slru.c

postgresql8.3.4源码,开源数据库

			/* Otherwise, it's ready to use */
			SlruRecentlyUsed(shared, slotno);
			return slotno;
		}

		/* We found no match; assert we selected a freeable slot */
		Assert(shared->page_status[slotno] == SLRU_PAGE_EMPTY ||
			   (shared->page_status[slotno] == SLRU_PAGE_VALID &&
				!shared->page_dirty[slotno]));

		/* Mark the slot read-busy */
		shared->page_number[slotno] = pageno;
		shared->page_status[slotno] = SLRU_PAGE_READ_IN_PROGRESS;
		shared->page_dirty[slotno] = false;

		/* Acquire per-buffer lock (cannot deadlock, see notes at top) */
		LWLockAcquire(shared->buffer_locks[slotno], LW_EXCLUSIVE);

		/*
		 * Temporarily mark page as recently-used to discourage
		 * SlruSelectLRUPage from selecting it again for someone else.
		 */
		SlruRecentlyUsed(shared, slotno);

		/* Release control lock while doing I/O */
		LWLockRelease(shared->ControlLock);

		/* Do the read */
		ok = SlruPhysicalReadPage(ctl, pageno, slotno);

		/* Set the LSNs for this newly read-in page to zero */
		SimpleLruZeroLSNs(ctl, slotno);

		/* Re-acquire control lock and update page state */
		LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);

		Assert(shared->page_number[slotno] == pageno &&
			   shared->page_status[slotno] == SLRU_PAGE_READ_IN_PROGRESS &&
			   !shared->page_dirty[slotno]);

		shared->page_status[slotno] = ok ? SLRU_PAGE_VALID : SLRU_PAGE_EMPTY;

		LWLockRelease(shared->buffer_locks[slotno]);

		/* Now it's okay to ereport if we failed */
		if (!ok)
			SlruReportIOError(ctl, pageno, xid);

		SlruRecentlyUsed(shared, slotno);
		return slotno;
	}
}

/*
 * Find a page in a shared buffer, reading it in if necessary.
 * The page number must correspond to an already-initialized page.
 * The caller must intend only read-only access to the page.
 *
 * The passed-in xid is used only for error reporting, and may be
 * InvalidTransactionId if no specific xid is associated with the action.
 *
 * Return value is the shared-buffer slot number now holding the page.
 * The buffer's LRU access info is updated.
 *
 * Control lock must NOT be held at entry, but will be held at exit.
 * It is unspecified whether the lock will be shared or exclusive.
 */
int
SimpleLruReadPage_ReadOnly(SlruCtl ctl, int pageno, TransactionId xid)
{
	SlruShared	shared = ctl->shared;
	int			slotno;

	/* Try to find the page while holding only shared lock */
	LWLockAcquire(shared->ControlLock, LW_SHARED);

	/* See if page is already in a buffer */
	for (slotno = 0; slotno < shared->num_slots; slotno++)
	{
		if (shared->page_number[slotno] == pageno &&
			shared->page_status[slotno] != SLRU_PAGE_EMPTY &&
			shared->page_status[slotno] != SLRU_PAGE_READ_IN_PROGRESS)
		{
			/* See comments for SlruRecentlyUsed macro */
			SlruRecentlyUsed(shared, slotno);
			return slotno;
		}
	}

	/* No luck, so switch to normal exclusive lock and do regular read */
	LWLockRelease(shared->ControlLock);
	LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);

	return SimpleLruReadPage(ctl, pageno, true, xid);
}

/*
 * Write a page from a shared buffer, if necessary.
 * Does nothing if the specified slot is not dirty.
 *
 * NOTE: only one write attempt is made here.  Hence, it is possible that
 * the page is still dirty at exit (if someone else re-dirtied it during
 * the write).	However, we *do* attempt a fresh write even if the page
 * is already being written; this is for checkpoints.
 *
 * Control lock must be held at entry, and will be held at exit.
 */
void
SimpleLruWritePage(SlruCtl ctl, int slotno, SlruFlush fdata)
{
	SlruShared	shared = ctl->shared;
	int			pageno = shared->page_number[slotno];
	bool		ok;

	/* If a write is in progress, wait for it to finish */
	while (shared->page_status[slotno] == SLRU_PAGE_WRITE_IN_PROGRESS &&
		   shared->page_number[slotno] == pageno)
	{
		SimpleLruWaitIO(ctl, slotno);
	}

	/*
	 * Do nothing if page is not dirty, or if buffer no longer contains the
	 * same page we were called for.
	 */
	if (!shared->page_dirty[slotno] ||
		shared->page_status[slotno] != SLRU_PAGE_VALID ||
		shared->page_number[slotno] != pageno)
		return;

	/*
	 * Mark the slot write-busy, and clear the dirtybit.  After this point, a
	 * transaction status update on this page will mark it dirty again.
	 */
	shared->page_status[slotno] = SLRU_PAGE_WRITE_IN_PROGRESS;
	shared->page_dirty[slotno] = false;

	/* Acquire per-buffer lock (cannot deadlock, see notes at top) */
	LWLockAcquire(shared->buffer_locks[slotno], LW_EXCLUSIVE);

	/* Release control lock while doing I/O */
	LWLockRelease(shared->ControlLock);

	/* Do the write */
	ok = SlruPhysicalWritePage(ctl, pageno, slotno, fdata);

	/* If we failed, and we're in a flush, better close the files */
	if (!ok && fdata)
	{
		int			i;

		for (i = 0; i < fdata->num_files; i++)
			close(fdata->fd[i]);
	}

	/* Re-acquire control lock and update page state */
	LWLockAcquire(shared->ControlLock, LW_EXCLUSIVE);

	Assert(shared->page_number[slotno] == pageno &&
		   shared->page_status[slotno] == SLRU_PAGE_WRITE_IN_PROGRESS);

	/* If we failed to write, mark the page dirty again */
	if (!ok)
		shared->page_dirty[slotno] = true;

	shared->page_status[slotno] = SLRU_PAGE_VALID;

	LWLockRelease(shared->buffer_locks[slotno]);

	/* Now it's okay to ereport if we failed */
	if (!ok)
		SlruReportIOError(ctl, pageno, InvalidTransactionId);
}

/*
 * Physical read of a (previously existing) page into a buffer slot
 *
 * On failure, we cannot just ereport(ERROR) since caller has put state in
 * shared memory that must be undone.  So, we return FALSE and save enough
 * info in static variables to let SlruReportIOError make the report.
 *
 * For now, assume it's not worth keeping a file pointer open across
 * read/write operations.  We could cache one virtual file pointer ...
 */
static bool
SlruPhysicalReadPage(SlruCtl ctl, int pageno, int slotno)
{
	SlruShared	shared = ctl->shared;
	int			segno = pageno / SLRU_PAGES_PER_SEGMENT;
	int			rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
	int			offset = rpageno * BLCKSZ;
	char		path[MAXPGPATH];
	int			fd;

	SlruFileName(ctl, path, segno);

	/*
	 * In a crash-and-restart situation, it's possible for us to receive
	 * commands to set the commit status of transactions whose bits are in
	 * already-truncated segments of the commit log (see notes in
	 * SlruPhysicalWritePage).	Hence, if we are InRecovery, allow the case
	 * where the file doesn't exist, and return zeroes instead.
	 */
	fd = BasicOpenFile(path, O_RDWR | PG_BINARY, S_IRUSR | S_IWUSR);
	if (fd < 0)
	{
		if (errno != ENOENT || !InRecovery)
		{
			slru_errcause = SLRU_OPEN_FAILED;
			slru_errno = errno;
			return false;
		}

		ereport(LOG,
				(errmsg("file \"%s\" doesn't exist, reading as zeroes",
						path)));
		MemSet(shared->page_buffer[slotno], 0, BLCKSZ);
		return true;
	}

	if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
	{
		slru_errcause = SLRU_SEEK_FAILED;
		slru_errno = errno;
		close(fd);
		return false;
	}

	errno = 0;
	if (read(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
	{
		slru_errcause = SLRU_READ_FAILED;
		slru_errno = errno;
		close(fd);
		return false;
	}

	if (close(fd))
	{
		slru_errcause = SLRU_CLOSE_FAILED;
		slru_errno = errno;
		return false;
	}

	return true;
}

/*
 * Physical write of a page from a buffer slot
 *
 * On failure, we cannot just ereport(ERROR) since caller has put state in
 * shared memory that must be undone.  So, we return FALSE and save enough
 * info in static variables to let SlruReportIOError make the report.
 *
 * For now, assume it's not worth keeping a file pointer open across
 * independent read/write operations.  We do batch operations during
 * SimpleLruFlush, though.
 *
 * fdata is NULL for a standalone write, pointer to open-file info during
 * SimpleLruFlush.
 */
static bool
SlruPhysicalWritePage(SlruCtl ctl, int pageno, int slotno, SlruFlush fdata)
{
	SlruShared	shared = ctl->shared;
	int			segno = pageno / SLRU_PAGES_PER_SEGMENT;
	int			rpageno = pageno % SLRU_PAGES_PER_SEGMENT;
	int			offset = rpageno * BLCKSZ;
	char		path[MAXPGPATH];
	int			fd = -1;

	/*
	 * Honor the write-WAL-before-data rule, if appropriate, so that we do not
	 * write out data before associated WAL records.  This is the same action
	 * performed during FlushBuffer() in the main buffer manager.
	 */
	if (shared->group_lsn != NULL)
	{
		/*
		 * We must determine the largest async-commit LSN for the page. This
		 * is a bit tedious, but since this entire function is a slow path
		 * anyway, it seems better to do this here than to maintain a per-page
		 * LSN variable (which'd need an extra comparison in the
		 * transaction-commit path).
		 */
		XLogRecPtr	max_lsn;
		int			lsnindex,
					lsnoff;

		lsnindex = slotno * shared->lsn_groups_per_page;
		max_lsn = shared->group_lsn[lsnindex++];
		for (lsnoff = 1; lsnoff < shared->lsn_groups_per_page; lsnoff++)
		{
			XLogRecPtr	this_lsn = shared->group_lsn[lsnindex++];

			if (XLByteLT(max_lsn, this_lsn))
				max_lsn = this_lsn;
		}

		if (!XLogRecPtrIsInvalid(max_lsn))
		{
			/*
			 * As noted above, elog(ERROR) is not acceptable here, so if
			 * XLogFlush were to fail, we must PANIC.  This isn't much of a
			 * restriction because XLogFlush is just about all critical
			 * section anyway, but let's make sure.
			 */
			START_CRIT_SECTION();
			XLogFlush(max_lsn);
			END_CRIT_SECTION();
		}
	}

	/*
	 * During a Flush, we may already have the desired file open.
	 */
	if (fdata)
	{
		int			i;

		for (i = 0; i < fdata->num_files; i++)
		{
			if (fdata->segno[i] == segno)
			{
				fd = fdata->fd[i];
				break;
			}
		}
	}

	if (fd < 0)
	{
		/*
		 * If the file doesn't already exist, we should create it.  It is
		 * possible for this to need to happen when writing a page that's not
		 * first in its segment; we assume the OS can cope with that. (Note:
		 * it might seem that it'd be okay to create files only when
		 * SimpleLruZeroPage is called for the first page of a segment.
		 * However, if after a crash and restart the REDO logic elects to
		 * replay the log from a checkpoint before the latest one, then it's
		 * possible that we will get commands to set transaction status of
		 * transactions that have already been truncated from the commit log.
		 * Easiest way to deal with that is to accept references to
		 * nonexistent files here and in SlruPhysicalReadPage.)
		 *
		 * Note: it is possible for more than one backend to be executing this
		 * code simultaneously for different pages of the same file. Hence,
		 * don't use O_EXCL or O_TRUNC or anything like that.
		 */
		SlruFileName(ctl, path, segno);
		fd = BasicOpenFile(path, O_RDWR | O_CREAT | PG_BINARY,
						   S_IRUSR | S_IWUSR);
		if (fd < 0)
		{
			slru_errcause = SLRU_OPEN_FAILED;
			slru_errno = errno;
			return false;
		}

		if (fdata)
		{
			if (fdata->num_files < MAX_FLUSH_BUFFERS)
			{
				fdata->fd[fdata->num_files] = fd;
				fdata->segno[fdata->num_files] = segno;
				fdata->num_files++;
			}
			else
			{
				/*
				 * In the unlikely event that we exceed MAX_FLUSH_BUFFERS,
				 * fall back to treating it as a standalone write.
				 */
				fdata = NULL;
			}
		}
	}

	if (lseek(fd, (off_t) offset, SEEK_SET) < 0)
	{
		slru_errcause = SLRU_SEEK_FAILED;
		slru_errno = errno;
		if (!fdata)
			close(fd);
		return false;
	}

	errno = 0;
	if (write(fd, shared->page_buffer[slotno], BLCKSZ) != BLCKSZ)
	{
		/* if write didn't set errno, assume problem is no disk space */
		if (errno == 0)
			errno = ENOSPC;
		slru_errcause = SLRU_WRITE_FAILED;
		slru_errno = errno;
		if (!fdata)
			close(fd);
		return false;
	}