C++ RelationGetNumberOfBlocks函数代码示例

/*
 * pgstat_index -- returns live/dead tuples info in a generic index
 */
static Datum
pgstat_index(Relation rel, BlockNumber start, pgstat_page pagefn,
			 FunctionCallInfo fcinfo)
{
	BlockNumber nblocks;
	BlockNumber blkno;
	BufferAccessStrategy bstrategy;
	pgstattuple_type stat = {0};

	/* prepare access strategy for this index */
	bstrategy = GetAccessStrategy(BAS_BULKREAD);

	blkno = start;
	for (;;)
	{
		/* Get the current relation length */
		LockRelationForExtension(rel, ExclusiveLock);
		nblocks = RelationGetNumberOfBlocks(rel);
		UnlockRelationForExtension(rel, ExclusiveLock);

		/* Quit if we've scanned the whole relation */
		if (blkno >= nblocks)
		{
			stat.table_len = (uint64) nblocks *BLCKSZ;

			break;
		}

		for (; blkno < nblocks; blkno++)
		{
			CHECK_FOR_INTERRUPTS();

			pagefn(&stat, rel, blkno, bstrategy);
		}
	}

	relation_close(rel, AccessShareLock);

	return build_pgstattuple_type(&stat, fcinfo);
}

/*
 * Build a new bloom index.
 */
IndexBuildResult *
blbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
	IndexBuildResult *result;
	double		reltuples;
	BloomBuildState buildstate;

	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/* Initialize the meta page */
	BloomInitMetapage(index);

	/* Initialize the bloom build state */
	memset(&buildstate, 0, sizeof(buildstate));
	initBloomState(&buildstate.blstate, index);
	buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
											  "Bloom build temporary context",
											  ALLOCSET_DEFAULT_SIZES);
	initCachedPage(&buildstate);

	/* Do the heap scan */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
								   bloomBuildCallback, (void *) &buildstate);

	/*
	 * There are could be some items in cached page.  Flush this page if
	 * needed.
	 */
	if (buildstate.count > 0)
		flushCachedPage(index, &buildstate);

	MemoryContextDelete(buildstate.tmpCtx);

	result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
	result->heap_tuples = result->index_tuples = reltuples;

	return result;
}

Datum
pg_relpagesbyid(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	int64		relpages;
	Relation	rel;

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

	rel = relation_open(relid, AccessShareLock);

	/* note: this will work OK on non-local temp tables */

	relpages = RelationGetNumberOfBlocks(rel);

	relation_close(rel, AccessShareLock);

	PG_RETURN_INT64(relpages);
}

/*
 *	hashbuild() -- build a new hash index.
 */
Datum
hashbuild(PG_FUNCTION_ARGS)
{
	Relation	heap = (Relation) PG_GETARG_POINTER(0);
	Relation	index = (Relation) PG_GETARG_POINTER(1);
	IndexInfo  *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
	IndexBuildResult *result;
	double		reltuples;
	HashBuildState buildstate;

	/*
	 * We expect to be called exactly once for any index relation. If that's
	 * not the case, big trouble's what we have.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/* initialize the hash index metadata page */
	_hash_metapinit(index);

	/* build the index */
	buildstate.indtuples = 0;

	/* do the heap scan */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo,
								   hashbuildCallback, (void *) &buildstate);

	/*
	 * Return statistics
	 */
	result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));

	result->heap_tuples = reltuples;
	result->index_tuples = buildstate.indtuples;

	PG_RETURN_POINTER(result);
}

/* --------------------------------------------------------
 * pg_relpages()
 *
 * Get a number of pages of the table/index.
 *
 * Usage: SELECT pg_relpages('t1');
 *		  SELECT pg_relpages('t1_pkey');
 * --------------------------------------------------------
 */
Datum
pg_relpages(PG_FUNCTION_ARGS)
{
	text	   *relname = PG_GETARG_TEXT_P(0);

	Relation	rel;
	RangeVar   *relrv;
	int4		relpages;

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

	relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
	rel = relation_openrv(relrv, AccessShareLock);

	relpages = RelationGetNumberOfBlocks(rel);

	relation_close(rel, AccessShareLock);

	PG_RETURN_INT32(relpages);
}

/*
 * GetPageWithFreeSpace - try to find a page in the given relation with
 *		at least the specified amount of free space.
 *
 * If successful, return the block number; if not, return InvalidBlockNumber.
 *
 * The caller must be prepared for the possibility that the returned page
 * will turn out to have too little space available by the time the caller
 * gets a lock on it.  In that case, the caller should report the actual
 * amount of free space available on that page and then try again (see
 * RecordAndGetPageWithFreeSpace).  If InvalidBlockNumber is returned,
 * extend the relation.
 *
 * For very small heap relations that don't have a FSM, we try every other
 * page before extending the relation.  To keep track of which pages have
 * been tried, initialize a local in-memory map of pages.
 */
BlockNumber
GetPageWithFreeSpace(Relation rel, Size spaceNeeded, bool check_fsm_only)
{
	uint8		min_cat = fsm_space_needed_to_cat(spaceNeeded);
	BlockNumber target_block,
				nblocks;

	/* First try the FSM, if it exists. */
	target_block = fsm_search(rel, min_cat);

	if (target_block == InvalidBlockNumber &&
		(rel->rd_rel->relkind == RELKIND_RELATION ||
		 rel->rd_rel->relkind == RELKIND_TOASTVALUE) &&
		!check_fsm_only)
	{
		nblocks = RelationGetNumberOfBlocks(rel);

		if (nblocks > HEAP_FSM_CREATION_THRESHOLD)
		{
			/*
			 * If the FSM knows nothing of the rel, try the last page before
			 * we give up and extend.  This avoids one-tuple-per-page syndrome
			 * during bootstrapping or in a recently-started system.
			 */
			target_block = nblocks - 1;
		}
		else if (nblocks > 0)
		{
			/* Create or update local map and get first candidate block. */
			fsm_local_set(rel, nblocks);
			target_block = fsm_local_search();
		}
	}

	return target_block;
}

/*
 * Post-VACUUM cleanup.
 *
 * Result: a palloc'd struct containing statistical info for VACUUM displays.
 */
Datum bingo_vacuumcleanup(PG_FUNCTION_ARGS) {
   IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
   IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
   Relation rel = info->index;
   BlockNumber num_pages = 0;

   elog(NOTICE, "start test vacuum");
   /* 
    * If bulkdelete wasn't called, return NULL signifying no change
    * Note: this covers the analyze_only case too
    */
   if (stats == NULL) {
      PG_RETURN_POINTER(NULL);
   }
   /*
    * update statistics
    */
   num_pages = RelationGetNumberOfBlocks(rel);
   stats->num_pages = num_pages;
   stats->num_index_tuples = 1;
   stats->estimated_count = false;

   PG_RETURN_POINTER(stats);
}

/*
 * Main entry point to GiST index build. Initially calls insert over and over,
 * but switches to more efficient buffering build algorithm after a certain
 * number of tuples (unless buffering mode is disabled).
 */
Datum
gistbuild(PG_FUNCTION_ARGS)
{
	Relation	heap = (Relation) PG_GETARG_POINTER(0);
	Relation	index = (Relation) PG_GETARG_POINTER(1);
	IndexInfo  *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
	IndexBuildResult *result;
	double		reltuples;
	GISTBuildState buildstate;
	Buffer		buffer;
	Page		page;
	MemoryContext oldcxt = CurrentMemoryContext;
	int			fillfactor;

	buildstate.indexrel = index;
	if (index->rd_options)
	{
		/* Get buffering mode from the options string */
		GiSTOptions *options = (GiSTOptions *) index->rd_options;
		char	   *bufferingMode = (char *) options + options->bufferingModeOffset;

		if (strcmp(bufferingMode, "on") == 0)
			buildstate.bufferingMode = GIST_BUFFERING_STATS;
		else if (strcmp(bufferingMode, "off") == 0)
			buildstate.bufferingMode = GIST_BUFFERING_DISABLED;
		else
			buildstate.bufferingMode = GIST_BUFFERING_AUTO;

		fillfactor = options->fillfactor;
	}
	else
	{
		/*
		 * By default, switch to buffering mode when the index grows too large
		 * to fit in cache.
		 */
		buildstate.bufferingMode = GIST_BUFFERING_AUTO;
		fillfactor = GIST_DEFAULT_FILLFACTOR;
	}
	/* Calculate target amount of free space to leave on pages */
	buildstate.freespace = BLCKSZ * (100 - fillfactor) / 100;

	/*
	 * We expect to be called exactly once for any index relation. If that's
	 * not the case, big trouble's what we have.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/* no locking is needed */
	buildstate.giststate = initGISTstate(index);

	/*
	 * Create a temporary memory context that is reset once for each tuple
	 * processed.  (Note: we don't bother to make this a child of the
	 * giststate's scanCxt, so we have to delete it separately at the end.)
	 */
	buildstate.giststate->tempCxt = createTempGistContext();

	/* initialize the root page */
	buffer = gistNewBuffer(index);
	Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
	page = BufferGetPage(buffer);

	START_CRIT_SECTION();

	GISTInitBuffer(buffer, F_LEAF);

	MarkBufferDirty(buffer);

	if (RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;
		XLogRecData rdata;

		rdata.data = (char *) &(index->rd_node);
		rdata.len = sizeof(RelFileNode);
		rdata.buffer = InvalidBuffer;
		rdata.next = NULL;

		recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX, &rdata);
		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}
	else
		PageSetLSN(page, gistGetFakeLSN(heap));

	UnlockReleaseBuffer(buffer);

	END_CRIT_SECTION();

	/* build the index */
	buildstate.indtuples = 0;
	buildstate.indtuplesSize = 0;
//.........这里部分代码省略.........

/*
 *	hashbuild() -- build a new hash index.
 */
IndexBuildResult *
hashbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
	IndexBuildResult *result;
	BlockNumber relpages;
	double		reltuples;
	double		allvisfrac;
	uint32		num_buckets;
	long		sort_threshold;
	HashBuildState buildstate;

	/*
	 * We expect to be called exactly once for any index relation. If that's
	 * not the case, big trouble's what we have.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/* Estimate the number of rows currently present in the table */
	estimate_rel_size(heap, NULL, &relpages, &reltuples, &allvisfrac);

	/* Initialize the hash index metadata page and initial buckets */
	num_buckets = _hash_init(index, reltuples, MAIN_FORKNUM);

	/*
	 * If we just insert the tuples into the index in scan order, then
	 * (assuming their hash codes are pretty random) there will be no locality
	 * of access to the index, and if the index is bigger than available RAM
	 * then we'll thrash horribly.  To prevent that scenario, we can sort the
	 * tuples by (expected) bucket number.  However, such a sort is useless
	 * overhead when the index does fit in RAM.  We choose to sort if the
	 * initial index size exceeds maintenance_work_mem, or the number of
	 * buffers usable for the index, whichever is less.  (Limiting by the
	 * number of buffers should reduce thrashing between PG buffers and kernel
	 * buffers, which seems useful even if no physical I/O results.  Limiting
	 * by maintenance_work_mem is useful to allow easy testing of the sort
	 * code path, and may be useful to DBAs as an additional control knob.)
	 *
	 * NOTE: this test will need adjustment if a bucket is ever different from
	 * one page.  Also, "initial index size" accounting does not include the
	 * metapage, nor the first bitmap page.
	 */
	sort_threshold = (maintenance_work_mem * 1024L) / BLCKSZ;
	if (index->rd_rel->relpersistence != RELPERSISTENCE_TEMP)
		sort_threshold = Min(sort_threshold, NBuffers);
	else
		sort_threshold = Min(sort_threshold, NLocBuffer);

	if (num_buckets >= (uint32) sort_threshold)
		buildstate.spool = _h_spoolinit(heap, index, num_buckets);
	else
		buildstate.spool = NULL;

	/* prepare to build the index */
	buildstate.indtuples = 0;
	buildstate.heapRel = heap;

	/* do the heap scan */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
								   hashbuildCallback, (void *) &buildstate);

	if (buildstate.spool)
	{
		/* sort the tuples and insert them into the index */
		_h_indexbuild(buildstate.spool, buildstate.heapRel);
		_h_spooldestroy(buildstate.spool);
	}

	/*
	 * Return statistics
	 */
	result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));

	result->heap_tuples = reltuples;
	result->index_tuples = buildstate.indtuples;

	return result;
}

static Datum
pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo)
{
	Datum		result;
	BlockNumber nblocks;
	BlockNumber blkno;
	BTIndexStat indexStat;
	BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);

	if (!IS_INDEX(rel) || !IS_BTREE(rel))
		elog(ERROR, "relation \"%s\" is not a btree index",
			 RelationGetRelationName(rel));

	/*
	 * Reject attempts to read non-local temporary relations; we would be
	 * likely to get wrong data since we have no visibility into the owning
	 * session's local buffers.
	 */
	if (RELATION_IS_OTHER_TEMP(rel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot access temporary tables of other sessions")));

	/*
	 * Read metapage
	 */
	{
		Buffer		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, 0, RBM_NORMAL, bstrategy);
		Page		page = BufferGetPage(buffer);
		BTMetaPageData *metad = BTPageGetMeta(page);

		indexStat.version = metad->btm_version;
		indexStat.level = metad->btm_level;
		indexStat.root_blkno = metad->btm_root;

		ReleaseBuffer(buffer);
	}

	/* -- init counters -- */
	indexStat.internal_pages = 0;
	indexStat.leaf_pages = 0;
	indexStat.empty_pages = 0;
	indexStat.deleted_pages = 0;

	indexStat.max_avail = 0;
	indexStat.free_space = 0;

	indexStat.fragments = 0;

	/*
	 * Scan all blocks except the metapage
	 */
	nblocks = RelationGetNumberOfBlocks(rel);

	for (blkno = 1; blkno < nblocks; blkno++)
	{
		Buffer		buffer;
		Page		page;
		BTPageOpaque opaque;

		CHECK_FOR_INTERRUPTS();

		/* Read and lock buffer */
		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
		LockBuffer(buffer, BUFFER_LOCK_SHARE);

		page = BufferGetPage(buffer);
		opaque = (BTPageOpaque) PageGetSpecialPointer(page);

		/* Determine page type, and update totals */

		if (P_ISDELETED(opaque))
			indexStat.deleted_pages++;
		else if (P_IGNORE(opaque))
			indexStat.empty_pages++;	/* this is the "half dead" state */
		else if (P_ISLEAF(opaque))
		{
			int			max_avail;

			max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
			indexStat.max_avail += max_avail;
			indexStat.free_space += PageGetFreeSpace(page);

			indexStat.leaf_pages++;

			/*
			 * If the next leaf is on an earlier block, it means a
			 * fragmentation.
			 */
			if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
				indexStat.fragments++;
		}
		else
			indexStat.internal_pages++;

		/* Unlock and release buffer */
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		ReleaseBuffer(buffer);
	}

//.........这里部分代码省略.........

//.........这里部分代码省略.........
			{
				info->indexkeys[i] = index->indkey.values[i];
				info->opfamily[i] = indexRelation->rd_opfamily[i];
				info->opcintype[i] = indexRelation->rd_opcintype[i];
			}

			info->relam = indexRelation->rd_rel->relam;
			info->amcostestimate = indexRelation->rd_am->amcostestimate;
			info->amoptionalkey = indexRelation->rd_am->amoptionalkey;
			info->amsearchnulls = indexRelation->rd_am->amsearchnulls;
			info->amhasgettuple = OidIsValid(indexRelation->rd_am->amgettuple);
			info->amhasgetbitmap = OidIsValid(indexRelation->rd_am->amgetbitmap);

			/*
			 * Fetch the ordering operators associated with the index, if any.
			 * We expect that all ordering-capable indexes use btree's
			 * strategy numbers for the ordering operators.
			 */
			if (indexRelation->rd_am->amcanorder)
			{
				int			nstrat = indexRelation->rd_am->amstrategies;

				for (i = 0; i < ncolumns; i++)
				{
					int16		opt = indexRelation->rd_indoption[i];
					int			fwdstrat;
					int			revstrat;

					if (opt & INDOPTION_DESC)
					{
						fwdstrat = BTGreaterStrategyNumber;
						revstrat = BTLessStrategyNumber;
					}
					else
					{
						fwdstrat = BTLessStrategyNumber;
						revstrat = BTGreaterStrategyNumber;
					}

					/*
					 * Index AM must have a fixed set of strategies for it to
					 * make sense to specify amcanorder, so we need not allow
					 * the case amstrategies == 0.
					 */
					if (fwdstrat > 0)
					{
						Assert(fwdstrat <= nstrat);
						info->fwdsortop[i] = indexRelation->rd_operator[i * nstrat + fwdstrat - 1];
					}
					if (revstrat > 0)
					{
						Assert(revstrat <= nstrat);
						info->revsortop[i] = indexRelation->rd_operator[i * nstrat + revstrat - 1];
					}
					info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
				}
			}

			/*
			 * Fetch the index expressions and predicate, if any.  We must
			 * modify the copies we obtain from the relcache to have the
			 * correct varno for the parent relation, so that they match up
			 * correctly against qual clauses.
			 */
			info->indexprs = RelationGetIndexExpressions(indexRelation);
			info->indpred = RelationGetIndexPredicate(indexRelation);
			if (info->indexprs && varno != 1)
				ChangeVarNodes((Node *) info->indexprs, 1, varno, 0);
			if (info->indpred && varno != 1)
				ChangeVarNodes((Node *) info->indpred, 1, varno, 0);
			info->predOK = false;		/* set later in indxpath.c */
			info->unique = index->indisunique;

			/*
			 * Estimate the index size.  If it's not a partial index, we lock
			 * the number-of-tuples estimate to equal the parent table; if it
			 * is partial then we have to use the same methods as we would for
			 * a table, except we can be sure that the index is not larger
			 * than the table.
			 */
			if (info->indpred == NIL)
			{
				info->pages = RelationGetNumberOfBlocks(indexRelation);
				info->tuples = rel->tuples;
			}
			else
			{
				estimate_rel_size(indexRelation, NULL,
								  &info->pages, &info->tuples);
				if (info->tuples > rel->tuples)
					info->tuples = rel->tuples;
			}

			index_close(indexRelation, NoLock);

			indexinfos = lcons(info, indexinfos);
		}

		list_free(indexoidlist);
	}

/*
 * lazy_truncate_heap - try to truncate off any empty pages at the end
 */
static void
lazy_truncate_heap(Relation onerel, LVRelStats *vacrelstats)
{
	BlockNumber old_rel_pages = vacrelstats->rel_pages;
	BlockNumber new_rel_pages;
	PGRUsage	ru0;

	pg_rusage_init(&ru0);

	/*
	 * We need full exclusive lock on the relation in order to do truncation.
	 * If we can't get it, give up rather than waiting --- we don't want to
	 * block other backends, and we don't want to deadlock (which is quite
	 * possible considering we already hold a lower-grade lock).
	 */
	if (!ConditionalLockRelation(onerel, AccessExclusiveLock))
		return;

	/*
	 * Now that we have exclusive lock, look to see if the rel has grown
	 * whilst we were vacuuming with non-exclusive lock.  If so, give up; the
	 * newly added pages presumably contain non-deletable tuples.
	 */
	new_rel_pages = RelationGetNumberOfBlocks(onerel);
	if (new_rel_pages != old_rel_pages)
	{
		/*
		 * Note: we intentionally don't update vacrelstats->rel_pages with the
		 * new rel size here.  If we did, it would amount to assuming that the
		 * new pages are empty, which is unlikely.	Leaving the numbers alone
		 * amounts to assuming that the new pages have the same tuple density
		 * as existing ones, which is less unlikely.
		 */
		UnlockRelation(onerel, AccessExclusiveLock);
		return;
	}

	/*
	 * Scan backwards from the end to verify that the end pages actually
	 * contain no tuples.  This is *necessary*, not optional, because other
	 * backends could have added tuples to these pages whilst we were
	 * vacuuming.
	 */
	new_rel_pages = count_nondeletable_pages(onerel, vacrelstats);

	if (new_rel_pages >= old_rel_pages)
	{
		/* can't do anything after all */
		UnlockRelation(onerel, AccessExclusiveLock);
		return;
	}

	/*
	 * Okay to truncate.
	 */
	RelationTruncate(onerel, new_rel_pages);

	/*
	 * We can release the exclusive lock as soon as we have truncated.	Other
	 * backends can't safely access the relation until they have processed the
	 * smgr invalidation that smgrtruncate sent out ... but that should happen
	 * as part of standard invalidation processing once they acquire lock on
	 * the relation.
	 */
	UnlockRelation(onerel, AccessExclusiveLock);

	/*
	 * Update statistics.  Here, it *is* correct to adjust rel_pages without
	 * also touching reltuples, since the tuple count wasn't changed by the
	 * truncation.
	 */
	vacrelstats->rel_pages = new_rel_pages;
	vacrelstats->pages_removed = old_rel_pages - new_rel_pages;

	ereport(elevel,
			(errmsg("\"%s\": truncated %u to %u pages",
					RelationGetRelationName(onerel),
					old_rel_pages, new_rel_pages),
			 errdetail("%s.",
					   pg_rusage_show(&ru0))));
}

/*
 * btvacuumscan --- scan the index for VACUUMing purposes
 *
 * This combines the functions of looking for leaf tuples that are deletable
 * according to the vacuum callback, looking for empty pages that can be
 * deleted, and looking for old deleted pages that can be recycled.  Both
 * btbulkdelete and btvacuumcleanup invoke this (the latter only if no
 * btbulkdelete call occurred).
 *
 * The caller is responsible for initially allocating/zeroing a stats struct
 * and for obtaining a vacuum cycle ID if necessary.
 */
static void
btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
			 IndexBulkDeleteCallback callback, void *callback_state,
			 BTCycleId cycleid)
{
	MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;

	Relation	rel = info->index;
	BTVacState	vstate;
	BlockNumber num_pages;
	BlockNumber blkno;
	bool		needLock;

	MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;

	/*
	 * Reset counts that will be incremented during the scan; needed in case
	 * of multiple scans during a single VACUUM command
	 */
	stats->num_index_tuples = 0;
	stats->pages_deleted = 0;

	/* Set up info to pass down to btvacuumpage */
	vstate.info = info;
	vstate.stats = stats;
	vstate.callback = callback;
	vstate.callback_state = callback_state;
	vstate.cycleid = cycleid;
	vstate.freePages = NULL;	/* temporarily */
	vstate.nFreePages = 0;
	vstate.maxFreePages = 0;
	vstate.totFreePages = 0;

	/* Create a temporary memory context to run _bt_pagedel in */
	vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
												  "_bt_pagedel",
												  ALLOCSET_DEFAULT_MINSIZE,
												  ALLOCSET_DEFAULT_INITSIZE,
												  ALLOCSET_DEFAULT_MAXSIZE);

	/*
	 * The outer loop iterates over all index pages except the metapage, in
	 * physical order (we hope the kernel will cooperate in providing
	 * read-ahead for speed).  It is critical that we visit all leaf pages,
	 * including ones added after we start the scan, else we might fail to
	 * delete some deletable tuples.  Hence, we must repeatedly check the
	 * relation length.  We must acquire the relation-extension lock while
	 * doing so to avoid a race condition: if someone else is extending the
	 * relation, there is a window where bufmgr/smgr have created a new
	 * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
	 * we manage to scan such a page here, we'll improperly assume it can be
	 * recycled.  Taking the lock synchronizes things enough to prevent a
	 * problem: either num_pages won't include the new page, or _bt_getbuf
	 * already has write lock on the buffer and it will be fully initialized
	 * before we can examine it.  (See also vacuumlazy.c, which has the same
	 * issue.)	Also, we need not worry if a page is added immediately after
	 * we look; the page splitting code already has write-lock on the left
	 * page before it adds a right page, so we must already have processed any
	 * tuples due to be moved into such a page.
	 *
	 * We can skip locking for new or temp relations, however, since no one
	 * else could be accessing them.
	 */
	needLock = !RELATION_IS_LOCAL(rel);

	blkno = BTREE_METAPAGE + 1;
	for (;;)
	{
		/* Get the current relation length */
		if (needLock)
			LockRelationForExtension(rel, ExclusiveLock);
		num_pages = RelationGetNumberOfBlocks(rel);
		if (needLock)
			UnlockRelationForExtension(rel, ExclusiveLock);

		/* Allocate freePages after we read num_pages the first time */
		if (vstate.freePages == NULL)
		{
			/* No point in remembering more than MaxFSMPages pages */
			vstate.maxFreePages = MaxFSMPages;
			if ((BlockNumber) vstate.maxFreePages > num_pages)
				vstate.maxFreePages = (int) num_pages;
			vstate.freePages = (BlockNumber *)
				palloc(vstate.maxFreePages * sizeof(BlockNumber));
		}

		/* Quit if we've scanned the whole relation */
		if (blkno >= num_pages)
//.........这里部分代码省略.........

/*
 *	btbuild() -- build a new btree index.
 */
IndexBuildResult *
btbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
	IndexBuildResult *result;
	double		reltuples;
	BTBuildState buildstate;

	buildstate.isUnique = indexInfo->ii_Unique;
	buildstate.haveDead = false;
	buildstate.heapRel = heap;
	buildstate.spool = NULL;
	buildstate.spool2 = NULL;
	buildstate.indtuples = 0;

#ifdef BTREE_BUILD_STATS
	if (log_btree_build_stats)
		ResetUsage();
#endif							/* BTREE_BUILD_STATS */

	/*
	 * We expect to be called exactly once for any index relation. If that's
	 * not the case, big trouble's what we have.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	buildstate.spool = _bt_spoolinit(heap, index, indexInfo->ii_Unique, false);

	/*
	 * If building a unique index, put dead tuples in a second spool to keep
	 * them out of the uniqueness check.
	 */
	if (indexInfo->ii_Unique)
		buildstate.spool2 = _bt_spoolinit(heap, index, false, true);

	/* do the heap scan */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
								   btbuildCallback, (void *) &buildstate);

	/* okay, all heap tuples are indexed */
	if (buildstate.spool2 && !buildstate.haveDead)
	{
		/* spool2 turns out to be unnecessary */
		_bt_spooldestroy(buildstate.spool2);
		buildstate.spool2 = NULL;
	}

	/*
	 * Finish the build by (1) completing the sort of the spool file, (2)
	 * inserting the sorted tuples into btree pages and (3) building the upper
	 * levels.
	 */
	_bt_leafbuild(buildstate.spool, buildstate.spool2);
	_bt_spooldestroy(buildstate.spool);
	if (buildstate.spool2)
		_bt_spooldestroy(buildstate.spool2);

#ifdef BTREE_BUILD_STATS
	if (log_btree_build_stats)
	{
		ShowUsage("BTREE BUILD STATS");
		ResetUsage();
	}
#endif							/* BTREE_BUILD_STATS */

	/*
	 * Return statistics
	 */
	result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));

	result->heap_tuples = reltuples;
	result->index_tuples = buildstate.indtuples;

	return result;
}

/*
 * For a newly inserted heap tid, check if an entry with this tid
 * already exists in a unique index.  If it does, abort the inserting
 * transaction.
 */
static void
_bt_validate_tid(Relation irel, ItemPointer h_tid)
{
	MIRROREDLOCK_BUFMGR_DECLARE;

	BlockNumber blkno;
	BlockNumber num_pages;
	Buffer buf;
	Page page;
	BTPageOpaque opaque;
	IndexTuple itup;
	OffsetNumber maxoff,
			minoff,
			offnum;

	elog(DEBUG1, "validating tid (%d,%d) for index (%s)",
		 ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
		 RelationGetRelationName(irel));

	blkno = BTREE_METAPAGE + 1;
	num_pages = RelationGetNumberOfBlocks(irel);

	MIRROREDLOCK_BUFMGR_LOCK;
	for (; blkno < num_pages; blkno++)
	{
		buf = ReadBuffer(irel, blkno);
		page = BufferGetPage(buf);
		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
		if (!PageIsNew(page))
			_bt_checkpage(irel, buf);
		if (P_ISLEAF(opaque))
		{
			minoff = P_FIRSTDATAKEY(opaque);
			maxoff = PageGetMaxOffsetNumber(page);
			for (offnum = minoff;
				 offnum <= maxoff;
				 offnum = OffsetNumberNext(offnum))
			{
				itup = (IndexTuple) PageGetItem(page,
												PageGetItemId(page, offnum));
				if (ItemPointerEquals(&itup->t_tid, h_tid))
				{
					Form_pg_attribute key_att = RelationGetDescr(irel)->attrs[0];
					Oid key = InvalidOid;
					bool isnull;
					if (key_att->atttypid == OIDOID)
					{
						key = DatumGetInt32(
								index_getattr(itup, 1, RelationGetDescr(irel), &isnull));
						elog(ERROR, "found tid (%d,%d), %s (%d) already in index (%s)",
							 ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
							 NameStr(key_att->attname), key, RelationGetRelationName(irel));
					}
					else
					{
						elog(ERROR, "found tid (%d,%d) already in index (%s)",
							 ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
							 RelationGetRelationName(irel));
					}
				}
			}
		}
		ReleaseBuffer(buf);
	}
	MIRROREDLOCK_BUFMGR_UNLOCK;
}