fd.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

	{
		switch (whence)
		{
			case SEEK_SET:
				if (offset < 0)
					elog(ERROR, "invalid seek offset: %ld", offset);
				VfdCache[file].seekPos = offset;
				break;
			case SEEK_CUR:
				VfdCache[file].seekPos += offset;
				break;
			case SEEK_END:
				returnCode = FileAccess(file);
				if (returnCode < 0)
					return returnCode;
				VfdCache[file].seekPos = lseek(VfdCache[file].fd,
											   offset, whence);
				break;
			default:
				elog(ERROR, "invalid whence: %d", whence);
				break;
		}
	}
	else
	{
		switch (whence)
		{
			case SEEK_SET:
				if (offset < 0)
					elog(ERROR, "invalid seek offset: %ld", offset);
				if (VfdCache[file].seekPos != offset)
					VfdCache[file].seekPos = lseek(VfdCache[file].fd,
												   offset, whence);
				break;
			case SEEK_CUR:
				if (offset != 0 || VfdCache[file].seekPos == FileUnknownPos)
					VfdCache[file].seekPos = lseek(VfdCache[file].fd,
												   offset, whence);
				break;
			case SEEK_END:
				VfdCache[file].seekPos = lseek(VfdCache[file].fd,
											   offset, whence);
				break;
			default:
				elog(ERROR, "invalid whence: %d", whence);
				break;
		}
	}
	return VfdCache[file].seekPos;
}

/*
 * XXX not actually used but here for completeness
 */
#ifdef NOT_USED
long
FileTell(File file)
{
	Assert(FileIsValid(file));
	DO_DB(elog(LOG, "FileTell %d (%s)",
			   file, VfdCache[file].fileName));
	return VfdCache[file].seekPos;
}
#endif

int
FileTruncate(File file, long offset)
{
	int			returnCode;

	Assert(FileIsValid(file));

	DO_DB(elog(LOG, "FileTruncate %d (%s)",
			   file, VfdCache[file].fileName));

	returnCode = FileAccess(file);
	if (returnCode < 0)
		return returnCode;

	returnCode = ftruncate(VfdCache[file].fd, (size_t) offset);
	return returnCode;
}


/*
 * Routines that want to use stdio (ie, FILE*) should use AllocateFile
 * rather than plain fopen().  This lets fd.c deal with freeing FDs if
 * necessary to open the file.	When done, call FreeFile rather than fclose.
 *
 * Note that files that will be open for any significant length of time
 * should NOT be handled this way, since they cannot share kernel file
 * descriptors with other files; there is grave risk of running out of FDs
 * if anyone locks down too many FDs.  Most callers of this routine are
 * simply reading a config file that they will read and close immediately.
 *
 * fd.c will automatically close all files opened with AllocateFile at
 * transaction commit or abort; this prevents FD leakage if a routine
 * that calls AllocateFile is terminated prematurely by ereport(ERROR).
 *
 * Ideally this should be the *only* direct call of fopen() in the backend.
 */
FILE *
AllocateFile(char *name, char *mode)
{
	FILE	   *file;

	DO_DB(elog(LOG, "AllocateFile: Allocated %d (%s)",
			   numAllocatedDescs, name));

	/*
	 * The test against MAX_ALLOCATED_DESCS prevents us from overflowing
	 * allocatedFiles[]; the test against max_safe_fds prevents AllocateFile
	 * from hogging every one of the available FDs, which'd lead to infinite
	 * looping.
	 */
	if (numAllocatedDescs >= MAX_ALLOCATED_DESCS ||
		numAllocatedDescs >= max_safe_fds - 1)
		elog(ERROR, "too many private files demanded");

TryAgain:
	if ((file = fopen(name, mode)) != NULL)
	{
		AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];

		desc->kind = AllocateDescFile;
		desc->desc.file = file;
		desc->create_subid = GetCurrentSubTransactionId();
		numAllocatedDescs++;
		return desc->desc.file;
	}

	if (errno == EMFILE || errno == ENFILE)
	{
		int			save_errno = errno;

		ereport(LOG,
				(errcode(ERRCODE_INSUFFICIENT_RESOURCES),
				 errmsg("out of file descriptors: %m; release and retry")));
		errno = 0;
		if (ReleaseLruFile())
			goto TryAgain;
		errno = save_errno;
	}

	return NULL;
}

/*
 * Free an AllocateDesc of either type.
 *
 * The argument *must* point into the allocatedDescs[] array.
 */
static int
FreeDesc(AllocateDesc *desc)
{
	int			result;

	/* Close the underlying object */
	switch (desc->kind)
	{
		case AllocateDescFile:
			result = fclose(desc->desc.file);
			break;
		case AllocateDescDir:
			result = closedir(desc->desc.dir);
			break;
		default:
			elog(ERROR, "AllocateDesc kind not recognized");
			result = 0;			/* keep compiler quiet */
			break;
	}

	/* Compact storage in the allocatedDescs array */
	numAllocatedDescs--;
	*desc = allocatedDescs[numAllocatedDescs];

	return result;
}

/*
 * Close a file returned by AllocateFile.
 *
 * Note we do not check fclose's return value --- it is up to the caller
 * to handle close errors.
 */
int
FreeFile(FILE *file)
{
	int			i;

	DO_DB(elog(LOG, "FreeFile: Allocated %d", numAllocatedDescs));

	/* Remove file from list of allocated files, if it's present */
	for (i = numAllocatedDescs; --i >= 0;)
	{
		AllocateDesc *desc = &allocatedDescs[i];

		if (desc->kind == AllocateDescFile && desc->desc.file == file)
			return FreeDesc(desc);
	}

	/* Only get here if someone passes us a file not in allocatedDescs */
	elog(WARNING, "file passed to FreeFile was not obtained from AllocateFile");

	return fclose(file);
}


/*
 * Routines that want to use <dirent.h> (ie, DIR*) should use AllocateDir
 * rather than plain opendir().  This lets fd.c deal with freeing FDs if
 * necessary to open the directory, and with closing it after an elog.
 * When done, call FreeDir rather than closedir.
 *
 * Ideally this should be the *only* direct call of opendir() in the backend.
 */
DIR *
AllocateDir(const char *dirname)
{
	DIR		   *dir;

	DO_DB(elog(LOG, "AllocateDir: Allocated %d (%s)",
			   numAllocatedDescs, dirname));

	/*
	 * The test against MAX_ALLOCATED_DESCS prevents us from overflowing
	 * allocatedDescs[]; the test against max_safe_fds prevents AllocateDir
	 * from hogging every one of the available FDs, which'd lead to infinite
	 * looping.
	 */
	if (numAllocatedDescs >= MAX_ALLOCATED_DESCS ||
		numAllocatedDescs >= max_safe_fds - 1)
		elog(ERROR, "too many private dirs demanded");

TryAgain:
	if ((dir = opendir(dirname)) != NULL)
	{
		AllocateDesc *desc = &allocatedDescs[numAllocatedDescs];

		desc->kind = AllocateDescDir;
		desc->desc.dir = dir;
		desc->create_subid = GetCurrentSubTransactionId();
		numAllocatedDescs++;
		return desc->desc.dir;
	}

	if (errno == EMFILE || errno == ENFILE)
	{
		int			save_errno = errno;

		ereport(LOG,
				(errcode(ERRCODE_INSUFFICIENT_RESOURCES),
				 errmsg("out of file descriptors: %m; release and retry")));
		errno = 0;
		if (ReleaseLruFile())
			goto TryAgain;
		errno = save_errno;
	}

	return NULL;
}

/*
 * Read a directory opened with AllocateDir, ereport'ing any error.
 *
 * This is easier to use than raw readdir() since it takes care of some
 * otherwise rather tedious and error-prone manipulation of errno.	Also,
 * if you are happy with a generic error message for AllocateDir failure,
 * you can just do
 *
 *		dir = AllocateDir(path);
 *		while ((dirent = ReadDir(dir, path)) != NULL)
 *			process dirent;
 *		FreeDir(path);
 *
 * since a NULL dir parameter is taken as indicating AllocateDir failed.
 * (Make sure errno hasn't been changed since AllocateDir if you use this
 * shortcut.)
 *
 * The pathname passed to AllocateDir must be passed to this routine too,
 * but it is only used for error reporting.
 */
struct dirent *
ReadDir(DIR *dir, const char *dirname)
{
	struct dirent *dent;

	/* Give a generic message for AllocateDir failure, if caller didn't */
	if (dir == NULL)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not open directory \"%s\": %m",
						dirname)));

	errno = 0;
	if ((dent = readdir(dir)) != NULL)
		return dent;

#ifdef WIN32

	/*
	 * This fix is in mingw cvs (runtime/mingwex/dirent.c rev 1.4), but not in
	 * released version
	 */
	if (GetLastError() == ERROR_NO_MORE_FILES)
		errno = 0;
#endif

	if (errno)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not read directory \"%s\": %m",
						dirname)));
	return NULL;
}

/*
 * Close a directory opened with AllocateDir.
 *
 * Note we do not check closedir's return value --- it is up to the caller
 * to handle close errors.
 */
int
FreeDir(DIR *dir)
{
	int			i;

	DO_DB(elog(LOG, "FreeDir: Allocated %d", numAllocatedDescs));

	/* Remove dir from list of allocated dirs, if it's present */
	for (i = numAllocatedDescs; --i >= 0;)
	{
		AllocateDesc *desc = &allocatedDescs[i];

		if (desc->kind == AllocateDescDir && desc->desc.dir == dir)
			return FreeDesc(desc);
	}

	/* Only get here if someone passes us a dir not in allocatedDescs */
	elog(WARNING, "dir passed to FreeDir was not obtained from AllocateDir");

	return closedir(dir);
}


/*
 * closeAllVfds
 *
 * Force all VFDs into the physically-closed state, so that the fewest
 * possible number of kernel file descriptors are in use.  There is no
 * change in the logical state of the VFDs.
 */
void
closeAllVfds(void)
{
	Index		i;

	if (SizeVfdCache > 0)
	{
		Assert(FileIsNotOpen(0));		/* Make sure ring not corrupted */
		for (i = 1; i < SizeVfdCache; i++)
		{
			if (!FileIsNotOpen(i))
				LruDelete(i);
		}
	}
}

/*
 * AtEOSubXact_Files
 *
 * Take care of subtransaction commit/abort.  At abort, we close temp files
 * that the subtransaction may have opened.  At commit, we reassign the
 * files that were opened to the parent subtransaction.
 */
void
AtEOSubXact_Files(bool isCommit, SubTransactionId mySubid,
				  SubTransactionId parentSubid)
{
	Index		i;

	if (SizeVfdCache > 0)
	{
		Assert(FileIsNotOpen(0));		/* Make sure ring not corrupted */
		for (i = 1; i < SizeVfdCache; i++)
		{
			unsigned short fdstate = VfdCache[i].fdstate;

			if ((fdstate & FD_XACT_TEMPORARY) &&
				VfdCache[i].create_subid == mySubid)
			{
				if (isCommit)
					VfdCache[i].create_subid = parentSubid;
				else if (VfdCache[i].fileName != NULL)
					FileClose(i);
			}
		}
	}

	for (i = 0; i < numAllocatedDescs; i++)
	{
		if (allocatedDescs[i].create_subid == mySubid)
		{
			if (isCommit)
				allocatedDescs[i].create_subid = parentSubid;
			else
			{
				/* have to recheck the item after FreeDesc (ugly) */
				FreeDesc(&allocatedDescs[i--]);
			}
		}
	}
}

/*
 * AtEOXact_Files
 *
 * This routine is called during transaction commit or abort (it doesn't
 * particularly care which).  All still-open per-transaction temporary file
 * VFDs are closed, which also causes the underlying files to be
 * deleted. Furthermore, all "allocated" stdio files are closed.
 */
void
AtEOXact_Files(void)
{
	CleanupTempFiles(false);
}

/*
 * AtProcExit_Files
 *
 * on_proc_exit hook to clean up temp files during backend shutdown.
 * Here, we want to clean up *all* temp files including interXact ones.
 */
static void
AtProcExit_Files(int code, Datum arg)
{
	CleanupTempFiles(true);
}

/*
 * Close temporary files and delete their underlying files.
 *
 * isProcExit: if true, this is being called as the backend process is
 * exiting. If that's the case, we should remove all temporary files; if
 * that's not the case, we are being called for transaction commit/abort
 * and should only remove transaction-local temp files.  In either case,
 * also clean up "allocated" stdio files and dirs.
 */
static void
CleanupTempFiles(bool isProcExit)
{
	Index		i;

	if (SizeVfdCache > 0)
	{
		Assert(FileIsNotOpen(0));		/* Make sure ring not corrupted */
		for (i = 1; i < SizeVfdCache; i++)
		{
			unsigned short fdstate = VfdCache[i].fdstate;

			if ((fdstate & FD_TEMPORARY) && VfdCache[i].fileName != NULL)
			{
				/*
				 * If we're in the process of exiting a backend process, close
				 * all temporary files. Otherwise, only close temporary files
				 * local to the current transaction.
				 */
				if (isProcExit || (fdstate & FD_XACT_TEMPORARY))
					FileClose(i);
			}
		}
	}

	while (numAllocatedDescs > 0)
		FreeDesc(&allocatedDescs[0]);
}


/*
 * Remove temporary files left over from a prior postmaster session
 *
 * This should be called during postmaster startup.  It will forcibly
 * remove any leftover files created by OpenTemporaryFile.
 *
 * NOTE: we could, but don't, call this during a post-backend-crash restart
 * cycle.  The argument for not doing it is that someone might want to examine
 * the temp files for debugging purposes.  This does however mean that
 * OpenTemporaryFile had better allow for collision with an existing temp
 * file name.
 */
void
RemovePgTempFiles(void)
{
	char		temp_path[MAXPGPATH];
	DIR		   *db_dir;
	struct dirent *db_de;

	/*
	 * Cycle through pgsql_tmp directories for all databases and remove old
	 * temp files.
	 */
	db_dir = AllocateDir("base");

	while ((db_de = ReadDir(db_dir, "base")) != NULL)
	{
		if (strcmp(db_de->d_name, ".") == 0 ||
			strcmp(db_de->d_name, "..") == 0)
			continue;

		snprintf(temp_path, sizeof(temp_path), "base/%s/%s",
				 db_de->d_name, PG_TEMP_FILES_DIR);
		RemovePgTempFilesInDir(temp_path);
	}

	FreeDir(db_dir);

	/*
	 * In EXEC_BACKEND case there is a pgsql_tmp directory at the top level of
	 * DataDir as well.
	 */
#ifdef EXEC_BACKEND
	RemovePgTempFilesInDir(PG_TEMP_FILES_DIR);
#endif
}

/* Process one pgsql_tmp directory for RemovePgTempFiles */
static void
RemovePgTempFilesInDir(const char *tmpdirname)
{
	DIR		   *temp_dir;
	struct dirent *temp_de;
	char		rm_path[MAXPGPATH];

	temp_dir = AllocateDir(tmpdirname);
	if (temp_dir == NULL)
	{
		/* anything except ENOENT is fishy */
		if (errno != ENOENT)
			elog(LOG,
				 "could not open temporary-files directory \"%s\": %m",
				 tmpdirname);
		return;
	}

	while ((temp_de = ReadDir(temp_dir, tmpdirname)) != NULL)
	{
		if (strcmp(temp_de->d_name, ".") == 0 ||
			strcmp(temp_de->d_name, "..") == 0)
			continue;

		snprintf(rm_path, sizeof(rm_path), "%s/%s",
				 tmpdirname, temp_de->d_name);

		if (strncmp(temp_de->d_name,
					PG_TEMP_FILE_PREFIX,
					strlen(PG_TEMP_FILE_PREFIX)) == 0)
			unlink(rm_path);	/* note we ignore any error */
		else
			elog(LOG,
				 "unexpected file found in temporary-files directory: \"%s\"",
				 rm_path);
	}

	FreeDir(temp_dir);
}