我正在移植构建在ACE Proactor框架之上的应用程序.该应用程序适用于VxWorks和Windows,但在使用librt的内核2.6.X.X的Linux(CentOS 5.5,WindRiver Linux 1.4和3.0)上无法运行.

我把问题缩小到一个非常基本的问题：

应用程序在套接字上开始异步(通过aio_read)读取操作,然后在同一个套接字上开始异步(通过aio_write)写入.由于协议是从应用程序结束初始化的,因此无法实现读取操作.

– 当套接字处于阻塞模式时,永远不会写入并且协议“挂起”.

– 使用O_NONBLOCK套接字时,写入成功,但读取无限期地返回“EWOULDBLOCK / EAGAIN”错误,永远不会恢复(即使重新启动AIO操作).

我经历了多个论坛,无法找到一个明确的答案,说明这是否应该可行(而且我做错了)或Linux AIO不可能.是否可以放弃AIO并寻求不同的实现(通过epoll / poll / select等)？

附件是一个示例代码,可以在非阻塞套接字上快速重现问题：

#include

#include

#include

#include

#include

#include

#include

#include

#include

#include

#define BUFSIZE (100)

// Global variables

struct aiocb *cblist[2];

int theSocket;

void InitializeAiocbData(struct aiocb* pAiocb, char* pBuffer)

{

bzero( (char *)pAiocb, sizeof(struct aiocb) );

pAiocb->aio_fildes = theSocket;

pAiocb->aio_nbytes = BUFSIZE;

pAiocb->aio_offset = 0;

pAiocb->aio_buf = pBuffer;

}

void IssueReadOperation(struct aiocb* pAiocb, char* pBuffer)

{

InitializeAiocbData(pAiocb, pBuffer);

int ret = aio_read( pAiocb );

assert (ret >= 0);

}

void IssueWriteOperation(struct aiocb* pAiocb, char* pBuffer)

{

InitializeAiocbData(pAiocb, pBuffer);

int ret = aio_write( pAiocb );

assert (ret >= 0);

}

int main()

{

int ret;

int nPort = 11111;

char* szServer = "10.10.9.123";

// Connect to the remote server

theSocket = socket(AF_INET, SOCK_STREAM, 0);

assert (theSocket >= 0);

struct hostent *pServer;

struct sockaddr_in serv_addr;

pServer = gethostbyname(szServer);

bzero((char *) &serv_addr, sizeof(serv_addr));

serv_addr.sin_family = AF_INET;

serv_addr.sin_port = htons(nPort);

bcopy((char *)pServer->h_addr, (char *)&serv_addr.sin_addr.s_addr, pServer->h_length);

assert (connect(theSocket, (const sockaddr*)(&serv_addr), sizeof(serv_addr)) >= 0);

// Set the socket to be non-blocking

int oldFlags = fcntl(theSocket, F_GETFL) ;

int newFlags = oldFlags | O_NONBLOCK;

fcntl(theSocket, F_SETFL, newFlags);

printf("Socket flags: before=%o, after=%o\n", oldFlags, newFlags);

// Construct the AIO callbacks array

struct aiocb my_aiocb1, my_aiocb2;

char* pBuffer = new char[BUFSIZE+1];

bzero( (char *)cblist, sizeof(cblist) );

cblist[0] = &my_aiocb1;

cblist[1] = &my_aiocb2;

// Start the read and write operations on the same socket

IssueReadOperation(&my_aiocb1, pBuffer);

IssueWriteOperation(&my_aiocb2, pBuffer);

// Wait for I/O completion on both operations

int nRound = 1;

printf("\naio_suspend round #%d:\n", nRound++);

ret = aio_suspend( cblist, 2, NULL );

assert (ret == 0);

// Check the error status for the read and write operations

ret = aio_error(&my_aiocb1);

assert (ret == EWOULDBLOCK);

// Get the return code for the read

{

ssize_t retcode = aio_return(&my_aiocb1);

printf("First read operation results: aio_error=%d, aio_return=%d - That's the first EWOULDBLOCK\n", ret, retcode);

}

ret = aio_error(&my_aiocb2);

assert (ret == EINPROGRESS);

printf("Write operation is still \"in progress\"\n");

// Re-issue the read operation

IssueReadOperation(&my_aiocb1, pBuffer);

// Wait for I/O completion on both operations

printf("\naio_suspend round #%d:\n", nRound++);

ret = aio_suspend( cblist, 2, NULL );

assert (ret == 0);

// Check the error status for the read and write operations for the second time

ret = aio_error(&my_aiocb1);

assert (ret == EINPROGRESS);

printf("Second read operation request is suddenly marked as \"in progress\"\n");

ret = aio_error(&my_aiocb2);

assert (ret == 0);

// Get the return code for the write

{

ssize_t retcode = aio_return(&my_aiocb2);

printf("Write operation has completed with results: aio_error=%d, aio_return=%d\n", ret, retcode);

}

// Now try waiting for the read operation to complete - it'll just busy-wait, receiving "EWOULDBLOCK" indefinitely

do

{

printf("\naio_suspend round #%d:\n", nRound++);

ret = aio_suspend( cblist, 1, NULL );

assert (ret == 0);

// Check the error of the read operation and re-issue if needed

ret = aio_error(&my_aiocb1);

if (ret == EWOULDBLOCK)

{

IssueReadOperation(&my_aiocb1, pBuffer);

printf("EWOULDBLOCK again on the read operation!\n");

}

}

while (ret == EWOULDBLOCK);

}

提前致谢,

Yotam.

解决方法:

首先,O_NONBLOCK和AIO不混合.当相应的读或写不会被阻塞时,AIO将报告异步操作完成 – 并且使用O_NONBLOCK,它们永远不会阻塞,因此aio请求将始终立即完成(使用aio_return()给出EWOULDBLOCK).

其次,不要为两个同时发生的未完成的aio请求使用相同的缓冲区.在发出aio请求的时间和aio_error()告诉你已完成的时间之间,缓冲区应被视为完全禁止.

第三,AIO对同一文件描述符的请求排队,以便给出明智的结果.这意味着在读取完成之前不会发生写入 – 如果您需要先写入数据,则需要以相反的顺序发出AIO.以下工作正常,无需设置O_NONBLOCK：

struct aiocb my_aiocb1, my_aiocb2;

char pBuffer1[BUFSIZE+1], pBuffer2[BUFSIZE+1] = "Some test message";

const struct aiocb *cblist[2] = { &my_aiocb1, &my_aiocb2 };

// Start the read and write operations on the same socket

IssueWriteOperation(&my_aiocb2, pBuffer2);

IssueReadOperation(&my_aiocb1, pBuffer1);

// Wait for I/O completion on both operations

int nRound = 1;

int aio_status1, aio_status2;

do {

printf("\naio_suspend round #%d:\n", nRound++);

ret = aio_suspend( cblist, 2, NULL );

assert (ret == 0);

// Check the error status for the read and write operations

aio_status1 = aio_error(&my_aiocb1);

if (aio_status1 == EINPROGRESS)

puts("aio1 still in progress.");

else

puts("aio1 completed.");

aio_status2 = aio_error(&my_aiocb2);

if (aio_status2 == EINPROGRESS)

puts("aio2 still in progress.");

else

puts("aio2 completed.");

} while (aio_status1 == EINPROGRESS || aio_status2 == EINPROGRESS);

// Get the return code for the read

ssize_t retcode;

retcode = aio_return(&my_aiocb1);

printf("First operation results: aio_error=%d, aio_return=%d\n", aio_status1, retcode);

retcode = aio_return(&my_aiocb1);

printf("Second operation results: aio_error=%d, aio_return=%d\n", aio_status1, retcode);

或者,如果您不关心相互之间的读取和写入,您可以使用dup()为套接字创建两个文件描述符,并使用一个用于读取而另一个用于写入 – 每个都将具有AIO操作单独排队.

标签：linux,sockets,kernel,nonblocking,aio

来源： https://codeday.me/bug/20190630/1340573.html