bufpage.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*-------------------------------------------------------------------------
 *
 * bufpage.c
 *	  POSTGRES standard buffer page code.
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/storage/page/bufpage.c,v 1.67.2.1 2005/11/22 18:23:19 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "storage/bufpage.h"


/* ----------------------------------------------------------------
 *						Page support functions
 * ----------------------------------------------------------------
 */

/*
 * PageInit
 *		Initializes the contents of a page.
 */
void
PageInit(Page page, Size pageSize, Size specialSize)
{
	PageHeader	p = (PageHeader) page;

	specialSize = MAXALIGN(specialSize);

	Assert(pageSize == BLCKSZ);
	Assert(pageSize > specialSize + SizeOfPageHeaderData);

	/* Make sure all fields of page are zero, as well as unused space */
	MemSet(p, 0, pageSize);

	p->pd_lower = SizeOfPageHeaderData;
	p->pd_upper = pageSize - specialSize;
	p->pd_special = pageSize - specialSize;
	PageSetPageSizeAndVersion(page, pageSize, PG_PAGE_LAYOUT_VERSION);
}


/*
 * PageHeaderIsValid
 *		Check that the header fields of a page appear valid.
 *
 * This is called when a page has just been read in from disk.	The idea is
 * to cheaply detect trashed pages before we go nuts following bogus item
 * pointers, testing invalid transaction identifiers, etc.
 *
 * It turns out to be necessary to allow zeroed pages here too.  Even though
 * this routine is *not* called when deliberately adding a page to a relation,
 * there are scenarios in which a zeroed page might be found in a table.
 * (Example: a backend extends a relation, then crashes before it can write
 * any WAL entry about the new page.  The kernel will already have the
 * zeroed page in the file, and it will stay that way after restart.)  So we
 * allow zeroed pages here, and are careful that the page access macros
 * treat such a page as empty and without free space.  Eventually, VACUUM
 * will clean up such a page and make it usable.
 */
bool
PageHeaderIsValid(PageHeader page)
{
	char	   *pagebytes;
	int			i;

	/* Check normal case */
	if (PageGetPageSize(page) == BLCKSZ &&
		PageGetPageLayoutVersion(page) == PG_PAGE_LAYOUT_VERSION &&
		page->pd_lower >= SizeOfPageHeaderData &&
		page->pd_lower <= page->pd_upper &&
		page->pd_upper <= page->pd_special &&
		page->pd_special <= BLCKSZ &&
		page->pd_special == MAXALIGN(page->pd_special))
		return true;

	/* Check all-zeroes case */
	pagebytes = (char *) page;
	for (i = 0; i < BLCKSZ; i++)
	{
		if (pagebytes[i] != 0)
			return false;
	}
	return true;
}


/*
 *	PageAddItem
 *
 *	Add an item to a page.	Return value is offset at which it was
 *	inserted, or InvalidOffsetNumber if there's not room to insert.
 *
 *	If offsetNumber is valid and <= current max offset in the page,
 *	insert item into the array at that position by shuffling ItemId's
 *	down to make room.
 *	If offsetNumber is not valid, then assign one by finding the first
 *	one that is both unused and deallocated.
 *
 *	!!! EREPORT(ERROR) IS DISALLOWED HERE !!!
 */
OffsetNumber
PageAddItem(Page page,
			Item item,
			Size size,
			OffsetNumber offsetNumber,
			ItemIdFlags flags)
{
	PageHeader	phdr = (PageHeader) page;
	Size		alignedSize;
	int			lower;
	int			upper;
	ItemId		itemId;
	OffsetNumber limit;
	bool		needshuffle = false;
	bool		overwritemode = (flags & OverwritePageMode) != 0;

	flags &= ~OverwritePageMode;

	/*
	 * Be wary about corrupted page pointers
	 */
	if (phdr->pd_lower < SizeOfPageHeaderData ||
		phdr->pd_lower > phdr->pd_upper ||
		phdr->pd_upper > phdr->pd_special ||
		phdr->pd_special > BLCKSZ)
		ereport(PANIC,
				(errcode(ERRCODE_DATA_CORRUPTED),
				 errmsg("corrupted page pointers: lower = %u, upper = %u, special = %u",
						phdr->pd_lower, phdr->pd_upper, phdr->pd_special)));

	/*
	 * Select offsetNumber to place the new item at
	 */
	limit = OffsetNumberNext(PageGetMaxOffsetNumber(page));

	/* was offsetNumber passed in? */
	if (OffsetNumberIsValid(offsetNumber))
	{
		/* yes, check it */
		if (overwritemode)
		{
			if (offsetNumber < limit)
			{
				itemId = PageGetItemId(phdr, offsetNumber);
				if (ItemIdIsUsed(itemId) || ItemIdGetLength(itemId) != 0)
				{
					elog(WARNING, "will not overwrite a used ItemId");
					return InvalidOffsetNumber;
				}
			}
		}
		else
		{
			if (offsetNumber < limit)
				needshuffle = true;		/* need to move existing linp's */
		}
	}
	else
	{
		/* offsetNumber was not passed in, so find a free slot */
		/* look for "recyclable" (unused & deallocated) ItemId */
		for (offsetNumber = 1; offsetNumber < limit; offsetNumber++)
		{
			itemId = PageGetItemId(phdr, offsetNumber);
			if (!ItemIdIsUsed(itemId) && ItemIdGetLength(itemId) == 0)
				break;
		}
		/* if no free slot, we'll put it at limit (1st open slot) */
	}

	if (offsetNumber > limit)
	{
		elog(WARNING, "specified item offset is too large");
		return InvalidOffsetNumber;
	}

	/*
	 * Compute new lower and upper pointers for page, see if it'll fit.
	 *
	 * Note: do arithmetic as signed ints, to avoid mistakes if, say,
	 * alignedSize > pd_upper.
	 */
	if (offsetNumber == limit || needshuffle)
		lower = phdr->pd_lower + sizeof(ItemIdData);
	else
		lower = phdr->pd_lower;

	alignedSize = MAXALIGN(size);

	upper = (int) phdr->pd_upper - (int) alignedSize;

	if (lower > upper)
		return InvalidOffsetNumber;

	/*
	 * OK to insert the item.  First, shuffle the existing pointers if needed.
	 */
	itemId = PageGetItemId(phdr, offsetNumber);

	if (needshuffle)
		memmove(itemId + 1, itemId,
				(limit - offsetNumber) * sizeof(ItemIdData));

	/* set the item pointer */
	itemId->lp_off = upper;
	itemId->lp_len = size;
	itemId->lp_flags = flags;

	/* copy the item's data onto the page */
	memcpy((char *) page + upper, item, size);

	/* adjust page header */
	phdr->pd_lower = (LocationIndex) lower;
	phdr->pd_upper = (LocationIndex) upper;

	return offsetNumber;
}

/*
 * PageGetTempPage
 *		Get a temporary page in local memory for special processing
 */
Page
PageGetTempPage(Page page, Size specialSize)
{
	Size		pageSize;
	Size		size;
	Page		temp;
	PageHeader	thdr;

	pageSize = PageGetPageSize(page);
	temp = (Page) palloc(pageSize);
	thdr = (PageHeader) temp;

	/* copy old page in */
	memcpy(temp, page, pageSize);

	/* clear out the middle */
	size = pageSize - SizeOfPageHeaderData;
	size -= MAXALIGN(specialSize);
	MemSet(PageGetContents(thdr), 0, size);

	/* set high, low water marks */
	thdr->pd_lower = SizeOfPageHeaderData;
	thdr->pd_upper = pageSize - MAXALIGN(specialSize);

	return temp;
}

/*
 * PageRestoreTempPage
 *		Copy temporary page back to permanent page after special processing
 *		and release the temporary page.
 */
void
PageRestoreTempPage(Page tempPage, Page oldPage)
{
	Size		pageSize;

	pageSize = PageGetPageSize(tempPage);
	memcpy((char *) oldPage, (char *) tempPage, pageSize);

	pfree(tempPage);
}

/*
 * sorting support for PageRepairFragmentation and PageIndexMultiDelete
 */
typedef struct itemIdSortData
{
	int			offsetindex;	/* linp array index */
	int			itemoff;		/* page offset of item data */
	Size		alignedlen;		/* MAXALIGN(item data len) */
	ItemIdData	olditemid;		/* used only in PageIndexMultiDelete */
} itemIdSortData;
typedef itemIdSortData *itemIdSort;

static int
itemoffcompare(const void *itemidp1, const void *itemidp2)
{
	/* Sort in decreasing itemoff order */
	return ((itemIdSort) itemidp2)->itemoff -
		((itemIdSort) itemidp1)->itemoff;
}

/*
 * PageRepairFragmentation
 *
 * Frees fragmented space on a page.
 * It doesn't remove unused line pointers! Please don't change this.
 *
 * This routine is usable for heap pages only, but see PageIndexMultiDelete.
 *
 * Returns number of unused line pointers on page.	If "unused" is not NULL
 * then the unused[] array is filled with indexes of unused line pointers.
 */
int
PageRepairFragmentation(Page page, OffsetNumber *unused)
{
	Offset		pd_lower = ((PageHeader) page)->pd_lower;
	Offset		pd_upper = ((PageHeader) page)->pd_upper;
	Offset		pd_special = ((PageHeader) page)->pd_special;
	itemIdSort	itemidbase,
				itemidptr;
	ItemId		lp;
	int			nline,
				nused;
	int			i;
	Size		totallen;
	Offset		upper;

	/*
	 * It's worth the trouble to be more paranoid here than in most places,
	 * because we are about to reshuffle data in (what is usually) a shared
	 * disk buffer.  If we aren't careful then corrupted pointers, lengths,
	 * etc could cause us to clobber adjacent disk buffers, spreading the data
	 * loss further.  So, check everything.
	 */
	if (pd_lower < SizeOfPageHeaderData ||
		pd_lower > pd_upper ||
		pd_upper > pd_special ||
		pd_special > BLCKSZ ||
		pd_special != MAXALIGN(pd_special))
		ereport(ERROR,
				(errcode(ERRCODE_DATA_CORRUPTED),
				 errmsg("corrupted page pointers: lower = %u, upper = %u, special = %u",
						pd_lower, pd_upper, pd_special)));

	nline = PageGetMaxOffsetNumber(page);
	nused = 0;
	for (i = 0; i < nline; i++)