verify_nbtree.c File Reference

#include "postgres.h"
#include "access/htup_details.h"
#include "access/nbtree.h"
#include "access/table.h"
#include "access/tableam.h"
#include "access/transam.h"
#include "access/xact.h"
#include "catalog/index.h"
#include "catalog/pg_am.h"
#include "commands/tablecmds.h"
#include "common/pg_prng.h"
#include "lib/bloomfilter.h"
#include "miscadmin.h"
#include "storage/lmgr.h"
#include "storage/smgr.h"
#include "utils/memutils.h"
#include "utils/snapmgr.h"

Include dependency graph for verify_nbtree.c:

Go to the source code of this file.

Data Structures
struct	BtreeCheckState
struct	BtreeLevel

Macros
#define	InvalidBtreeLevel   ((uint32) InvalidBlockNumber)
#define	BTreeTupleGetNKeyAtts(itup, rel)    Min(IndexRelationGetNumberOfKeyAttributes(rel), BTreeTupleGetNAtts(itup, rel))

Typedefs
typedef struct BtreeCheckState	BtreeCheckState
typedef struct BtreeLevel	BtreeLevel

Functions
	PG_FUNCTION_INFO_V1 (bt_index_check)
	PG_FUNCTION_INFO_V1 (bt_index_parent_check)
static void	bt_index_check_internal (Oid indrelid, bool parentcheck, bool heapallindexed, bool rootdescend)
static void	btree_index_checkable (Relation rel)
static bool	btree_index_mainfork_expected (Relation rel)
static void	bt_check_every_level (Relation rel, Relation heaprel, bool heapkeyspace, bool readonly, bool heapallindexed, bool rootdescend)
static BtreeLevel	bt_check_level_from_leftmost (BtreeCheckState *state, BtreeLevel level)
static void	bt_recheck_sibling_links (BtreeCheckState *state, BlockNumber btpo_prev_from_target, BlockNumber leftcurrent)
static void	bt_target_page_check (BtreeCheckState *state)
static BTScanInsert	bt_right_page_check_scankey (BtreeCheckState *state)
static void	bt_child_check (BtreeCheckState *state, BTScanInsert targetkey, OffsetNumber downlinkoffnum)
static void	bt_child_highkey_check (BtreeCheckState *state, OffsetNumber target_downlinkoffnum, Page loaded_child, uint32 target_level)
static void	bt_downlink_missing_check (BtreeCheckState *state, bool rightsplit, BlockNumber targetblock, Page target)
static void	bt_tuple_present_callback (Relation index, ItemPointer tid, Datum *values, bool *isnull, bool tupleIsAlive, void *checkstate)
static IndexTuple	bt_normalize_tuple (BtreeCheckState *state, IndexTuple itup)
static IndexTuple	bt_posting_plain_tuple (IndexTuple itup, int n)
static bool	bt_rootdescend (BtreeCheckState *state, IndexTuple itup)
static bool	offset_is_negative_infinity (BTPageOpaque opaque, OffsetNumber offset)
static bool	invariant_l_offset (BtreeCheckState *state, BTScanInsert key, OffsetNumber upperbound)
static bool	invariant_leq_offset (BtreeCheckState *state, BTScanInsert key, OffsetNumber upperbound)
static bool	invariant_g_offset (BtreeCheckState *state, BTScanInsert key, OffsetNumber lowerbound)
static bool	invariant_l_nontarget_offset (BtreeCheckState *state, BTScanInsert key, BlockNumber nontargetblock, Page nontarget, OffsetNumber upperbound)
static Page	palloc_btree_page (BtreeCheckState *state, BlockNumber blocknum)
static BTScanInsert	bt_mkscankey_pivotsearch (Relation rel, IndexTuple itup)
static ItemId	PageGetItemIdCareful (BtreeCheckState *state, BlockNumber block, Page page, OffsetNumber offset)
static ItemPointer	BTreeTupleGetHeapTIDCareful (BtreeCheckState *state, IndexTuple itup, bool nonpivot)
static ItemPointer	BTreeTupleGetPointsToTID (IndexTuple itup)
Datum	bt_index_check (PG_FUNCTION_ARGS)
Datum	bt_index_parent_check (PG_FUNCTION_ARGS)
static bool	bt_pivot_tuple_identical (bool heapkeyspace, IndexTuple itup1, IndexTuple itup2)

Variables
	PG_MODULE_MAGIC

Macro Definition Documentation

BTreeTupleGetNKeyAtts

#define BTreeTupleGetNKeyAtts	(		itup,
			rel
	)		Min(IndexRelationGetNumberOfKeyAttributes(rel), BTreeTupleGetNAtts(itup, rel))

Definition at line 51 of file verify_nbtree.c.

InvalidBtreeLevel

#define InvalidBtreeLevel   ((uint32) InvalidBlockNumber)

Definition at line 50 of file verify_nbtree.c.

Typedef Documentation

BtreeCheckState

typedef struct BtreeCheckState BtreeCheckState

BtreeLevel

typedef struct BtreeLevel BtreeLevel

Function Documentation

bt_check_every_level()

static void bt_check_every_level ( Relation  rel, Relation  heaprel, bool  heapkeyspace, bool  readonly, bool  heapallindexed, bool  rootdescend  )

static

Definition at line 420 of file verify_nbtree.c.

{
    BtreeCheckState *state;
    Page        metapage;
    BTMetaPageData *metad;
    uint32      previouslevel;
    BtreeLevel  current;
    Snapshot    snapshot = SnapshotAny;
 
    if (!readonly)
        elog(DEBUG1, "verifying consistency of tree structure for index \"%s\"",
             RelationGetRelationName(rel));
    else
        elog(DEBUG1, "verifying consistency of tree structure for index \"%s\" with cross-level checks",
             RelationGetRelationName(rel));
 
    /*
     * This assertion matches the one in index_getnext_tid().  See page
     * recycling/"visible to everyone" notes in nbtree README.
     */
    Assert(TransactionIdIsValid(RecentXmin));
 
    /*
     * Initialize state for entire verification operation
     */
    state = palloc0(sizeof(BtreeCheckState));
    state->rel = rel;
    state->heaprel = heaprel;
    state->heapkeyspace = heapkeyspace;
    state->readonly = readonly;
    state->heapallindexed = heapallindexed;
    state->rootdescend = rootdescend;
 
    if (state->heapallindexed)
    {
        int64       total_pages;
        int64       total_elems;
        uint64      seed;
 
        /*
         * Size Bloom filter based on estimated number of tuples in index,
         * while conservatively assuming that each block must contain at least
         * MaxTIDsPerBTreePage / 3 "plain" tuples -- see
         * bt_posting_plain_tuple() for definition, and details of how posting
         * list tuples are handled.
         */
        total_pages = RelationGetNumberOfBlocks(rel);
        total_elems = Max(total_pages * (MaxTIDsPerBTreePage / 3),
                          (int64) state->rel->rd_rel->reltuples);
        /* Generate a random seed to avoid repetition */
        seed = pg_prng_uint64(&pg_global_prng_state);
        /* Create Bloom filter to fingerprint index */
        state->filter = bloom_create(total_elems, maintenance_work_mem, seed);
        state->heaptuplespresent = 0;
 
        /*
         * Register our own snapshot in !readonly case, rather than asking
         * table_index_build_scan() to do this for us later.  This needs to
         * happen before index fingerprinting begins, so we can later be
         * certain that index fingerprinting should have reached all tuples
         * returned by table_index_build_scan().
         */
        if (!state->readonly)
        {
            snapshot = RegisterSnapshot(GetTransactionSnapshot());
 
            /*
             * GetTransactionSnapshot() always acquires a new MVCC snapshot in
             * READ COMMITTED mode.  A new snapshot is guaranteed to have all
             * the entries it requires in the index.
             *
             * We must defend against the possibility that an old xact
             * snapshot was returned at higher isolation levels when that
             * snapshot is not safe for index scans of the target index.  This
             * is possible when the snapshot sees tuples that are before the
             * index's indcheckxmin horizon.  Throwing an error here should be
             * very rare.  It doesn't seem worth using a secondary snapshot to
             * avoid this.
             */
            if (IsolationUsesXactSnapshot() && rel->rd_index->indcheckxmin &&
                !TransactionIdPrecedes(HeapTupleHeaderGetXmin(rel->rd_indextuple->t_data),
                                       snapshot->xmin))
                ereport(ERROR,
                        (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
                         errmsg("index \"%s\" cannot be verified using transaction snapshot",
                                RelationGetRelationName(rel))));
        }
    }
 
    Assert(!state->rootdescend || state->readonly);
    if (state->rootdescend && !state->heapkeyspace)
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("cannot verify that tuples from index \"%s\" can each be found by an independent index search",
                        RelationGetRelationName(rel)),
                 errhint("Only B-Tree version 4 indexes support rootdescend verification.")));
 
    /* Create context for page */
    state->targetcontext = AllocSetContextCreate(CurrentMemoryContext,
                                                 "amcheck context",
                                                 ALLOCSET_DEFAULT_SIZES);
    state->checkstrategy = GetAccessStrategy(BAS_BULKREAD);
 
    /* Get true root block from meta-page */
    metapage = palloc_btree_page(state, BTREE_METAPAGE);
    metad = BTPageGetMeta(metapage);
 
    /*
     * Certain deletion patterns can result in "skinny" B-Tree indexes, where
     * the fast root and true root differ.
     *
     * Start from the true root, not the fast root, unlike conventional index
     * scans.  This approach is more thorough, and removes the risk of
     * following a stale fast root from the meta page.
     */
    if (metad->btm_fastroot != metad->btm_root)
        ereport(DEBUG1,
                (errcode(ERRCODE_NO_DATA),
                 errmsg_internal("harmless fast root mismatch in index \"%s\"",
                                 RelationGetRelationName(rel)),
                 errdetail_internal("Fast root block %u (level %u) differs from true root block %u (level %u).",
                                    metad->btm_fastroot, metad->btm_fastlevel,
                                    metad->btm_root, metad->btm_level)));
 
    /*
     * Starting at the root, verify every level.  Move left to right, top to
     * bottom.  Note that there may be no pages other than the meta page (meta
     * page can indicate that root is P_NONE when the index is totally empty).
     */
    previouslevel = InvalidBtreeLevel;
    current.level = metad->btm_level;
    current.leftmost = metad->btm_root;
    current.istruerootlevel = true;
    while (current.leftmost != P_NONE)
    {
        /*
         * Verify this level, and get left most page for next level down, if
         * not at leaf level
         */
        current = bt_check_level_from_leftmost(state, current);
 
        if (current.leftmost == InvalidBlockNumber)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index \"%s\" has no valid pages on level below %u or first level",
                            RelationGetRelationName(rel), previouslevel)));
 
        previouslevel = current.level;
    }
 
    /*
     * * Check whether heap contains unindexed/malformed tuples *
     */
    if (state->heapallindexed)
    {
        IndexInfo  *indexinfo = BuildIndexInfo(state->rel);
        TableScanDesc scan;
 
        /*
         * Create our own scan for table_index_build_scan(), rather than
         * getting it to do so for us.  This is required so that we can
         * actually use the MVCC snapshot registered earlier in !readonly
         * case.
         *
         * Note that table_index_build_scan() calls heap_endscan() for us.
         */
        scan = table_beginscan_strat(state->heaprel,    /* relation */
                                     snapshot,  /* snapshot */
                                     0, /* number of keys */
                                     NULL,  /* scan key */
                                     true,  /* buffer access strategy OK */
                                     true); /* syncscan OK? */
 
        /*
         * Scan will behave as the first scan of a CREATE INDEX CONCURRENTLY
         * behaves in !readonly case.
         *
         * It's okay that we don't actually use the same lock strength for the
         * heap relation as any other ii_Concurrent caller would in !readonly
         * case.  We have no reason to care about a concurrent VACUUM
         * operation, since there isn't going to be a second scan of the heap
         * that needs to be sure that there was no concurrent recycling of
         * TIDs.
         */
        indexinfo->ii_Concurrent = !state->readonly;
 
        /*
         * Don't wait for uncommitted tuple xact commit/abort when index is a
         * unique index on a catalog (or an index used by an exclusion
         * constraint).  This could otherwise happen in the readonly case.
         */
        indexinfo->ii_Unique = false;
        indexinfo->ii_ExclusionOps = NULL;
        indexinfo->ii_ExclusionProcs = NULL;
        indexinfo->ii_ExclusionStrats = NULL;
 
        elog(DEBUG1, "verifying that tuples from index \"%s\" are present in \"%s\"",
             RelationGetRelationName(state->rel),
             RelationGetRelationName(state->heaprel));
 
        table_index_build_scan(state->heaprel, state->rel, indexinfo, true, false,
                               bt_tuple_present_callback, (void *) state, scan);
 
        ereport(DEBUG1,
                (errmsg_internal("finished verifying presence of " INT64_FORMAT " tuples from table \"%s\" with bitset %.2f%% set",
                                 state->heaptuplespresent, RelationGetRelationName(heaprel),
                                 100.0 * bloom_prop_bits_set(state->filter))));
 
        if (snapshot != SnapshotAny)
            UnregisterSnapshot(snapshot);
 
        bloom_free(state->filter);
    }
 
    /* Be tidy: */
    MemoryContextDelete(state->targetcontext);
}

References ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate, Assert(), BAS_BULKREAD, bloom_create(), bloom_free(), bloom_prop_bits_set(), bt_check_level_from_leftmost(), bt_tuple_present_callback(), BTMetaPageData::btm_fastlevel, BTMetaPageData::btm_fastroot, BTMetaPageData::btm_level, BTMetaPageData::btm_root, BTPageGetMeta, BTREE_METAPAGE, BuildIndexInfo(), CurrentMemoryContext, DEBUG1, elog, ereport, errcode(), errdetail_internal(), errhint(), errmsg(), errmsg_internal(), ERROR, GetAccessStrategy(), GetTransactionSnapshot(), HeapTupleHeaderGetXmin, IndexInfo::ii_Concurrent, IndexInfo::ii_ExclusionOps, IndexInfo::ii_ExclusionProcs, IndexInfo::ii_ExclusionStrats, IndexInfo::ii_Unique, INT64_FORMAT, InvalidBlockNumber, InvalidBtreeLevel, IsolationUsesXactSnapshot, BtreeLevel::istruerootlevel, BtreeLevel::leftmost, BtreeLevel::level, maintenance_work_mem, Max, MaxTIDsPerBTreePage, MemoryContextDelete(), P_NONE, palloc0(), palloc_btree_page(), pg_global_prng_state, pg_prng_uint64(), RelationData::rd_index, RelationData::rd_indextuple, RecentXmin, RegisterSnapshot(), RelationGetNumberOfBlocks, RelationGetRelationName, SnapshotAny, HeapTupleData::t_data, table_beginscan_strat(), table_index_build_scan(), TransactionIdIsValid, TransactionIdPrecedes(), UnregisterSnapshot(), and SnapshotData::xmin.

Referenced by bt_index_check_internal().

bt_check_level_from_leftmost()

static BtreeLevel bt_check_level_from_leftmost ( BtreeCheckState *  state, BtreeLevel  level  )

static

Definition at line 658 of file verify_nbtree.c.

{
    /* State to establish early, concerning entire level */
    BTPageOpaque opaque;
    MemoryContext oldcontext;
    BtreeLevel  nextleveldown;
 
    /* Variables for iterating across level using right links */
    BlockNumber leftcurrent = P_NONE;
    BlockNumber current = level.leftmost;
 
    /* Initialize return state */
    nextleveldown.leftmost = InvalidBlockNumber;
    nextleveldown.level = InvalidBtreeLevel;
    nextleveldown.istruerootlevel = false;
 
    /* Use page-level context for duration of this call */
    oldcontext = MemoryContextSwitchTo(state->targetcontext);
 
    elog(DEBUG1, "verifying level %u%s", level.level,
         level.istruerootlevel ?
         " (true root level)" : level.level == 0 ? " (leaf level)" : "");
 
    state->prevrightlink = InvalidBlockNumber;
    state->previncompletesplit = false;
 
    do
    {
        /* Don't rely on CHECK_FOR_INTERRUPTS() calls at lower level */
        CHECK_FOR_INTERRUPTS();
 
        /* Initialize state for this iteration */
        state->targetblock = current;
        state->target = palloc_btree_page(state, state->targetblock);
        state->targetlsn = PageGetLSN(state->target);
 
        opaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
 
        if (P_IGNORE(opaque))
        {
            /*
             * Since there cannot be a concurrent VACUUM operation in readonly
             * mode, and since a page has no links within other pages
             * (siblings and parent) once it is marked fully deleted, it
             * should be impossible to land on a fully deleted page in
             * readonly mode. See bt_child_check() for further details.
             *
             * The bt_child_check() P_ISDELETED() check is repeated here so
             * that pages that are only reachable through sibling links get
             * checked.
             */
            if (state->readonly && P_ISDELETED(opaque))
                ereport(ERROR,
                        (errcode(ERRCODE_INDEX_CORRUPTED),
                         errmsg("downlink or sibling link points to deleted block in index \"%s\"",
                                RelationGetRelationName(state->rel)),
                         errdetail_internal("Block=%u left block=%u left link from block=%u.",
                                            current, leftcurrent, opaque->btpo_prev)));
 
            if (P_RIGHTMOST(opaque))
                ereport(ERROR,
                        (errcode(ERRCODE_INDEX_CORRUPTED),
                         errmsg("block %u fell off the end of index \"%s\"",
                                current, RelationGetRelationName(state->rel))));
            else
                ereport(DEBUG1,
                        (errcode(ERRCODE_NO_DATA),
                         errmsg_internal("block %u of index \"%s\" concurrently deleted",
                                         current, RelationGetRelationName(state->rel))));
            goto nextpage;
        }
        else if (nextleveldown.leftmost == InvalidBlockNumber)
        {
            /*
             * A concurrent page split could make the caller supplied leftmost
             * block no longer contain the leftmost page, or no longer be the
             * true root, but where that isn't possible due to heavyweight
             * locking, check that the first valid page meets caller's
             * expectations.
             */
            if (state->readonly)
            {
                if (!P_LEFTMOST(opaque))
                    ereport(ERROR,
                            (errcode(ERRCODE_INDEX_CORRUPTED),
                             errmsg("block %u is not leftmost in index \"%s\"",
                                    current, RelationGetRelationName(state->rel))));
 
                if (level.istruerootlevel && !P_ISROOT(opaque))
                    ereport(ERROR,
                            (errcode(ERRCODE_INDEX_CORRUPTED),
                             errmsg("block %u is not true root in index \"%s\"",
                                    current, RelationGetRelationName(state->rel))));
            }
 
            /*
             * Before beginning any non-trivial examination of level, prepare
             * state for next bt_check_level_from_leftmost() invocation for
             * the next level for the next level down (if any).
             *
             * There should be at least one non-ignorable page per level,
             * unless this is the leaf level, which is assumed by caller to be
             * final level.
             */
            if (!P_ISLEAF(opaque))
            {
                IndexTuple  itup;
                ItemId      itemid;
 
                /* Internal page -- downlink gets leftmost on next level */
                itemid = PageGetItemIdCareful(state, state->targetblock,
                                              state->target,
                                              P_FIRSTDATAKEY(opaque));
                itup = (IndexTuple) PageGetItem(state->target, itemid);
                nextleveldown.leftmost = BTreeTupleGetDownLink(itup);
                nextleveldown.level = opaque->btpo_level - 1;
            }
            else
            {
                /*
                 * Leaf page -- final level caller must process.
                 *
                 * Note that this could also be the root page, if there has
                 * been no root page split yet.
                 */
                nextleveldown.leftmost = P_NONE;
                nextleveldown.level = InvalidBtreeLevel;
            }
 
            /*
             * Finished setting up state for this call/level.  Control will
             * never end up back here in any future loop iteration for this
             * level.
             */
        }
 
        /* Sibling links should be in mutual agreement */
        if (opaque->btpo_prev != leftcurrent)
            bt_recheck_sibling_links(state, opaque->btpo_prev, leftcurrent);
 
        /* Check level */
        if (level.level != opaque->btpo_level)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("leftmost down link for level points to block in index \"%s\" whose level is not one level down",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Block pointed to=%u expected level=%u level in pointed to block=%u.",
                                        current, level.level, opaque->btpo_level)));
 
        /* Verify invariants for page */
        bt_target_page_check(state);
 
nextpage:
 
        /* Try to detect circular links */
        if (current == leftcurrent || current == opaque->btpo_prev)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("circular link chain found in block %u of index \"%s\"",
                            current, RelationGetRelationName(state->rel))));
 
        leftcurrent = current;
        current = opaque->btpo_next;
 
        if (state->lowkey)
        {
            Assert(state->readonly);
            pfree(state->lowkey);
            state->lowkey = NULL;
        }
 
        /*
         * Copy current target high key as the low key of right sibling.
         * Allocate memory in upper level context, so it would be cleared
         * after reset of target context.
         *
         * We only need the low key in corner cases of checking child high
         * keys. We use high key only when incomplete split on the child level
         * falls to the boundary of pages on the target level.  See
         * bt_child_highkey_check() for details.  So, typically we won't end
         * up doing anything with low key, but it's simpler for general case
         * high key verification to always have it available.
         *
         * The correctness of managing low key in the case of concurrent
         * splits wasn't investigated yet.  Thankfully we only need low key
         * for readonly verification and concurrent splits won't happen.
         */
        if (state->readonly && !P_RIGHTMOST(opaque))
        {
            IndexTuple  itup;
            ItemId      itemid;
 
            itemid = PageGetItemIdCareful(state, state->targetblock,
                                          state->target, P_HIKEY);
            itup = (IndexTuple) PageGetItem(state->target, itemid);
 
            state->lowkey = MemoryContextAlloc(oldcontext, IndexTupleSize(itup));
            memcpy(state->lowkey, itup, IndexTupleSize(itup));
        }
 
        /* Free page and associated memory for this iteration */
        MemoryContextReset(state->targetcontext);
    }
    while (current != P_NONE);
 
    if (state->lowkey)
    {
        Assert(state->readonly);
        pfree(state->lowkey);
        state->lowkey = NULL;
    }
 
    /* Don't change context for caller */
    MemoryContextSwitchTo(oldcontext);
 
    return nextleveldown;
}

References Assert(), bt_recheck_sibling_links(), bt_target_page_check(), BTPageOpaqueData::btpo_level, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BTreeTupleGetDownLink(), CHECK_FOR_INTERRUPTS, DEBUG1, elog, ereport, errcode(), errdetail_internal(), errmsg(), errmsg_internal(), ERROR, IndexTupleSize, InvalidBlockNumber, InvalidBtreeLevel, BtreeLevel::istruerootlevel, BtreeLevel::leftmost, BtreeLevel::level, MemoryContextAlloc(), MemoryContextReset(), MemoryContextSwitchTo(), P_FIRSTDATAKEY, P_HIKEY, P_IGNORE, P_ISDELETED, P_ISLEAF, P_ISROOT, P_LEFTMOST, P_NONE, P_RIGHTMOST, PageGetItem, PageGetItemIdCareful(), PageGetLSN, PageGetSpecialPointer, palloc_btree_page(), pfree(), and RelationGetRelationName.

Referenced by bt_check_every_level().

bt_child_check()

static void bt_child_check ( BtreeCheckState *  state, BTScanInsert  targetkey, OffsetNumber  downlinkoffnum  )

static

Definition at line 2070 of file verify_nbtree.c.

{
    ItemId      itemid;
    IndexTuple  itup;
    BlockNumber childblock;
    OffsetNumber offset;
    OffsetNumber maxoffset;
    Page        child;
    BTPageOpaque copaque;
    BTPageOpaque topaque;
 
    itemid = PageGetItemIdCareful(state, state->targetblock,
                                  state->target, downlinkoffnum);
    itup = (IndexTuple) PageGetItem(state->target, itemid);
    childblock = BTreeTupleGetDownLink(itup);
 
    /*
     * Caller must have ShareLock on target relation, because of
     * considerations around page deletion by VACUUM.
     *
     * NB: In general, page deletion deletes the right sibling's downlink, not
     * the downlink of the page being deleted; the deleted page's downlink is
     * reused for its sibling.  The key space is thereby consolidated between
     * the deleted page and its right sibling.  (We cannot delete a parent
     * page's rightmost child unless it is the last child page, and we intend
     * to also delete the parent itself.)
     *
     * If this verification happened without a ShareLock, the following race
     * condition could cause false positives:
     *
     * In general, concurrent page deletion might occur, including deletion of
     * the left sibling of the child page that is examined here.  If such a
     * page deletion were to occur, closely followed by an insertion into the
     * newly expanded key space of the child, a window for the false positive
     * opens up: the stale parent/target downlink originally followed to get
     * to the child legitimately ceases to be a lower bound on all items in
     * the page, since the key space was concurrently expanded "left".
     * (Insertion followed the "new" downlink for the child, not our now-stale
     * downlink, which was concurrently physically removed in target/parent as
     * part of deletion's first phase.)
     *
     * While we use various techniques elsewhere to perform cross-page
     * verification for !readonly callers, a similar trick seems difficult
     * here.  The tricks used by bt_recheck_sibling_links and by
     * bt_right_page_check_scankey both involve verification of a same-level,
     * cross-sibling invariant.  Cross-level invariants are far more squishy,
     * though.  The nbtree REDO routines do not actually couple buffer locks
     * across levels during page splits, so making any cross-level check work
     * reliably in !readonly mode may be impossible.
     */
    Assert(state->readonly);
 
    /*
     * Verify child page has the downlink key from target page (its parent) as
     * a lower bound; downlink must be strictly less than all keys on the
     * page.
     *
     * Check all items, rather than checking just the first and trusting that
     * the operator class obeys the transitive law.
     */
    topaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
    child = palloc_btree_page(state, childblock);
    copaque = (BTPageOpaque) PageGetSpecialPointer(child);
    maxoffset = PageGetMaxOffsetNumber(child);
 
    /*
     * Since we've already loaded the child block, combine this check with
     * check for downlink connectivity.
     */
    bt_child_highkey_check(state, downlinkoffnum,
                           child, topaque->btpo_level);
 
    /*
     * Since there cannot be a concurrent VACUUM operation in readonly mode,
     * and since a page has no links within other pages (siblings and parent)
     * once it is marked fully deleted, it should be impossible to land on a
     * fully deleted page.
     *
     * It does not quite make sense to enforce that the page cannot even be
     * half-dead, despite the fact the downlink is modified at the same stage
     * that the child leaf page is marked half-dead.  That's incorrect because
     * there may occasionally be multiple downlinks from a chain of pages
     * undergoing deletion, where multiple successive calls are made to
     * _bt_unlink_halfdead_page() by VACUUM before it can finally safely mark
     * the leaf page as fully dead.  While _bt_mark_page_halfdead() usually
     * removes the downlink to the leaf page that is marked half-dead, that's
     * not guaranteed, so it's possible we'll land on a half-dead page with a
     * downlink due to an interrupted multi-level page deletion.
     *
     * We go ahead with our checks if the child page is half-dead.  It's safe
     * to do so because we do not test the child's high key, so it does not
     * matter that the original high key will have been replaced by a dummy
     * truncated high key within _bt_mark_page_halfdead().  All other page
     * items are left intact on a half-dead page, so there is still something
     * to test.
     */
    if (P_ISDELETED(copaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("downlink to deleted page found in index \"%s\"",
                        RelationGetRelationName(state->rel)),
                 errdetail_internal("Parent block=%u child block=%u parent page lsn=%X/%X.",
                                    state->targetblock, childblock,
                                    LSN_FORMAT_ARGS(state->targetlsn))));
 
    for (offset = P_FIRSTDATAKEY(copaque);
         offset <= maxoffset;
         offset = OffsetNumberNext(offset))
    {
        /*
         * Skip comparison of target page key against "negative infinity"
         * item, if any.  Checking it would indicate that it's not a strict
         * lower bound, but that's only because of the hard-coding for
         * negative infinity items within _bt_compare().
         *
         * If nbtree didn't truncate negative infinity tuples during internal
         * page splits then we'd expect child's negative infinity key to be
         * equal to the scankey/downlink from target/parent (it would be a
         * "low key" in this hypothetical scenario, and so it would still need
         * to be treated as a special case here).
         *
         * Negative infinity items can be thought of as a strict lower bound
         * that works transitively, with the last non-negative-infinity pivot
         * followed during a descent from the root as its "true" strict lower
         * bound.  Only a small number of negative infinity items are truly
         * negative infinity; those that are the first items of leftmost
         * internal pages.  In more general terms, a negative infinity item is
         * only negative infinity with respect to the subtree that the page is
         * at the root of.
         *
         * See also: bt_rootdescend(), which can even detect transitive
         * inconsistencies on cousin leaf pages.
         */
        if (offset_is_negative_infinity(copaque, offset))
            continue;
 
        if (!invariant_l_nontarget_offset(state, targetkey, childblock, child,
                                          offset))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("down-link lower bound invariant violated for index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Parent block=%u child index tid=(%u,%u) parent page lsn=%X/%X.",
                                        state->targetblock, childblock, offset,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
    }
 
    pfree(child);
}

References Assert(), bt_child_highkey_check(), BTPageOpaqueData::btpo_level, BTreeTupleGetDownLink(), ereport, errcode(), errdetail_internal(), errmsg(), ERROR, invariant_l_nontarget_offset(), LSN_FORMAT_ARGS, offset_is_negative_infinity(), OffsetNumberNext, P_FIRSTDATAKEY, P_ISDELETED, PageGetItem, PageGetItemIdCareful(), PageGetMaxOffsetNumber, PageGetSpecialPointer, palloc_btree_page(), pfree(), and RelationGetRelationName.

Referenced by bt_target_page_check().

bt_child_highkey_check()

static void bt_child_highkey_check ( BtreeCheckState *  state, OffsetNumber  target_downlinkoffnum, Page  loaded_child, uint32  target_level  )

static

Definition at line 1824 of file verify_nbtree.c.

{
    BlockNumber blkno = state->prevrightlink;
    Page        page;
    BTPageOpaque opaque;
    bool        rightsplit = state->previncompletesplit;
    bool        first = true;
    ItemId      itemid;
    IndexTuple  itup;
    BlockNumber downlink;
 
    if (OffsetNumberIsValid(target_downlinkoffnum))
    {
        itemid = PageGetItemIdCareful(state, state->targetblock,
                                      state->target, target_downlinkoffnum);
        itup = (IndexTuple) PageGetItem(state->target, itemid);
        downlink = BTreeTupleGetDownLink(itup);
    }
    else
    {
        downlink = P_NONE;
    }
 
    /*
     * If no previous rightlink is memorized for current level just below
     * target page's level, we are about to start from the leftmost page. We
     * can't follow rightlinks from previous page, because there is no
     * previous page.  But we still can match high key.
     *
     * So we initialize variables for the loop above like there is previous
     * page referencing current child.  Also we imply previous page to not
     * have incomplete split flag, that would make us require downlink for
     * current child.  That's correct, because leftmost page on the level
     * should always have parent downlink.
     */
    if (!BlockNumberIsValid(blkno))
    {
        blkno = downlink;
        rightsplit = false;
    }
 
    /* Move to the right on the child level */
    while (true)
    {
        /*
         * Did we traverse the whole tree level and this is check for pages to
         * the right of rightmost downlink?
         */
        if (blkno == P_NONE && downlink == P_NONE)
        {
            state->prevrightlink = InvalidBlockNumber;
            state->previncompletesplit = false;
            return;
        }
 
        /* Did we traverse the whole tree level and don't find next downlink? */
        if (blkno == P_NONE)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("can't traverse from downlink %u to downlink %u of index \"%s\"",
                            state->prevrightlink, downlink,
                            RelationGetRelationName(state->rel))));
 
        /* Load page contents */
        if (blkno == downlink && loaded_child)
            page = loaded_child;
        else
            page = palloc_btree_page(state, blkno);
 
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
 
        /* The first page we visit at the level should be leftmost */
        if (first && !BlockNumberIsValid(state->prevrightlink) && !P_LEFTMOST(opaque))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("the first child of leftmost target page is not leftmost of its level in index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Target block=%u child block=%u target page lsn=%X/%X.",
                                        state->targetblock, blkno,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
 
        /* Do level sanity check */
        if ((!P_ISDELETED(opaque) || P_HAS_FULLXID(opaque)) &&
            opaque->btpo_level != target_level - 1)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("block found while following rightlinks from child of index \"%s\" has invalid level",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Block pointed to=%u expected level=%u level in pointed to block=%u.",
                                        blkno, target_level - 1, opaque->btpo_level)));
 
        /* Try to detect circular links */
        if ((!first && blkno == state->prevrightlink) || blkno == opaque->btpo_prev)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("circular link chain found in block %u of index \"%s\"",
                            blkno, RelationGetRelationName(state->rel))));
 
        if (blkno != downlink && !P_IGNORE(opaque))
        {
            /* blkno probably has missing parent downlink */
            bt_downlink_missing_check(state, rightsplit, blkno, page);
        }
 
        rightsplit = P_INCOMPLETE_SPLIT(opaque);
 
        /*
         * If we visit page with high key, check that it is equal to the
         * target key next to corresponding downlink.
         */
        if (!rightsplit && !P_RIGHTMOST(opaque))
        {
            BTPageOpaque topaque;
            IndexTuple  highkey;
            OffsetNumber pivotkey_offset;
 
            /* Get high key */
            itemid = PageGetItemIdCareful(state, blkno, page, P_HIKEY);
            highkey = (IndexTuple) PageGetItem(page, itemid);
 
            /*
             * There might be two situations when we examine high key.  If
             * current child page is referenced by given target downlink, we
             * should look to the next offset number for matching key from
             * target page.
             *
             * Alternatively, we're following rightlinks somewhere in the
             * middle between page referenced by previous target's downlink
             * and the page referenced by current target's downlink.  If
             * current child page hasn't incomplete split flag set, then its
             * high key should match to the target's key of current offset
             * number. This happens when a previous call here (to
             * bt_child_highkey_check()) found an incomplete split, and we
             * reach a right sibling page without a downlink -- the right
             * sibling page's high key still needs to be matched to a
             * separator key on the parent/target level.
             *
             * Don't apply OffsetNumberNext() to target_downlinkoffnum when we
             * already had to step right on the child level. Our traversal of
             * the child level must try to move in perfect lockstep behind (to
             * the left of) the target/parent level traversal.
             */
            if (blkno == downlink)
                pivotkey_offset = OffsetNumberNext(target_downlinkoffnum);
            else
                pivotkey_offset = target_downlinkoffnum;
 
            topaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
 
            if (!offset_is_negative_infinity(topaque, pivotkey_offset))
            {
                /*
                 * If we're looking for the next pivot tuple in target page,
                 * but there is no more pivot tuples, then we should match to
                 * high key instead.
                 */
                if (pivotkey_offset > PageGetMaxOffsetNumber(state->target))
                {
                    if (P_RIGHTMOST(topaque))
                        ereport(ERROR,
                                (errcode(ERRCODE_INDEX_CORRUPTED),
                                 errmsg("child high key is greater than rightmost pivot key on target level in index \"%s\"",
                                        RelationGetRelationName(state->rel)),
                                 errdetail_internal("Target block=%u child block=%u target page lsn=%X/%X.",
                                                    state->targetblock, blkno,
                                                    LSN_FORMAT_ARGS(state->targetlsn))));
                    pivotkey_offset = P_HIKEY;
                }
                itemid = PageGetItemIdCareful(state, state->targetblock,
                                              state->target, pivotkey_offset);
                itup = (IndexTuple) PageGetItem(state->target, itemid);
            }
            else
            {
                /*
                 * We cannot try to match child's high key to a negative
                 * infinity key in target, since there is nothing to compare.
                 * However, it's still possible to match child's high key
                 * outside of target page.  The reason why we're are is that
                 * bt_child_highkey_check() was previously called for the
                 * cousin page of 'loaded_child', which is incomplete split.
                 * So, now we traverse to the right of that cousin page and
                 * current child level page under consideration still belongs
                 * to the subtree of target's left sibling.  Thus, we need to
                 * match child's high key to it's left uncle page high key.
                 * Thankfully we saved it, it's called a "low key" of target
                 * page.
                 */
                if (!state->lowkey)
                    ereport(ERROR,
                            (errcode(ERRCODE_INDEX_CORRUPTED),
                             errmsg("can't find left sibling high key in index \"%s\"",
                                    RelationGetRelationName(state->rel)),
                             errdetail_internal("Target block=%u child block=%u target page lsn=%X/%X.",
                                                state->targetblock, blkno,
                                                LSN_FORMAT_ARGS(state->targetlsn))));
                itup = state->lowkey;
            }
 
            if (!bt_pivot_tuple_identical(state->heapkeyspace, highkey, itup))
            {
                ereport(ERROR,
                        (errcode(ERRCODE_INDEX_CORRUPTED),
                         errmsg("mismatch between parent key and child high key in index \"%s\"",
                                RelationGetRelationName(state->rel)),
                         errdetail_internal("Target block=%u child block=%u target page lsn=%X/%X.",
                                            state->targetblock, blkno,
                                            LSN_FORMAT_ARGS(state->targetlsn))));
            }
        }
 
        /* Exit if we already found next downlink */
        if (blkno == downlink)
        {
            state->prevrightlink = opaque->btpo_next;
            state->previncompletesplit = rightsplit;
            return;
        }
 
        /* Traverse to the next page using rightlink */
        blkno = opaque->btpo_next;
 
        /* Free page contents if it's allocated by us */
        if (page != loaded_child)
            pfree(page);
        first = false;
    }
}

References BlockNumberIsValid, bt_downlink_missing_check(), bt_pivot_tuple_identical(), BTPageOpaqueData::btpo_level, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BTreeTupleGetDownLink(), ereport, errcode(), errdetail_internal(), errmsg(), ERROR, InvalidBlockNumber, LSN_FORMAT_ARGS, offset_is_negative_infinity(), OffsetNumberIsValid, OffsetNumberNext, P_HAS_FULLXID, P_HIKEY, P_IGNORE, P_INCOMPLETE_SPLIT, P_ISDELETED, P_LEFTMOST, P_NONE, P_RIGHTMOST, PageGetItem, PageGetItemIdCareful(), PageGetMaxOffsetNumber, PageGetSpecialPointer, palloc_btree_page(), pfree(), and RelationGetRelationName.

Referenced by bt_child_check(), and bt_target_page_check().

bt_downlink_missing_check()

static void bt_downlink_missing_check ( BtreeCheckState *  state, bool  rightsplit, BlockNumber  targetblock, Page  target  )

static

Definition at line 2235 of file verify_nbtree.c.

{
    BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page);
    ItemId      itemid;
    IndexTuple  itup;
    Page        child;
    BTPageOpaque copaque;
    uint32      level;
    BlockNumber childblk;
    XLogRecPtr  pagelsn;
 
    Assert(state->readonly);
    Assert(!P_IGNORE(opaque));
 
    /* No next level up with downlinks to fingerprint from the true root */
    if (P_ISROOT(opaque))
        return;
 
    pagelsn = PageGetLSN(page);
 
    /*
     * Incomplete (interrupted) page splits can account for the lack of a
     * downlink.  Some inserting transaction should eventually complete the
     * page split in passing, when it notices that the left sibling page is
     * P_INCOMPLETE_SPLIT().
     *
     * In general, VACUUM is not prepared for there to be no downlink to a
     * page that it deletes.  This is the main reason why the lack of a
     * downlink can be reported as corruption here.  It's not obvious that an
     * invalid missing downlink can result in wrong answers to queries,
     * though, since index scans that land on the child may end up
     * consistently moving right. The handling of concurrent page splits (and
     * page deletions) within _bt_moveright() cannot distinguish
     * inconsistencies that last for a moment from inconsistencies that are
     * permanent and irrecoverable.
     *
     * VACUUM isn't even prepared to delete pages that have no downlink due to
     * an incomplete page split, but it can detect and reason about that case
     * by design, so it shouldn't be taken to indicate corruption.  See
     * _bt_pagedel() for full details.
     */
    if (rightsplit)
    {
        ereport(DEBUG1,
                (errcode(ERRCODE_NO_DATA),
                 errmsg_internal("harmless interrupted page split detected in index \"%s\"",
                                 RelationGetRelationName(state->rel)),
                 errdetail_internal("Block=%u level=%u left sibling=%u page lsn=%X/%X.",
                                    blkno, opaque->btpo_level,
                                    opaque->btpo_prev,
                                    LSN_FORMAT_ARGS(pagelsn))));
        return;
    }
 
    /*
     * Page under check is probably the "top parent" of a multi-level page
     * deletion.  We'll need to descend the subtree to make sure that
     * descendant pages are consistent with that, though.
     *
     * If the page (which must be non-ignorable) is a leaf page, then clearly
     * it can't be the top parent.  The lack of a downlink is probably a
     * symptom of a broad problem that could just as easily cause
     * inconsistencies anywhere else.
     */
    if (P_ISLEAF(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("leaf index block lacks downlink in index \"%s\"",
                        RelationGetRelationName(state->rel)),
                 errdetail_internal("Block=%u page lsn=%X/%X.",
                                    blkno,
                                    LSN_FORMAT_ARGS(pagelsn))));
 
    /* Descend from the given page, which is an internal page */
    elog(DEBUG1, "checking for interrupted multi-level deletion due to missing downlink in index \"%s\"",
         RelationGetRelationName(state->rel));
 
    level = opaque->btpo_level;
    itemid = PageGetItemIdCareful(state, blkno, page, P_FIRSTDATAKEY(opaque));
    itup = (IndexTuple) PageGetItem(page, itemid);
    childblk = BTreeTupleGetDownLink(itup);
    for (;;)
    {
        CHECK_FOR_INTERRUPTS();
 
        child = palloc_btree_page(state, childblk);
        copaque = (BTPageOpaque) PageGetSpecialPointer(child);
 
        if (P_ISLEAF(copaque))
            break;
 
        /* Do an extra sanity check in passing on internal pages */
        if (copaque->btpo_level != level - 1)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("downlink points to block in index \"%s\" whose level is not one level down",
                                     RelationGetRelationName(state->rel)),
                     errdetail_internal("Top parent/under check block=%u block pointed to=%u expected level=%u level in pointed to block=%u.",
                                        blkno, childblk,
                                        level - 1, copaque->btpo_level)));
 
        level = copaque->btpo_level;
        itemid = PageGetItemIdCareful(state, childblk, child,
                                      P_FIRSTDATAKEY(copaque));
        itup = (IndexTuple) PageGetItem(child, itemid);
        childblk = BTreeTupleGetDownLink(itup);
        /* Be slightly more pro-active in freeing this memory, just in case */
        pfree(child);
    }
 
    /*
     * Since there cannot be a concurrent VACUUM operation in readonly mode,
     * and since a page has no links within other pages (siblings and parent)
     * once it is marked fully deleted, it should be impossible to land on a
     * fully deleted page.  See bt_child_check() for further details.
     *
     * The bt_child_check() P_ISDELETED() check is repeated here because
     * bt_child_check() does not visit pages reachable through negative
     * infinity items.  Besides, bt_child_check() is unwilling to descend
     * multiple levels.  (The similar bt_child_check() P_ISDELETED() check
     * within bt_check_level_from_leftmost() won't reach the page either,
     * since the leaf's live siblings should have their sibling links updated
     * to bypass the deletion target page when it is marked fully dead.)
     *
     * If this error is raised, it might be due to a previous multi-level page
     * deletion that failed to realize that it wasn't yet safe to mark the
     * leaf page as fully dead.  A "dangling downlink" will still remain when
     * this happens.  The fact that the dangling downlink's page (the leaf's
     * parent/ancestor page) lacked a downlink is incidental.
     */
    if (P_ISDELETED(copaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("downlink to deleted leaf page found in index \"%s\"",
                                 RelationGetRelationName(state->rel)),
                 errdetail_internal("Top parent/target block=%u leaf block=%u top parent/under check lsn=%X/%X.",
                                    blkno, childblk,
                                    LSN_FORMAT_ARGS(pagelsn))));
 
    /*
     * Iff leaf page is half-dead, its high key top parent link should point
     * to what VACUUM considered to be the top parent page at the instant it
     * was interrupted.  Provided the high key link actually points to the
     * page under check, the missing downlink we detected is consistent with
     * there having been an interrupted multi-level page deletion.  This means
     * that the subtree with the page under check at its root (a page deletion
     * chain) is in a consistent state, enabling VACUUM to resume deleting the
     * entire chain the next time it encounters the half-dead leaf page.
     */
    if (P_ISHALFDEAD(copaque) && !P_RIGHTMOST(copaque))
    {
        itemid = PageGetItemIdCareful(state, childblk, child, P_HIKEY);
        itup = (IndexTuple) PageGetItem(child, itemid);
        if (BTreeTupleGetTopParent(itup) == blkno)
            return;
    }
 
    ereport(ERROR,
            (errcode(ERRCODE_INDEX_CORRUPTED),
             errmsg("internal index block lacks downlink in index \"%s\"",
                    RelationGetRelationName(state->rel)),
             errdetail_internal("Block=%u level=%u page lsn=%X/%X.",
                                blkno, opaque->btpo_level,
                                LSN_FORMAT_ARGS(pagelsn))));
}

References Assert(), BTPageOpaqueData::btpo_level, BTPageOpaqueData::btpo_prev, BTreeTupleGetDownLink(), BTreeTupleGetTopParent(), CHECK_FOR_INTERRUPTS, DEBUG1, elog, ereport, errcode(), errdetail_internal(), errmsg(), errmsg_internal(), ERROR, LSN_FORMAT_ARGS, P_FIRSTDATAKEY, P_HIKEY, P_IGNORE, P_ISDELETED, P_ISHALFDEAD, P_ISLEAF, P_ISROOT, P_RIGHTMOST, PageGetItem, PageGetItemIdCareful(), PageGetLSN, PageGetSpecialPointer, palloc_btree_page(), pfree(), and RelationGetRelationName.

Referenced by bt_child_highkey_check().

bt_index_check()

Datum bt_index_check

(

PG_FUNCTION_ARGS

)

Definition at line 202 of file verify_nbtree.c.

{
    Oid         indrelid = PG_GETARG_OID(0);
    bool        heapallindexed = false;
 
    if (PG_NARGS() == 2)
        heapallindexed = PG_GETARG_BOOL(1);
 
    bt_index_check_internal(indrelid, false, heapallindexed, false);
 
    PG_RETURN_VOID();
}

References bt_index_check_internal(), PG_GETARG_BOOL, PG_GETARG_OID, PG_NARGS, and PG_RETURN_VOID.

bt_index_check_internal()

static void bt_index_check_internal ( Oid  indrelid, bool  parentcheck, bool  heapallindexed, bool  rootdescend  )

static

Definition at line 245 of file verify_nbtree.c.

{
    Oid         heapid;
    Relation    indrel;
    Relation    heaprel;
    LOCKMODE    lockmode;
 
    if (parentcheck)
        lockmode = ShareLock;
    else
        lockmode = AccessShareLock;
 
    /*
     * We must lock table before index to avoid deadlocks.  However, if the
     * passed indrelid isn't an index then IndexGetRelation() will fail.
     * Rather than emitting a not-very-helpful error message, postpone
     * complaining, expecting that the is-it-an-index test below will fail.
     *
     * In hot standby mode this will raise an error when parentcheck is true.
     */
    heapid = IndexGetRelation(indrelid, true);
    if (OidIsValid(heapid))
        heaprel = table_open(heapid, lockmode);
    else
        heaprel = NULL;
 
    /*
     * Open the target index relations separately (like relation_openrv(), but
     * with heap relation locked first to prevent deadlocking).  In hot
     * standby mode this will raise an error when parentcheck is true.
     *
     * There is no need for the usual indcheckxmin usability horizon test
     * here, even in the heapallindexed case, because index undergoing
     * verification only needs to have entries for a new transaction snapshot.
     * (If this is a parentcheck verification, there is no question about
     * committed or recently dead heap tuples lacking index entries due to
     * concurrent activity.)
     */
    indrel = index_open(indrelid, lockmode);
 
    /*
     * Since we did the IndexGetRelation call above without any lock, it's
     * barely possible that a race against an index drop/recreation could have
     * netted us the wrong table.
     */
    if (heaprel == NULL || heapid != IndexGetRelation(indrelid, false))
        ereport(ERROR,
                (errcode(ERRCODE_UNDEFINED_TABLE),
                 errmsg("could not open parent table of index \"%s\"",
                        RelationGetRelationName(indrel))));
 
    /* Relation suitable for checking as B-Tree? */
    btree_index_checkable(indrel);
 
    if (btree_index_mainfork_expected(indrel))
    {
        bool        heapkeyspace,
                    allequalimage;
 
        if (!smgrexists(RelationGetSmgr(indrel), MAIN_FORKNUM))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index \"%s\" lacks a main relation fork",
                            RelationGetRelationName(indrel))));
 
        /* Extract metadata from metapage, and sanitize it in passing */
        _bt_metaversion(indrel, &heapkeyspace, &allequalimage);
        if (allequalimage && !heapkeyspace)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index \"%s\" metapage has equalimage field set on unsupported nbtree version",
                            RelationGetRelationName(indrel))));
        if (allequalimage && !_bt_allequalimage(indrel, false))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index \"%s\" metapage incorrectly indicates that deduplication is safe",
                            RelationGetRelationName(indrel))));
 
        /* Check index, possibly against table it is an index on */
        bt_check_every_level(indrel, heaprel, heapkeyspace, parentcheck,
                             heapallindexed, rootdescend);
    }
 
    /*
     * Release locks early. That's ok here because nothing in the called
     * routines will trigger shared cache invalidations to be sent, so we can
     * relax the usual pattern of only releasing locks after commit.
     */
    index_close(indrel, lockmode);
    if (heaprel)
        table_close(heaprel, lockmode);
}

References _bt_allequalimage(), _bt_metaversion(), AccessShareLock, bt_check_every_level(), btree_index_checkable(), btree_index_mainfork_expected(), ereport, errcode(), ERRCODE_UNDEFINED_TABLE, errmsg(), ERROR, index_close(), index_open(), IndexGetRelation(), MAIN_FORKNUM, OidIsValid, RelationGetRelationName, RelationGetSmgr(), ShareLock, smgrexists(), table_close(), and table_open().

Referenced by bt_index_check(), and bt_index_parent_check().

bt_index_parent_check()

Datum bt_index_parent_check

(

PG_FUNCTION_ARGS

)

Definition at line 225 of file verify_nbtree.c.

{
    Oid         indrelid = PG_GETARG_OID(0);
    bool        heapallindexed = false;
    bool        rootdescend = false;
 
    if (PG_NARGS() >= 2)
        heapallindexed = PG_GETARG_BOOL(1);
    if (PG_NARGS() == 3)
        rootdescend = PG_GETARG_BOOL(2);
 
    bt_index_check_internal(indrelid, true, heapallindexed, rootdescend);
 
    PG_RETURN_VOID();
}

References bt_index_check_internal(), PG_GETARG_BOOL, PG_GETARG_OID, PG_NARGS, and PG_RETURN_VOID.

bt_mkscankey_pivotsearch()

static BTScanInsert bt_mkscankey_pivotsearch ( Relation  rel, IndexTuple  itup  )

inlinestatic

Definition at line 3108 of file verify_nbtree.c.

{
    BTScanInsert skey;
 
    skey = _bt_mkscankey(rel, itup);
    skey->pivotsearch = true;
 
    return skey;
}

References _bt_mkscankey(), and BTScanInsertData::pivotsearch.

Referenced by bt_right_page_check_scankey(), and bt_target_page_check().

bt_normalize_tuple()

static IndexTuple bt_normalize_tuple ( BtreeCheckState *  state, IndexTuple  itup  )

static

Definition at line 2526 of file verify_nbtree.c.

{
    TupleDesc   tupleDescriptor = RelationGetDescr(state->rel);
    Datum       normalized[INDEX_MAX_KEYS];
    bool        isnull[INDEX_MAX_KEYS];
    bool        toast_free[INDEX_MAX_KEYS];
    bool        formnewtup = false;
    IndexTuple  reformed;
    int         i;
 
    /* Caller should only pass "logical" non-pivot tuples here */
    Assert(!BTreeTupleIsPosting(itup) && !BTreeTupleIsPivot(itup));
 
    /* Easy case: It's immediately clear that tuple has no varlena datums */
    if (!IndexTupleHasVarwidths(itup))
        return itup;
 
    for (i = 0; i < tupleDescriptor->natts; i++)
    {
        Form_pg_attribute att;
 
        att = TupleDescAttr(tupleDescriptor, i);
 
        /* Assume untoasted/already normalized datum initially */
        toast_free[i] = false;
        normalized[i] = index_getattr(itup, att->attnum,
                                      tupleDescriptor,
                                      &isnull[i]);
        if (att->attbyval || att->attlen != -1 || isnull[i])
            continue;
 
        /*
         * Callers always pass a tuple that could safely be inserted into the
         * index without further processing, so an external varlena header
         * should never be encountered here
         */
        if (VARATT_IS_EXTERNAL(DatumGetPointer(normalized[i])))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("external varlena datum in tuple that references heap row (%u,%u) in index \"%s\"",
                            ItemPointerGetBlockNumber(&(itup->t_tid)),
                            ItemPointerGetOffsetNumber(&(itup->t_tid)),
                            RelationGetRelationName(state->rel))));
        else if (VARATT_IS_COMPRESSED(DatumGetPointer(normalized[i])))
        {
            formnewtup = true;
            normalized[i] = PointerGetDatum(PG_DETOAST_DATUM(normalized[i]));
            toast_free[i] = true;
        }
    }
 
    /* Easier case: Tuple has varlena datums, none of which are compressed */
    if (!formnewtup)
        return itup;
 
    /*
     * Hard case: Tuple had compressed varlena datums that necessitate
     * creating normalized version of the tuple from uncompressed input datums
     * (normalized input datums).  This is rather naive, but shouldn't be
     * necessary too often.
     *
     * Note that we rely on deterministic index_form_tuple() TOAST compression
     * of normalized input.
     */
    reformed = index_form_tuple(tupleDescriptor, normalized, isnull);
    reformed->t_tid = itup->t_tid;
 
    /* Cannot leak memory here */
    for (i = 0; i < tupleDescriptor->natts; i++)
        if (toast_free[i])
            pfree(DatumGetPointer(normalized[i]));
 
    return reformed;
}

References Assert(), BTreeTupleIsPivot(), BTreeTupleIsPosting(), DatumGetPointer, ereport, errcode(), errmsg(), ERROR, i, index_form_tuple(), index_getattr, INDEX_MAX_KEYS, IndexTupleHasVarwidths, ItemPointerGetBlockNumber, ItemPointerGetOffsetNumber, TupleDescData::natts, pfree(), PG_DETOAST_DATUM, PointerGetDatum, RelationGetDescr, RelationGetRelationName, IndexTupleData::t_tid, TupleDescAttr, VARATT_IS_COMPRESSED, and VARATT_IS_EXTERNAL.

Referenced by bt_target_page_check(), and bt_tuple_present_callback().

bt_pivot_tuple_identical()

static bool bt_pivot_tuple_identical ( bool  heapkeyspace, IndexTuple  itup1, IndexTuple  itup2  )

static

Definition at line 1751 of file verify_nbtree.c.

{
    if (IndexTupleSize(itup1) != IndexTupleSize(itup2))
        return false;
 
    if (heapkeyspace)
    {
        /*
         * Offset number will contain important information in heapkeyspace
         * indexes: the number of attributes left in the pivot tuple following
         * suffix truncation.  Don't skip over it (compare it too).
         */
        if (memcmp(&itup1->t_tid.ip_posid, &itup2->t_tid.ip_posid,
                   IndexTupleSize(itup1) -
                   offsetof(ItemPointerData, ip_posid)) != 0)
            return false;
    }
    else
    {
        /*
         * Cannot rely on offset number field having consistent value across
         * levels on pg_upgrade'd !heapkeyspace indexes.  Compare contents of
         * tuple starting from just after item pointer (i.e. after block
         * number and offset number).
         */
        if (memcmp(&itup1->t_info, &itup2->t_info,
                   IndexTupleSize(itup1) -
                   offsetof(IndexTupleData, t_info)) != 0)
            return false;
    }
 
    return true;
}

References IndexTupleSize, ItemPointerData::ip_posid, offsetof, IndexTupleData::t_info, and IndexTupleData::t_tid.

Referenced by bt_child_highkey_check().

bt_posting_plain_tuple()

static IndexTuple bt_posting_plain_tuple ( IndexTuple  itup, int  n  )

inlinestatic

Definition at line 2616 of file verify_nbtree.c.

{
    Assert(BTreeTupleIsPosting(itup));
 
    /* Returns non-posting-list tuple */
    return _bt_form_posting(itup, BTreeTupleGetPostingN(itup, n), 1);
}

References _bt_form_posting(), Assert(), BTreeTupleGetPostingN(), and BTreeTupleIsPosting().

Referenced by bt_target_page_check().

bt_recheck_sibling_links()

static void bt_recheck_sibling_links ( BtreeCheckState *  state, BlockNumber  btpo_prev_from_target, BlockNumber  leftcurrent  )

static

Definition at line 912 of file verify_nbtree.c.

{
    if (!state->readonly)
    {
        Buffer      lbuf;
        Buffer      newtargetbuf;
        Page        page;
        BTPageOpaque opaque;
        BlockNumber newtargetblock;
 
        /* Couple locks in the usual order for nbtree:  Left to right */
        lbuf = ReadBufferExtended(state->rel, MAIN_FORKNUM, leftcurrent,
                                  RBM_NORMAL, state->checkstrategy);
        LockBuffer(lbuf, BT_READ);
        _bt_checkpage(state->rel, lbuf);
        page = BufferGetPage(lbuf);
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
        if (P_ISDELETED(opaque))
        {
            /*
             * Cannot reason about concurrently deleted page -- the left link
             * in the page to the right is expected to point to some other
             * page to the left (not leftcurrent page).
             *
             * Note that we deliberately don't give up with a half-dead page.
             */
            UnlockReleaseBuffer(lbuf);
            return;
        }
 
        newtargetblock = opaque->btpo_next;
        /* Avoid self-deadlock when newtargetblock == leftcurrent */
        if (newtargetblock != leftcurrent)
        {
            newtargetbuf = ReadBufferExtended(state->rel, MAIN_FORKNUM,
                                              newtargetblock, RBM_NORMAL,
                                              state->checkstrategy);
            LockBuffer(newtargetbuf, BT_READ);
            _bt_checkpage(state->rel, newtargetbuf);
            page = BufferGetPage(newtargetbuf);
            opaque = (BTPageOpaque) PageGetSpecialPointer(page);
            /* btpo_prev_from_target may have changed; update it */
            btpo_prev_from_target = opaque->btpo_prev;
        }
        else
        {
            /*
             * leftcurrent right sibling points back to leftcurrent block.
             * Index is corrupt.  Easiest way to handle this is to pretend
             * that we actually read from a distinct page that has an invalid
             * block number in its btpo_prev.
             */
            newtargetbuf = InvalidBuffer;
            btpo_prev_from_target = InvalidBlockNumber;
        }
 
        /*
         * No need to check P_ISDELETED here, since new target block cannot be
         * marked deleted as long as we hold a lock on lbuf
         */
        if (BufferIsValid(newtargetbuf))
            UnlockReleaseBuffer(newtargetbuf);
        UnlockReleaseBuffer(lbuf);
 
        if (btpo_prev_from_target == leftcurrent)
        {
            /* Report split in left sibling, not target (or new target) */
            ereport(DEBUG1,
                    (errcode(ERRCODE_INTERNAL_ERROR),
                     errmsg_internal("harmless concurrent page split detected in index \"%s\"",
                                     RelationGetRelationName(state->rel)),
                     errdetail_internal("Block=%u new right sibling=%u original right sibling=%u.",
                                        leftcurrent, newtargetblock,
                                        state->targetblock)));
            return;
        }
 
        /*
         * Index is corrupt.  Make sure that we report correct target page.
         *
         * This could have changed in cases where there was a concurrent page
         * split, as well as index corruption (at least in theory).  Note that
         * btpo_prev_from_target was already updated above.
         */
        state->targetblock = newtargetblock;
    }
 
    ereport(ERROR,
            (errcode(ERRCODE_INDEX_CORRUPTED),
             errmsg("left link/right link pair in index \"%s\" not in agreement",
                    RelationGetRelationName(state->rel)),
             errdetail_internal("Block=%u left block=%u left link from block=%u.",
                                state->targetblock, leftcurrent,
                                btpo_prev_from_target)));
}

References _bt_checkpage(), BT_READ, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, BufferGetPage, BufferIsValid, DEBUG1, ereport, errcode(), errdetail_internal(), errmsg(), errmsg_internal(), ERROR, InvalidBlockNumber, InvalidBuffer, LockBuffer(), MAIN_FORKNUM, P_ISDELETED, PageGetSpecialPointer, RBM_NORMAL, ReadBufferExtended(), RelationGetRelationName, and UnlockReleaseBuffer().

Referenced by bt_check_level_from_leftmost().

bt_right_page_check_scankey()

static BTScanInsert bt_right_page_check_scankey ( BtreeCheckState *  state )

static

Definition at line 1545 of file verify_nbtree.c.

{
    BTPageOpaque opaque;
    ItemId      rightitem;
    IndexTuple  firstitup;
    BlockNumber targetnext;
    Page        rightpage;
    OffsetNumber nline;
 
    /* Determine target's next block number */
    opaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
 
    /* If target is already rightmost, no right sibling; nothing to do here */
    if (P_RIGHTMOST(opaque))
        return NULL;
 
    /*
     * General notes on concurrent page splits and page deletion:
     *
     * Routines like _bt_search() don't require *any* page split interlock
     * when descending the tree, including something very light like a buffer
     * pin. That's why it's okay that we don't either.  This avoidance of any
     * need to "couple" buffer locks is the raison d' etre of the Lehman & Yao
     * algorithm, in fact.
     *
     * That leaves deletion.  A deleted page won't actually be recycled by
     * VACUUM early enough for us to fail to at least follow its right link
     * (or left link, or downlink) and find its sibling, because recycling
     * does not occur until no possible index scan could land on the page.
     * Index scans can follow links with nothing more than their snapshot as
     * an interlock and be sure of at least that much.  (See page
     * recycling/"visible to everyone" notes in nbtree README.)
     *
     * Furthermore, it's okay if we follow a rightlink and find a half-dead or
     * dead (ignorable) page one or more times.  There will either be a
     * further right link to follow that leads to a live page before too long
     * (before passing by parent's rightmost child), or we will find the end
     * of the entire level instead (possible when parent page is itself the
     * rightmost on its level).
     */
    targetnext = opaque->btpo_next;
    for (;;)
    {
        CHECK_FOR_INTERRUPTS();
 
        rightpage = palloc_btree_page(state, targetnext);
        opaque = (BTPageOpaque) PageGetSpecialPointer(rightpage);
 
        if (!P_IGNORE(opaque) || P_RIGHTMOST(opaque))
            break;
 
        /*
         * We landed on a deleted or half-dead sibling page.  Step right until
         * we locate a live sibling page.
         */
        ereport(DEBUG2,
                (errcode(ERRCODE_NO_DATA),
                 errmsg_internal("level %u sibling page in block %u of index \"%s\" was found deleted or half dead",
                                 opaque->btpo_level, targetnext, RelationGetRelationName(state->rel)),
                 errdetail_internal("Deleted page found when building scankey from right sibling.")));
 
        targetnext = opaque->btpo_next;
 
        /* Be slightly more pro-active in freeing this memory, just in case */
        pfree(rightpage);
    }
 
    /*
     * No ShareLock held case -- why it's safe to proceed.
     *
     * Problem:
     *
     * We must avoid false positive reports of corruption when caller treats
     * item returned here as an upper bound on target's last item.  In
     * general, false positives are disallowed.  Avoiding them here when
     * caller is !readonly is subtle.
     *
     * A concurrent page deletion by VACUUM of the target page can result in
     * the insertion of items on to this right sibling page that would
     * previously have been inserted on our target page.  There might have
     * been insertions that followed the target's downlink after it was made
     * to point to right sibling instead of target by page deletion's first
     * phase. The inserters insert items that would belong on target page.
     * This race is very tight, but it's possible.  This is our only problem.
     *
     * Non-problems:
     *
     * We are not hindered by a concurrent page split of the target; we'll
     * never land on the second half of the page anyway.  A concurrent split
     * of the right page will also not matter, because the first data item
     * remains the same within the left half, which we'll reliably land on. If
     * we had to skip over ignorable/deleted pages, it cannot matter because
     * their key space has already been atomically merged with the first
     * non-ignorable page we eventually find (doesn't matter whether the page
     * we eventually find is a true sibling or a cousin of target, which we go
     * into below).
     *
     * Solution:
     *
     * Caller knows that it should reverify that target is not ignorable
     * (half-dead or deleted) when cross-page sibling item comparison appears
     * to indicate corruption (invariant fails).  This detects the single race
     * condition that exists for caller.  This is correct because the
     * continued existence of target block as non-ignorable (not half-dead or
     * deleted) implies that target page was not merged into from the right by
     * deletion; the key space at or after target never moved left.  Target's
     * parent either has the same downlink to target as before, or a <
     * downlink due to deletion at the left of target.  Target either has the
     * same highkey as before, or a highkey < before when there is a page
     * split. (The rightmost concurrently-split-from-target-page page will
     * still have the same highkey as target was originally found to have,
     * which for our purposes is equivalent to target's highkey itself never
     * changing, since we reliably skip over
     * concurrently-split-from-target-page pages.)
     *
     * In simpler terms, we allow that the key space of the target may expand
     * left (the key space can move left on the left side of target only), but
     * the target key space cannot expand right and get ahead of us without
     * our detecting it.  The key space of the target cannot shrink, unless it
     * shrinks to zero due to the deletion of the original page, our canary
     * condition.  (To be very precise, we're a bit stricter than that because
     * it might just have been that the target page split and only the
     * original target page was deleted.  We can be more strict, just not more
     * lax.)
     *
     * Top level tree walk caller moves on to next page (makes it the new
     * target) following recovery from this race.  (cf.  The rationale for
     * child/downlink verification needing a ShareLock within
     * bt_child_check(), where page deletion is also the main source of
     * trouble.)
     *
     * Note that it doesn't matter if right sibling page here is actually a
     * cousin page, because in order for the key space to be readjusted in a
     * way that causes us issues in next level up (guiding problematic
     * concurrent insertions to the cousin from the grandparent rather than to
     * the sibling from the parent), there'd have to be page deletion of
     * target's parent page (affecting target's parent's downlink in target's
     * grandparent page).  Internal page deletion only occurs when there are
     * no child pages (they were all fully deleted), and caller is checking
     * that the target's parent has at least one non-deleted (so
     * non-ignorable) child: the target page.  (Note that the first phase of
     * deletion atomically marks the page to be deleted half-dead/ignorable at
     * the same time downlink in its parent is removed, so caller will
     * definitely not fail to detect that this happened.)
     *
     * This trick is inspired by the method backward scans use for dealing
     * with concurrent page splits; concurrent page deletion is a problem that
     * similarly receives special consideration sometimes (it's possible that
     * the backwards scan will re-read its "original" block after failing to
     * find a right-link to it, having already moved in the opposite direction
     * (right/"forwards") a few times to try to locate one).  Just like us,
     * that happens only to determine if there was a concurrent page deletion
     * of a reference page, and just like us if there was a page deletion of
     * that reference page it means we can move on from caring about the
     * reference page.  See the nbtree README for a full description of how
     * that works.
     */
    nline = PageGetMaxOffsetNumber(rightpage);
 
    /*
     * Get first data item, if any
     */
    if (P_ISLEAF(opaque) && nline >= P_FIRSTDATAKEY(opaque))
    {
        /* Return first data item (if any) */
        rightitem = PageGetItemIdCareful(state, targetnext, rightpage,
                                         P_FIRSTDATAKEY(opaque));
    }
    else if (!P_ISLEAF(opaque) &&
             nline >= OffsetNumberNext(P_FIRSTDATAKEY(opaque)))
    {
        /*
         * Return first item after the internal page's "negative infinity"
         * item
         */
        rightitem = PageGetItemIdCareful(state, targetnext, rightpage,
                                         OffsetNumberNext(P_FIRSTDATAKEY(opaque)));
    }
    else
    {
        /*
         * No first item.  Page is probably empty leaf page, but it's also
         * possible that it's an internal page with only a negative infinity
         * item.
         */
        ereport(DEBUG2,
                (errcode(ERRCODE_NO_DATA),
                 errmsg_internal("%s block %u of index \"%s\" has no first data item",
                                 P_ISLEAF(opaque) ? "leaf" : "internal", targetnext,
                                 RelationGetRelationName(state->rel))));
        return NULL;
    }
 
    /*
     * Return first real item scankey.  Note that this relies on right page
     * memory remaining allocated.
     */
    firstitup = (IndexTuple) PageGetItem(rightpage, rightitem);
    return bt_mkscankey_pivotsearch(state->rel, firstitup);
}

References bt_mkscankey_pivotsearch(), BTPageOpaqueData::btpo_level, BTPageOpaqueData::btpo_next, CHECK_FOR_INTERRUPTS, DEBUG2, ereport, errcode(), errdetail_internal(), errmsg_internal(), OffsetNumberNext, P_FIRSTDATAKEY, P_IGNORE, P_ISLEAF, P_RIGHTMOST, PageGetItem, PageGetItemIdCareful(), PageGetMaxOffsetNumber, PageGetSpecialPointer, palloc_btree_page(), pfree(), and RelationGetRelationName.

Referenced by bt_target_page_check().

bt_rootdescend()

static bool bt_rootdescend ( BtreeCheckState *  state, IndexTuple  itup  )

static

Definition at line 2649 of file verify_nbtree.c.

{
    BTScanInsert key;
    BTStack     stack;
    Buffer      lbuf;
    bool        exists;
 
    key = _bt_mkscankey(state->rel, itup);
    Assert(key->heapkeyspace && key->scantid != NULL);
 
    /*
     * Search from root.
     *
     * Ideally, we would arrange to only move right within _bt_search() when
     * an interrupted page split is detected (i.e. when the incomplete split
     * bit is found to be set), but for now we accept the possibility that
     * that could conceal an inconsistency.
     */
    Assert(state->readonly && state->rootdescend);
    exists = false;
    stack = _bt_search(state->rel, key, &lbuf, BT_READ, NULL);
 
    if (BufferIsValid(lbuf))
    {
        BTInsertStateData insertstate;
        OffsetNumber offnum;
        Page        page;
 
        insertstate.itup = itup;
        insertstate.itemsz = MAXALIGN(IndexTupleSize(itup));
        insertstate.itup_key = key;
        insertstate.postingoff = 0;
        insertstate.bounds_valid = false;
        insertstate.buf = lbuf;
 
        /* Get matching tuple on leaf page */
        offnum = _bt_binsrch_insert(state->rel, &insertstate);
        /* Compare first >= matching item on leaf page, if any */
        page = BufferGetPage(lbuf);
        /* Should match on first heap TID when tuple has a posting list */
        if (offnum <= PageGetMaxOffsetNumber(page) &&
            insertstate.postingoff <= 0 &&
            _bt_compare(state->rel, key, page, offnum) == 0)
            exists = true;
        _bt_relbuf(state->rel, lbuf);
    }
 
    _bt_freestack(stack);
    pfree(key);
 
    return exists;
}

References _bt_binsrch_insert(), _bt_compare(), _bt_freestack(), _bt_mkscankey(), _bt_relbuf(), _bt_search(), Assert(), BTInsertStateData::bounds_valid, BT_READ, BTInsertStateData::buf, BufferGetPage, BufferIsValid, IndexTupleSize, BTInsertStateData::itemsz, BTInsertStateData::itup, BTInsertStateData::itup_key, sort-test::key, MAXALIGN, PageGetMaxOffsetNumber, pfree(), and BTInsertStateData::postingoff.

Referenced by bt_target_page_check().

bt_target_page_check()

static void bt_target_page_check ( BtreeCheckState *  state )

static

Definition at line 1046 of file verify_nbtree.c.

{
    OffsetNumber offset;
    OffsetNumber max;
    BTPageOpaque topaque;
 
    topaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
    max = PageGetMaxOffsetNumber(state->target);
 
    elog(DEBUG2, "verifying %u items on %s block %u", max,
         P_ISLEAF(topaque) ? "leaf" : "internal", state->targetblock);
 
    /*
     * Check the number of attributes in high key. Note, rightmost page
     * doesn't contain a high key, so nothing to check
     */
    if (!P_RIGHTMOST(topaque))
    {
        ItemId      itemid;
        IndexTuple  itup;
 
        /* Verify line pointer before checking tuple */
        itemid = PageGetItemIdCareful(state, state->targetblock,
                                      state->target, P_HIKEY);
        if (!_bt_check_natts(state->rel, state->heapkeyspace, state->target,
                             P_HIKEY))
        {
            itup = (IndexTuple) PageGetItem(state->target, itemid);
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("wrong number of high key index tuple attributes in index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Index block=%u natts=%u block type=%s page lsn=%X/%X.",
                                        state->targetblock,
                                        BTreeTupleGetNAtts(itup, state->rel),
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
    }
 
    /*
     * Loop over page items, starting from first non-highkey item, not high
     * key (if any).  Most tests are not performed for the "negative infinity"
     * real item (if any).
     */
    for (offset = P_FIRSTDATAKEY(topaque);
         offset <= max;
         offset = OffsetNumberNext(offset))
    {
        ItemId      itemid;
        IndexTuple  itup;
        size_t      tupsize;
        BTScanInsert skey;
        bool        lowersizelimit;
        ItemPointer scantid;
 
        CHECK_FOR_INTERRUPTS();
 
        itemid = PageGetItemIdCareful(state, state->targetblock,
                                      state->target, offset);
        itup = (IndexTuple) PageGetItem(state->target, itemid);
        tupsize = IndexTupleSize(itup);
 
        /*
         * lp_len should match the IndexTuple reported length exactly, since
         * lp_len is completely redundant in indexes, and both sources of
         * tuple length are MAXALIGN()'d.  nbtree does not use lp_len all that
         * frequently, and is surprisingly tolerant of corrupt lp_len fields.
         */
        if (tupsize != ItemIdGetLength(itemid))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index tuple size does not equal lp_len in index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Index tid=(%u,%u) tuple size=%zu lp_len=%u page lsn=%X/%X.",
                                        state->targetblock, offset,
                                        tupsize, ItemIdGetLength(itemid),
                                        LSN_FORMAT_ARGS(state->targetlsn)),
                     errhint("This could be a torn page problem.")));
 
        /* Check the number of index tuple attributes */
        if (!_bt_check_natts(state->rel, state->heapkeyspace, state->target,
                             offset))
        {
            ItemPointer tid;
            char       *itid,
                       *htid;
 
            itid = psprintf("(%u,%u)", state->targetblock, offset);
            tid = BTreeTupleGetPointsToTID(itup);
            htid = psprintf("(%u,%u)",
                            ItemPointerGetBlockNumberNoCheck(tid),
                            ItemPointerGetOffsetNumberNoCheck(tid));
 
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("wrong number of index tuple attributes in index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Index tid=%s natts=%u points to %s tid=%s page lsn=%X/%X.",
                                        itid,
                                        BTreeTupleGetNAtts(itup, state->rel),
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        htid,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
 
        /*
         * Don't try to generate scankey using "negative infinity" item on
         * internal pages. They are always truncated to zero attributes.
         */
        if (offset_is_negative_infinity(topaque, offset))
        {
            /*
             * We don't call bt_child_check() for "negative infinity" items.
             * But if we're performing downlink connectivity check, we do it
             * for every item including "negative infinity" one.
             */
            if (!P_ISLEAF(topaque) && state->readonly)
            {
                bt_child_highkey_check(state,
                                       offset,
                                       NULL,
                                       topaque->btpo_level);
            }
            continue;
        }
 
        /*
         * Readonly callers may optionally verify that non-pivot tuples can
         * each be found by an independent search that starts from the root.
         * Note that we deliberately don't do individual searches for each
         * TID, since the posting list itself is validated by other checks.
         */
        if (state->rootdescend && P_ISLEAF(topaque) &&
            !bt_rootdescend(state, itup))
        {
            ItemPointer tid = BTreeTupleGetPointsToTID(itup);
            char       *itid,
                       *htid;
 
            itid = psprintf("(%u,%u)", state->targetblock, offset);
            htid = psprintf("(%u,%u)", ItemPointerGetBlockNumber(tid),
                            ItemPointerGetOffsetNumber(tid));
 
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("could not find tuple using search from root page in index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Index tid=%s points to heap tid=%s page lsn=%X/%X.",
                                        itid, htid,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
 
        /*
         * If tuple is a posting list tuple, make sure posting list TIDs are
         * in order
         */
        if (BTreeTupleIsPosting(itup))
        {
            ItemPointerData last;
            ItemPointer current;
 
            ItemPointerCopy(BTreeTupleGetHeapTID(itup), &last);
 
            for (int i = 1; i < BTreeTupleGetNPosting(itup); i++)
            {
 
                current = BTreeTupleGetPostingN(itup, i);
 
                if (ItemPointerCompare(current, &last) <= 0)
                {
                    char       *itid = psprintf("(%u,%u)", state->targetblock, offset);
 
                    ereport(ERROR,
                            (errcode(ERRCODE_INDEX_CORRUPTED),
                             errmsg_internal("posting list contains misplaced TID in index \"%s\"",
                                             RelationGetRelationName(state->rel)),
                             errdetail_internal("Index tid=%s posting list offset=%d page lsn=%X/%X.",
                                                itid, i,
                                                LSN_FORMAT_ARGS(state->targetlsn))));
                }
 
                ItemPointerCopy(current, &last);
            }
        }
 
        /* Build insertion scankey for current page offset */
        skey = bt_mkscankey_pivotsearch(state->rel, itup);
 
        /*
         * Make sure tuple size does not exceed the relevant BTREE_VERSION
         * specific limit.
         *
         * BTREE_VERSION 4 (which introduced heapkeyspace rules) requisitioned
         * a small amount of space from BTMaxItemSize() in order to ensure
         * that suffix truncation always has enough space to add an explicit
         * heap TID back to a tuple -- we pessimistically assume that every
         * newly inserted tuple will eventually need to have a heap TID
         * appended during a future leaf page split, when the tuple becomes
         * the basis of the new high key (pivot tuple) for the leaf page.
         *
         * Since the reclaimed space is reserved for that purpose, we must not
         * enforce the slightly lower limit when the extra space has been used
         * as intended.  In other words, there is only a cross-version
         * difference in the limit on tuple size within leaf pages.
         *
         * Still, we're particular about the details within BTREE_VERSION 4
         * internal pages.  Pivot tuples may only use the extra space for its
         * designated purpose.  Enforce the lower limit for pivot tuples when
         * an explicit heap TID isn't actually present. (In all other cases
         * suffix truncation is guaranteed to generate a pivot tuple that's no
         * larger than the firstright tuple provided to it by its caller.)
         */
        lowersizelimit = skey->heapkeyspace &&
            (P_ISLEAF(topaque) || BTreeTupleGetHeapTID(itup) == NULL);
        if (tupsize > (lowersizelimit ? BTMaxItemSize(state->target) :
                       BTMaxItemSizeNoHeapTid(state->target)))
        {
            ItemPointer tid = BTreeTupleGetPointsToTID(itup);
            char       *itid,
                       *htid;
 
            itid = psprintf("(%u,%u)", state->targetblock, offset);
            htid = psprintf("(%u,%u)",
                            ItemPointerGetBlockNumberNoCheck(tid),
                            ItemPointerGetOffsetNumberNoCheck(tid));
 
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index row size %zu exceeds maximum for index \"%s\"",
                            tupsize, RelationGetRelationName(state->rel)),
                     errdetail_internal("Index tid=%s points to %s tid=%s page lsn=%X/%X.",
                                        itid,
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        htid,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
 
        /* Fingerprint leaf page tuples (those that point to the heap) */
        if (state->heapallindexed && P_ISLEAF(topaque) && !ItemIdIsDead(itemid))
        {
            IndexTuple  norm;
 
            if (BTreeTupleIsPosting(itup))
            {
                /* Fingerprint all elements as distinct "plain" tuples */
                for (int i = 0; i < BTreeTupleGetNPosting(itup); i++)
                {
                    IndexTuple  logtuple;
 
                    logtuple = bt_posting_plain_tuple(itup, i);
                    norm = bt_normalize_tuple(state, logtuple);
                    bloom_add_element(state->filter, (unsigned char *) norm,
                                      IndexTupleSize(norm));
                    /* Be tidy */
                    if (norm != logtuple)
                        pfree(norm);
                    pfree(logtuple);
                }
            }
            else
            {
                norm = bt_normalize_tuple(state, itup);
                bloom_add_element(state->filter, (unsigned char *) norm,
                                  IndexTupleSize(norm));
                /* Be tidy */
                if (norm != itup)
                    pfree(norm);
            }
        }
 
        /*
         * * High key check *
         *
         * If there is a high key (if this is not the rightmost page on its
         * entire level), check that high key actually is upper bound on all
         * page items.  If this is a posting list tuple, we'll need to set
         * scantid to be highest TID in posting list.
         *
         * We prefer to check all items against high key rather than checking
         * just the last and trusting that the operator class obeys the
         * transitive law (which implies that all previous items also
         * respected the high key invariant if they pass the item order
         * check).
         *
         * Ideally, we'd compare every item in the index against every other
         * item in the index, and not trust opclass obedience of the
         * transitive law to bridge the gap between children and their
         * grandparents (as well as great-grandparents, and so on).  We don't
         * go to those lengths because that would be prohibitively expensive,
         * and probably not markedly more effective in practice.
         *
         * On the leaf level, we check that the key is <= the highkey.
         * However, on non-leaf levels we check that the key is < the highkey,
         * because the high key is "just another separator" rather than a copy
         * of some existing key item; we expect it to be unique among all keys
         * on the same level.  (Suffix truncation will sometimes produce a
         * leaf highkey that is an untruncated copy of the lastleft item, but
         * never any other item, which necessitates weakening the leaf level
         * check to <=.)
         *
         * Full explanation for why a highkey is never truly a copy of another
         * item from the same level on internal levels:
         *
         * While the new left page's high key is copied from the first offset
         * on the right page during an internal page split, that's not the
         * full story.  In effect, internal pages are split in the middle of
         * the firstright tuple, not between the would-be lastleft and
         * firstright tuples: the firstright key ends up on the left side as
         * left's new highkey, and the firstright downlink ends up on the
         * right side as right's new "negative infinity" item.  The negative
         * infinity tuple is truncated to zero attributes, so we're only left
         * with the downlink.  In other words, the copying is just an
         * implementation detail of splitting in the middle of a (pivot)
         * tuple. (See also: "Notes About Data Representation" in the nbtree
         * README.)
         */
        scantid = skey->scantid;
        if (state->heapkeyspace && BTreeTupleIsPosting(itup))
            skey->scantid = BTreeTupleGetMaxHeapTID(itup);
 
        if (!P_RIGHTMOST(topaque) &&
            !(P_ISLEAF(topaque) ? invariant_leq_offset(state, skey, P_HIKEY) :
              invariant_l_offset(state, skey, P_HIKEY)))
        {
            ItemPointer tid = BTreeTupleGetPointsToTID(itup);
            char       *itid,
                       *htid;
 
            itid = psprintf("(%u,%u)", state->targetblock, offset);
            htid = psprintf("(%u,%u)",
                            ItemPointerGetBlockNumberNoCheck(tid),
                            ItemPointerGetOffsetNumberNoCheck(tid));
 
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("high key invariant violated for index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Index tid=%s points to %s tid=%s page lsn=%X/%X.",
                                        itid,
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        htid,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
        /* Reset, in case scantid was set to (itup) posting tuple's max TID */
        skey->scantid = scantid;
 
        /*
         * * Item order check *
         *
         * Check that items are stored on page in logical order, by checking
         * current item is strictly less than next item (if any).
         */
        if (OffsetNumberNext(offset) <= max &&
            !invariant_l_offset(state, skey, OffsetNumberNext(offset)))
        {
            ItemPointer tid;
            char       *itid,
                       *htid,
                       *nitid,
                       *nhtid;
 
            itid = psprintf("(%u,%u)", state->targetblock, offset);
            tid = BTreeTupleGetPointsToTID(itup);
            htid = psprintf("(%u,%u)",
                            ItemPointerGetBlockNumberNoCheck(tid),
                            ItemPointerGetOffsetNumberNoCheck(tid));
            nitid = psprintf("(%u,%u)", state->targetblock,
                             OffsetNumberNext(offset));
 
            /* Reuse itup to get pointed-to heap location of second item */
            itemid = PageGetItemIdCareful(state, state->targetblock,
                                          state->target,
                                          OffsetNumberNext(offset));
            itup = (IndexTuple) PageGetItem(state->target, itemid);
            tid = BTreeTupleGetPointsToTID(itup);
            nhtid = psprintf("(%u,%u)",
                             ItemPointerGetBlockNumberNoCheck(tid),
                             ItemPointerGetOffsetNumberNoCheck(tid));
 
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("item order invariant violated for index \"%s\"",
                            RelationGetRelationName(state->rel)),
                     errdetail_internal("Lower index tid=%s (points to %s tid=%s) "
                                        "higher index tid=%s (points to %s tid=%s) "
                                        "page lsn=%X/%X.",
                                        itid,
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        htid,
                                        nitid,
                                        P_ISLEAF(topaque) ? "heap" : "index",
                                        nhtid,
                                        LSN_FORMAT_ARGS(state->targetlsn))));
        }
 
        /*
         * * Last item check *
         *
         * Check last item against next/right page's first data item's when
         * last item on page is reached.  This additional check will detect
         * transposed pages iff the supposed right sibling page happens to
         * belong before target in the key space.  (Otherwise, a subsequent
         * heap verification will probably detect the problem.)
         *
         * This check is similar to the item order check that will have
         * already been performed for every other "real" item on target page
         * when last item is checked.  The difference is that the next item
         * (the item that is compared to target's last item) needs to come
         * from the next/sibling page.  There may not be such an item
         * available from sibling for various reasons, though (e.g., target is
         * the rightmost page on level).
         */
        else if (offset == max)
        {
            BTScanInsert rightkey;
 
            /* Get item in next/right page */
            rightkey = bt_right_page_check_scankey(state);
 
            if (rightkey &&
                !invariant_g_offset(state, rightkey, max))
            {
                /*
                 * As explained at length in bt_right_page_check_scankey(),
                 * there is a known !readonly race that could account for
                 * apparent violation of invariant, which we must check for
                 * before actually proceeding with raising error.  Our canary
                 * condition is that target page was deleted.
                 */
                if (!state->readonly)
                {
                    /* Get fresh copy of target page */
                    state->target = palloc_btree_page(state, state->targetblock);
                    /* Note that we deliberately do not update target LSN */
                    topaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
 
                    /*
                     * All !readonly checks now performed; just return
                     */
                    if (P_IGNORE(topaque))
                        return;
                }
 
                ereport(ERROR,
                        (errcode(ERRCODE_INDEX_CORRUPTED),
                         errmsg("cross page item order invariant violated for index \"%s\"",
                                RelationGetRelationName(state->rel)),
                         errdetail_internal("Last item on page tid=(%u,%u) page lsn=%X/%X.",
                                            state->targetblock, offset,
                                            LSN_FORMAT_ARGS(state->targetlsn))));
            }
        }
 
        /*
         * * Downlink check *
         *
         * Additional check of child items iff this is an internal page and
         * caller holds a ShareLock.  This happens for every downlink (item)
         * in target excluding the negative-infinity downlink (again, this is
         * because it has no useful value to compare).
         */
        if (!P_ISLEAF(topaque) && state->readonly)
            bt_child_check(state, skey, offset);
    }
 
    /*
     * Special case bt_child_highkey_check() call
     *
     * We don't pass a real downlink, but we've to finish the level
     * processing. If condition is satisfied, we've already processed all the
     * downlinks from the target level.  But there still might be pages to the
     * right of the child page pointer to by our rightmost downlink.  And they
     * might have missing downlinks.  This final call checks for them.
     */
    if (!P_ISLEAF(topaque) && P_RIGHTMOST(topaque) && state->readonly)
    {
        bt_child_highkey_check(state, InvalidOffsetNumber,
                               NULL, topaque->btpo_level);
    }
}

References _bt_check_natts(), bloom_add_element(), bt_child_check(), bt_child_highkey_check(), bt_mkscankey_pivotsearch(), bt_normalize_tuple(), bt_posting_plain_tuple(), bt_right_page_check_scankey(), bt_rootdescend(), BTMaxItemSize, BTMaxItemSizeNoHeapTid, BTPageOpaqueData::btpo_level, BTreeTupleGetHeapTID(), BTreeTupleGetMaxHeapTID(), BTreeTupleGetNAtts, BTreeTupleGetNPosting(), BTreeTupleGetPointsToTID(), BTreeTupleGetPostingN(), BTreeTupleIsPosting(), CHECK_FOR_INTERRUPTS, DEBUG2, elog, ereport, errcode(), errdetail_internal(), errhint(), errmsg(), errmsg_internal(), ERROR, BTScanInsertData::heapkeyspace, i, IndexTupleSize, InvalidOffsetNumber, invariant_g_offset(), invariant_l_offset(), invariant_leq_offset(), ItemIdGetLength, ItemIdIsDead, ItemPointerCompare(), ItemPointerCopy, ItemPointerGetBlockNumber, ItemPointerGetBlockNumberNoCheck, ItemPointerGetOffsetNumber, ItemPointerGetOffsetNumberNoCheck, LSN_FORMAT_ARGS, offset_is_negative_infinity(), OffsetNumberNext, P_FIRSTDATAKEY, P_HIKEY, P_IGNORE, P_ISLEAF, P_RIGHTMOST, PageGetItem, PageGetItemIdCareful(), PageGetMaxOffsetNumber, PageGetSpecialPointer, palloc_btree_page(), pfree(), psprintf(), RelationGetRelationName, and BTScanInsertData::scantid.

Referenced by bt_check_level_from_leftmost().

bt_tuple_present_callback()

static void bt_tuple_present_callback ( Relation  index, ItemPointer  tid, Datum *  values, bool *  isnull, bool  tupleIsAlive, void *  checkstate  )

static

Definition at line 2458 of file verify_nbtree.c.

{
    BtreeCheckState *state = (BtreeCheckState *) checkstate;
    IndexTuple  itup,
                norm;
 
    Assert(state->heapallindexed);
 
    /* Generate a normalized index tuple for fingerprinting */
    itup = index_form_tuple(RelationGetDescr(index), values, isnull);
    itup->t_tid = *tid;
    norm = bt_normalize_tuple(state, itup);
 
    /* Probe Bloom filter -- tuple should be present */
    if (bloom_lacks_element(state->filter, (unsigned char *) norm,
                            IndexTupleSize(norm)))
        ereport(ERROR,
                (errcode(ERRCODE_DATA_CORRUPTED),
                 errmsg("heap tuple (%u,%u) from table \"%s\" lacks matching index tuple within index \"%s\"",
                        ItemPointerGetBlockNumber(&(itup->t_tid)),
                        ItemPointerGetOffsetNumber(&(itup->t_tid)),
                        RelationGetRelationName(state->heaprel),
                        RelationGetRelationName(state->rel)),
                 !state->readonly
                 ? errhint("Retrying verification using the function bt_index_parent_check() might provide a more specific error.")
                 : 0));
 
    state->heaptuplespresent++;
    pfree(itup);
    /* Cannot leak memory here */
    if (norm != itup)
        pfree(norm);
}

References Assert(), bloom_lacks_element(), bt_normalize_tuple(), ereport, errcode(), ERRCODE_DATA_CORRUPTED, errhint(), errmsg(), ERROR, index_form_tuple(), IndexTupleSize, ItemPointerGetBlockNumber, ItemPointerGetOffsetNumber, pfree(), RelationGetDescr, RelationGetRelationName, IndexTupleData::t_tid, and values.

Referenced by bt_check_every_level().

btree_index_checkable()

static void btree_index_checkable ( Relation  rel )

inlinestatic

Definition at line 348 of file verify_nbtree.c.

{
    if (rel->rd_rel->relkind != RELKIND_INDEX ||
        rel->rd_rel->relam != BTREE_AM_OID)
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("only B-Tree indexes are supported as targets for verification"),
                 errdetail("Relation \"%s\" is not a B-Tree index.",
                           RelationGetRelationName(rel))));
 
    if (RELATION_IS_OTHER_TEMP(rel))
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("cannot access temporary tables of other sessions"),
                 errdetail("Index \"%s\" is associated with temporary relation.",
                           RelationGetRelationName(rel))));
 
    if (!rel->rd_index->indisvalid)
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("cannot check index \"%s\"",
                        RelationGetRelationName(rel)),
                 errdetail("Index is not valid.")));
}

References ereport, errcode(), errdetail(), errmsg(), ERROR, RelationData::rd_index, RelationData::rd_rel, RELATION_IS_OTHER_TEMP, and RelationGetRelationName.

Referenced by bt_index_check_internal().

btree_index_mainfork_expected()

static bool btree_index_mainfork_expected ( Relation  rel )

inlinestatic

Definition at line 382 of file verify_nbtree.c.

{
    if (rel->rd_rel->relpersistence != RELPERSISTENCE_UNLOGGED ||
        !RecoveryInProgress())
        return true;
 
    ereport(DEBUG1,
            (errcode(ERRCODE_READ_ONLY_SQL_TRANSACTION),
             errmsg("cannot verify unlogged index \"%s\" during recovery, skipping",
                    RelationGetRelationName(rel))));
 
    return false;
}

References DEBUG1, ereport, errcode(), errmsg(), RelationData::rd_rel, RecoveryInProgress(), and RelationGetRelationName.

Referenced by bt_index_check_internal().

BTreeTupleGetHeapTIDCareful()

static ItemPointer BTreeTupleGetHeapTIDCareful ( BtreeCheckState *  state, IndexTuple  itup, bool  nonpivot  )

inlinestatic

Definition at line 3172 of file verify_nbtree.c.

{
    ItemPointer htid;
 
    /*
     * Caller determines whether this is supposed to be a pivot or non-pivot
     * tuple using page type and item offset number.  Verify that tuple
     * metadata agrees with this.
     */
    Assert(state->heapkeyspace);
    if (BTreeTupleIsPivot(itup) && nonpivot)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("block %u or its right sibling block or child block in index \"%s\" has unexpected pivot tuple",
                                 state->targetblock,
                                 RelationGetRelationName(state->rel))));
 
    if (!BTreeTupleIsPivot(itup) && !nonpivot)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("block %u or its right sibling block or child block in index \"%s\" has unexpected non-pivot tuple",
                                 state->targetblock,
                                 RelationGetRelationName(state->rel))));
 
    htid = BTreeTupleGetHeapTID(itup);
    if (!ItemPointerIsValid(htid) && nonpivot)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("block %u or its right sibling block or child block in index \"%s\" contains non-pivot tuple that lacks a heap TID",
                        state->targetblock,
                        RelationGetRelationName(state->rel))));
 
    return htid;
}

References Assert(), BTreeTupleGetHeapTID(), BTreeTupleIsPivot(), ereport, errcode(), errmsg(), errmsg_internal(), ERROR, ItemPointerIsValid, and RelationGetRelationName.

Referenced by invariant_l_nontarget_offset(), and invariant_l_offset().

BTreeTupleGetPointsToTID()

static ItemPointer BTreeTupleGetPointsToTID ( IndexTuple  itup )

inlinestatic

Definition at line 3220 of file verify_nbtree.c.

{
    /*
     * Rely on the assumption that !heapkeyspace internal page data items will
     * correctly return TID with downlink here -- BTreeTupleGetHeapTID() won't
     * recognize it as a pivot tuple, but everything still works out because
     * the t_tid field is still returned
     */
    if (!BTreeTupleIsPivot(itup))
        return BTreeTupleGetHeapTID(itup);
 
    /* Pivot tuple returns TID with downlink block (heapkeyspace variant) */
    return &itup->t_tid;
}

References BTreeTupleGetHeapTID(), BTreeTupleIsPivot(), and IndexTupleData::t_tid.

Referenced by bt_target_page_check().

invariant_g_offset()

static bool invariant_g_offset ( BtreeCheckState *  state, BTScanInsert  key, OffsetNumber  lowerbound  )

inlinestatic

Definition at line 2834 of file verify_nbtree.c.

{
    int32       cmp;
 
    Assert(key->pivotsearch);
 
    cmp = _bt_compare(state->rel, key, state->target, lowerbound);
 
    /* pg_upgrade'd indexes may legally have equal sibling tuples */
    if (!key->heapkeyspace)
        return cmp >= 0;
 
    /*
     * No need to consider the possibility that scankey has attributes that we
     * need to force to be interpreted as negative infinity.  _bt_compare() is
     * able to determine that scankey is greater than negative infinity.  The
     * distinction between "==" and "<" isn't interesting here, since
     * corruption is indicated either way.
     */
    return cmp > 0;
}

References _bt_compare(), Assert(), cmp(), and sort-test::key.

Referenced by bt_target_page_check().

invariant_l_nontarget_offset()

static bool invariant_l_nontarget_offset ( BtreeCheckState *  state, BTScanInsert  key, BlockNumber  nontargetblock, Page  nontarget, OffsetNumber  upperbound  )

inlinestatic

Definition at line 2870 of file verify_nbtree.c.

{
    ItemId      itemid;
    int32       cmp;
 
    Assert(key->pivotsearch);
 
    /* Verify line pointer before checking tuple */
    itemid = PageGetItemIdCareful(state, nontargetblock, nontarget,
                                  upperbound);
    cmp = _bt_compare(state->rel, key, nontarget, upperbound);
 
    /* pg_upgrade'd indexes may legally have equal sibling tuples */
    if (!key->heapkeyspace)
        return cmp <= 0;
 
    /* See invariant_l_offset() for an explanation of this extra step */
    if (cmp == 0)
    {
        IndexTuple  child;
        int         uppnkeyatts;
        ItemPointer childheaptid;
        BTPageOpaque copaque;
        bool        nonpivot;
 
        child = (IndexTuple) PageGetItem(nontarget, itemid);
        copaque = (BTPageOpaque) PageGetSpecialPointer(nontarget);
        nonpivot = P_ISLEAF(copaque) && upperbound >= P_FIRSTDATAKEY(copaque);
 
        /* Get number of keys + heap TID for child/non-target item */
        uppnkeyatts = BTreeTupleGetNKeyAtts(child, state->rel);
        childheaptid = BTreeTupleGetHeapTIDCareful(state, child, nonpivot);
 
        /* Heap TID is tiebreaker key attribute */
        if (key->keysz == uppnkeyatts)
            return key->scantid == NULL && childheaptid != NULL;
 
        return key->keysz < uppnkeyatts;
    }
 
    return cmp < 0;
}

References _bt_compare(), Assert(), BTreeTupleGetHeapTIDCareful(), BTreeTupleGetNKeyAtts, cmp(), sort-test::key, P_FIRSTDATAKEY, P_ISLEAF, PageGetItem, PageGetItemIdCareful(), and PageGetSpecialPointer.

Referenced by bt_child_check().

invariant_l_offset()

static bool invariant_l_offset ( BtreeCheckState *  state, BTScanInsert  key, OffsetNumber  upperbound  )

inlinestatic

Definition at line 2748 of file verify_nbtree.c.

{
    ItemId      itemid;
    int32       cmp;
 
    Assert(key->pivotsearch);
 
    /* Verify line pointer before checking tuple */
    itemid = PageGetItemIdCareful(state, state->targetblock, state->target,
                                  upperbound);
    /* pg_upgrade'd indexes may legally have equal sibling tuples */
    if (!key->heapkeyspace)
        return invariant_leq_offset(state, key, upperbound);
 
    cmp = _bt_compare(state->rel, key, state->target, upperbound);
 
    /*
     * _bt_compare() is capable of determining that a scankey with a
     * filled-out attribute is greater than pivot tuples where the comparison
     * is resolved at a truncated attribute (value of attribute in pivot is
     * minus infinity).  However, it is not capable of determining that a
     * scankey is _less than_ a tuple on the basis of a comparison resolved at
     * _scankey_ minus infinity attribute.  Complete an extra step to simulate
     * having minus infinity values for omitted scankey attribute(s).
     */
    if (cmp == 0)
    {
        BTPageOpaque topaque;
        IndexTuple  ritup;
        int         uppnkeyatts;
        ItemPointer rheaptid;
        bool        nonpivot;
 
        ritup = (IndexTuple) PageGetItem(state->target, itemid);
        topaque = (BTPageOpaque) PageGetSpecialPointer(state->target);
        nonpivot = P_ISLEAF(topaque) && upperbound >= P_FIRSTDATAKEY(topaque);
 
        /* Get number of keys + heap TID for item to the right */
        uppnkeyatts = BTreeTupleGetNKeyAtts(ritup, state->rel);
        rheaptid = BTreeTupleGetHeapTIDCareful(state, ritup, nonpivot);
 
        /* Heap TID is tiebreaker key attribute */
        if (key->keysz == uppnkeyatts)
            return key->scantid == NULL && rheaptid != NULL;
 
        return key->keysz < uppnkeyatts;
    }
 
    return cmp < 0;
}

References _bt_compare(), Assert(), BTreeTupleGetHeapTIDCareful(), BTreeTupleGetNKeyAtts, cmp(), invariant_leq_offset(), sort-test::key, P_FIRSTDATAKEY, P_ISLEAF, PageGetItem, PageGetItemIdCareful(), and PageGetSpecialPointer.

Referenced by bt_target_page_check().

invariant_leq_offset()

static bool invariant_leq_offset ( BtreeCheckState *  state, BTScanInsert  key, OffsetNumber  upperbound  )

inlinestatic

Definition at line 2811 of file verify_nbtree.c.

{
    int32       cmp;
 
    Assert(key->pivotsearch);
 
    cmp = _bt_compare(state->rel, key, state->target, upperbound);
 
    return cmp <= 0;
}

References _bt_compare(), Assert(), cmp(), and sort-test::key.

Referenced by bt_target_page_check(), and invariant_l_offset().

offset_is_negative_infinity()

static bool offset_is_negative_infinity ( BTPageOpaque  opaque, OffsetNumber  offset  )

inlinestatic

Definition at line 2713 of file verify_nbtree.c.

{
    /*
     * For internal pages only, the first item after high key, if any, is
     * negative infinity item.  Internal pages always have a negative infinity
     * item, whereas leaf pages never have one.  This implies that negative
     * infinity item is either first or second line item, or there is none
     * within page.
     *
     * Negative infinity items are a special case among pivot tuples.  They
     * always have zero attributes, while all other pivot tuples always have
     * nkeyatts attributes.
     *
     * Right-most pages don't have a high key, but could be said to
     * conceptually have a "positive infinity" high key.  Thus, there is a
     * symmetry between down link items in parent pages, and high keys in
     * children.  Together, they represent the part of the key space that
     * belongs to each page in the index.  For example, all children of the
     * root page will have negative infinity as a lower bound from root
     * negative infinity downlink, and positive infinity as an upper bound
     * (implicitly, from "imaginary" positive infinity high key in root).
     */
    return !P_ISLEAF(opaque) && offset == P_FIRSTDATAKEY(opaque);
}

References P_FIRSTDATAKEY, and P_ISLEAF.

Referenced by bt_child_check(), bt_child_highkey_check(), and bt_target_page_check().

PageGetItemIdCareful()

static ItemId PageGetItemIdCareful ( BtreeCheckState *  state, BlockNumber  block, Page  page, OffsetNumber  offset  )

static

Definition at line 3132 of file verify_nbtree.c.

{
    ItemId      itemid = PageGetItemId(page, offset);
 
    if (ItemIdGetOffset(itemid) + ItemIdGetLength(itemid) >
        BLCKSZ - MAXALIGN(sizeof(BTPageOpaqueData)))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("line pointer points past end of tuple space in index \"%s\"",
                        RelationGetRelationName(state->rel)),
                 errdetail_internal("Index tid=(%u,%u) lp_off=%u, lp_len=%u lp_flags=%u.",
                                    block, offset, ItemIdGetOffset(itemid),
                                    ItemIdGetLength(itemid),
                                    ItemIdGetFlags(itemid))));
 
    /*
     * Verify that line pointer isn't LP_REDIRECT or LP_UNUSED, since nbtree
     * never uses either.  Verify that line pointer has storage, too, since
     * even LP_DEAD items should within nbtree.
     */
    if (ItemIdIsRedirected(itemid) || !ItemIdIsUsed(itemid) ||
        ItemIdGetLength(itemid) == 0)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("invalid line pointer storage in index \"%s\"",
                        RelationGetRelationName(state->rel)),
                 errdetail_internal("Index tid=(%u,%u) lp_off=%u, lp_len=%u lp_flags=%u.",
                                    block, offset, ItemIdGetOffset(itemid),
                                    ItemIdGetLength(itemid),
                                    ItemIdGetFlags(itemid))));
 
    return itemid;
}

References ereport, errcode(), errdetail_internal(), errmsg(), ERROR, ItemIdGetFlags, ItemIdGetLength, ItemIdGetOffset, ItemIdIsRedirected, ItemIdIsUsed, MAXALIGN, PageGetItemId, and RelationGetRelationName.

Referenced by bt_check_level_from_leftmost(), bt_child_check(), bt_child_highkey_check(), bt_downlink_missing_check(), bt_right_page_check_scankey(), bt_target_page_check(), invariant_l_nontarget_offset(), and invariant_l_offset().

palloc_btree_page()

static Page palloc_btree_page ( BtreeCheckState *  state, BlockNumber  blocknum  )

static

Definition at line 2930 of file verify_nbtree.c.

{
    Buffer      buffer;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber maxoffset;
 
    page = palloc(BLCKSZ);
 
    /*
     * We copy the page into local storage to avoid holding pin on the buffer
     * longer than we must.
     */
    buffer = ReadBufferExtended(state->rel, MAIN_FORKNUM, blocknum, RBM_NORMAL,
                                state->checkstrategy);
    LockBuffer(buffer, BT_READ);
 
    /*
     * Perform the same basic sanity checking that nbtree itself performs for
     * every page:
     */
    _bt_checkpage(state->rel, buffer);
 
    /* Only use copy of page in palloc()'d memory */
    memcpy(page, BufferGetPage(buffer), BLCKSZ);
    UnlockReleaseBuffer(buffer);
 
    opaque = (BTPageOpaque) PageGetSpecialPointer(page);
 
    if (P_ISMETA(opaque) && blocknum != BTREE_METAPAGE)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("invalid meta page found at block %u in index \"%s\"",
                        blocknum, RelationGetRelationName(state->rel))));
 
    /* Check page from block that ought to be meta page */
    if (blocknum == BTREE_METAPAGE)
    {
        BTMetaPageData *metad = BTPageGetMeta(page);
 
        if (!P_ISMETA(opaque) ||
            metad->btm_magic != BTREE_MAGIC)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("index \"%s\" meta page is corrupt",
                            RelationGetRelationName(state->rel))));
 
        if (metad->btm_version < BTREE_MIN_VERSION ||
            metad->btm_version > BTREE_VERSION)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg("version mismatch in index \"%s\": file version %d, "
                            "current version %d, minimum supported version %d",
                            RelationGetRelationName(state->rel),
                            metad->btm_version, BTREE_VERSION,
                            BTREE_MIN_VERSION)));
 
        /* Finished with metapage checks */
        return page;
    }
 
    /*
     * Deleted pages that still use the old 32-bit XID representation have no
     * sane "level" field because they type pun the field, but all other pages
     * (including pages deleted on Postgres 14+) have a valid value.
     */
    if (!P_ISDELETED(opaque) || P_HAS_FULLXID(opaque))
    {
        /* Okay, no reason not to trust btpo_level field from page */
 
        if (P_ISLEAF(opaque) && opaque->btpo_level != 0)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("invalid leaf page level %u for block %u in index \"%s\"",
                                     opaque->btpo_level, blocknum,
                                     RelationGetRelationName(state->rel))));
 
        if (!P_ISLEAF(opaque) && opaque->btpo_level == 0)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("invalid internal page level 0 for block %u in index \"%s\"",
                                     blocknum,
                                     RelationGetRelationName(state->rel))));
    }
 
    /*
     * Sanity checks for number of items on page.
     *
     * As noted at the beginning of _bt_binsrch(), an internal page must have
     * children, since there must always be a negative infinity downlink
     * (there may also be a highkey).  In the case of non-rightmost leaf
     * pages, there must be at least a highkey.  The exceptions are deleted
     * pages, which contain no items.
     *
     * This is correct when pages are half-dead, since internal pages are
     * never half-dead, and leaf pages must have a high key when half-dead
     * (the rightmost page can never be deleted).  It's also correct with
     * fully deleted pages: _bt_unlink_halfdead_page() doesn't change anything
     * about the target page other than setting the page as fully dead, and
     * setting its xact field.  In particular, it doesn't change the sibling
     * links in the deletion target itself, since they're required when index
     * scans land on the deletion target, and then need to move right (or need
     * to move left, in the case of backward index scans).
     */
    maxoffset = PageGetMaxOffsetNumber(page);
    if (maxoffset > MaxIndexTuplesPerPage)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("Number of items on block %u of index \"%s\" exceeds MaxIndexTuplesPerPage (%u)",
                        blocknum, RelationGetRelationName(state->rel),
                        MaxIndexTuplesPerPage)));
 
    if (!P_ISLEAF(opaque) && !P_ISDELETED(opaque) && maxoffset < P_FIRSTDATAKEY(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("internal block %u in index \"%s\" lacks high key and/or at least one downlink",
                        blocknum, RelationGetRelationName(state->rel))));
 
    if (P_ISLEAF(opaque) && !P_ISDELETED(opaque) && !P_RIGHTMOST(opaque) && maxoffset < P_HIKEY)
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("non-rightmost leaf block %u in index \"%s\" lacks high key item",
                        blocknum, RelationGetRelationName(state->rel))));
 
    /*
     * In general, internal pages are never marked half-dead, except on
     * versions of Postgres prior to 9.4, where it can be valid transient
     * state.  This state is nonetheless treated as corruption by VACUUM on
     * from version 9.4 on, so do the same here.  See _bt_pagedel() for full
     * details.
     */
    if (!P_ISLEAF(opaque) && P_ISHALFDEAD(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg("internal page block %u in index \"%s\" is half-dead",
                        blocknum, RelationGetRelationName(state->rel)),
                 errhint("This can be caused by an interrupted VACUUM in version 9.3 or older, before upgrade. Please REINDEX it.")));
 
    /*
     * Check that internal pages have no garbage items, and that no page has
     * an invalid combination of deletion-related page level flags
     */
    if (!P_ISLEAF(opaque) && P_HAS_GARBAGE(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("internal page block %u in index \"%s\" has garbage items",
                                 blocknum, RelationGetRelationName(state->rel))));
 
    if (P_HAS_FULLXID(opaque) && !P_ISDELETED(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("full transaction id page flag appears in non-deleted block %u in index \"%s\"",
                                 blocknum, RelationGetRelationName(state->rel))));
 
    if (P_ISDELETED(opaque) && P_ISHALFDEAD(opaque))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("deleted page block %u in index \"%s\" is half-dead",
                                 blocknum, RelationGetRelationName(state->rel))));
 
    return page;
}

References _bt_checkpage(), BT_READ, BTMetaPageData::btm_magic, BTMetaPageData::btm_version, BTPageGetMeta, BTPageOpaqueData::btpo_level, BTREE_MAGIC, BTREE_METAPAGE, BTREE_MIN_VERSION, BTREE_VERSION, BufferGetPage, ereport, errcode(), errhint(), errmsg(), errmsg_internal(), ERROR, LockBuffer(), MAIN_FORKNUM, MaxIndexTuplesPerPage, P_FIRSTDATAKEY, P_HAS_FULLXID, P_HAS_GARBAGE, P_HIKEY, P_ISDELETED, P_ISHALFDEAD, P_ISLEAF, P_ISMETA, P_RIGHTMOST, PageGetMaxOffsetNumber, PageGetSpecialPointer, palloc(), RBM_NORMAL, ReadBufferExtended(), RelationGetRelationName, and UnlockReleaseBuffer().

Referenced by bt_check_every_level(), bt_check_level_from_leftmost(), bt_child_check(), bt_child_highkey_check(), bt_downlink_missing_check(), bt_right_page_check_scankey(), and bt_target_page_check().

PG_FUNCTION_INFO_V1() [1/2]

PG_FUNCTION_INFO_V1

(

bt_index_check

)

PG_FUNCTION_INFO_V1() [2/2]

PG_FUNCTION_INFO_V1

(

bt_index_parent_check

)

Variable Documentation

PG_MODULE_MAGIC

PG_MODULE_MAGIC

Definition at line 44 of file verify_nbtree.c.