nbtpage.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * nbtpage.c
 *	  BTree-specific page management code for the Postgres btree access
 *	  method.
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/access/nbtree/nbtpage.c,v 1.106 2008/01/01 19:45:46 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 "access/transam.h"
#include "miscadmin.h"
#include "storage/freespace.h"
#include "storage/lmgr.h"
#include "utils/inval.h"


/*
 *	_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;

	/*
	 * Try to use previously-cached metapage data to find the root.  This
	 * normally saves one buffer access per index search, which is a very
	 * helpful savings in bufmgr traffic and hence contention.
	 */
	if (rel->rd_amcache != NULL)
	{
		metad = (BTMetaPageData *) rel->rd_amcache;
		/* We shouldn't have cached it if any of these fail */
		Assert(metad->btm_magic == BTREE_MAGIC);
		Assert(metad->btm_version == BTREE_VERSION);
		Assert(metad->btm_root != P_NONE);

		rootblkno = metad->btm_fastroot;
		Assert(rootblkno != P_NONE);
		rootlevel = metad->btm_fastlevel;

		rootbuf = _bt_getbuf(rel, rootblkno, BT_READ);
		rootpage = BufferGetPage(rootbuf);
		rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);

		/*
		 * Since the cache might be stale, we check the page more carefully
		 * here than normal.  We *must* check that it's not deleted. If it's
		 * not alone on its level, then we reject too --- this may be overly
		 * paranoid but better safe than sorry.  Note we don't check P_ISROOT,
		 * because that's not set in a "fast root".
		 */
		if (!P_IGNORE(rootopaque) &&
			rootopaque->btpo.level == rootlevel &&
			P_LEFTMOST(rootopaque) &&
			P_RIGHTMOST(rootopaque))
		{
			/* OK, accept cached page as the root */
			return rootbuf;
		}
		_bt_relbuf(rel, rootbuf);
		/* Cache is stale, throw it away */
		if (rel->rd_amcache)
			pfree(rel->rd_amcache);
		rel->rd_amcache = NULL;
	}

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

		MarkBufferDirty(rootbuf);
		MarkBufferDirty(metabuf);

		/* 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();

		/*
		 * Send out relcache inval for metapage change (probably unnecessary
		 * here, but let's be safe).
		 */
		CacheInvalidateRelcache(rel);

		/*
		 * 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, release lock on it */
		_bt_relbuf(rel, metabuf);
	}
	else
	{
		rootblkno = metad->btm_fastroot;
		Assert(rootblkno != P_NONE);
		rootlevel = metad->btm_fastlevel;

		/*
		 * Cache the metapage data for next time
		 */
		rel->rd_amcache = MemoryContextAlloc(rel->rd_indexcxt,
											 sizeof(BTMetaPageData));
		memcpy(rel->rd_amcache, metad, sizeof(BTMetaPageData));

		/*
		 * 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 index \"%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 index \"%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;

	/*
	 * We don't try to use cached metapage data here, since (a) this path is
	 * not performance-critical, and (b) if we are here it suggests our cache
	 * is out-of-date anyway.  In light of point (b), it's probably safest to
	 * actively flush any cached metapage info.
	 */
	if (rel->rd_amcache)
		pfree(rel->rd_amcache);
	rel->rd_amcache = NULL;

	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
	 */
	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 index \"%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 index \"%s\" has level %u, expected %u",
			 rootblkno, RelationGetRelationName(rel),
			 rootopaque->btpo.level, rootlevel);

	return rootbuf;
}

/*
 *	_bt_checkpage() -- Verify that a freshly-read page looks sane.
 */
void
_bt_checkpage(Relation rel, Buffer buf)
{
	Page		page = BufferGetPage(buf);

	/*
	 * ReadBuffer verifies that every newly-read page passes
	 * PageHeaderIsValid, which means it either contains a reasonably sane
	 * page header or is all-zero.	We have to defend against the all-zero
	 * case, however.
	 */
	if (PageIsNew(page))
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
			 errmsg("index \"%s\" contains unexpected zero page at block %u",
					RelationGetRelationName(rel),
					BufferGetBlockNumber(buf)),
				 errhint("Please REINDEX it.")));

	/*
	 * Additionally check that the special area looks sane.
	 */
	if (((PageHeader) (page))->pd_special !=
		(BLCKSZ - MAXALIGN(sizeof(BTPageOpaqueData))))
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("index \"%s\" contains corrupted page at block %u",
						RelationGetRelationName(rel),
						BufferGetBlockNumber(buf)),