nbtpage.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*-------------------------------------------------------------------------
 *
 * nbtpage.c
 *	  BTree-specific page management code for the Postgres btree access
 *	  method.
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/access/nbtree/nbtpage.c,v 1.88.2.1 2005/11/22 18:23:04 momjian Exp $
 *
 *	NOTES
 *	   Postgres btree pages look like ordinary relation pages.	The opaque
 *	   data at high addresses includes pointers to left and right siblings
 *	   and flag data describing page state.  The first page in a btree, page
 *	   zero, is special -- it stores meta-information describing the tree.
 *	   Pages one and higher store the actual tree data.
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/nbtree.h"
#include "miscadmin.h"
#include "storage/freespace.h"
#include "storage/lmgr.h"


/*
 *	_bt_metapinit() -- Initialize the metadata page of a new btree.
 *
 * Note: this is actually not used for standard btree index building;
 * nbtsort.c prefers not to make the metadata page valid until completion
 * of build.
 *
 * Note: there's no real need for any locking here.  Since the transaction
 * creating the index hasn't committed yet, no one else can even see the index
 * much less be trying to use it.  (In a REINDEX-in-place scenario, that's
 * not true, but we assume the caller holds sufficient locks on the index.)
 */
void
_bt_metapinit(Relation rel)
{
	Buffer		buf;
	Page		pg;
	BTMetaPageData *metad;

	if (RelationGetNumberOfBlocks(rel) != 0)
		elog(ERROR, "cannot initialize non-empty btree index \"%s\"",
			 RelationGetRelationName(rel));

	buf = ReadBuffer(rel, P_NEW);
	Assert(BufferGetBlockNumber(buf) == BTREE_METAPAGE);
	pg = BufferGetPage(buf);

	_bt_initmetapage(pg, P_NONE, 0);
	metad = BTPageGetMeta(pg);

	/* NO ELOG(ERROR) from here till newmeta op is logged */
	START_CRIT_SECTION();

	/* XLOG stuff */
	if (!rel->rd_istemp)
	{
		xl_btree_newmeta xlrec;
		XLogRecPtr	recptr;
		XLogRecData rdata[1];

		xlrec.node = rel->rd_node;
		xlrec.meta.root = metad->btm_root;
		xlrec.meta.level = metad->btm_level;
		xlrec.meta.fastroot = metad->btm_fastroot;
		xlrec.meta.fastlevel = metad->btm_fastlevel;

		rdata[0].data = (char *) &xlrec;
		rdata[0].len = SizeOfBtreeNewmeta;
		rdata[0].buffer = InvalidBuffer;
		rdata[0].next = NULL;

		recptr = XLogInsert(RM_BTREE_ID,
							XLOG_BTREE_NEWMETA,
							rdata);

		PageSetLSN(pg, recptr);
		PageSetTLI(pg, ThisTimeLineID);
	}

	END_CRIT_SECTION();

	WriteBuffer(buf);
}

/*
 *	_bt_initmetapage() -- Fill a page buffer with a correct metapage image
 */
void
_bt_initmetapage(Page page, BlockNumber rootbknum, uint32 level)
{
	BTMetaPageData *metad;
	BTPageOpaque metaopaque;

	_bt_pageinit(page, BLCKSZ);

	metad = BTPageGetMeta(page);
	metad->btm_magic = BTREE_MAGIC;
	metad->btm_version = BTREE_VERSION;
	metad->btm_root = rootbknum;
	metad->btm_level = level;
	metad->btm_fastroot = rootbknum;
	metad->btm_fastlevel = level;

	metaopaque = (BTPageOpaque) PageGetSpecialPointer(page);
	metaopaque->btpo_flags = BTP_META;

	/*
	 * Set pd_lower just past the end of the metadata.	This is not essential
	 * but it makes the page look compressible to xlog.c.
	 */
	((PageHeader) page)->pd_lower =
		((char *) metad + sizeof(BTMetaPageData)) - (char *) page;
}

/*
 *	_bt_getroot() -- Get the root page of the btree.
 *
 *		Since the root page can move around the btree file, we have to read
 *		its location from the metadata page, and then read the root page
 *		itself.  If no root page exists yet, we have to create one.  The
 *		standard class of race conditions exists here; I think I covered
 *		them all in the Hopi Indian rain dance of lock requests below.
 *
 *		The access type parameter (BT_READ or BT_WRITE) controls whether
 *		a new root page will be created or not.  If access = BT_READ,
 *		and no root page exists, we just return InvalidBuffer.	For
 *		BT_WRITE, we try to create the root page if it doesn't exist.
 *		NOTE that the returned root page will have only a read lock set
 *		on it even if access = BT_WRITE!
 *
 *		The returned page is not necessarily the true root --- it could be
 *		a "fast root" (a page that is alone in its level due to deletions).
 *		Also, if the root page is split while we are "in flight" to it,
 *		what we will return is the old root, which is now just the leftmost
 *		page on a probably-not-very-wide level.  For most purposes this is
 *		as good as or better than the true root, so we do not bother to
 *		insist on finding the true root.  We do, however, guarantee to
 *		return a live (not deleted or half-dead) page.
 *
 *		On successful return, the root page is pinned and read-locked.
 *		The metadata page is not locked or pinned on exit.
 */
Buffer
_bt_getroot(Relation rel, int access)
{
	Buffer		metabuf;
	Page		metapg;
	BTPageOpaque metaopaque;
	Buffer		rootbuf;
	Page		rootpage;
	BTPageOpaque rootopaque;
	BlockNumber rootblkno;
	uint32		rootlevel;
	BTMetaPageData *metad;

	metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_READ);
	metapg = BufferGetPage(metabuf);
	metaopaque = (BTPageOpaque) PageGetSpecialPointer(metapg);
	metad = BTPageGetMeta(metapg);

	/* sanity-check the metapage */
	if (!(metaopaque->btpo_flags & BTP_META) ||
		metad->btm_magic != BTREE_MAGIC)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("index \"%s\" is not a btree",
						RelationGetRelationName(rel))));

	if (metad->btm_version != BTREE_VERSION)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("version mismatch in index \"%s\": file version %d, code version %d",
						RelationGetRelationName(rel),
						metad->btm_version, BTREE_VERSION)));

	/* if no root page initialized yet, do it */
	if (metad->btm_root == P_NONE)
	{
		/* If access = BT_READ, caller doesn't want us to create root yet */
		if (access == BT_READ)
		{
			_bt_relbuf(rel, metabuf);
			return InvalidBuffer;
		}

		/* trade in our read lock for a write lock */
		LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
		LockBuffer(metabuf, BT_WRITE);

		/*
		 * Race condition:	if someone else initialized the metadata between
		 * the time we released the read lock and acquired the write lock, we
		 * must avoid doing it again.
		 */
		if (metad->btm_root != P_NONE)
		{
			/*
			 * Metadata initialized by someone else.  In order to guarantee no
			 * deadlocks, we have to release the metadata page and start all
			 * over again.	(Is that really true? But it's hardly worth trying
			 * to optimize this case.)
			 */
			_bt_relbuf(rel, metabuf);
			return _bt_getroot(rel, access);
		}

		/*
		 * Get, initialize, write, and leave a lock of the appropriate type on
		 * the new root page.  Since this is the first page in the tree, it's
		 * a leaf as well as the root.
		 */
		rootbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
		rootblkno = BufferGetBlockNumber(rootbuf);
		rootpage = BufferGetPage(rootbuf);

		_bt_pageinit(rootpage, BufferGetPageSize(rootbuf));
		rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
		rootopaque->btpo_prev = rootopaque->btpo_next = P_NONE;
		rootopaque->btpo_flags = (BTP_LEAF | BTP_ROOT);
		rootopaque->btpo.level = 0;

		/* NO ELOG(ERROR) till meta is updated */
		START_CRIT_SECTION();

		metad->btm_root = rootblkno;
		metad->btm_level = 0;
		metad->btm_fastroot = rootblkno;
		metad->btm_fastlevel = 0;

		/* XLOG stuff */
		if (!rel->rd_istemp)
		{
			xl_btree_newroot xlrec;
			XLogRecPtr	recptr;
			XLogRecData rdata;

			xlrec.node = rel->rd_node;
			xlrec.rootblk = rootblkno;
			xlrec.level = 0;

			rdata.data = (char *) &xlrec;
			rdata.len = SizeOfBtreeNewroot;
			rdata.buffer = InvalidBuffer;
			rdata.next = NULL;

			recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT, &rdata);

			PageSetLSN(rootpage, recptr);
			PageSetTLI(rootpage, ThisTimeLineID);
			PageSetLSN(metapg, recptr);
			PageSetTLI(metapg, ThisTimeLineID);
		}

		END_CRIT_SECTION();

		_bt_wrtnorelbuf(rel, rootbuf);

		/*
		 * swap root write lock for read lock.	There is no danger of anyone
		 * else accessing the new root page while it's unlocked, since no one
		 * else knows where it is yet.
		 */
		LockBuffer(rootbuf, BUFFER_LOCK_UNLOCK);
		LockBuffer(rootbuf, BT_READ);

		/* okay, metadata is correct, write and release it */
		_bt_wrtbuf(rel, metabuf);
	}
	else
	{
		rootblkno = metad->btm_fastroot;
		Assert(rootblkno != P_NONE);
		rootlevel = metad->btm_fastlevel;

		/*
		 * We are done with the metapage; arrange to release it via first
		 * _bt_relandgetbuf call
		 */
		rootbuf = metabuf;

		for (;;)
		{
			rootbuf = _bt_relandgetbuf(rel, rootbuf, rootblkno, BT_READ);
			rootpage = BufferGetPage(rootbuf);
			rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);

			if (!P_IGNORE(rootopaque))
				break;

			/* it's dead, Jim.  step right one page */
			if (P_RIGHTMOST(rootopaque))
				elog(ERROR, "no live root page found in \"%s\"",
					 RelationGetRelationName(rel));
			rootblkno = rootopaque->btpo_next;
		}

		/* Note: can't check btpo.level on deleted pages */
		if (rootopaque->btpo.level != rootlevel)
			elog(ERROR, "root page %u of \"%s\" has level %u, expected %u",
				 rootblkno, RelationGetRelationName(rel),
				 rootopaque->btpo.level, rootlevel);
	}

	/*
	 * By here, we have a pin and read lock on the root page, and no lock set
	 * on the metadata page.  Return the root page's buffer.
	 */
	return rootbuf;
}

/*
 *	_bt_gettrueroot() -- Get the true root page of the btree.
 *
 *		This is the same as the BT_READ case of _bt_getroot(), except
 *		we follow the true-root link not the fast-root link.
 *
 * By the time we acquire lock on the root page, it might have been split and
 * not be the true root anymore.  This is okay for the present uses of this
 * routine; we only really need to be able to move up at least one tree level
 * from whatever non-root page we were at.	If we ever do need to lock the
 * one true root page, we could loop here, re-reading the metapage on each
 * failure.  (Note that it wouldn't do to hold the lock on the metapage while
 * moving to the root --- that'd deadlock against any concurrent root split.)
 */
Buffer
_bt_gettrueroot(Relation rel)
{
	Buffer		metabuf;
	Page		metapg;
	BTPageOpaque metaopaque;
	Buffer		rootbuf;
	Page		rootpage;
	BTPageOpaque rootopaque;
	BlockNumber rootblkno;
	uint32		rootlevel;
	BTMetaPageData *metad;

	metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_READ);
	metapg = BufferGetPage(metabuf);
	metaopaque = (BTPageOpaque) PageGetSpecialPointer(metapg);
	metad = BTPageGetMeta(metapg);

	if (!(metaopaque->btpo_flags & BTP_META) ||
		metad->btm_magic != BTREE_MAGIC)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("index \"%s\" is not a btree",
						RelationGetRelationName(rel))));

	if (metad->btm_version != BTREE_VERSION)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("version mismatch in index \"%s\": file version %d, code version %d",
						RelationGetRelationName(rel),
						metad->btm_version, BTREE_VERSION)));

	/* if no root page initialized yet, fail */
	if (metad->btm_root == P_NONE)
	{
		_bt_relbuf(rel, metabuf);
		return InvalidBuffer;
	}

	rootblkno = metad->btm_root;
	rootlevel = metad->btm_level;

	/*
	 * We are done with the metapage; arrange to release it via first
	 * _bt_relandgetbuf call
	 */