bufmgr.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * bufmgr.c
 *	  buffer manager interface routines
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/storage/buffer/bufmgr.c,v 1.228 2008/01/01 19:45:51 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */
/*
 * Principal entry points:
 *
 * ReadBuffer() -- find or create a buffer holding the requested page,
 *		and pin it so that no one can destroy it while this process
 *		is using it.
 *
 * ReleaseBuffer() -- unpin a buffer
 *
 * MarkBufferDirty() -- mark a pinned buffer's contents as "dirty".
 *		The disk write is delayed until buffer replacement or checkpoint.
 *
 * See also these files:
 *		freelist.c -- chooses victim for buffer replacement
 *		buf_table.c -- manages the buffer lookup table
 */
#include "postgres.h"

#include <sys/file.h>
#include <unistd.h>

#include "miscadmin.h"
#include "postmaster/bgwriter.h"
#include "storage/buf_internals.h"
#include "storage/bufpage.h"
#include "storage/ipc.h"
#include "storage/proc.h"
#include "storage/smgr.h"
#include "utils/resowner.h"
#include "pgstat.h"


/* Note: these two macros only work on shared buffers, not local ones! */
#define BufHdrGetBlock(bufHdr)	((Block) (BufferBlocks + ((Size) (bufHdr)->buf_id) * BLCKSZ))
#define BufferGetLSN(bufHdr)	(*((XLogRecPtr*) BufHdrGetBlock(bufHdr)))

/* Note: this macro only works on local buffers, not shared ones! */
#define LocalBufHdrGetBlock(bufHdr) \
	LocalBufferBlockPointers[-((bufHdr)->buf_id + 2)]

/* Bits in SyncOneBuffer's return value */
#define BUF_WRITTEN				0x01
#define BUF_REUSABLE			0x02


/* GUC variables */
bool		zero_damaged_pages = false;
int			bgwriter_lru_maxpages = 100;
double		bgwriter_lru_multiplier = 2.0;


long		NDirectFileRead;	/* some I/O's are direct file access. bypass
								 * bufmgr */
long		NDirectFileWrite;	/* e.g., I/O in psort and hashjoin. */


/* local state for StartBufferIO and related functions */
static volatile BufferDesc *InProgressBuf = NULL;
static bool IsForInput;

/* local state for LockBufferForCleanup */
static volatile BufferDesc *PinCountWaitBuf = NULL;


static Buffer ReadBuffer_common(Relation reln, BlockNumber blockNum,
				  bool zeroPage,
				  BufferAccessStrategy strategy);
static bool PinBuffer(volatile BufferDesc *buf, BufferAccessStrategy strategy);
static void PinBuffer_Locked(volatile BufferDesc *buf);
static void UnpinBuffer(volatile BufferDesc *buf, bool fixOwner);
static void BufferSync(int flags);
static int	SyncOneBuffer(int buf_id, bool skip_recently_used);
static void WaitIO(volatile BufferDesc *buf);
static bool StartBufferIO(volatile BufferDesc *buf, bool forInput);
static void TerminateBufferIO(volatile BufferDesc *buf, bool clear_dirty,
				  int set_flag_bits);
static void buffer_write_error_callback(void *arg);
static volatile BufferDesc *BufferAlloc(Relation reln, BlockNumber blockNum,
			BufferAccessStrategy strategy,
			bool *foundPtr);
static void FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln);
static void AtProcExit_Buffers(int code, Datum arg);


/*
 * ReadBuffer -- returns a buffer containing the requested
 *		block of the requested relation.  If the blknum
 *		requested is P_NEW, extend the relation file and
 *		allocate a new block.  (Caller is responsible for
 *		ensuring that only one backend tries to extend a
 *		relation at the same time!)
 *
 * Returns: the buffer number for the buffer containing
 *		the block read.  The returned buffer has been pinned.
 *		Does not return on error --- elog's instead.
 *
 * Assume when this function is called, that reln has been
 *		opened already.
 */
Buffer
ReadBuffer(Relation reln, BlockNumber blockNum)
{
	return ReadBuffer_common(reln, blockNum, false, NULL);
}

/*
 * ReadBufferWithStrategy -- same as ReadBuffer, except caller can specify
 *		a nondefault buffer access strategy.  See buffer/README for details.
 */
Buffer
ReadBufferWithStrategy(Relation reln, BlockNumber blockNum,
					   BufferAccessStrategy strategy)
{
	return ReadBuffer_common(reln, blockNum, false, strategy);
}

/*
 * ReadOrZeroBuffer -- like ReadBuffer, but if the page isn't in buffer
 *		cache already, it's filled with zeros instead of reading it from
 *		disk.  Useful when the caller intends to fill the page from scratch,
 *		since this saves I/O and avoids unnecessary failure if the
 *		page-on-disk has corrupt page headers.
 *
 *		Caution: do not use this to read a page that is beyond the relation's
 *		current physical EOF; that is likely to cause problems in md.c when
 *		the page is modified and written out.  P_NEW is OK, though.
 */
Buffer
ReadOrZeroBuffer(Relation reln, BlockNumber blockNum)
{
	return ReadBuffer_common(reln, blockNum, true, NULL);
}

/*
 * ReadBuffer_common -- common logic for ReadBuffer variants
 */
static Buffer
ReadBuffer_common(Relation reln, BlockNumber blockNum, bool zeroPage,
				  BufferAccessStrategy strategy)
{
	volatile BufferDesc *bufHdr;
	Block		bufBlock;
	bool		found;
	bool		isExtend;
	bool		isLocalBuf;

	/* Make sure we will have room to remember the buffer pin */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	isExtend = (blockNum == P_NEW);
	isLocalBuf = reln->rd_istemp;

	/* Open it at the smgr level if not already done */
	RelationOpenSmgr(reln);

	/* Substitute proper block number if caller asked for P_NEW */
	if (isExtend)
		blockNum = smgrnblocks(reln->rd_smgr);

	pgstat_count_buffer_read(reln);

	if (isLocalBuf)
	{
		ReadLocalBufferCount++;
		bufHdr = LocalBufferAlloc(reln, blockNum, &found);
		if (found)
			LocalBufferHitCount++;
	}
	else
	{
		ReadBufferCount++;

		/*
		 * lookup the buffer.  IO_IN_PROGRESS is set if the requested block is
		 * not currently in memory.
		 */
		bufHdr = BufferAlloc(reln, blockNum, strategy, &found);
		if (found)
			BufferHitCount++;
	}

	/* At this point we do NOT hold any locks. */

	/* if it was already in the buffer pool, we're done */
	if (found)
	{
		if (!isExtend)
		{
			/* Just need to update stats before we exit */
			pgstat_count_buffer_hit(reln);

			if (VacuumCostActive)
				VacuumCostBalance += VacuumCostPageHit;

			return BufferDescriptorGetBuffer(bufHdr);
		}

		/*
		 * We get here only in the corner case where we are trying to extend
		 * the relation but we found a pre-existing buffer marked BM_VALID.
		 * This can happen because mdread doesn't complain about reads beyond
		 * EOF (when zero_damaged_pages is ON) and so a previous attempt to
		 * read a block beyond EOF could have left a "valid" zero-filled
		 * buffer.	Unfortunately, we have also seen this case occurring
		 * because of buggy Linux kernels that sometimes return an
		 * lseek(SEEK_END) result that doesn't account for a recent write. In
		 * that situation, the pre-existing buffer would contain valid data
		 * that we don't want to overwrite.  Since the legitimate case should
		 * always have left a zero-filled buffer, complain if not PageIsNew.
		 */
		bufBlock = isLocalBuf ? LocalBufHdrGetBlock(bufHdr) : BufHdrGetBlock(bufHdr);
		if (!PageIsNew((PageHeader) bufBlock))
			ereport(ERROR,
					(errmsg("unexpected data beyond EOF in block %u of relation \"%s\"",
							blockNum, RelationGetRelationName(reln)),
					 errhint("This has been seen to occur with buggy kernels; consider updating your system.")));

		/*
		 * We *must* do smgrextend before succeeding, else the page will not
		 * be reserved by the kernel, and the next P_NEW call will decide to
		 * return the same page.  Clear the BM_VALID bit, do the StartBufferIO
		 * call that BufferAlloc didn't, and proceed.
		 */
		if (isLocalBuf)
		{
			/* Only need to adjust flags */
			Assert(bufHdr->flags & BM_VALID);
			bufHdr->flags &= ~BM_VALID;
		}
		else
		{
			/*
			 * Loop to handle the very small possibility that someone re-sets
			 * BM_VALID between our clearing it and StartBufferIO inspecting
			 * it.
			 */
			do
			{
				LockBufHdr(bufHdr);
				Assert(bufHdr->flags & BM_VALID);
				bufHdr->flags &= ~BM_VALID;
				UnlockBufHdr(bufHdr);
			} while (!StartBufferIO(bufHdr, true));
		}
	}

	/*
	 * if we have gotten to this point, we have allocated a buffer for the
	 * page but its contents are not yet valid.  IO_IN_PROGRESS is set for it,
	 * if it's a shared buffer.
	 *
	 * Note: if smgrextend fails, we will end up with a buffer that is
	 * allocated but not marked BM_VALID.  P_NEW will still select the same
	 * block number (because the relation didn't get any longer on disk) and
	 * so future attempts to extend the relation will find the same buffer (if
	 * it's not been recycled) but come right back here to try smgrextend
	 * again.
	 */
	Assert(!(bufHdr->flags & BM_VALID));		/* spinlock not needed */

	bufBlock = isLocalBuf ? LocalBufHdrGetBlock(bufHdr) : BufHdrGetBlock(bufHdr);

	if (isExtend)
	{
		/* new buffers are zero-filled */
		MemSet((char *) bufBlock, 0, BLCKSZ);
		smgrextend(reln->rd_smgr, blockNum, (char *) bufBlock,
				   reln->rd_istemp);
	}
	else
	{
		/*
		 * Read in the page, unless the caller intends to overwrite it and
		 * just wants us to allocate a buffer.
		 */
		if (zeroPage)
			MemSet((char *) bufBlock, 0, BLCKSZ);
		else
			smgrread(reln->rd_smgr, blockNum, (char *) bufBlock);
		/* check for garbage data */
		if (!PageHeaderIsValid((PageHeader) bufBlock))
		{
			if (zero_damaged_pages)
			{
				ereport(WARNING,
						(errcode(ERRCODE_DATA_CORRUPTED),
						 errmsg("invalid page header in block %u of relation \"%s\"; zeroing out page",
								blockNum, RelationGetRelationName(reln))));
				MemSet((char *) bufBlock, 0, BLCKSZ);
			}
			else
				ereport(ERROR,
						(errcode(ERRCODE_DATA_CORRUPTED),
				 errmsg("invalid page header in block %u of relation \"%s\"",
						blockNum, RelationGetRelationName(reln))));
		}
	}

	if (isLocalBuf)
	{
		/* Only need to adjust flags */
		bufHdr->flags |= BM_VALID;
	}
	else
	{
		/* Set BM_VALID, terminate IO, and wake up any waiters */
		TerminateBufferIO(bufHdr, false, BM_VALID);
	}

	if (VacuumCostActive)
		VacuumCostBalance += VacuumCostPageMiss;

	return BufferDescriptorGetBuffer(bufHdr);
}

/*
 * BufferAlloc -- subroutine for ReadBuffer.  Handles lookup of a shared
 *		buffer.  If no buffer exists already, selects a replacement
 *		victim and evicts the old page, but does NOT read in new page.
 *
 * "strategy" can be a buffer replacement strategy object, or NULL for
 * the default strategy.  The selected buffer's usage_count is advanced when
 * using the default strategy, but otherwise possibly not (see PinBuffer).
 *
 * The returned buffer is pinned and is already marked as holding the
 * desired page.  If it already did have the desired page, *foundPtr is
 * set TRUE.  Otherwise, *foundPtr is set FALSE and the buffer is marked
 * as IO_IN_PROGRESS; ReadBuffer will now need to do I/O to fill it.
 *
 * *foundPtr is actually redundant with the buffer's BM_VALID flag, but
 * we keep it for simplicity in ReadBuffer.
 *
 * No locks are held either at entry or exit.
 */
static volatile BufferDesc *
BufferAlloc(Relation reln,
			BlockNumber blockNum,
			BufferAccessStrategy strategy,
			bool *foundPtr)
{
	BufferTag	newTag;			/* identity of requested block */
	uint32		newHash;		/* hash value for newTag */
	LWLockId	newPartitionLock;		/* buffer partition lock for it */
	BufferTag	oldTag;			/* previous identity of selected buffer */
	uint32		oldHash;		/* hash value for oldTag */
	LWLockId	oldPartitionLock;		/* buffer partition lock for it */
	BufFlags	oldFlags;
	int			buf_id;
	volatile BufferDesc *buf;
	bool		valid;

	/* create a tag so we can lookup the buffer */
	INIT_BUFFERTAG(newTag, reln, blockNum);

	/* determine its hash code and partition lock ID */
	newHash = BufTableHashCode(&newTag);
	newPartitionLock = BufMappingPartitionLock(newHash);

	/* see if the block is in the buffer pool already */
	LWLockAcquire(newPartitionLock, LW_SHARED);
	buf_id = BufTableLookup(&newTag, newHash);
	if (buf_id >= 0)
	{
		/*
		 * Found it.  Now, pin the buffer so no one can steal it from the
		 * buffer pool, and check to see if the correct data has been loaded
		 * into the buffer.
		 */
		buf = &BufferDescriptors[buf_id];

		valid = PinBuffer(buf, strategy);

		/* Can release the mapping lock as soon as we've pinned it */
		LWLockRelease(newPartitionLock);

		*foundPtr = TRUE;

		if (!valid)
		{
			/*
			 * We can only get here if (a) someone else is still reading in
			 * the page, or (b) a previous read attempt failed.  We have to
			 * wait for any active read attempt to finish, and then set up our
			 * own read attempt if the page is still not BM_VALID.
			 * StartBufferIO does it all.
			 */
			if (StartBufferIO(buf, true))
			{
				/*
				 * If we get here, previous attempts to read the buffer must
				 * have failed ... but we shall bravely try again.
				 */
				*foundPtr = FALSE;
			}
		}

		return buf;
	}

	/*
	 * Didn't find it in the buffer pool.  We'll have to initialize a new
	 * buffer.	Remember to unlock the mapping lock while doing the work.
	 */
	LWLockRelease(newPartitionLock);

	/* Loop here in case we have to try another victim buffer */
	for (;;)
	{
		bool		lock_held;

		/*
		 * Select a victim buffer.	The buffer is returned with its header
		 * spinlock still held!  Also (in most cases) the BufFreelistLock is
		 * still held, since it would be bad to hold the spinlock while
		 * possibly waking up other processes.
		 */
		buf = StrategyGetBuffer(strategy, &lock_held);

		Assert(buf->refcount == 0);

		/* Must copy buffer flags while we still hold the spinlock */
		oldFlags = buf->flags;

		/* Pin the buffer and then release the buffer spinlock */
		PinBuffer_Locked(buf);

		/* Now it's safe to release the freelist lock */
		if (lock_held)
			LWLockRelease(BufFreelistLock);

		/*
		 * If the buffer was dirty, try to write it out.  There is a race
		 * condition here, in that someone might dirty it after we released it