人有任何建议,或者这听起来像什么。请告诉我。
如果您有任何疑问,请询问。
谢谢。
我想分享我的TCP服务器代码: 这是一个单线程。工作好几个小时然后我只会收到" New Connections"和"断开"。没有客户端包进来。
int opt = 1;
int addrlen;
int sd;
int max_sd;
int valread;
int activity;
int new_socket;
char buffer[MAX_BUFFER_SIZE];
int client_socket[m_max_clients];
struct sockaddr_in address;
fd_set readfds;
for(int i = 0; i<m_max_clients; i++)
{
client_socket[i]=0;
}
if((m_master_socket = socket(AF_INET,SOCK_STREAM,0))==0)
LOG(FATAL)<<"Unable to create master socket";
if(setsockopt(m_master_socket,SOL_SOCKET,SO_REUSEADDR,(char*)&opt,sizeof(opt))<0)
LOG(FATAL)<<"Unable to set master socket";
address.sin_family = AF_INET;
address.sin_addr.s_addr = INADDR_ANY;
address.sin_port = htons(m_listenPort);
if(bind(m_master_socket,(struct sockaddr*)& address, sizeof(address))!=0)
LOG(FATAL)<<"Unable to bind master socket";
if(listen(m_master_socket,SOMAXCONN)!=0)
LOG(FATAL)<<"listen() failed with err";
addrlen = sizeof(address);
LOG(INFO)<<"Waiting for connections......";
while(true)
{
FD_ZERO(&readfds);
FD_SET(m_master_socket, &readfds);
max_sd = m_master_socket;
for(int i = 0; i<m_max_clients; i++)
{
sd = client_socket[i];
if(sd > 0)
FD_SET(sd, &readfds);
if(sd>max_sd)
max_sd = sd;
}
activity = select(max_sd+1,&readfds,NULL,NULL,NULL);
if((activity<0)&&(errno!=EINTR))
{
// int err = errno;
// LOG(ERROR)<<"SELECT ERROR:"<<activity<<" "<<err;
continue;
}
if(FD_ISSET(m_master_socket, &readfds))
{
if((new_socket = accept(m_master_socket,(struct sockaddr*)&address, (socklen_t*)&addrlen))<0)
LOG(FATAL)<<"ERROR:ACCEPT FAILED!";
LOG(INFO)<<"New Connection, socket fd is (" << new_socket << ") client_addr:" << inet_ntoa(address.sin_addr) << " Port:" << ntohs(address.sin_port);
for(int i =0;i<m_max_clients;i++)
{
if(client_socket[i]==0)
{
//try to set the socket to non blocking, tcp nagle and keep alive
if ( !SetSocketBlockingEnabled(new_socket, false) )
LOG(INFO)<<"UNABLE TO SET NON-BLOCK: ("<<new_socket<<")" ;
if ( !SetSocketNoDelay(new_socket,false) )
LOG(INFO)<<"UNABLE TO SET DELAY: ("<<new_socket<<")" ;
// if ( !SetSocketKeepAlive(new_socket,true) )
// LOG(INFO)<<"UNABLE TO SET KeepAlive: ("<<new_socket<<")" ;
ClientConnection* con = new ClientConnection(m_mocSrv, m_udpPortGenerator, inet_ntoa(address.sin_addr), ntohs(address.sin_port), new_socket);
if(con->login())
{
client_socket[i] = new_socket;
m_clientConnectionSocketMap[new_socket] = con;
LOG(INFO)<<"Client Connection Logon Complete";
}
else
delete con;
break;
}
}//for
}
else
{
try{
for(int i = 0; i<m_max_clients; i++)
{
sd = client_socket[i];
if(FD_ISSET(sd,&readfds))
{
if ( (valread = recv(sd, buffer, sizeof(buffer),MSG_DONTWAIT|MSG_NOSIGNAL)) <= 0 )
{
//remove from the fd listening set
LOG(INFO)<<"RESET CLIENT_SOCKET:("<<sd<<")";
client_socket[i]=0;
handleDisconnect(sd,true);
}
else
{
std::map<int, ClientConnection*>::iterator client_connection_socket_iter = m_clientConnectionSocketMap.find(sd);
if(client_connection_socket_iter != m_clientConnectionSocketMap.end())
{
client_connection_socket_iter->second->handle_message(buffer, valread);
if(client_connection_socket_iter->second->m_logoff)
{
LOG(INFO)<<"SOCKET LOGGED OFF:"<<sd;
client_socket[i]=0;
handleDisconnect(sd,true);
}
}
else
{
LOG(ERROR)<<"UNABLE TO FIND SOCKET DESCRIPTOR:"<<sd;
}
}
}
}
}catch(...)
{
LOG(ERROR)<<"EXCEPTION CATCH!!!";
}
}
}
答案 0 :(得分:2)
根据给出的信息,我将陈述以下内容:
简而言之,我会把钱花在线程僵局和/或饥饿上。我亲自进行过实验,我使用Epoll创建了一个多线程服务器和一个单线程服务器。结果在日夜不同,Epoll吹走了多线程实现(用于I / O)并使代码编写,调试和维护更简单。