Re: [ADMIN] ERROR: could not read block

[Qingqing Zhou <zhouqq(at)cs(dot)toronto(dot)edu>]

I come up with a patch to fix server-side problem. The basic idea is to
convert ERROR_NO_SYSTEM_RESOURCES to EINTR and add code to do retry unless
a new error encountered or successfully done. I tweak the FileRead() logic
on "returnCode <= 0" a little bit by separating it to "<0" and "==0"
parts. This is because if our read passed EOF, read() will not set errno
which may cause a dead loop if a previous read() is interrupted.

For windows, I set a one second waiting time - this should be ok since the
problem is very rare. If the error is permenate, you can always SIGINT the
process since the waiting is done by pg_usleep().

Regards,
Qingqing

---

Index: src/backend/storage/file/fd.c
===================================================================
RCS file: /projects/cvsroot/pgsql/src/backend/storage/file/fd.c,v
retrieving revision 1.122
diff -c -r1.122 fd.c
*** src/backend/storage/file/fd.c	22 Nov 2005 18:17:20 -0000	1.122
--- src/backend/storage/file/fd.c	1 Dec 2005 01:09:59 -0000
***************
*** 1009,1019 ****
  	if (returnCode < 0)
  		return returnCode;

! 	returnCode = read(VfdCache[file].fd, buffer, amount);
! 	if (returnCode > 0)
! 		VfdCache[file].seekPos += returnCode;
! 	else
! 		VfdCache[file].seekPos = FileUnknownPos;

  	return returnCode;
  }
--- 1009,1052 ----
  	if (returnCode < 0)
  		return returnCode;

! 	for (;;)
! 	{
! 		returnCode = read(VfdCache[file].fd, buffer, amount);
!
! 		if (returnCode > 0)
! 			VfdCache[file].seekPos += returnCode;
! 		else if (returnCode == 0)
! 			VfdCache[file].seekPos = FileUnknownPos;
! 		else
! 		{
! #ifdef WIN32
! 			DWORD error = GetLastError();
!
! 			switch (error)
! 			{
! 				/*
! 				 * Since we are using buffered IO now, so windows may run
! 				 * out of kernel buffer and return a "Insufficient system
! 				 * resources" error. Retry to solve it.
! 				 */
! 				case ERROR_NO_SYSTEM_RESOURCES:
! 					pg_usleep(1000);
! 					errno = EINTR;
! 					break;
! 				default:
! 					_dosmaperr(error);
! 					Assert(errno != EINTR);
! 			}
! #endif
! 			/* Ok if interrupted and retry */
! 			if (errno == EINTR)
! 				continue;
!
! 			VfdCache[file].seekPos = FileUnknownPos;
! 		}
!
! 		break;
! 	}

  	return returnCode;
  }
***************
*** 1033,1049 ****
  	if (returnCode < 0)
  		return returnCode;

! 	errno = 0;
! 	returnCode = write(VfdCache[file].fd, buffer, amount);

! 	/* if write didn't set errno, assume problem is no disk space */
! 	if (returnCode != amount && errno == 0)
! 		errno = ENOSPC;

! 	if (returnCode > 0)
! 		VfdCache[file].seekPos += returnCode;
! 	else
! 		VfdCache[file].seekPos = FileUnknownPos;

  	return returnCode;
  }
--- 1066,1108 ----
  	if (returnCode < 0)
  		return returnCode;

! 	for (;;)
! 	{
! 		errno = 0;
! 		returnCode = write(VfdCache[file].fd, buffer, amount);

! 		/* if write didn't set errno, assume problem is no disk space */
! 		if (returnCode != amount && errno == 0)
! 			errno = ENOSPC;

! 		if (returnCode > 0)
! 			VfdCache[file].seekPos += returnCode;
! 		else
! 		{
! #ifdef WIN32
! 			DWORD error = GetLastError();
!
! 			switch (error)
! 			{
! 				/* see comments in FileRead() */
! 				case ERROR_NO_SYSTEM_RESOURCES:
! 					pg_usleep(1000);
! 					errno = EINTR;
! 					break;
! 				default:
! 					_dosmaperr(error);
! 					Assert(errno != EINTR);
! 			}
! #endif
! 			/* Ok if interrupted and retry */
! 			if (errno == EINTR)
! 				continue;
!
! 			VfdCache[file].seekPos = FileUnknownPos;
! 		}
!
! 		break;
! 	}

  	return returnCode;
  }