nbtxlog.c File Reference

#include "postgres.h"
#include "access/bufmask.h"
#include "access/nbtree.h"
#include "access/nbtxlog.h"
#include "access/transam.h"
#include "access/xlog.h"
#include "access/xlogutils.h"
#include "miscadmin.h"
#include "storage/procarray.h"

Include dependency graph for nbtxlog.c:

Go to the source code of this file.

Functions
static void	_bt_restore_page (Page page, char *from, int len)
static void	_bt_restore_meta (XLogReaderState *record, uint8 block_id)
static void	_bt_clear_incomplete_split (XLogReaderState *record, uint8 block_id)
static void	btree_xlog_insert (bool isleaf, bool ismeta, XLogReaderState *record)
static void	btree_xlog_split (bool onleft, XLogReaderState *record)
static void	btree_xlog_vacuum (XLogReaderState *record)
static void	btree_xlog_delete (XLogReaderState *record)
static void	btree_xlog_mark_page_halfdead (uint8 info, XLogReaderState *record)
static void	btree_xlog_unlink_page (uint8 info, XLogReaderState *record)
static void	btree_xlog_newroot (XLogReaderState *record)
static void	btree_xlog_reuse_page (XLogReaderState *record)
void	btree_redo (XLogReaderState *record)
void	btree_mask (char *pagedata, BlockNumber blkno)

Function Documentation

_bt_clear_incomplete_split()

static void _bt_clear_incomplete_split ( XLogReaderState *  record, uint8  block_id  )

static

Definition at line 138 of file nbtxlog.c.

References Assert, BLK_NEEDS_REDO, BTP_INCOMPLETE_SPLIT, BTPageOpaqueData::btpo_flags, buf, BufferGetPage, BufferIsValid, XLogReaderState::EndRecPtr, MarkBufferDirty(), P_INCOMPLETE_SPLIT, PageGetSpecialPointer, PageSetLSN, UnlockReleaseBuffer(), and XLogReadBufferForRedo().

Referenced by btree_xlog_insert(), btree_xlog_newroot(), and btree_xlog_split().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    Buffer      buf;

    if (XLogReadBufferForRedo(record, block_id, &buf) == BLK_NEEDS_REDO)
    {
        Page        page = (Page) BufferGetPage(buf);
        BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);

        Assert(P_INCOMPLETE_SPLIT(pageop));
        pageop->btpo_flags &= ~BTP_INCOMPLETE_SPLIT;

        PageSetLSN(page, lsn);
        MarkBufferDirty(buf);
    }
    if (BufferIsValid(buf))
        UnlockReleaseBuffer(buf);
}

_bt_restore_meta()

static void _bt_restore_meta ( XLogReaderState *  record, uint8  block_id  )

static

Definition at line 82 of file nbtxlog.c.

References _bt_pageinit(), Assert, BTMetaPageData::btm_fastlevel, BTMetaPageData::btm_fastroot, BTMetaPageData::btm_last_cleanup_num_heap_tuples, BTMetaPageData::btm_level, BTMetaPageData::btm_magic, BTMetaPageData::btm_oldest_btpo_xact, BTMetaPageData::btm_root, BTMetaPageData::btm_version, BTP_META, BTPageGetMeta, BTPageOpaqueData::btpo_flags, BTREE_MAGIC, BTREE_METAPAGE, BTREE_NOVAC_VERSION, BufferGetBlockNumber(), BufferGetPage, BufferGetPageSize, XLogReaderState::EndRecPtr, xl_btree_metadata::fastlevel, xl_btree_metadata::fastroot, xl_btree_metadata::last_cleanup_num_heap_tuples, xl_btree_metadata::level, MarkBufferDirty(), xl_btree_metadata::oldest_btpo_xact, PageGetSpecialPointer, PageSetLSN, xl_btree_metadata::root, UnlockReleaseBuffer(), xl_btree_metadata::version, XLogInitBufferForRedo(), and XLogRecGetBlockData().

Referenced by btree_redo(), btree_xlog_insert(), btree_xlog_newroot(), and btree_xlog_unlink_page().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    Buffer      metabuf;
    Page        metapg;
    BTMetaPageData *md;
    BTPageOpaque pageop;
    xl_btree_metadata *xlrec;
    char       *ptr;
    Size        len;

    metabuf = XLogInitBufferForRedo(record, block_id);
    ptr = XLogRecGetBlockData(record, block_id, &len);

    Assert(len == sizeof(xl_btree_metadata));
    Assert(BufferGetBlockNumber(metabuf) == BTREE_METAPAGE);
    xlrec = (xl_btree_metadata *) ptr;
    metapg = BufferGetPage(metabuf);

    _bt_pageinit(metapg, BufferGetPageSize(metabuf));

    md = BTPageGetMeta(metapg);
    md->btm_magic = BTREE_MAGIC;
    md->btm_version = xlrec->version;
    md->btm_root = xlrec->root;
    md->btm_level = xlrec->level;
    md->btm_fastroot = xlrec->fastroot;
    md->btm_fastlevel = xlrec->fastlevel;
    /* Cannot log BTREE_MIN_VERSION index metapage without upgrade */
    Assert(md->btm_version >= BTREE_NOVAC_VERSION);
    md->btm_oldest_btpo_xact = xlrec->oldest_btpo_xact;
    md->btm_last_cleanup_num_heap_tuples = xlrec->last_cleanup_num_heap_tuples;

    pageop = (BTPageOpaque) PageGetSpecialPointer(metapg);
    pageop->btpo_flags = BTP_META;

    /*
     * Set pd_lower just past the end of the metadata.  This is essential,
     * because without doing so, metadata will be lost if xlog.c compresses
     * the page.
     */
    ((PageHeader) metapg)->pd_lower =
        ((char *) md + sizeof(BTMetaPageData)) - (char *) metapg;

    PageSetLSN(metapg, lsn);
    MarkBufferDirty(metabuf);
    UnlockReleaseBuffer(metabuf);
}

_bt_restore_page()

static void _bt_restore_page ( Page  page, char *  from, int  len  )

static

Definition at line 35 of file nbtxlog.c.

References elog, i, IndexTupleSize, InvalidOffsetNumber, MAXALIGN, MaxIndexTuplesPerPage, PageAddItem, and PANIC.

Referenced by btree_xlog_newroot(), and btree_xlog_split().

{
    IndexTupleData itupdata;
    Size        itemsz;
    char       *end = from + len;
    Item        items[MaxIndexTuplesPerPage];
    uint16      itemsizes[MaxIndexTuplesPerPage];
    int         i;
    int         nitems;

    /*
     * To get the items back in the original order, we add them to the page in
     * reverse.  To figure out where one tuple ends and another begins, we
     * have to scan them in forward order first.
     */
    i = 0;
    while (from < end)
    {
        /*
         * As we step through the items, 'from' won't always be properly
         * aligned, so we need to use memcpy().  Further, we use Item (which
         * is just a char*) here for our items array for the same reason;
         * wouldn't want the compiler or anyone thinking that an item is
         * aligned when it isn't.
         */
        memcpy(&itupdata, from, sizeof(IndexTupleData));
        itemsz = IndexTupleSize(&itupdata);
        itemsz = MAXALIGN(itemsz);

        items[i] = (Item) from;
        itemsizes[i] = itemsz;
        i++;

        from += itemsz;
    }
    nitems = i;

    for (i = nitems - 1; i >= 0; i--)
    {
        if (PageAddItem(page, items[i], itemsizes[i], nitems - i,
                        false, false) == InvalidOffsetNumber)
            elog(PANIC, "_bt_restore_page: cannot add item to page");
        from += itemsz;
    }
}

btree_mask()

void btree_mask	(	char *	pagedata,
		BlockNumber	blkno
	)

Definition at line 872 of file nbtxlog.c.

References BTP_HAS_GARBAGE, BTP_SPLIT_END, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, mask_lp_flags(), mask_page_content(), mask_page_hint_bits(), mask_page_lsn_and_checksum(), mask_unused_space(), P_ISDELETED, P_ISLEAF, and PageGetSpecialPointer.

{
    Page        page = (Page) pagedata;
    BTPageOpaque maskopaq;

    mask_page_lsn_and_checksum(page);

    mask_page_hint_bits(page);
    mask_unused_space(page);

    maskopaq = (BTPageOpaque) PageGetSpecialPointer(page);

    if (P_ISDELETED(maskopaq))
    {
        /*
         * Mask page content on a DELETED page since it will be re-initialized
         * during replay. See btree_xlog_unlink_page() for details.
         */
        mask_page_content(page);
    }
    else if (P_ISLEAF(maskopaq))
    {
        /*
         * In btree leaf pages, it is possible to modify the LP_FLAGS without
         * emitting any WAL record. Hence, mask the line pointer flags. See
         * _bt_killitems(), _bt_check_unique() for details.
         */
        mask_lp_flags(page);
    }

    /*
     * BTP_HAS_GARBAGE is just an un-logged hint bit. So, mask it. See
     * _bt_killitems(), _bt_check_unique() for details.
     */
    maskopaq->btpo_flags &= ~BTP_HAS_GARBAGE;

    /*
     * During replay of a btree page split, we don't set the BTP_SPLIT_END
     * flag of the right sibling and initialize the cycle_id to 0 for the same
     * page. See btree_xlog_split() for details.
     */
    maskopaq->btpo_flags &= ~BTP_SPLIT_END;
    maskopaq->btpo_cycleid = 0;
}

btree_redo()

void btree_redo

(

XLogReaderState *

record

)

Definition at line 820 of file nbtxlog.c.

References _bt_restore_meta(), btree_xlog_delete(), btree_xlog_insert(), btree_xlog_mark_page_halfdead(), btree_xlog_newroot(), btree_xlog_reuse_page(), btree_xlog_split(), btree_xlog_unlink_page(), btree_xlog_vacuum(), elog, PANIC, XLOG_BTREE_DELETE, XLOG_BTREE_INSERT_LEAF, XLOG_BTREE_INSERT_META, XLOG_BTREE_INSERT_UPPER, XLOG_BTREE_MARK_PAGE_HALFDEAD, XLOG_BTREE_META_CLEANUP, XLOG_BTREE_NEWROOT, XLOG_BTREE_REUSE_PAGE, XLOG_BTREE_SPLIT_L, XLOG_BTREE_SPLIT_R, XLOG_BTREE_UNLINK_PAGE, XLOG_BTREE_UNLINK_PAGE_META, XLOG_BTREE_VACUUM, XLogRecGetInfo, and XLR_INFO_MASK.

{
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;

    switch (info)
    {
        case XLOG_BTREE_INSERT_LEAF:
            btree_xlog_insert(true, false, record);
            break;
        case XLOG_BTREE_INSERT_UPPER:
            btree_xlog_insert(false, false, record);
            break;
        case XLOG_BTREE_INSERT_META:
            btree_xlog_insert(false, true, record);
            break;
        case XLOG_BTREE_SPLIT_L:
            btree_xlog_split(true, record);
            break;
        case XLOG_BTREE_SPLIT_R:
            btree_xlog_split(false, record);
            break;
        case XLOG_BTREE_VACUUM:
            btree_xlog_vacuum(record);
            break;
        case XLOG_BTREE_DELETE:
            btree_xlog_delete(record);
            break;
        case XLOG_BTREE_MARK_PAGE_HALFDEAD:
            btree_xlog_mark_page_halfdead(info, record);
            break;
        case XLOG_BTREE_UNLINK_PAGE:
        case XLOG_BTREE_UNLINK_PAGE_META:
            btree_xlog_unlink_page(info, record);
            break;
        case XLOG_BTREE_NEWROOT:
            btree_xlog_newroot(record);
            break;
        case XLOG_BTREE_REUSE_PAGE:
            btree_xlog_reuse_page(record);
            break;
        case XLOG_BTREE_META_CLEANUP:
            _bt_restore_meta(record, 0);
            break;
        default:
            elog(PANIC, "btree_redo: unknown op code %u", info);
    }
}

btree_xlog_delete()

static void btree_xlog_delete ( XLogReaderState *  record )

static

Definition at line 506 of file nbtxlog.c.

References BLK_NEEDS_REDO, BTP_HAS_GARBAGE, BTPageOpaqueData::btpo_flags, BufferGetPage, BufferIsValid, XLogReaderState::EndRecPtr, InHotStandby, xl_btree_delete::latestRemovedXid, MarkBufferDirty(), xl_btree_delete::nitems, PageGetSpecialPointer, PageIndexMultiDelete(), PageSetLSN, ResolveRecoveryConflictWithSnapshot(), SizeOfBtreeDelete, UnlockReleaseBuffer(), XLogReadBufferForRedo(), XLogRecGetBlockTag(), XLogRecGetData, and XLogRecGetDataLen.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_delete *xlrec = (xl_btree_delete *) XLogRecGetData(record);
    Buffer      buffer;
    Page        page;
    BTPageOpaque opaque;

    /*
     * If we have any conflict processing to do, it must happen before we
     * update the page.
     *
     * Btree delete records can conflict with standby queries.  You might
     * think that vacuum records would conflict as well, but we've handled
     * that already.  XLOG_HEAP2_CLEANUP_INFO records provide the highest xid
     * cleaned by the vacuum of the heap and so we can resolve any conflicts
     * just once when that arrives.  After that we know that no conflicts
     * exist from individual btree vacuum records on that index.
     */
    if (InHotStandby)
    {
        RelFileNode rnode;

        XLogRecGetBlockTag(record, 0, &rnode, NULL, NULL);

        ResolveRecoveryConflictWithSnapshot(xlrec->latestRemovedXid, rnode);
    }

    /*
     * We don't need to take a cleanup lock to apply these changes. See
     * nbtree/README for details.
     */
    if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
    {
        page = (Page) BufferGetPage(buffer);

        if (XLogRecGetDataLen(record) > SizeOfBtreeDelete)
        {
            OffsetNumber *unused;

            unused = (OffsetNumber *) ((char *) xlrec + SizeOfBtreeDelete);

            PageIndexMultiDelete(page, unused, xlrec->nitems);
        }

        /*
         * Mark the page as not containing any LP_DEAD items --- see comments
         * in _bt_delitems_delete().
         */
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
        opaque->btpo_flags &= ~BTP_HAS_GARBAGE;

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
    }
    if (BufferIsValid(buffer))
        UnlockReleaseBuffer(buffer);
}

btree_xlog_insert()

static void btree_xlog_insert ( bool  isleaf, bool  ismeta, XLogReaderState *  record  )

static

Definition at line 159 of file nbtxlog.c.

References _bt_clear_incomplete_split(), _bt_restore_meta(), BLK_NEEDS_REDO, BufferGetPage, BufferIsValid, elog, XLogReaderState::EndRecPtr, InvalidOffsetNumber, MarkBufferDirty(), xl_btree_insert::offnum, PageAddItem, PageSetLSN, PANIC, UnlockReleaseBuffer(), XLogReadBufferForRedo(), XLogRecGetBlockData(), and XLogRecGetData.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_insert *xlrec = (xl_btree_insert *) XLogRecGetData(record);
    Buffer      buffer;
    Page        page;

    /*
     * Insertion to an internal page finishes an incomplete split at the child
     * level.  Clear the incomplete-split flag in the child.  Note: during
     * normal operation, the child and parent pages are locked at the same
     * time, so that clearing the flag and inserting the downlink appear
     * atomic to other backends.  We don't bother with that during replay,
     * because readers don't care about the incomplete-split flag and there
     * cannot be updates happening.
     */
    if (!isleaf)
        _bt_clear_incomplete_split(record, 1);
    if (XLogReadBufferForRedo(record, 0, &buffer) == BLK_NEEDS_REDO)
    {
        Size        datalen;
        char       *datapos = XLogRecGetBlockData(record, 0, &datalen);

        page = BufferGetPage(buffer);

        if (PageAddItem(page, (Item) datapos, datalen, xlrec->offnum,
                        false, false) == InvalidOffsetNumber)
            elog(PANIC, "btree_xlog_insert: failed to add item");

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
    }
    if (BufferIsValid(buffer))
        UnlockReleaseBuffer(buffer);

    /*
     * Note: in normal operation, we'd update the metapage while still holding
     * lock on the page we inserted into.  But during replay it's not
     * necessary to hold that lock, since no other index updates can be
     * happening concurrently, and readers will cope fine with following an
     * obsolete link from the metapage.
     */
    if (ismeta)
        _bt_restore_meta(record, 2);
}

btree_xlog_mark_page_halfdead()

static void btree_xlog_mark_page_halfdead ( uint8  info, XLogReaderState *  record  )

static

Definition at line 566 of file nbtxlog.c.

References _bt_pageinit(), BLK_NEEDS_REDO, BTP_HALF_DEAD, BTP_LEAF, BTPageOpaqueData::btpo, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BTreeInnerTupleGetDownLink, BTreeInnerTupleSetDownLink, BTreeTupleSetTopParent, BufferGetPage, BufferGetPageSize, BufferIsValid, elog, XLogReaderState::EndRecPtr, ERROR, InvalidOffsetNumber, xl_btree_mark_page_halfdead::leftblk, BTPageOpaqueData::level, MarkBufferDirty(), MemSet, OffsetNumberNext, P_HIKEY, PageAddItem, PageGetItem, PageGetItemId, PageGetSpecialPointer, PageIndexTupleDelete(), PageSetLSN, xl_btree_mark_page_halfdead::poffset, xl_btree_mark_page_halfdead::rightblk, IndexTupleData::t_info, xl_btree_mark_page_halfdead::topparent, UnlockReleaseBuffer(), XLogInitBufferForRedo(), XLogReadBufferForRedo(), and XLogRecGetData.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_mark_page_halfdead *xlrec = (xl_btree_mark_page_halfdead *) XLogRecGetData(record);
    Buffer      buffer;
    Page        page;
    BTPageOpaque pageop;
    IndexTupleData trunctuple;

    /*
     * In normal operation, we would lock all the pages this WAL record
     * touches before changing any of them.  In WAL replay, it should be okay
     * to lock just one page at a time, since no concurrent index updates can
     * be happening, and readers should not care whether they arrive at the
     * target page or not (since it's surely empty).
     */

    /* parent page */
    if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
    {
        OffsetNumber poffset;
        ItemId      itemid;
        IndexTuple  itup;
        OffsetNumber nextoffset;
        BlockNumber rightsib;

        page = (Page) BufferGetPage(buffer);
        pageop = (BTPageOpaque) PageGetSpecialPointer(page);

        poffset = xlrec->poffset;

        nextoffset = OffsetNumberNext(poffset);
        itemid = PageGetItemId(page, nextoffset);
        itup = (IndexTuple) PageGetItem(page, itemid);
        rightsib = BTreeInnerTupleGetDownLink(itup);

        itemid = PageGetItemId(page, poffset);
        itup = (IndexTuple) PageGetItem(page, itemid);
        BTreeInnerTupleSetDownLink(itup, rightsib);
        nextoffset = OffsetNumberNext(poffset);
        PageIndexTupleDelete(page, nextoffset);

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
    }
    if (BufferIsValid(buffer))
        UnlockReleaseBuffer(buffer);

    /* Rewrite the leaf page as a halfdead page */
    buffer = XLogInitBufferForRedo(record, 0);
    page = (Page) BufferGetPage(buffer);

    _bt_pageinit(page, BufferGetPageSize(buffer));
    pageop = (BTPageOpaque) PageGetSpecialPointer(page);

    pageop->btpo_prev = xlrec->leftblk;
    pageop->btpo_next = xlrec->rightblk;
    pageop->btpo.level = 0;
    pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
    pageop->btpo_cycleid = 0;

    /*
     * Construct a dummy hikey item that points to the next parent to be
     * deleted (if any).
     */
    MemSet(&trunctuple, 0, sizeof(IndexTupleData));
    trunctuple.t_info = sizeof(IndexTupleData);
    BTreeTupleSetTopParent(&trunctuple, xlrec->topparent);

    if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
                    false, false) == InvalidOffsetNumber)
        elog(ERROR, "could not add dummy high key to half-dead page");

    PageSetLSN(page, lsn);
    MarkBufferDirty(buffer);
    UnlockReleaseBuffer(buffer);
}

btree_xlog_newroot()

static void btree_xlog_newroot ( XLogReaderState *  record )

static

Definition at line 758 of file nbtxlog.c.

References _bt_clear_incomplete_split(), _bt_pageinit(), _bt_restore_meta(), _bt_restore_page(), BTP_LEAF, BTP_ROOT, BTPageOpaqueData::btpo, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BufferGetPage, BufferGetPageSize, XLogReaderState::EndRecPtr, BTPageOpaqueData::level, xl_btree_newroot::level, MarkBufferDirty(), P_NONE, PageGetSpecialPointer, PageSetLSN, UnlockReleaseBuffer(), XLogInitBufferForRedo(), XLogRecGetBlockData(), and XLogRecGetData.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_newroot *xlrec = (xl_btree_newroot *) XLogRecGetData(record);
    Buffer      buffer;
    Page        page;
    BTPageOpaque pageop;
    char       *ptr;
    Size        len;

    buffer = XLogInitBufferForRedo(record, 0);
    page = (Page) BufferGetPage(buffer);

    _bt_pageinit(page, BufferGetPageSize(buffer));
    pageop = (BTPageOpaque) PageGetSpecialPointer(page);

    pageop->btpo_flags = BTP_ROOT;
    pageop->btpo_prev = pageop->btpo_next = P_NONE;
    pageop->btpo.level = xlrec->level;
    if (xlrec->level == 0)
        pageop->btpo_flags |= BTP_LEAF;
    pageop->btpo_cycleid = 0;

    if (xlrec->level > 0)
    {
        ptr = XLogRecGetBlockData(record, 0, &len);
        _bt_restore_page(page, ptr, len);

        /* Clear the incomplete-split flag in left child */
        _bt_clear_incomplete_split(record, 1);
    }

    PageSetLSN(page, lsn);
    MarkBufferDirty(buffer);
    UnlockReleaseBuffer(buffer);

    _bt_restore_meta(record, 2);
}

btree_xlog_reuse_page()

static void btree_xlog_reuse_page ( XLogReaderState *  record )

static

Definition at line 798 of file nbtxlog.c.

References InHotStandby, xl_btree_reuse_page::latestRemovedXid, xl_btree_reuse_page::node, ResolveRecoveryConflictWithSnapshot(), and XLogRecGetData.

Referenced by btree_redo().

{
    xl_btree_reuse_page *xlrec = (xl_btree_reuse_page *) XLogRecGetData(record);

    /*
     * Btree reuse_page records exist to provide a conflict point when we
     * reuse pages in the index via the FSM.  That's all they do though.
     *
     * latestRemovedXid was the page's btpo.xact.  The btpo.xact <
     * RecentGlobalXmin test in _bt_page_recyclable() conceptually mirrors the
     * pgxact->xmin > limitXmin test in GetConflictingVirtualXIDs().
     * Consequently, one XID value achieves the same exclusion effect on
     * master and standby.
     */
    if (InHotStandby)
    {
        ResolveRecoveryConflictWithSnapshot(xlrec->latestRemovedXid,
                                            xlrec->node);
    }
}

btree_xlog_split()

static void btree_xlog_split ( bool  onleft, XLogReaderState *  record  )

static

Definition at line 206 of file nbtxlog.c.

References _bt_clear_incomplete_split(), _bt_pageinit(), _bt_restore_page(), Assert, BLK_NEEDS_REDO, BTP_INCOMPLETE_SPLIT, BTP_LEAF, BTPageOpaqueData::btpo, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BufferGetPage, BufferGetPageSize, BufferIsValid, elog, XLogReaderState::EndRecPtr, ERROR, xl_btree_split::firstright, IndexTupleSize, InvalidOffsetNumber, ItemIdGetLength, BTPageOpaqueData::level, xl_btree_split::level, MarkBufferDirty(), MAXALIGN, xl_btree_split::newitemoff, OffsetNumberNext, P_FIRSTDATAKEY, P_HIKEY, P_NONE, PageAddItem, PageGetItem, PageGetItemId, PageGetSpecialPointer, PageGetTempPageCopySpecial(), PageRestoreTempPage(), PageSetLSN, PANIC, UnlockReleaseBuffer(), XLogInitBufferForRedo(), XLogReadBufferForRedo(), XLogRecGetBlockData(), XLogRecGetBlockTag(), and XLogRecGetData.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record);
    bool        isleaf = (xlrec->level == 0);
    Buffer      lbuf;
    Buffer      rbuf;
    Page        rpage;
    BTPageOpaque ropaque;
    char       *datapos;
    Size        datalen;
    BlockNumber leftsib;
    BlockNumber rightsib;
    BlockNumber rnext;

    XLogRecGetBlockTag(record, 0, NULL, NULL, &leftsib);
    XLogRecGetBlockTag(record, 1, NULL, NULL, &rightsib);
    if (!XLogRecGetBlockTag(record, 2, NULL, NULL, &rnext))
        rnext = P_NONE;

    /*
     * Clear the incomplete split flag on the left sibling of the child page
     * this is a downlink for.  (Like in btree_xlog_insert, this can be done
     * before locking the other pages)
     */
    if (!isleaf)
        _bt_clear_incomplete_split(record, 3);

    /* Reconstruct right (new) sibling page from scratch */
    rbuf = XLogInitBufferForRedo(record, 1);
    datapos = XLogRecGetBlockData(record, 1, &datalen);
    rpage = (Page) BufferGetPage(rbuf);

    _bt_pageinit(rpage, BufferGetPageSize(rbuf));
    ropaque = (BTPageOpaque) PageGetSpecialPointer(rpage);

    ropaque->btpo_prev = leftsib;
    ropaque->btpo_next = rnext;
    ropaque->btpo.level = xlrec->level;
    ropaque->btpo_flags = isleaf ? BTP_LEAF : 0;
    ropaque->btpo_cycleid = 0;

    _bt_restore_page(rpage, datapos, datalen);

    PageSetLSN(rpage, lsn);
    MarkBufferDirty(rbuf);

    /* Now reconstruct left (original) sibling page */
    if (XLogReadBufferForRedo(record, 0, &lbuf) == BLK_NEEDS_REDO)
    {
        /*
         * To retain the same physical order of the tuples that they had, we
         * initialize a temporary empty page for the left page and add all the
         * items to that in item number order.  This mirrors how _bt_split()
         * works.  Retaining the same physical order makes WAL consistency
         * checking possible.  See also _bt_restore_page(), which does the
         * same for the right page.
         */
        Page        lpage = (Page) BufferGetPage(lbuf);
        BTPageOpaque lopaque = (BTPageOpaque) PageGetSpecialPointer(lpage);
        OffsetNumber off;
        IndexTuple  newitem = NULL,
                    left_hikey = NULL;
        Size        newitemsz = 0,
                    left_hikeysz = 0;
        Page        newlpage;
        OffsetNumber leftoff;

        datapos = XLogRecGetBlockData(record, 0, &datalen);

        if (onleft)
        {
            newitem = (IndexTuple) datapos;
            newitemsz = MAXALIGN(IndexTupleSize(newitem));
            datapos += newitemsz;
            datalen -= newitemsz;
        }

        /* Extract left hikey and its size (assuming 16-bit alignment) */
        left_hikey = (IndexTuple) datapos;
        left_hikeysz = MAXALIGN(IndexTupleSize(left_hikey));
        datapos += left_hikeysz;
        datalen -= left_hikeysz;

        Assert(datalen == 0);

        newlpage = PageGetTempPageCopySpecial(lpage);

        /* Set high key */
        leftoff = P_HIKEY;
        if (PageAddItem(newlpage, (Item) left_hikey, left_hikeysz,
                        P_HIKEY, false, false) == InvalidOffsetNumber)
            elog(PANIC, "failed to add high key to left page after split");
        leftoff = OffsetNumberNext(leftoff);

        for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstright; off++)
        {
            ItemId      itemid;
            Size        itemsz;
            IndexTuple  item;

            /* add the new item if it was inserted on left page */
            if (onleft && off == xlrec->newitemoff)
            {
                if (PageAddItem(newlpage, (Item) newitem, newitemsz, leftoff,
                                false, false) == InvalidOffsetNumber)
                    elog(ERROR, "failed to add new item to left page after split");
                leftoff = OffsetNumberNext(leftoff);
            }

            itemid = PageGetItemId(lpage, off);
            itemsz = ItemIdGetLength(itemid);
            item = (IndexTuple) PageGetItem(lpage, itemid);
            if (PageAddItem(newlpage, (Item) item, itemsz, leftoff,
                            false, false) == InvalidOffsetNumber)
                elog(ERROR, "failed to add old item to left page after split");
            leftoff = OffsetNumberNext(leftoff);
        }

        /* cope with possibility that newitem goes at the end */
        if (onleft && off == xlrec->newitemoff)
        {
            if (PageAddItem(newlpage, (Item) newitem, newitemsz, leftoff,
                            false, false) == InvalidOffsetNumber)
                elog(ERROR, "failed to add new item to left page after split");
            leftoff = OffsetNumberNext(leftoff);
        }

        PageRestoreTempPage(newlpage, lpage);

        /* Fix opaque fields */
        lopaque->btpo_flags = BTP_INCOMPLETE_SPLIT;
        if (isleaf)
            lopaque->btpo_flags |= BTP_LEAF;
        lopaque->btpo_next = rightsib;
        lopaque->btpo_cycleid = 0;

        PageSetLSN(lpage, lsn);
        MarkBufferDirty(lbuf);
    }

    /*
     * We no longer need the buffers.  They must be released together, so that
     * readers cannot observe two inconsistent halves.
     */
    if (BufferIsValid(lbuf))
        UnlockReleaseBuffer(lbuf);
    UnlockReleaseBuffer(rbuf);

    /*
     * Fix left-link of the page to the right of the new right sibling.
     *
     * Note: in normal operation, we do this while still holding lock on the
     * two split pages.  However, that's not necessary for correctness in WAL
     * replay, because no other index update can be in progress, and readers
     * will cope properly when following an obsolete left-link.
     */
    if (rnext != P_NONE)
    {
        Buffer      buffer;

        if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
        {
            Page        page = (Page) BufferGetPage(buffer);
            BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);

            pageop->btpo_prev = rightsib;

            PageSetLSN(page, lsn);
            MarkBufferDirty(buffer);
        }
        if (BufferIsValid(buffer))
            UnlockReleaseBuffer(buffer);
    }
}

btree_xlog_unlink_page()

static void btree_xlog_unlink_page ( uint8  info, XLogReaderState *  record  )

static

Definition at line 646 of file nbtxlog.c.

References _bt_pageinit(), _bt_restore_meta(), BLK_NEEDS_REDO, BTP_DELETED, BTP_HALF_DEAD, BTP_LEAF, BTPageOpaqueData::btpo, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, xl_btree_unlink_page::btpo_xact, BTreeTupleSetTopParent, BufferGetPage, BufferGetPageSize, BufferIsValid, elog, XLogReaderState::EndRecPtr, ERROR, InvalidOffsetNumber, xl_btree_unlink_page::leafleftsib, xl_btree_unlink_page::leafrightsib, xl_btree_unlink_page::leftsib, BTPageOpaqueData::level, MarkBufferDirty(), MemSet, P_HIKEY, P_NONE, PageAddItem, PageGetSpecialPointer, PageSetLSN, xl_btree_unlink_page::rightsib, IndexTupleData::t_info, xl_btree_unlink_page::topparent, UnlockReleaseBuffer(), BTPageOpaqueData::xact, XLOG_BTREE_UNLINK_PAGE_META, XLogInitBufferForRedo(), XLogReadBufferForRedo(), XLogRecGetData, and XLogRecHasBlockRef.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    xl_btree_unlink_page *xlrec = (xl_btree_unlink_page *) XLogRecGetData(record);
    BlockNumber leftsib;
    BlockNumber rightsib;
    Buffer      buffer;
    Page        page;
    BTPageOpaque pageop;

    leftsib = xlrec->leftsib;
    rightsib = xlrec->rightsib;

    /*
     * In normal operation, we would lock all the pages this WAL record
     * touches before changing any of them.  In WAL replay, it should be okay
     * to lock just one page at a time, since no concurrent index updates can
     * be happening, and readers should not care whether they arrive at the
     * target page or not (since it's surely empty).
     */

    /* Fix left-link of right sibling */
    if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
    {
        page = (Page) BufferGetPage(buffer);
        pageop = (BTPageOpaque) PageGetSpecialPointer(page);
        pageop->btpo_prev = leftsib;

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
    }
    if (BufferIsValid(buffer))
        UnlockReleaseBuffer(buffer);

    /* Fix right-link of left sibling, if any */
    if (leftsib != P_NONE)
    {
        if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
        {
            page = (Page) BufferGetPage(buffer);
            pageop = (BTPageOpaque) PageGetSpecialPointer(page);
            pageop->btpo_next = rightsib;

            PageSetLSN(page, lsn);
            MarkBufferDirty(buffer);
        }
        if (BufferIsValid(buffer))
            UnlockReleaseBuffer(buffer);
    }

    /* Rewrite target page as empty deleted page */
    buffer = XLogInitBufferForRedo(record, 0);
    page = (Page) BufferGetPage(buffer);

    _bt_pageinit(page, BufferGetPageSize(buffer));
    pageop = (BTPageOpaque) PageGetSpecialPointer(page);

    pageop->btpo_prev = leftsib;
    pageop->btpo_next = rightsib;
    pageop->btpo.xact = xlrec->btpo_xact;
    pageop->btpo_flags = BTP_DELETED;
    pageop->btpo_cycleid = 0;

    PageSetLSN(page, lsn);
    MarkBufferDirty(buffer);
    UnlockReleaseBuffer(buffer);

    /*
     * If we deleted a parent of the targeted leaf page, instead of the leaf
     * itself, update the leaf to point to the next remaining child in the
     * branch.
     */
    if (XLogRecHasBlockRef(record, 3))
    {
        /*
         * There is no real data on the page, so we just re-create it from
         * scratch using the information from the WAL record.
         */
        IndexTupleData trunctuple;

        buffer = XLogInitBufferForRedo(record, 3);
        page = (Page) BufferGetPage(buffer);

        _bt_pageinit(page, BufferGetPageSize(buffer));
        pageop = (BTPageOpaque) PageGetSpecialPointer(page);

        pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
        pageop->btpo_prev = xlrec->leafleftsib;
        pageop->btpo_next = xlrec->leafrightsib;
        pageop->btpo.level = 0;
        pageop->btpo_cycleid = 0;

        /* Add a dummy hikey item */
        MemSet(&trunctuple, 0, sizeof(IndexTupleData));
        trunctuple.t_info = sizeof(IndexTupleData);
        BTreeTupleSetTopParent(&trunctuple, xlrec->topparent);

        if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
                        false, false) == InvalidOffsetNumber)
            elog(ERROR, "could not add dummy high key to half-dead page");

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
        UnlockReleaseBuffer(buffer);
    }

    /* Update metapage if needed */
    if (info == XLOG_BTREE_UNLINK_PAGE_META)
        _bt_restore_meta(record, 4);
}

btree_xlog_vacuum()

static void btree_xlog_vacuum ( XLogReaderState *  record )

static

Definition at line 383 of file nbtxlog.c.

References BLK_NEEDS_REDO, BlockNumberIsValid, BTP_HAS_GARBAGE, BTPageOpaqueData::btpo_flags, BufferGetPage, BufferIsValid, XLogReaderState::EndRecPtr, HotStandbyActiveInReplay(), xl_btree_vacuum::lastBlockVacuumed, LockBufferForCleanup(), MAIN_FORKNUM, MarkBufferDirty(), PageGetSpecialPointer, PageIndexMultiDelete(), PageSetLSN, RBM_NORMAL, RBM_NORMAL_NO_LOG, UnlockReleaseBuffer(), XLogReadBufferExtended(), XLogReadBufferForRedoExtended(), XLogRecGetBlockData(), XLogRecGetBlockTag(), and XLogRecGetData.

Referenced by btree_redo().

{
    XLogRecPtr  lsn = record->EndRecPtr;
    Buffer      buffer;
    Page        page;
    BTPageOpaque opaque;
#ifdef UNUSED
    xl_btree_vacuum *xlrec = (xl_btree_vacuum *) XLogRecGetData(record);

    /*
     * This section of code is thought to be no longer needed, after analysis
     * of the calling paths. It is retained to allow the code to be reinstated
     * if a flaw is revealed in that thinking.
     *
     * If we are running non-MVCC scans using this index we need to do some
     * additional work to ensure correctness, which is known as a "pin scan"
     * described in more detail in next paragraphs. We used to do the extra
     * work in all cases, whereas we now avoid that work in most cases. If
     * lastBlockVacuumed is set to InvalidBlockNumber then we skip the
     * additional work required for the pin scan.
     *
     * Avoiding this extra work is important since it requires us to touch
     * every page in the index, so is an O(N) operation. Worse, it is an
     * operation performed in the foreground during redo, so it delays
     * replication directly.
     *
     * If queries might be active then we need to ensure every leaf page is
     * unpinned between the lastBlockVacuumed and the current block, if there
     * are any.  This prevents replay of the VACUUM from reaching the stage of
     * removing heap tuples while there could still be indexscans "in flight"
     * to those particular tuples for those scans which could be confused by
     * finding new tuples at the old TID locations (see nbtree/README).
     *
     * It might be worth checking if there are actually any backends running;
     * if not, we could just skip this.
     *
     * Since VACUUM can visit leaf pages out-of-order, it might issue records
     * with lastBlockVacuumed >= block; that's not an error, it just means
     * nothing to do now.
     *
     * Note: since we touch all pages in the range, we will lock non-leaf
     * pages, and also any empty (all-zero) pages that may be in the index. It
     * doesn't seem worth the complexity to avoid that.  But it's important
     * that HotStandbyActiveInReplay() will not return true if the database
     * isn't yet consistent; so we need not fear reading still-corrupt blocks
     * here during crash recovery.
     */
    if (HotStandbyActiveInReplay() && BlockNumberIsValid(xlrec->lastBlockVacuumed))
    {
        RelFileNode thisrnode;
        BlockNumber thisblkno;
        BlockNumber blkno;

        XLogRecGetBlockTag(record, 0, &thisrnode, NULL, &thisblkno);

        for (blkno = xlrec->lastBlockVacuumed + 1; blkno < thisblkno; blkno++)
        {
            /*
             * We use RBM_NORMAL_NO_LOG mode because it's not an error
             * condition to see all-zero pages.  The original btvacuumpage
             * scan would have skipped over all-zero pages, noting them in FSM
             * but not bothering to initialize them just yet; so we mustn't
             * throw an error here.  (We could skip acquiring the cleanup lock
             * if PageIsNew, but it's probably not worth the cycles to test.)
             *
             * XXX we don't actually need to read the block, we just need to
             * confirm it is unpinned. If we had a special call into the
             * buffer manager we could optimise this so that if the block is
             * not in shared_buffers we confirm it as unpinned. Optimizing
             * this is now moot, since in most cases we avoid the scan.
             */
            buffer = XLogReadBufferExtended(thisrnode, MAIN_FORKNUM, blkno,
                                            RBM_NORMAL_NO_LOG);
            if (BufferIsValid(buffer))
            {
                LockBufferForCleanup(buffer);
                UnlockReleaseBuffer(buffer);
            }
        }
    }
#endif

    /*
     * Like in btvacuumpage(), we need to take a cleanup lock on every leaf
     * page. See nbtree/README for details.
     */
    if (XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, true, &buffer)
        == BLK_NEEDS_REDO)
    {
        char       *ptr;
        Size        len;

        ptr = XLogRecGetBlockData(record, 0, &len);

        page = (Page) BufferGetPage(buffer);

        if (len > 0)
        {
            OffsetNumber *unused;
            OffsetNumber *unend;

            unused = (OffsetNumber *) ptr;
            unend = (OffsetNumber *) ((char *) ptr + len);

            if ((unend - unused) > 0)
                PageIndexMultiDelete(page, unused, unend - unused);
        }

        /*
         * Mark the page as not containing any LP_DEAD items --- see comments
         * in _bt_delitems_vacuum().
         */
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
        opaque->btpo_flags &= ~BTP_HAS_GARBAGE;

        PageSetLSN(page, lsn);
        MarkBufferDirty(buffer);
    }
    if (BufferIsValid(buffer))
        UnlockReleaseBuffer(buffer);
}