Exemple #1
0
/* ------------------------------------------------
 * hash_bitmap_info()
 *
 * Get bitmap information for a particular overflow page
 *
 * Usage: SELECT * FROM hash_bitmap_info('con_hash_index'::regclass, 5);
 * ------------------------------------------------
 */
Datum
hash_bitmap_info(PG_FUNCTION_ARGS)
{
	Oid			indexRelid = PG_GETARG_OID(0);
	uint64		ovflblkno = PG_GETARG_INT64(1);
	HashMetaPage metap;
	Buffer		metabuf,
				mapbuf;
	BlockNumber bitmapblkno;
	Page		mappage;
	bool		bit = false;
	TupleDesc	tupleDesc;
	Relation	indexRel;
	uint32		ovflbitno;
	int32		bitmappage,
				bitmapbit;
	HeapTuple	tuple;
	int			i,
				j;
	Datum		values[3];
	bool		nulls[3];
	uint32	   *freep;

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 (errmsg("must be superuser to use raw page functions"))));

	indexRel = index_open(indexRelid, AccessShareLock);

	if (!IS_HASH(indexRel))
		elog(ERROR, "relation \"%s\" is not a hash index",
			 RelationGetRelationName(indexRel));

	if (RELATION_IS_OTHER_TEMP(indexRel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot access temporary tables of other sessions")));

	if (ovflblkno >= RelationGetNumberOfBlocks(indexRel))
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("block number " UINT64_FORMAT " is out of range for relation \"%s\"",
						ovflblkno, RelationGetRelationName(indexRel))));

	/* Read the metapage so we can determine which bitmap page to use */
	metabuf = _hash_getbuf(indexRel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
	metap = HashPageGetMeta(BufferGetPage(metabuf));

	/*
	 * Reject attempt to read the bit for a metapage or bitmap page; this is
	 * only meaningful for overflow pages.
	 */
	if (ovflblkno == 0)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("invalid overflow block number %u",
						(BlockNumber) ovflblkno)));
	for (i = 0; i < metap->hashm_nmaps; i++)
		if (metap->hashm_mapp[i] == ovflblkno)
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
					 errmsg("invalid overflow block number %u",
							(BlockNumber) ovflblkno)));

	/*
	 * Identify overflow bit number.  This will error out for primary bucket
	 * pages, and we've already rejected the metapage and bitmap pages above.
	 */
	ovflbitno = _hash_ovflblkno_to_bitno(metap, (BlockNumber) ovflblkno);

	bitmappage = ovflbitno >> BMPG_SHIFT(metap);
	bitmapbit = ovflbitno & BMPG_MASK(metap);

	if (bitmappage >= metap->hashm_nmaps)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("invalid overflow block number %u",
						(BlockNumber) ovflblkno)));

	bitmapblkno = metap->hashm_mapp[bitmappage];

	_hash_relbuf(indexRel, metabuf);

	/* Check the status of bitmap bit for overflow page */
	mapbuf = _hash_getbuf(indexRel, bitmapblkno, HASH_READ, LH_BITMAP_PAGE);
	mappage = BufferGetPage(mapbuf);
	freep = HashPageGetBitmap(mappage);

	bit = ISSET(freep, bitmapbit) != 0;

	_hash_relbuf(indexRel, mapbuf);
	index_close(indexRel, AccessShareLock);

	/* Build a tuple descriptor for our result type */
	if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");
	tupleDesc = BlessTupleDesc(tupleDesc);

	MemSet(nulls, 0, sizeof(nulls));

	j = 0;
	values[j++] = Int64GetDatum((int64) bitmapblkno);
	values[j++] = Int32GetDatum(bitmapbit);
	values[j++] = BoolGetDatum(bit);

	tuple = heap_form_tuple(tupleDesc, values, nulls);

	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
}
Exemple #2
0
/*
 *	_hash_freeovflpage() -
 *
 *	Remove this overflow page from its bucket's chain, and mark the page as
 *	free.  On entry, ovflbuf is write-locked; it is released before exiting.
 *
 *	Add the tuples (itups) to wbuf in this function.  We could do that in the
 *	caller as well, but the advantage of doing it here is we can easily write
 *	the WAL for XLOG_HASH_SQUEEZE_PAGE operation.  Addition of tuples and
 *	removal of overflow page has to done as an atomic operation, otherwise
 *	during replay on standby users might find duplicate records.
 *
 *	Since this function is invoked in VACUUM, we provide an access strategy
 *	parameter that controls fetches of the bucket pages.
 *
 *	Returns the block number of the page that followed the given page
 *	in the bucket, or InvalidBlockNumber if no following page.
 *
 *	NB: caller must not hold lock on metapage, nor on page, that's next to
 *	ovflbuf in the bucket chain.  We don't acquire the lock on page that's
 *	prior to ovflbuf in chain if it is same as wbuf because the caller already
 *	has a lock on same.
 */
BlockNumber
_hash_freeovflpage(Relation rel, Buffer bucketbuf, Buffer ovflbuf,
				   Buffer wbuf, IndexTuple *itups, OffsetNumber *itup_offsets,
				   Size *tups_size, uint16 nitups,
				   BufferAccessStrategy bstrategy)
{
	HashMetaPage metap;
	Buffer		metabuf;
	Buffer		mapbuf;
	BlockNumber ovflblkno;
	BlockNumber prevblkno;
	BlockNumber blkno;
	BlockNumber nextblkno;
	BlockNumber writeblkno;
	HashPageOpaque ovflopaque;
	Page		ovflpage;
	Page		mappage;
	uint32	   *freep;
	uint32		ovflbitno;
	int32		bitmappage,
				bitmapbit;
	Bucket		bucket PG_USED_FOR_ASSERTS_ONLY;
	Buffer		prevbuf = InvalidBuffer;
	Buffer		nextbuf = InvalidBuffer;
	bool		update_metap = false;

	/* Get information from the doomed page */
	_hash_checkpage(rel, ovflbuf, LH_OVERFLOW_PAGE);
	ovflblkno = BufferGetBlockNumber(ovflbuf);
	ovflpage = BufferGetPage(ovflbuf);
	ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
	nextblkno = ovflopaque->hasho_nextblkno;
	prevblkno = ovflopaque->hasho_prevblkno;
	writeblkno = BufferGetBlockNumber(wbuf);
	bucket = ovflopaque->hasho_bucket;

	/*
	 * Fix up the bucket chain.  this is a doubly-linked list, so we must fix
	 * up the bucket chain members behind and ahead of the overflow page being
	 * deleted.  Concurrency issues are avoided by using lock chaining as
	 * described atop hashbucketcleanup.
	 */
	if (BlockNumberIsValid(prevblkno))
	{
		if (prevblkno == writeblkno)
			prevbuf = wbuf;
		else
			prevbuf = _hash_getbuf_with_strategy(rel,
												 prevblkno,
												 HASH_WRITE,
												 LH_BUCKET_PAGE | LH_OVERFLOW_PAGE,
												 bstrategy);
	}
	if (BlockNumberIsValid(nextblkno))
		nextbuf = _hash_getbuf_with_strategy(rel,
											 nextblkno,
											 HASH_WRITE,
											 LH_OVERFLOW_PAGE,
											 bstrategy);

	/* Note: bstrategy is intentionally not used for metapage and bitmap */

	/* Read the metapage so we can determine which bitmap page to use */
	metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
	metap = HashPageGetMeta(BufferGetPage(metabuf));

	/* Identify which bit to set */
	ovflbitno = _hash_ovflblkno_to_bitno(metap, ovflblkno);

	bitmappage = ovflbitno >> BMPG_SHIFT(metap);
	bitmapbit = ovflbitno & BMPG_MASK(metap);

	if (bitmappage >= metap->hashm_nmaps)
		elog(ERROR, "invalid overflow bit number %u", ovflbitno);
	blkno = metap->hashm_mapp[bitmappage];

	/* Release metapage lock while we access the bitmap page */
	LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);

	/* read the bitmap page to clear the bitmap bit */
	mapbuf = _hash_getbuf(rel, blkno, HASH_WRITE, LH_BITMAP_PAGE);
	mappage = BufferGetPage(mapbuf);
	freep = HashPageGetBitmap(mappage);
	Assert(ISSET(freep, bitmapbit));

	/* Get write-lock on metapage to update firstfree */
	LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);

	/* This operation needs to log multiple tuples, prepare WAL for that */
	if (RelationNeedsWAL(rel))
		XLogEnsureRecordSpace(HASH_XLOG_FREE_OVFL_BUFS, 4 + nitups);

	START_CRIT_SECTION();

	/*
	 * we have to insert tuples on the "write" page, being careful to preserve
	 * hashkey ordering.  (If we insert many tuples into the same "write" page
	 * it would be worth qsort'ing them).
	 */
	if (nitups > 0)
	{
		_hash_pgaddmultitup(rel, wbuf, itups, itup_offsets, nitups);
		MarkBufferDirty(wbuf);
	}

	/*
	 * Reinitialize the freed overflow page.  Just zeroing the page won't
	 * work, because WAL replay routines expect pages to be initialized. See
	 * explanation of RBM_NORMAL mode atop XLogReadBufferExtended.  We are
	 * careful to make the special space valid here so that tools like
	 * pageinspect won't get confused.
	 */
	_hash_pageinit(ovflpage, BufferGetPageSize(ovflbuf));

	ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);

	ovflopaque->hasho_prevblkno = InvalidBlockNumber;
	ovflopaque->hasho_nextblkno = InvalidBlockNumber;
	ovflopaque->hasho_bucket = -1;
	ovflopaque->hasho_flag = LH_UNUSED_PAGE;
	ovflopaque->hasho_page_id = HASHO_PAGE_ID;

	MarkBufferDirty(ovflbuf);

	if (BufferIsValid(prevbuf))
	{
		Page		prevpage = BufferGetPage(prevbuf);
		HashPageOpaque prevopaque = (HashPageOpaque) PageGetSpecialPointer(prevpage);

		Assert(prevopaque->hasho_bucket == bucket);
		prevopaque->hasho_nextblkno = nextblkno;
		MarkBufferDirty(prevbuf);
	}
	if (BufferIsValid(nextbuf))
	{
		Page		nextpage = BufferGetPage(nextbuf);
		HashPageOpaque nextopaque = (HashPageOpaque) PageGetSpecialPointer(nextpage);

		Assert(nextopaque->hasho_bucket == bucket);
		nextopaque->hasho_prevblkno = prevblkno;
		MarkBufferDirty(nextbuf);
	}

	/* Clear the bitmap bit to indicate that this overflow page is free */
	CLRBIT(freep, bitmapbit);
	MarkBufferDirty(mapbuf);

	/* if this is now the first free page, update hashm_firstfree */
	if (ovflbitno < metap->hashm_firstfree)
	{
		metap->hashm_firstfree = ovflbitno;
		update_metap = true;
		MarkBufferDirty(metabuf);
	}

	/* XLOG stuff */
	if (RelationNeedsWAL(rel))
	{
		xl_hash_squeeze_page xlrec;
		XLogRecPtr	recptr;
		int			i;

		xlrec.prevblkno = prevblkno;
		xlrec.nextblkno = nextblkno;
		xlrec.ntups = nitups;
		xlrec.is_prim_bucket_same_wrt = (wbuf == bucketbuf);
		xlrec.is_prev_bucket_same_wrt = (wbuf == prevbuf);

		XLogBeginInsert();
		XLogRegisterData((char *) &xlrec, SizeOfHashSqueezePage);

		/*
		 * bucket buffer needs to be registered to ensure that we can acquire
		 * a cleanup lock on it during replay.
		 */
		if (!xlrec.is_prim_bucket_same_wrt)
			XLogRegisterBuffer(0, bucketbuf, REGBUF_STANDARD | REGBUF_NO_IMAGE);

		XLogRegisterBuffer(1, wbuf, REGBUF_STANDARD);
		if (xlrec.ntups > 0)
		{
			XLogRegisterBufData(1, (char *) itup_offsets,
								nitups * sizeof(OffsetNumber));
			for (i = 0; i < nitups; i++)
				XLogRegisterBufData(1, (char *) itups[i], tups_size[i]);
		}

		XLogRegisterBuffer(2, ovflbuf, REGBUF_STANDARD);

		/*
		 * If prevpage and the writepage (block in which we are moving tuples
		 * from overflow) are same, then no need to separately register
		 * prevpage.  During replay, we can directly update the nextblock in
		 * writepage.
		 */
		if (BufferIsValid(prevbuf) && !xlrec.is_prev_bucket_same_wrt)
			XLogRegisterBuffer(3, prevbuf, REGBUF_STANDARD);

		if (BufferIsValid(nextbuf))
			XLogRegisterBuffer(4, nextbuf, REGBUF_STANDARD);

		XLogRegisterBuffer(5, mapbuf, REGBUF_STANDARD);
		XLogRegisterBufData(5, (char *) &bitmapbit, sizeof(uint32));

		if (update_metap)
		{
			XLogRegisterBuffer(6, metabuf, REGBUF_STANDARD);
			XLogRegisterBufData(6, (char *) &metap->hashm_firstfree, sizeof(uint32));
		}

		recptr = XLogInsert(RM_HASH_ID, XLOG_HASH_SQUEEZE_PAGE);

		PageSetLSN(BufferGetPage(wbuf), recptr);
		PageSetLSN(BufferGetPage(ovflbuf), recptr);

		if (BufferIsValid(prevbuf) && !xlrec.is_prev_bucket_same_wrt)
			PageSetLSN(BufferGetPage(prevbuf), recptr);
		if (BufferIsValid(nextbuf))
			PageSetLSN(BufferGetPage(nextbuf), recptr);

		PageSetLSN(BufferGetPage(mapbuf), recptr);

		if (update_metap)
			PageSetLSN(BufferGetPage(metabuf), recptr);
	}

	END_CRIT_SECTION();

	/* release previous bucket if it is not same as write bucket */
	if (BufferIsValid(prevbuf) && prevblkno != writeblkno)
		_hash_relbuf(rel, prevbuf);

	if (BufferIsValid(ovflbuf))
		_hash_relbuf(rel, ovflbuf);

	if (BufferIsValid(nextbuf))
		_hash_relbuf(rel, nextbuf);

	_hash_relbuf(rel, mapbuf);
	_hash_relbuf(rel, metabuf);

	return nextblkno;
}