heapam.c File Reference

#include "postgres.h"
#include "access/heapam.h"
#include "access/heaptoast.h"
#include "access/hio.h"
#include "access/multixact.h"
#include "access/subtrans.h"
#include "access/syncscan.h"
#include "access/valid.h"
#include "access/visibilitymap.h"
#include "access/xloginsert.h"
#include "catalog/pg_database.h"
#include "catalog/pg_database_d.h"
#include "commands/vacuum.h"
#include "pgstat.h"
#include "port/pg_bitutils.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "storage/procarray.h"
#include "utils/datum.h"
#include "utils/injection_point.h"
#include "utils/inval.h"
#include "utils/spccache.h"
#include "utils/syscache.h"

Include dependency graph for heapam.c:

Go to the source code of this file.

Data Structures
struct	IndexDeleteCounts

Macros
#define	LOCKMODE_from_mxstatus(status)    (tupleLockExtraInfo[TUPLOCK_from_mxstatus((status))].hwlock)
#define	LockTupleTuplock(rel, tup, mode)    LockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
#define	UnlockTupleTuplock(rel, tup, mode)    UnlockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
#define	ConditionalLockTupleTuplock(rel, tup, mode, log)    ConditionalLockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock, (log))
#define	BOTTOMUP_MAX_NBLOCKS   6
#define	BOTTOMUP_TOLERANCE_NBLOCKS   3
#define	TUPLOCK_from_mxstatus(status)    (MultiXactStatusLock[(status)])
#define	FRM_NOOP   0x0001
#define	FRM_INVALIDATE_XMAX   0x0002
#define	FRM_RETURN_IS_XID   0x0004
#define	FRM_RETURN_IS_MULTI   0x0008
#define	FRM_MARK_COMMITTED   0x0010

Typedefs
typedef struct IndexDeleteCounts	IndexDeleteCounts

Functions
static HeapTuple	heap_prepare_insert (Relation relation, HeapTuple tup, TransactionId xid, CommandId cid, int options)
static XLogRecPtr	log_heap_update (Relation reln, Buffer oldbuf, Buffer newbuf, HeapTuple oldtup, HeapTuple newtup, HeapTuple old_key_tuple, bool all_visible_cleared, bool new_all_visible_cleared)
static Bitmapset *	HeapDetermineColumnsInfo (Relation relation, Bitmapset *interesting_cols, Bitmapset *external_cols, HeapTuple oldtup, HeapTuple newtup, bool *has_external)
static bool	heap_acquire_tuplock (Relation relation, ItemPointer tid, LockTupleMode mode, LockWaitPolicy wait_policy, bool *have_tuple_lock)
static BlockNumber	heapgettup_advance_block (HeapScanDesc scan, BlockNumber block, ScanDirection dir)
static pg_noinline BlockNumber	heapgettup_initial_block (HeapScanDesc scan, ScanDirection dir)
static void	compute_new_xmax_infomask (TransactionId xmax, uint16 old_infomask, uint16 old_infomask2, TransactionId add_to_xmax, LockTupleMode mode, bool is_update, TransactionId *result_xmax, uint16 *result_infomask, uint16 *result_infomask2)
static TM_Result	heap_lock_updated_tuple (Relation rel, HeapTuple tuple, ItemPointer ctid, TransactionId xid, LockTupleMode mode)
static void	GetMultiXactIdHintBits (MultiXactId multi, uint16 *new_infomask, uint16 *new_infomask2)
static TransactionId	MultiXactIdGetUpdateXid (TransactionId xmax, uint16 t_infomask)
static bool	DoesMultiXactIdConflict (MultiXactId multi, uint16 infomask, LockTupleMode lockmode, bool *current_is_member)
static void	MultiXactIdWait (MultiXactId multi, MultiXactStatus status, uint16 infomask, Relation rel, ItemPointer ctid, XLTW_Oper oper, int *remaining)
static bool	ConditionalMultiXactIdWait (MultiXactId multi, MultiXactStatus status, uint16 infomask, Relation rel, int *remaining, bool logLockFailure)
static void	index_delete_sort (TM_IndexDeleteOp *delstate)
static int	bottomup_sort_and_shrink (TM_IndexDeleteOp *delstate)
static XLogRecPtr	log_heap_new_cid (Relation relation, HeapTuple tup)
static HeapTuple	ExtractReplicaIdentity (Relation relation, HeapTuple tp, bool key_required, bool *copy)
static void	AssertHasSnapshotForToast (Relation rel)
static BlockNumber	heap_scan_stream_read_next_parallel (ReadStream *stream, void *callback_private_data, void *per_buffer_data)
static BlockNumber	heap_scan_stream_read_next_serial (ReadStream *stream, void *callback_private_data, void *per_buffer_data)
static BlockNumber	bitmapheap_stream_read_next (ReadStream *pgsr, void *private_data, void *per_buffer_data)
static void	initscan (HeapScanDesc scan, ScanKey key, bool keep_startblock)
void	heap_setscanlimits (TableScanDesc sscan, BlockNumber startBlk, BlockNumber numBlks)
static pg_attribute_always_inline int	page_collect_tuples (HeapScanDesc scan, Snapshot snapshot, Page page, Buffer buffer, BlockNumber block, int lines, bool all_visible, bool check_serializable)
void	heap_prepare_pagescan (TableScanDesc sscan)
static void	heap_fetch_next_buffer (HeapScanDesc scan, ScanDirection dir)
static Page	heapgettup_start_page (HeapScanDesc scan, ScanDirection dir, int *linesleft, OffsetNumber *lineoff)
static Page	heapgettup_continue_page (HeapScanDesc scan, ScanDirection dir, int *linesleft, OffsetNumber *lineoff)
static void	heapgettup (HeapScanDesc scan, ScanDirection dir, int nkeys, ScanKey key)
static void	heapgettup_pagemode (HeapScanDesc scan, ScanDirection dir, int nkeys, ScanKey key)
TableScanDesc	heap_beginscan (Relation relation, Snapshot snapshot, int nkeys, ScanKey key, ParallelTableScanDesc parallel_scan, uint32 flags)
void	heap_rescan (TableScanDesc sscan, ScanKey key, bool set_params, bool allow_strat, bool allow_sync, bool allow_pagemode)
void	heap_endscan (TableScanDesc sscan)
HeapTuple	heap_getnext (TableScanDesc sscan, ScanDirection direction)
bool	heap_getnextslot (TableScanDesc sscan, ScanDirection direction, TupleTableSlot *slot)
void	heap_set_tidrange (TableScanDesc sscan, ItemPointer mintid, ItemPointer maxtid)
bool	heap_getnextslot_tidrange (TableScanDesc sscan, ScanDirection direction, TupleTableSlot *slot)
bool	heap_fetch (Relation relation, Snapshot snapshot, HeapTuple tuple, Buffer *userbuf, bool keep_buf)
bool	heap_hot_search_buffer (ItemPointer tid, Relation relation, Buffer buffer, Snapshot snapshot, HeapTuple heapTuple, bool *all_dead, bool first_call)
void	heap_get_latest_tid (TableScanDesc sscan, ItemPointer tid)
static void	UpdateXmaxHintBits (HeapTupleHeader tuple, Buffer buffer, TransactionId xid)
BulkInsertState	GetBulkInsertState (void)
void	FreeBulkInsertState (BulkInsertState bistate)
void	ReleaseBulkInsertStatePin (BulkInsertState bistate)
void	heap_insert (Relation relation, HeapTuple tup, CommandId cid, int options, BulkInsertState bistate)
static int	heap_multi_insert_pages (HeapTuple *heaptuples, int done, int ntuples, Size saveFreeSpace)
void	heap_multi_insert (Relation relation, TupleTableSlot **slots, int ntuples, CommandId cid, int options, BulkInsertState bistate)
void	simple_heap_insert (Relation relation, HeapTuple tup)
static uint8	compute_infobits (uint16 infomask, uint16 infomask2)
static bool	xmax_infomask_changed (uint16 new_infomask, uint16 old_infomask)
TM_Result	heap_delete (Relation relation, ItemPointer tid, CommandId cid, Snapshot crosscheck, bool wait, TM_FailureData *tmfd, bool changingPart)
void	simple_heap_delete (Relation relation, ItemPointer tid)
TM_Result	heap_update (Relation relation, ItemPointer otid, HeapTuple newtup, CommandId cid, Snapshot crosscheck, bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes)
static bool	heap_attr_equals (TupleDesc tupdesc, int attrnum, Datum value1, Datum value2, bool isnull1, bool isnull2)
void	simple_heap_update (Relation relation, ItemPointer otid, HeapTuple tup, TU_UpdateIndexes *update_indexes)
static MultiXactStatus	get_mxact_status_for_lock (LockTupleMode mode, bool is_update)
TM_Result	heap_lock_tuple (Relation relation, HeapTuple tuple, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, bool follow_updates, Buffer *buffer, TM_FailureData *tmfd)
static TM_Result	test_lockmode_for_conflict (MultiXactStatus status, TransactionId xid, LockTupleMode mode, HeapTuple tup, bool *needwait)
static TM_Result	heap_lock_updated_tuple_rec (Relation rel, ItemPointer tid, TransactionId xid, LockTupleMode mode)
void	heap_finish_speculative (Relation relation, ItemPointer tid)
void	heap_abort_speculative (Relation relation, ItemPointer tid)
bool	heap_inplace_lock (Relation relation, HeapTuple oldtup_ptr, Buffer buffer, void(*release_callback)(void *), void *arg)
void	heap_inplace_update_and_unlock (Relation relation, HeapTuple oldtup, HeapTuple tuple, Buffer buffer)
void	heap_inplace_unlock (Relation relation, HeapTuple oldtup, Buffer buffer)
static TransactionId	FreezeMultiXactId (MultiXactId multi, uint16 t_infomask, const struct VacuumCutoffs *cutoffs, uint16 *flags, HeapPageFreeze *pagefrz)
bool	heap_prepare_freeze_tuple (HeapTupleHeader tuple, const struct VacuumCutoffs *cutoffs, HeapPageFreeze *pagefrz, HeapTupleFreeze *frz, bool *totally_frozen)
void	heap_pre_freeze_checks (Buffer buffer, HeapTupleFreeze *tuples, int ntuples)
void	heap_freeze_prepared_tuples (Buffer buffer, HeapTupleFreeze *tuples, int ntuples)
bool	heap_freeze_tuple (HeapTupleHeader tuple, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId FreezeLimit, TransactionId MultiXactCutoff)
TransactionId	HeapTupleGetUpdateXid (const HeapTupleHeaderData *tup)
static bool	Do_MultiXactIdWait (MultiXactId multi, MultiXactStatus status, uint16 infomask, bool nowait, Relation rel, ItemPointer ctid, XLTW_Oper oper, int *remaining, bool logLockFailure)
bool	heap_tuple_needs_eventual_freeze (HeapTupleHeader tuple)
bool	heap_tuple_should_freeze (HeapTupleHeader tuple, const struct VacuumCutoffs *cutoffs, TransactionId *NoFreezePageRelfrozenXid, MultiXactId *NoFreezePageRelminMxid)
void	HeapTupleHeaderAdvanceConflictHorizon (HeapTupleHeader tuple, TransactionId *snapshotConflictHorizon)
static void	index_delete_check_htid (TM_IndexDeleteOp *delstate, Page page, OffsetNumber maxoff, ItemPointer htid, TM_IndexStatus *istatus)
TransactionId	heap_index_delete_tuples (Relation rel, TM_IndexDeleteOp *delstate)
static int	index_delete_sort_cmp (TM_IndexDelete *deltid1, TM_IndexDelete *deltid2)
static int	bottomup_nblocksfavorable (IndexDeleteCounts *blockgroups, int nblockgroups, TM_IndexDelete *deltids)
static int	bottomup_sort_and_shrink_cmp (const void *arg1, const void *arg2)
XLogRecPtr	log_heap_visible (Relation rel, Buffer heap_buffer, Buffer vm_buffer, TransactionId snapshotConflictHorizon, uint8 vmflags)
void	HeapCheckForSerializableConflictOut (bool visible, Relation relation, HeapTuple tuple, Buffer buffer, Snapshot snapshot)

Variables
struct {
LOCKMODE   hwlock
int   lockstatus
int   updstatus
}	tupleLockExtraInfo [MaxLockTupleMode+1]
static const int	MultiXactStatusLock [MaxMultiXactStatus+1]

Macro Definition Documentation

BOTTOMUP_MAX_NBLOCKS

#define BOTTOMUP_MAX_NBLOCKS   6

Definition at line 184 of file heapam.c.

BOTTOMUP_TOLERANCE_NBLOCKS

#define BOTTOMUP_TOLERANCE_NBLOCKS   3

Definition at line 185 of file heapam.c.

ConditionalLockTupleTuplock

#define ConditionalLockTupleTuplock	(		rel,
			tup,
			mode,
			log
	)		ConditionalLockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock, (log))

Definition at line 166 of file heapam.c.

FRM_INVALIDATE_XMAX

#define FRM_INVALIDATE_XMAX   0x0002

Definition at line 6652 of file heapam.c.

FRM_MARK_COMMITTED

#define FRM_MARK_COMMITTED   0x0010

Definition at line 6655 of file heapam.c.

FRM_NOOP

#define FRM_NOOP   0x0001

Definition at line 6651 of file heapam.c.

FRM_RETURN_IS_MULTI

#define FRM_RETURN_IS_MULTI   0x0008

Definition at line 6654 of file heapam.c.

FRM_RETURN_IS_XID

#define FRM_RETURN_IS_XID   0x0004

Definition at line 6653 of file heapam.c.

LOCKMODE_from_mxstatus

#define LOCKMODE_from_mxstatus

(

status

)

(tupleLockExtraInfo[TUPLOCK_from_mxstatus((status))].hwlock)

Definition at line 154 of file heapam.c.

LockTupleTuplock

#define LockTupleTuplock	(		rel,
			tup,
			mode
	)		LockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)

Definition at line 162 of file heapam.c.

TUPLOCK_from_mxstatus

#define TUPLOCK_from_mxstatus

(

status

)

(MultiXactStatusLock[(status)])

Definition at line 213 of file heapam.c.

UnlockTupleTuplock

#define UnlockTupleTuplock	(		rel,
			tup,
			mode
	)		UnlockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)

Definition at line 164 of file heapam.c.

Typedef Documentation

IndexDeleteCounts

typedef struct IndexDeleteCounts IndexDeleteCounts

Function Documentation

AssertHasSnapshotForToast()

static void AssertHasSnapshotForToast ( Relation  rel )

inlinestatic

Definition at line 220 of file heapam.c.

{
#ifdef USE_ASSERT_CHECKING
 
    /* bootstrap mode in particular breaks this rule */
    if (!IsNormalProcessingMode())
        return;
 
    /* if the relation doesn't have a TOAST table, we are good */
    if (!OidIsValid(rel->rd_rel->reltoastrelid))
        return;
 
    Assert(HaveRegisteredOrActiveSnapshot());
 
#endif                          /* USE_ASSERT_CHECKING */
}

References Assert(), HaveRegisteredOrActiveSnapshot(), IsNormalProcessingMode, OidIsValid, and RelationData::rd_rel.

Referenced by heap_delete(), heap_insert(), heap_multi_insert(), and heap_update().

bitmapheap_stream_read_next()

static BlockNumber bitmapheap_stream_read_next ( ReadStream *  pgsr, void *  private_data, void *  per_buffer_data  )

static

Definition at line 310 of file heapam.c.

{
    TBMIterateResult *tbmres = per_buffer_data;
    BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) private_data;
    HeapScanDesc hscan = (HeapScanDesc) bscan;
    TableScanDesc sscan = &hscan->rs_base;
 
    for (;;)
    {
        CHECK_FOR_INTERRUPTS();
 
        /* no more entries in the bitmap */
        if (!tbm_iterate(&sscan->st.rs_tbmiterator, tbmres))
            return InvalidBlockNumber;
 
        /*
         * Ignore any claimed entries past what we think is the end of the
         * relation. It may have been extended after the start of our scan (we
         * only hold an AccessShareLock, and it could be inserts from this
         * backend).  We don't take this optimization in SERIALIZABLE
         * isolation though, as we need to examine all invisible tuples
         * reachable by the index.
         */
        if (!IsolationIsSerializable() &&
            tbmres->blockno >= hscan->rs_nblocks)
            continue;
 
        return tbmres->blockno;
    }
 
    /* not reachable */
    Assert(false);
}

References Assert(), TBMIterateResult::blockno, CHECK_FOR_INTERRUPTS, InvalidBlockNumber, IsolationIsSerializable, HeapScanDescData::rs_base, HeapScanDescData::rs_nblocks, TableScanDescData::rs_tbmiterator, TableScanDescData::st, and tbm_iterate().

Referenced by heap_beginscan().

bottomup_nblocksfavorable()

static int bottomup_nblocksfavorable ( IndexDeleteCounts *  blockgroups, int  nblockgroups, TM_IndexDelete *  deltids  )

static

Definition at line 8559 of file heapam.c.

{
    int64       lastblock = -1;
    int         nblocksfavorable = 0;
 
    Assert(nblockgroups >= 1);
    Assert(nblockgroups <= BOTTOMUP_MAX_NBLOCKS);
 
    /*
     * We tolerate heap blocks that will be accessed only slightly out of
     * physical order.  Small blips occur when a pair of almost-contiguous
     * blocks happen to fall into different buckets (perhaps due only to a
     * small difference in npromisingtids that the bucketing scheme didn't
     * quite manage to ignore).  We effectively ignore these blips by applying
     * a small tolerance.  The precise tolerance we use is a little arbitrary,
     * but it works well enough in practice.
     */
    for (int b = 0; b < nblockgroups; b++)
    {
        IndexDeleteCounts *group = blockgroups + b;
        TM_IndexDelete *firstdtid = deltids + group->ifirsttid;
        BlockNumber block = ItemPointerGetBlockNumber(&firstdtid->tid);
 
        if (lastblock != -1 &&
            ((int64) block < lastblock - BOTTOMUP_TOLERANCE_NBLOCKS ||
             (int64) block > lastblock + BOTTOMUP_TOLERANCE_NBLOCKS))
            break;
 
        nblocksfavorable++;
        lastblock = block;
    }
 
    /* Always indicate that there is at least 1 favorable block */
    Assert(nblocksfavorable >= 1);
 
    return nblocksfavorable;
}

References Assert(), b, BOTTOMUP_MAX_NBLOCKS, BOTTOMUP_TOLERANCE_NBLOCKS, IndexDeleteCounts::ifirsttid, ItemPointerGetBlockNumber(), and TM_IndexDelete::tid.

Referenced by bottomup_sort_and_shrink().

bottomup_sort_and_shrink()

static int bottomup_sort_and_shrink ( TM_IndexDeleteOp *  delstate )

static

Definition at line 8675 of file heapam.c.

{
    IndexDeleteCounts *blockgroups;
    TM_IndexDelete *reordereddeltids;
    BlockNumber curblock = InvalidBlockNumber;
    int         nblockgroups = 0;
    int         ncopied = 0;
    int         nblocksfavorable = 0;
 
    Assert(delstate->bottomup);
    Assert(delstate->ndeltids > 0);
 
    /* Calculate per-heap-block count of TIDs */
    blockgroups = palloc(sizeof(IndexDeleteCounts) * delstate->ndeltids);
    for (int i = 0; i < delstate->ndeltids; i++)
    {
        TM_IndexDelete *ideltid = &delstate->deltids[i];
        TM_IndexStatus *istatus = delstate->status + ideltid->id;
        ItemPointer htid = &ideltid->tid;
        bool        promising = istatus->promising;
 
        if (curblock != ItemPointerGetBlockNumber(htid))
        {
            /* New block group */
            nblockgroups++;
 
            Assert(curblock < ItemPointerGetBlockNumber(htid) ||
                   !BlockNumberIsValid(curblock));
 
            curblock = ItemPointerGetBlockNumber(htid);
            blockgroups[nblockgroups - 1].ifirsttid = i;
            blockgroups[nblockgroups - 1].ntids = 1;
            blockgroups[nblockgroups - 1].npromisingtids = 0;
        }
        else
        {
            blockgroups[nblockgroups - 1].ntids++;
        }
 
        if (promising)
            blockgroups[nblockgroups - 1].npromisingtids++;
    }
 
    /*
     * We're about ready to sort block groups to determine the optimal order
     * for visiting heap blocks.  But before we do, round the number of
     * promising tuples for each block group up to the next power-of-two,
     * unless it is very low (less than 4), in which case we round up to 4.
     * npromisingtids is far too noisy to trust when choosing between a pair
     * of block groups that both have very low values.
     *
     * This scheme divides heap blocks/block groups into buckets.  Each bucket
     * contains blocks that have _approximately_ the same number of promising
     * TIDs as each other.  The goal is to ignore relatively small differences
     * in the total number of promising entries, so that the whole process can
     * give a little weight to heapam factors (like heap block locality)
     * instead.  This isn't a trade-off, really -- we have nothing to lose. It
     * would be foolish to interpret small differences in npromisingtids
     * values as anything more than noise.
     *
     * We tiebreak on nhtids when sorting block group subsets that have the
     * same npromisingtids, but this has the same issues as npromisingtids,
     * and so nhtids is subject to the same power-of-two bucketing scheme. The
     * only reason that we don't fix nhtids in the same way here too is that
     * we'll need accurate nhtids values after the sort.  We handle nhtids
     * bucketization dynamically instead (in the sort comparator).
     *
     * See bottomup_nblocksfavorable() for a full explanation of when and how
     * heap locality/favorable blocks can significantly influence when and how
     * heap blocks are accessed.
     */
    for (int b = 0; b < nblockgroups; b++)
    {
        IndexDeleteCounts *group = blockgroups + b;
 
        /* Better off falling back on nhtids with low npromisingtids */
        if (group->npromisingtids <= 4)
            group->npromisingtids = 4;
        else
            group->npromisingtids =
                pg_nextpower2_32((uint32) group->npromisingtids);
    }
 
    /* Sort groups and rearrange caller's deltids array */
    qsort(blockgroups, nblockgroups, sizeof(IndexDeleteCounts),
          bottomup_sort_and_shrink_cmp);
    reordereddeltids = palloc(delstate->ndeltids * sizeof(TM_IndexDelete));
 
    nblockgroups = Min(BOTTOMUP_MAX_NBLOCKS, nblockgroups);
    /* Determine number of favorable blocks at the start of final deltids */
    nblocksfavorable = bottomup_nblocksfavorable(blockgroups, nblockgroups,
                                                 delstate->deltids);
 
    for (int b = 0; b < nblockgroups; b++)
    {
        IndexDeleteCounts *group = blockgroups + b;
        TM_IndexDelete *firstdtid = delstate->deltids + group->ifirsttid;
 
        memcpy(reordereddeltids + ncopied, firstdtid,
               sizeof(TM_IndexDelete) * group->ntids);
        ncopied += group->ntids;
    }
 
    /* Copy final grouped and sorted TIDs back into start of caller's array */
    memcpy(delstate->deltids, reordereddeltids,
           sizeof(TM_IndexDelete) * ncopied);
    delstate->ndeltids = ncopied;
 
    pfree(reordereddeltids);
    pfree(blockgroups);
 
    return nblocksfavorable;
}

References Assert(), b, BlockNumberIsValid(), TM_IndexDeleteOp::bottomup, BOTTOMUP_MAX_NBLOCKS, bottomup_nblocksfavorable(), bottomup_sort_and_shrink_cmp(), TM_IndexDeleteOp::deltids, i, TM_IndexDelete::id, IndexDeleteCounts::ifirsttid, InvalidBlockNumber, ItemPointerGetBlockNumber(), Min, TM_IndexDeleteOp::ndeltids, IndexDeleteCounts::npromisingtids, IndexDeleteCounts::ntids, palloc(), pfree(), pg_nextpower2_32(), TM_IndexStatus::promising, qsort, TM_IndexDeleteOp::status, and TM_IndexDelete::tid.

Referenced by heap_index_delete_tuples().

bottomup_sort_and_shrink_cmp()

static int bottomup_sort_and_shrink_cmp ( const void *  arg1, const void *  arg2  )

static

Definition at line 8602 of file heapam.c.

{
    const IndexDeleteCounts *group1 = (const IndexDeleteCounts *) arg1;
    const IndexDeleteCounts *group2 = (const IndexDeleteCounts *) arg2;
 
    /*
     * Most significant field is npromisingtids (which we invert the order of
     * so as to sort in desc order).
     *
     * Caller should have already normalized npromisingtids fields into
     * power-of-two values (buckets).
     */
    if (group1->npromisingtids > group2->npromisingtids)
        return -1;
    if (group1->npromisingtids < group2->npromisingtids)
        return 1;
 
    /*
     * Tiebreak: desc ntids sort order.
     *
     * We cannot expect power-of-two values for ntids fields.  We should
     * behave as if they were already rounded up for us instead.
     */
    if (group1->ntids != group2->ntids)
    {
        uint32      ntids1 = pg_nextpower2_32((uint32) group1->ntids);
        uint32      ntids2 = pg_nextpower2_32((uint32) group2->ntids);
 
        if (ntids1 > ntids2)
            return -1;
        if (ntids1 < ntids2)
            return 1;
    }
 
    /*
     * Tiebreak: asc offset-into-deltids-for-block (offset to first TID for
     * block in deltids array) order.
     *
     * This is equivalent to sorting in ascending heap block number order
     * (among otherwise equal subsets of the array).  This approach allows us
     * to avoid accessing the out-of-line TID.  (We rely on the assumption
     * that the deltids array was sorted in ascending heap TID order when
     * these offsets to the first TID from each heap block group were formed.)
     */
    if (group1->ifirsttid > group2->ifirsttid)
        return 1;
    if (group1->ifirsttid < group2->ifirsttid)
        return -1;
 
    pg_unreachable();
 
    return 0;
}

References IndexDeleteCounts::ifirsttid, IndexDeleteCounts::npromisingtids, IndexDeleteCounts::ntids, pg_nextpower2_32(), and pg_unreachable.

Referenced by bottomup_sort_and_shrink().

compute_infobits()

static uint8 compute_infobits ( uint16  infomask, uint16  infomask2  )

static

Definition at line 2733 of file heapam.c.

{
    return
        ((infomask & HEAP_XMAX_IS_MULTI) != 0 ? XLHL_XMAX_IS_MULTI : 0) |
        ((infomask & HEAP_XMAX_LOCK_ONLY) != 0 ? XLHL_XMAX_LOCK_ONLY : 0) |
        ((infomask & HEAP_XMAX_EXCL_LOCK) != 0 ? XLHL_XMAX_EXCL_LOCK : 0) |
    /* note we ignore HEAP_XMAX_SHR_LOCK here */
        ((infomask & HEAP_XMAX_KEYSHR_LOCK) != 0 ? XLHL_XMAX_KEYSHR_LOCK : 0) |
        ((infomask2 & HEAP_KEYS_UPDATED) != 0 ?
         XLHL_KEYS_UPDATED : 0);
}

References HEAP_KEYS_UPDATED, HEAP_XMAX_EXCL_LOCK, HEAP_XMAX_IS_MULTI, HEAP_XMAX_KEYSHR_LOCK, HEAP_XMAX_LOCK_ONLY, XLHL_KEYS_UPDATED, XLHL_XMAX_EXCL_LOCK, XLHL_XMAX_IS_MULTI, XLHL_XMAX_KEYSHR_LOCK, and XLHL_XMAX_LOCK_ONLY.

Referenced by heap_abort_speculative(), heap_delete(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), heap_update(), and log_heap_update().

compute_new_xmax_infomask()

static void compute_new_xmax_infomask ( TransactionId  xmax, uint16  old_infomask, uint16  old_infomask2, TransactionId  add_to_xmax, LockTupleMode  mode, bool  is_update, TransactionId *  result_xmax, uint16 *  result_infomask, uint16 *  result_infomask2  )

static

Definition at line 5326 of file heapam.c.

{
    TransactionId new_xmax;
    uint16      new_infomask,
                new_infomask2;
 
    Assert(TransactionIdIsCurrentTransactionId(add_to_xmax));
 
l5:
    new_infomask = 0;
    new_infomask2 = 0;
    if (old_infomask & HEAP_XMAX_INVALID)
    {
        /*
         * No previous locker; we just insert our own TransactionId.
         *
         * Note that it's critical that this case be the first one checked,
         * because there are several blocks below that come back to this one
         * to implement certain optimizations; old_infomask might contain
         * other dirty bits in those cases, but we don't really care.
         */
        if (is_update)
        {
            new_xmax = add_to_xmax;
            if (mode == LockTupleExclusive)
                new_infomask2 |= HEAP_KEYS_UPDATED;
        }
        else
        {
            new_infomask |= HEAP_XMAX_LOCK_ONLY;
            switch (mode)
            {
                case LockTupleKeyShare:
                    new_xmax = add_to_xmax;
                    new_infomask |= HEAP_XMAX_KEYSHR_LOCK;
                    break;
                case LockTupleShare:
                    new_xmax = add_to_xmax;
                    new_infomask |= HEAP_XMAX_SHR_LOCK;
                    break;
                case LockTupleNoKeyExclusive:
                    new_xmax = add_to_xmax;
                    new_infomask |= HEAP_XMAX_EXCL_LOCK;
                    break;
                case LockTupleExclusive:
                    new_xmax = add_to_xmax;
                    new_infomask |= HEAP_XMAX_EXCL_LOCK;
                    new_infomask2 |= HEAP_KEYS_UPDATED;
                    break;
                default:
                    new_xmax = InvalidTransactionId;    /* silence compiler */
                    elog(ERROR, "invalid lock mode");
            }
        }
    }
    else if (old_infomask & HEAP_XMAX_IS_MULTI)
    {
        MultiXactStatus new_status;
 
        /*
         * Currently we don't allow XMAX_COMMITTED to be set for multis, so
         * cross-check.
         */
        Assert(!(old_infomask & HEAP_XMAX_COMMITTED));
 
        /*
         * A multixact together with LOCK_ONLY set but neither lock bit set
         * (i.e. a pg_upgraded share locked tuple) cannot possibly be running
         * anymore.  This check is critical for databases upgraded by
         * pg_upgrade; both MultiXactIdIsRunning and MultiXactIdExpand assume
         * that such multis are never passed.
         */
        if (HEAP_LOCKED_UPGRADED(old_infomask))
        {
            old_infomask &= ~HEAP_XMAX_IS_MULTI;
            old_infomask |= HEAP_XMAX_INVALID;
            goto l5;
        }
 
        /*
         * If the XMAX is already a MultiXactId, then we need to expand it to
         * include add_to_xmax; but if all the members were lockers and are
         * all gone, we can do away with the IS_MULTI bit and just set
         * add_to_xmax as the only locker/updater.  If all lockers are gone
         * and we have an updater that aborted, we can also do without a
         * multi.
         *
         * The cost of doing GetMultiXactIdMembers would be paid by
         * MultiXactIdExpand if we weren't to do this, so this check is not
         * incurring extra work anyhow.
         */
        if (!MultiXactIdIsRunning(xmax, HEAP_XMAX_IS_LOCKED_ONLY(old_infomask)))
        {
            if (HEAP_XMAX_IS_LOCKED_ONLY(old_infomask) ||
                !TransactionIdDidCommit(MultiXactIdGetUpdateXid(xmax,
                                                                old_infomask)))
            {
                /*
                 * Reset these bits and restart; otherwise fall through to
                 * create a new multi below.
                 */
                old_infomask &= ~HEAP_XMAX_IS_MULTI;
                old_infomask |= HEAP_XMAX_INVALID;
                goto l5;
            }
        }
 
        new_status = get_mxact_status_for_lock(mode, is_update);
 
        new_xmax = MultiXactIdExpand((MultiXactId) xmax, add_to_xmax,
                                     new_status);
        GetMultiXactIdHintBits(new_xmax, &new_infomask, &new_infomask2);
    }
    else if (old_infomask & HEAP_XMAX_COMMITTED)
    {
        /*
         * It's a committed update, so we need to preserve him as updater of
         * the tuple.
         */
        MultiXactStatus status;
        MultiXactStatus new_status;
 
        if (old_infomask2 & HEAP_KEYS_UPDATED)
            status = MultiXactStatusUpdate;
        else
            status = MultiXactStatusNoKeyUpdate;
 
        new_status = get_mxact_status_for_lock(mode, is_update);
 
        /*
         * since it's not running, it's obviously impossible for the old
         * updater to be identical to the current one, so we need not check
         * for that case as we do in the block above.
         */
        new_xmax = MultiXactIdCreate(xmax, status, add_to_xmax, new_status);
        GetMultiXactIdHintBits(new_xmax, &new_infomask, &new_infomask2);
    }
    else if (TransactionIdIsInProgress(xmax))
    {
        /*
         * If the XMAX is a valid, in-progress TransactionId, then we need to
         * create a new MultiXactId that includes both the old locker or
         * updater and our own TransactionId.
         */
        MultiXactStatus new_status;
        MultiXactStatus old_status;
        LockTupleMode old_mode;
 
        if (HEAP_XMAX_IS_LOCKED_ONLY(old_infomask))
        {
            if (HEAP_XMAX_IS_KEYSHR_LOCKED(old_infomask))
                old_status = MultiXactStatusForKeyShare;
            else if (HEAP_XMAX_IS_SHR_LOCKED(old_infomask))
                old_status = MultiXactStatusForShare;
            else if (HEAP_XMAX_IS_EXCL_LOCKED(old_infomask))
            {
                if (old_infomask2 & HEAP_KEYS_UPDATED)
                    old_status = MultiXactStatusForUpdate;
                else
                    old_status = MultiXactStatusForNoKeyUpdate;
            }
            else
            {
                /*
                 * LOCK_ONLY can be present alone only when a page has been
                 * upgraded by pg_upgrade.  But in that case,
                 * TransactionIdIsInProgress() should have returned false.  We
                 * assume it's no longer locked in this case.
                 */
                elog(WARNING, "LOCK_ONLY found for Xid in progress %u", xmax);
                old_infomask |= HEAP_XMAX_INVALID;
                old_infomask &= ~HEAP_XMAX_LOCK_ONLY;
                goto l5;
            }
        }
        else
        {
            /* it's an update, but which kind? */
            if (old_infomask2 & HEAP_KEYS_UPDATED)
                old_status = MultiXactStatusUpdate;
            else
                old_status = MultiXactStatusNoKeyUpdate;
        }
 
        old_mode = TUPLOCK_from_mxstatus(old_status);
 
        /*
         * If the lock to be acquired is for the same TransactionId as the
         * existing lock, there's an optimization possible: consider only the
         * strongest of both locks as the only one present, and restart.
         */
        if (xmax == add_to_xmax)
        {
            /*
             * Note that it's not possible for the original tuple to be
             * updated: we wouldn't be here because the tuple would have been
             * invisible and we wouldn't try to update it.  As a subtlety,
             * this code can also run when traversing an update chain to lock
             * future versions of a tuple.  But we wouldn't be here either,
             * because the add_to_xmax would be different from the original
             * updater.
             */
            Assert(HEAP_XMAX_IS_LOCKED_ONLY(old_infomask));
 
            /* acquire the strongest of both */
            if (mode < old_mode)
                mode = old_mode;
            /* mustn't touch is_update */
 
            old_infomask |= HEAP_XMAX_INVALID;
            goto l5;
        }
 
        /* otherwise, just fall back to creating a new multixact */
        new_status = get_mxact_status_for_lock(mode, is_update);
        new_xmax = MultiXactIdCreate(xmax, old_status,
                                     add_to_xmax, new_status);
        GetMultiXactIdHintBits(new_xmax, &new_infomask, &new_infomask2);
    }
    else if (!HEAP_XMAX_IS_LOCKED_ONLY(old_infomask) &&
             TransactionIdDidCommit(xmax))
    {
        /*
         * It's a committed update, so we gotta preserve him as updater of the
         * tuple.
         */
        MultiXactStatus status;
        MultiXactStatus new_status;
 
        if (old_infomask2 & HEAP_KEYS_UPDATED)
            status = MultiXactStatusUpdate;
        else
            status = MultiXactStatusNoKeyUpdate;
 
        new_status = get_mxact_status_for_lock(mode, is_update);
 
        /*
         * since it's not running, it's obviously impossible for the old
         * updater to be identical to the current one, so we need not check
         * for that case as we do in the block above.
         */
        new_xmax = MultiXactIdCreate(xmax, status, add_to_xmax, new_status);
        GetMultiXactIdHintBits(new_xmax, &new_infomask, &new_infomask2);
    }
    else
    {
        /*
         * Can get here iff the locking/updating transaction was running when
         * the infomask was extracted from the tuple, but finished before
         * TransactionIdIsInProgress got to run.  Deal with it as if there was
         * no locker at all in the first place.
         */
        old_infomask |= HEAP_XMAX_INVALID;
        goto l5;
    }
 
    *result_infomask = new_infomask;
    *result_infomask2 = new_infomask2;
    *result_xmax = new_xmax;
}

References Assert(), elog, ERROR, get_mxact_status_for_lock(), GetMultiXactIdHintBits(), HEAP_KEYS_UPDATED, HEAP_LOCKED_UPGRADED(), HEAP_XMAX_COMMITTED, HEAP_XMAX_EXCL_LOCK, HEAP_XMAX_INVALID, HEAP_XMAX_IS_EXCL_LOCKED(), HEAP_XMAX_IS_KEYSHR_LOCKED(), HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HEAP_XMAX_IS_SHR_LOCKED(), HEAP_XMAX_KEYSHR_LOCK, HEAP_XMAX_LOCK_ONLY, HEAP_XMAX_SHR_LOCK, InvalidTransactionId, LockTupleExclusive, LockTupleKeyShare, LockTupleNoKeyExclusive, LockTupleShare, mode, MultiXactIdCreate(), MultiXactIdExpand(), MultiXactIdGetUpdateXid(), MultiXactIdIsRunning(), MultiXactStatusForKeyShare, MultiXactStatusForNoKeyUpdate, MultiXactStatusForShare, MultiXactStatusForUpdate, MultiXactStatusNoKeyUpdate, MultiXactStatusUpdate, TransactionIdDidCommit(), TransactionIdIsCurrentTransactionId(), TransactionIdIsInProgress(), TUPLOCK_from_mxstatus, and WARNING.

Referenced by heap_delete(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), and heap_update().

ConditionalMultiXactIdWait()

static bool ConditionalMultiXactIdWait ( MultiXactId  multi, MultiXactStatus  status, uint16  infomask, Relation  rel, int *  remaining, bool  logLockFailure  )

static

Definition at line 7795 of file heapam.c.

{
    return Do_MultiXactIdWait(multi, status, infomask, true,
                              rel, NULL, XLTW_None, remaining, logLockFailure);
}

References Do_MultiXactIdWait(), remaining, and XLTW_None.

Referenced by heap_lock_tuple().

Do_MultiXactIdWait()

static bool Do_MultiXactIdWait ( MultiXactId  multi, MultiXactStatus  status, uint16  infomask, bool  nowait, Relation  rel, ItemPointer  ctid, XLTW_Oper  oper, int *  remaining, bool  logLockFailure  )

static

Definition at line 7695 of file heapam.c.

{
    bool        result = true;
    MultiXactMember *members;
    int         nmembers;
    int         remain = 0;
 
    /* for pre-pg_upgrade tuples, no need to sleep at all */
    nmembers = HEAP_LOCKED_UPGRADED(infomask) ? -1 :
        GetMultiXactIdMembers(multi, &members, false,
                              HEAP_XMAX_IS_LOCKED_ONLY(infomask));
 
    if (nmembers >= 0)
    {
        int         i;
 
        for (i = 0; i < nmembers; i++)
        {
            TransactionId memxid = members[i].xid;
            MultiXactStatus memstatus = members[i].status;
 
            if (TransactionIdIsCurrentTransactionId(memxid))
            {
                remain++;
                continue;
            }
 
            if (!DoLockModesConflict(LOCKMODE_from_mxstatus(memstatus),
                                     LOCKMODE_from_mxstatus(status)))
            {
                if (remaining && TransactionIdIsInProgress(memxid))
                    remain++;
                continue;
            }
 
            /*
             * This member conflicts with our multi, so we have to sleep (or
             * return failure, if asked to avoid waiting.)
             *
             * Note that we don't set up an error context callback ourselves,
             * but instead we pass the info down to XactLockTableWait.  This
             * might seem a bit wasteful because the context is set up and
             * tore down for each member of the multixact, but in reality it
             * should be barely noticeable, and it avoids duplicate code.
             */
            if (nowait)
            {
                result = ConditionalXactLockTableWait(memxid, logLockFailure);
                if (!result)
                    break;
            }
            else
                XactLockTableWait(memxid, rel, ctid, oper);
        }
 
        pfree(members);
    }
 
    if (remaining)
        *remaining = remain;
 
    return result;
}

References ConditionalXactLockTableWait(), DoLockModesConflict(), GetMultiXactIdMembers(), HEAP_LOCKED_UPGRADED(), HEAP_XMAX_IS_LOCKED_ONLY(), i, LOCKMODE_from_mxstatus, oper(), pfree(), remaining, MultiXactMember::status, TransactionIdIsCurrentTransactionId(), TransactionIdIsInProgress(), XactLockTableWait(), and MultiXactMember::xid.

Referenced by ConditionalMultiXactIdWait(), and MultiXactIdWait().

DoesMultiXactIdConflict()

static bool DoesMultiXactIdConflict ( MultiXactId  multi, uint16  infomask, LockTupleMode  lockmode, bool *  current_is_member  )

static

Definition at line 7595 of file heapam.c.

{
    int         nmembers;
    MultiXactMember *members;
    bool        result = false;
    LOCKMODE    wanted = tupleLockExtraInfo[lockmode].hwlock;
 
    if (HEAP_LOCKED_UPGRADED(infomask))
        return false;
 
    nmembers = GetMultiXactIdMembers(multi, &members, false,
                                     HEAP_XMAX_IS_LOCKED_ONLY(infomask));
    if (nmembers >= 0)
    {
        int         i;
 
        for (i = 0; i < nmembers; i++)
        {
            TransactionId memxid;
            LOCKMODE    memlockmode;
 
            if (result && (current_is_member == NULL || *current_is_member))
                break;
 
            memlockmode = LOCKMODE_from_mxstatus(members[i].status);
 
            /* ignore members from current xact (but track their presence) */
            memxid = members[i].xid;
            if (TransactionIdIsCurrentTransactionId(memxid))
            {
                if (current_is_member != NULL)
                    *current_is_member = true;
                continue;
            }
            else if (result)
                continue;
 
            /* ignore members that don't conflict with the lock we want */
            if (!DoLockModesConflict(memlockmode, wanted))
                continue;
 
            if (ISUPDATE_from_mxstatus(members[i].status))
            {
                /* ignore aborted updaters */
                if (TransactionIdDidAbort(memxid))
                    continue;
            }
            else
            {
                /* ignore lockers-only that are no longer in progress */
                if (!TransactionIdIsInProgress(memxid))
                    continue;
            }
 
            /*
             * Whatever remains are either live lockers that conflict with our
             * wanted lock, and updaters that are not aborted.  Those conflict
             * with what we want.  Set up to return true, but keep going to
             * look for the current transaction among the multixact members,
             * if needed.
             */
            result = true;
        }
        pfree(members);
    }
 
    return result;
}

References DoLockModesConflict(), GetMultiXactIdMembers(), HEAP_LOCKED_UPGRADED(), HEAP_XMAX_IS_LOCKED_ONLY(), i, ISUPDATE_from_mxstatus, LOCKMODE_from_mxstatus, pfree(), TransactionIdDidAbort(), TransactionIdIsCurrentTransactionId(), TransactionIdIsInProgress(), tupleLockExtraInfo, and MultiXactMember::xid.

Referenced by heap_delete(), heap_inplace_lock(), heap_lock_tuple(), and heap_update().

ExtractReplicaIdentity()

static HeapTuple ExtractReplicaIdentity ( Relation  relation, HeapTuple  tp, bool  key_required, bool *  copy  )

static

Definition at line 9141 of file heapam.c.

{
    TupleDesc   desc = RelationGetDescr(relation);
    char        replident = relation->rd_rel->relreplident;
    Bitmapset  *idattrs;
    HeapTuple   key_tuple;
    bool        nulls[MaxHeapAttributeNumber];
    Datum       values[MaxHeapAttributeNumber];
 
    *copy = false;
 
    if (!RelationIsLogicallyLogged(relation))
        return NULL;
 
    if (replident == REPLICA_IDENTITY_NOTHING)
        return NULL;
 
    if (replident == REPLICA_IDENTITY_FULL)
    {
        /*
         * When logging the entire old tuple, it very well could contain
         * toasted columns. If so, force them to be inlined.
         */
        if (HeapTupleHasExternal(tp))
        {
            *copy = true;
            tp = toast_flatten_tuple(tp, desc);
        }
        return tp;
    }
 
    /* if the key isn't required and we're only logging the key, we're done */
    if (!key_required)
        return NULL;
 
    /* find out the replica identity columns */
    idattrs = RelationGetIndexAttrBitmap(relation,
                                         INDEX_ATTR_BITMAP_IDENTITY_KEY);
 
    /*
     * If there's no defined replica identity columns, treat as !key_required.
     * (This case should not be reachable from heap_update, since that should
     * calculate key_required accurately.  But heap_delete just passes
     * constant true for key_required, so we can hit this case in deletes.)
     */
    if (bms_is_empty(idattrs))
        return NULL;
 
    /*
     * Construct a new tuple containing only the replica identity columns,
     * with nulls elsewhere.  While we're at it, assert that the replica
     * identity columns aren't null.
     */
    heap_deform_tuple(tp, desc, values, nulls);
 
    for (int i = 0; i < desc->natts; i++)
    {
        if (bms_is_member(i + 1 - FirstLowInvalidHeapAttributeNumber,
                          idattrs))
            Assert(!nulls[i]);
        else
            nulls[i] = true;
    }
 
    key_tuple = heap_form_tuple(desc, values, nulls);
    *copy = true;
 
    bms_free(idattrs);
 
    /*
     * If the tuple, which by here only contains indexed columns, still has
     * toasted columns, force them to be inlined. This is somewhat unlikely
     * since there's limits on the size of indexed columns, so we don't
     * duplicate toast_flatten_tuple()s functionality in the above loop over
     * the indexed columns, even if it would be more efficient.
     */
    if (HeapTupleHasExternal(key_tuple))
    {
        HeapTuple   oldtup = key_tuple;
 
        key_tuple = toast_flatten_tuple(oldtup, desc);
        heap_freetuple(oldtup);
    }
 
    return key_tuple;
}

References Assert(), bms_free(), bms_is_empty, bms_is_member(), FirstLowInvalidHeapAttributeNumber, heap_deform_tuple(), heap_form_tuple(), heap_freetuple(), HeapTupleHasExternal(), i, INDEX_ATTR_BITMAP_IDENTITY_KEY, MaxHeapAttributeNumber, TupleDescData::natts, RelationData::rd_rel, RelationGetDescr, RelationGetIndexAttrBitmap(), RelationIsLogicallyLogged, toast_flatten_tuple(), and values.

Referenced by heap_delete(), and heap_update().

FreeBulkInsertState()

void FreeBulkInsertState

(

BulkInsertState

bistate

)

Definition at line 2038 of file heapam.c.

{
    if (bistate->current_buf != InvalidBuffer)
        ReleaseBuffer(bistate->current_buf);
    FreeAccessStrategy(bistate->strategy);
    pfree(bistate);
}

References BulkInsertStateData::current_buf, FreeAccessStrategy(), InvalidBuffer, pfree(), ReleaseBuffer(), and BulkInsertStateData::strategy.

Referenced by ATRewriteTable(), CopyFrom(), CopyMultiInsertBufferCleanup(), intorel_shutdown(), and transientrel_shutdown().

FreezeMultiXactId()

static TransactionId FreezeMultiXactId ( MultiXactId  multi, uint16  t_infomask, const struct VacuumCutoffs *  cutoffs, uint16 *  flags, HeapPageFreeze *  pagefrz  )

static

Definition at line 6704 of file heapam.c.

{
    TransactionId newxmax;
    MultiXactMember *members;
    int         nmembers;
    bool        need_replace;
    int         nnewmembers;
    MultiXactMember *newmembers;
    bool        has_lockers;
    TransactionId update_xid;
    bool        update_committed;
    TransactionId FreezePageRelfrozenXid;
 
    *flags = 0;
 
    /* We should only be called in Multis */
    Assert(t_infomask & HEAP_XMAX_IS_MULTI);
 
    if (!MultiXactIdIsValid(multi) ||
        HEAP_LOCKED_UPGRADED(t_infomask))
    {
        *flags |= FRM_INVALIDATE_XMAX;
        pagefrz->freeze_required = true;
        return InvalidTransactionId;
    }
    else if (MultiXactIdPrecedes(multi, cutoffs->relminmxid))
        ereport(ERROR,
                (errcode(ERRCODE_DATA_CORRUPTED),
                 errmsg_internal("found multixact %u from before relminmxid %u",
                                 multi, cutoffs->relminmxid)));
    else if (MultiXactIdPrecedes(multi, cutoffs->OldestMxact))
    {
        TransactionId update_xact;
 
        /*
         * This old multi cannot possibly have members still running, but
         * verify just in case.  If it was a locker only, it can be removed
         * without any further consideration; but if it contained an update,
         * we might need to preserve it.
         */
        if (MultiXactIdIsRunning(multi,
                                 HEAP_XMAX_IS_LOCKED_ONLY(t_infomask)))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("multixact %u from before multi freeze cutoff %u found to be still running",
                                     multi, cutoffs->OldestMxact)));
 
        if (HEAP_XMAX_IS_LOCKED_ONLY(t_infomask))
        {
            *flags |= FRM_INVALIDATE_XMAX;
            pagefrz->freeze_required = true;
            return InvalidTransactionId;
        }
 
        /* replace multi with single XID for its updater? */
        update_xact = MultiXactIdGetUpdateXid(multi, t_infomask);
        if (TransactionIdPrecedes(update_xact, cutoffs->relfrozenxid))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("multixact %u contains update XID %u from before relfrozenxid %u",
                                     multi, update_xact,
                                     cutoffs->relfrozenxid)));
        else if (TransactionIdPrecedes(update_xact, cutoffs->OldestXmin))
        {
            /*
             * Updater XID has to have aborted (otherwise the tuple would have
             * been pruned away instead, since updater XID is < OldestXmin).
             * Just remove xmax.
             */
            if (TransactionIdDidCommit(update_xact))
                ereport(ERROR,
                        (errcode(ERRCODE_DATA_CORRUPTED),
                         errmsg_internal("multixact %u contains committed update XID %u from before removable cutoff %u",
                                         multi, update_xact,
                                         cutoffs->OldestXmin)));
            *flags |= FRM_INVALIDATE_XMAX;
            pagefrz->freeze_required = true;
            return InvalidTransactionId;
        }
 
        /* Have to keep updater XID as new xmax */
        *flags |= FRM_RETURN_IS_XID;
        pagefrz->freeze_required = true;
        return update_xact;
    }
 
    /*
     * Some member(s) of this Multi may be below FreezeLimit xid cutoff, so we
     * need to walk the whole members array to figure out what to do, if
     * anything.
     */
    nmembers =
        GetMultiXactIdMembers(multi, &members, false,
                              HEAP_XMAX_IS_LOCKED_ONLY(t_infomask));
    if (nmembers <= 0)
    {
        /* Nothing worth keeping */
        *flags |= FRM_INVALIDATE_XMAX;
        pagefrz->freeze_required = true;
        return InvalidTransactionId;
    }
 
    /*
     * The FRM_NOOP case is the only case where we might need to ratchet back
     * FreezePageRelfrozenXid or FreezePageRelminMxid.  It is also the only
     * case where our caller might ratchet back its NoFreezePageRelfrozenXid
     * or NoFreezePageRelminMxid "no freeze" trackers to deal with a multi.
     * FRM_NOOP handling should result in the NewRelfrozenXid/NewRelminMxid
     * trackers managed by VACUUM being ratcheting back by xmax to the degree
     * required to make it safe to leave xmax undisturbed, independent of
     * whether or not page freezing is triggered somewhere else.
     *
     * Our policy is to force freezing in every case other than FRM_NOOP,
     * which obviates the need to maintain either set of trackers, anywhere.
     * Every other case will reliably execute a freeze plan for xmax that
     * either replaces xmax with an XID/MXID >= OldestXmin/OldestMxact, or
     * sets xmax to an InvalidTransactionId XID, rendering xmax fully frozen.
     * (VACUUM's NewRelfrozenXid/NewRelminMxid trackers are initialized with
     * OldestXmin/OldestMxact, so later values never need to be tracked here.)
     */
    need_replace = false;
    FreezePageRelfrozenXid = pagefrz->FreezePageRelfrozenXid;
    for (int i = 0; i < nmembers; i++)
    {
        TransactionId xid = members[i].xid;
 
        Assert(!TransactionIdPrecedes(xid, cutoffs->relfrozenxid));
 
        if (TransactionIdPrecedes(xid, cutoffs->FreezeLimit))
        {
            /* Can't violate the FreezeLimit postcondition */
            need_replace = true;
            break;
        }
        if (TransactionIdPrecedes(xid, FreezePageRelfrozenXid))
            FreezePageRelfrozenXid = xid;
    }
 
    /* Can't violate the MultiXactCutoff postcondition, either */
    if (!need_replace)
        need_replace = MultiXactIdPrecedes(multi, cutoffs->MultiXactCutoff);
 
    if (!need_replace)
    {
        /*
         * vacuumlazy.c might ratchet back NewRelminMxid, NewRelfrozenXid, or
         * both together to make it safe to retain this particular multi after
         * freezing its page
         */
        *flags |= FRM_NOOP;
        pagefrz->FreezePageRelfrozenXid = FreezePageRelfrozenXid;
        if (MultiXactIdPrecedes(multi, pagefrz->FreezePageRelminMxid))
            pagefrz->FreezePageRelminMxid = multi;
        pfree(members);
        return multi;
    }
 
    /*
     * Do a more thorough second pass over the multi to figure out which
     * member XIDs actually need to be kept.  Checking the precise status of
     * individual members might even show that we don't need to keep anything.
     * That is quite possible even though the Multi must be >= OldestMxact,
     * since our second pass only keeps member XIDs when it's truly necessary;
     * even member XIDs >= OldestXmin often won't be kept by second pass.
     */
    nnewmembers = 0;
    newmembers = palloc(sizeof(MultiXactMember) * nmembers);
    has_lockers = false;
    update_xid = InvalidTransactionId;
    update_committed = false;
 
    /*
     * Determine whether to keep each member xid, or to ignore it instead
     */
    for (int i = 0; i < nmembers; i++)
    {
        TransactionId xid = members[i].xid;
        MultiXactStatus mstatus = members[i].status;
 
        Assert(!TransactionIdPrecedes(xid, cutoffs->relfrozenxid));
 
        if (!ISUPDATE_from_mxstatus(mstatus))
        {
            /*
             * Locker XID (not updater XID).  We only keep lockers that are
             * still running.
             */
            if (TransactionIdIsCurrentTransactionId(xid) ||
                TransactionIdIsInProgress(xid))
            {
                if (TransactionIdPrecedes(xid, cutoffs->OldestXmin))
                    ereport(ERROR,
                            (errcode(ERRCODE_DATA_CORRUPTED),
                             errmsg_internal("multixact %u contains running locker XID %u from before removable cutoff %u",
                                             multi, xid,
                                             cutoffs->OldestXmin)));
                newmembers[nnewmembers++] = members[i];
                has_lockers = true;
            }
 
            continue;
        }
 
        /*
         * Updater XID (not locker XID).  Should we keep it?
         *
         * Since the tuple wasn't totally removed when vacuum pruned, the
         * update Xid cannot possibly be older than OldestXmin cutoff unless
         * the updater XID aborted.  If the updater transaction is known
         * aborted or crashed then it's okay to ignore it, otherwise not.
         *
         * In any case the Multi should never contain two updaters, whatever
         * their individual commit status.  Check for that first, in passing.
         */
        if (TransactionIdIsValid(update_xid))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("multixact %u has two or more updating members",
                                     multi),
                     errdetail_internal("First updater XID=%u second updater XID=%u.",
                                        update_xid, xid)));
 
        /*
         * As with all tuple visibility routines, it's critical to test
         * TransactionIdIsInProgress before TransactionIdDidCommit, because of
         * race conditions explained in detail in heapam_visibility.c.
         */
        if (TransactionIdIsCurrentTransactionId(xid) ||
            TransactionIdIsInProgress(xid))
            update_xid = xid;
        else if (TransactionIdDidCommit(xid))
        {
            /*
             * The transaction committed, so we can tell caller to set
             * HEAP_XMAX_COMMITTED.  (We can only do this because we know the
             * transaction is not running.)
             */
            update_committed = true;
            update_xid = xid;
        }
        else
        {
            /*
             * Not in progress, not committed -- must be aborted or crashed;
             * we can ignore it.
             */
            continue;
        }
 
        /*
         * We determined that updater must be kept -- add it to pending new
         * members list
         */
        if (TransactionIdPrecedes(xid, cutoffs->OldestXmin))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("multixact %u contains committed update XID %u from before removable cutoff %u",
                                     multi, xid, cutoffs->OldestXmin)));
        newmembers[nnewmembers++] = members[i];
    }
 
    pfree(members);
 
    /*
     * Determine what to do with caller's multi based on information gathered
     * during our second pass
     */
    if (nnewmembers == 0)
    {
        /* Nothing worth keeping */
        *flags |= FRM_INVALIDATE_XMAX;
        newxmax = InvalidTransactionId;
    }
    else if (TransactionIdIsValid(update_xid) && !has_lockers)
    {
        /*
         * If there's a single member and it's an update, pass it back alone
         * without creating a new Multi.  (XXX we could do this when there's a
         * single remaining locker, too, but that would complicate the API too
         * much; moreover, the case with the single updater is more
         * interesting, because those are longer-lived.)
         */
        Assert(nnewmembers == 1);
        *flags |= FRM_RETURN_IS_XID;
        if (update_committed)
            *flags |= FRM_MARK_COMMITTED;
        newxmax = update_xid;
    }
    else
    {
        /*
         * Create a new multixact with the surviving members of the previous
         * one, to set as new Xmax in the tuple
         */
        newxmax = MultiXactIdCreateFromMembers(nnewmembers, newmembers);
        *flags |= FRM_RETURN_IS_MULTI;
    }
 
    pfree(newmembers);
 
    pagefrz->freeze_required = true;
    return newxmax;
}

References Assert(), ereport, errcode(), ERRCODE_DATA_CORRUPTED, errdetail_internal(), errmsg_internal(), ERROR, HeapPageFreeze::freeze_required, VacuumCutoffs::FreezeLimit, HeapPageFreeze::FreezePageRelfrozenXid, HeapPageFreeze::FreezePageRelminMxid, FRM_INVALIDATE_XMAX, FRM_MARK_COMMITTED, FRM_NOOP, FRM_RETURN_IS_MULTI, FRM_RETURN_IS_XID, GetMultiXactIdMembers(), HEAP_LOCKED_UPGRADED(), HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, i, InvalidTransactionId, ISUPDATE_from_mxstatus, VacuumCutoffs::MultiXactCutoff, MultiXactIdCreateFromMembers(), MultiXactIdGetUpdateXid(), MultiXactIdIsRunning(), MultiXactIdIsValid, MultiXactIdPrecedes(), VacuumCutoffs::OldestMxact, VacuumCutoffs::OldestXmin, palloc(), pfree(), VacuumCutoffs::relfrozenxid, VacuumCutoffs::relminmxid, MultiXactMember::status, TransactionIdDidCommit(), TransactionIdIsCurrentTransactionId(), TransactionIdIsInProgress(), TransactionIdIsValid, TransactionIdPrecedes(), and MultiXactMember::xid.

Referenced by heap_prepare_freeze_tuple().

get_mxact_status_for_lock()

static MultiXactStatus get_mxact_status_for_lock ( LockTupleMode  mode, bool  is_update  )

static

Definition at line 4532 of file heapam.c.

{
    int         retval;
 
    if (is_update)
        retval = tupleLockExtraInfo[mode].updstatus;
    else
        retval = tupleLockExtraInfo[mode].lockstatus;
 
    if (retval == -1)
        elog(ERROR, "invalid lock tuple mode %d/%s", mode,
             is_update ? "true" : "false");
 
    return (MultiXactStatus) retval;
}

References elog, ERROR, mode, and tupleLockExtraInfo.

Referenced by compute_new_xmax_infomask(), heap_lock_tuple(), and test_lockmode_for_conflict().

GetBulkInsertState()

BulkInsertState GetBulkInsertState

(

void

)

Definition at line 2021 of file heapam.c.

{
    BulkInsertState bistate;
 
    bistate = (BulkInsertState) palloc(sizeof(BulkInsertStateData));
    bistate->strategy = GetAccessStrategy(BAS_BULKWRITE);
    bistate->current_buf = InvalidBuffer;
    bistate->next_free = InvalidBlockNumber;
    bistate->last_free = InvalidBlockNumber;
    bistate->already_extended_by = 0;
    return bistate;
}

References BulkInsertStateData::already_extended_by, BAS_BULKWRITE, BulkInsertStateData::current_buf, GetAccessStrategy(), InvalidBlockNumber, InvalidBuffer, BulkInsertStateData::last_free, BulkInsertStateData::next_free, palloc(), and BulkInsertStateData::strategy.

Referenced by ATRewriteTable(), CopyFrom(), CopyMultiInsertBufferInit(), intorel_startup(), and transientrel_startup().

GetMultiXactIdHintBits()

static void GetMultiXactIdHintBits ( MultiXactId  multi, uint16 *  new_infomask, uint16 *  new_infomask2  )

static

Definition at line 7446 of file heapam.c.

{
    int         nmembers;
    MultiXactMember *members;
    int         i;
    uint16      bits = HEAP_XMAX_IS_MULTI;
    uint16      bits2 = 0;
    bool        has_update = false;
    LockTupleMode strongest = LockTupleKeyShare;
 
    /*
     * We only use this in multis we just created, so they cannot be values
     * pre-pg_upgrade.
     */
    nmembers = GetMultiXactIdMembers(multi, &members, false, false);
 
    for (i = 0; i < nmembers; i++)
    {
        LockTupleMode mode;
 
        /*
         * Remember the strongest lock mode held by any member of the
         * multixact.
         */
        mode = TUPLOCK_from_mxstatus(members[i].status);
        if (mode > strongest)
            strongest = mode;
 
        /* See what other bits we need */
        switch (members[i].status)
        {
            case MultiXactStatusForKeyShare:
            case MultiXactStatusForShare:
            case MultiXactStatusForNoKeyUpdate:
                break;
 
            case MultiXactStatusForUpdate:
                bits2 |= HEAP_KEYS_UPDATED;
                break;
 
            case MultiXactStatusNoKeyUpdate:
                has_update = true;
                break;
 
            case MultiXactStatusUpdate:
                bits2 |= HEAP_KEYS_UPDATED;
                has_update = true;
                break;
        }
    }
 
    if (strongest == LockTupleExclusive ||
        strongest == LockTupleNoKeyExclusive)
        bits |= HEAP_XMAX_EXCL_LOCK;
    else if (strongest == LockTupleShare)
        bits |= HEAP_XMAX_SHR_LOCK;
    else if (strongest == LockTupleKeyShare)
        bits |= HEAP_XMAX_KEYSHR_LOCK;
 
    if (!has_update)
        bits |= HEAP_XMAX_LOCK_ONLY;
 
    if (nmembers > 0)
        pfree(members);
 
    *new_infomask = bits;
    *new_infomask2 = bits2;
}

References GetMultiXactIdMembers(), HEAP_KEYS_UPDATED, HEAP_XMAX_EXCL_LOCK, HEAP_XMAX_IS_MULTI, HEAP_XMAX_KEYSHR_LOCK, HEAP_XMAX_LOCK_ONLY, HEAP_XMAX_SHR_LOCK, i, LockTupleExclusive, LockTupleKeyShare, LockTupleNoKeyExclusive, LockTupleShare, mode, MultiXactStatusForKeyShare, MultiXactStatusForNoKeyUpdate, MultiXactStatusForShare, MultiXactStatusForUpdate, MultiXactStatusNoKeyUpdate, MultiXactStatusUpdate, pfree(), and TUPLOCK_from_mxstatus.

Referenced by compute_new_xmax_infomask(), heap_prepare_freeze_tuple(), and heap_update().

heap_abort_speculative()

void heap_abort_speculative	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 6175 of file heapam.c.

{
    TransactionId xid = GetCurrentTransactionId();
    ItemId      lp;
    HeapTupleData tp;
    Page        page;
    BlockNumber block;
    Buffer      buffer;
 
    Assert(ItemPointerIsValid(tid));
 
    block = ItemPointerGetBlockNumber(tid);
    buffer = ReadBuffer(relation, block);
    page = BufferGetPage(buffer);
 
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
    /*
     * Page can't be all visible, we just inserted into it, and are still
     * running.
     */
    Assert(!PageIsAllVisible(page));
 
    lp = PageGetItemId(page, ItemPointerGetOffsetNumber(tid));
    Assert(ItemIdIsNormal(lp));
 
    tp.t_tableOid = RelationGetRelid(relation);
    tp.t_data = (HeapTupleHeader) PageGetItem(page, lp);
    tp.t_len = ItemIdGetLength(lp);
    tp.t_self = *tid;
 
    /*
     * Sanity check that the tuple really is a speculatively inserted tuple,
     * inserted by us.
     */
    if (tp.t_data->t_choice.t_heap.t_xmin != xid)
        elog(ERROR, "attempted to kill a tuple inserted by another transaction");
    if (!(IsToastRelation(relation) || HeapTupleHeaderIsSpeculative(tp.t_data)))
        elog(ERROR, "attempted to kill a non-speculative tuple");
    Assert(!HeapTupleHeaderIsHeapOnly(tp.t_data));
 
    /*
     * No need to check for serializable conflicts here.  There is never a
     * need for a combo CID, either.  No need to extract replica identity, or
     * do anything special with infomask bits.
     */
 
    START_CRIT_SECTION();
 
    /*
     * The tuple will become DEAD immediately.  Flag that this page is a
     * candidate for pruning by setting xmin to TransactionXmin. While not
     * immediately prunable, it is the oldest xid we can cheaply determine
     * that's safe against wraparound / being older than the table's
     * relfrozenxid.  To defend against the unlikely case of a new relation
     * having a newer relfrozenxid than our TransactionXmin, use relfrozenxid
     * if so (vacuum can't subsequently move relfrozenxid to beyond
     * TransactionXmin, so there's no race here).
     */
    Assert(TransactionIdIsValid(TransactionXmin));
    {
        TransactionId relfrozenxid = relation->rd_rel->relfrozenxid;
        TransactionId prune_xid;
 
        if (TransactionIdPrecedes(TransactionXmin, relfrozenxid))
            prune_xid = relfrozenxid;
        else
            prune_xid = TransactionXmin;
        PageSetPrunable(page, prune_xid);
    }
 
    /* store transaction information of xact deleting the tuple */
    tp.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
    tp.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
 
    /*
     * Set the tuple header xmin to InvalidTransactionId.  This makes the
     * tuple immediately invisible everyone.  (In particular, to any
     * transactions waiting on the speculative token, woken up later.)
     */
    HeapTupleHeaderSetXmin(tp.t_data, InvalidTransactionId);
 
    /* Clear the speculative insertion token too */
    tp.t_data->t_ctid = tp.t_self;
 
    MarkBufferDirty(buffer);
 
    /*
     * XLOG stuff
     *
     * The WAL records generated here match heap_delete().  The same recovery
     * routines are used.
     */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_delete xlrec;
        XLogRecPtr  recptr;
 
        xlrec.flags = XLH_DELETE_IS_SUPER;
        xlrec.infobits_set = compute_infobits(tp.t_data->t_infomask,
                                              tp.t_data->t_infomask2);
        xlrec.offnum = ItemPointerGetOffsetNumber(&tp.t_self);
        xlrec.xmax = xid;
 
        XLogBeginInsert();
        XLogRegisterData(&xlrec, SizeOfHeapDelete);
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 
        /* No replica identity & replication origin logged */
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
    if (HeapTupleHasExternal(&tp))
    {
        Assert(!IsToastRelation(relation));
        heap_toast_delete(relation, &tp, true);
    }
 
    /*
     * Never need to mark tuple for invalidation, since catalogs don't support
     * speculative insertion
     */
 
    /* Now we can release the buffer */
    ReleaseBuffer(buffer);
 
    /* count deletion, as we counted the insertion too */
    pgstat_count_heap_delete(relation);
}

References Assert(), BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetPage(), compute_infobits(), elog, END_CRIT_SECTION, ERROR, xl_heap_delete::flags, GetCurrentTransactionId(), HEAP_MOVED, heap_toast_delete(), HEAP_XMAX_BITS, HeapTupleHasExternal(), HeapTupleHeaderIsHeapOnly(), HeapTupleHeaderIsSpeculative(), HeapTupleHeaderSetXmin(), xl_heap_delete::infobits_set, InvalidTransactionId, IsToastRelation(), ItemIdGetLength, ItemIdIsNormal, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), ItemPointerIsValid(), LockBuffer(), MarkBufferDirty(), xl_heap_delete::offnum, PageGetItem(), PageGetItemId(), PageIsAllVisible(), PageSetLSN(), PageSetPrunable, pgstat_count_heap_delete(), RelationData::rd_rel, ReadBuffer(), REGBUF_STANDARD, RelationGetRelid, RelationNeedsWAL, ReleaseBuffer(), SizeOfHeapDelete, START_CRIT_SECTION, HeapTupleHeaderData::t_choice, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleHeaderData::t_heap, HeapTupleHeaderData::t_infomask, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, HeapTupleFields::t_xmin, TransactionIdIsValid, TransactionIdPrecedes(), TransactionXmin, XLH_DELETE_IS_SUPER, XLOG_HEAP_DELETE, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), and xl_heap_delete::xmax.

Referenced by heapam_tuple_complete_speculative(), and toast_delete_datum().

heap_acquire_tuplock()

static bool heap_acquire_tuplock ( Relation  relation, ItemPointer  tid, LockTupleMode  mode, LockWaitPolicy  wait_policy, bool *  have_tuple_lock  )

static

Definition at line 5277 of file heapam.c.

{
    if (*have_tuple_lock)
        return true;
 
    switch (wait_policy)
    {
        case LockWaitBlock:
            LockTupleTuplock(relation, tid, mode);
            break;
 
        case LockWaitSkip:
            if (!ConditionalLockTupleTuplock(relation, tid, mode, false))
                return false;
            break;
 
        case LockWaitError:
            if (!ConditionalLockTupleTuplock(relation, tid, mode, log_lock_failures))
                ereport(ERROR,
                        (errcode(ERRCODE_LOCK_NOT_AVAILABLE),
                         errmsg("could not obtain lock on row in relation \"%s\"",
                                RelationGetRelationName(relation))));
            break;
    }
    *have_tuple_lock = true;
 
    return true;
}

References ConditionalLockTupleTuplock, ereport, errcode(), errmsg(), ERROR, LockTupleTuplock, LockWaitBlock, LockWaitError, LockWaitSkip, log_lock_failures, mode, and RelationGetRelationName.

Referenced by heap_delete(), heap_lock_tuple(), and heap_update().

heap_attr_equals()

static bool heap_attr_equals ( TupleDesc  tupdesc, int  attrnum, Datum  value1, Datum  value2, bool  isnull1, bool  isnull2  )

static

Definition at line 4350 of file heapam.c.

{
    /*
     * If one value is NULL and other is not, then they are certainly not
     * equal
     */
    if (isnull1 != isnull2)
        return false;
 
    /*
     * If both are NULL, they can be considered equal.
     */
    if (isnull1)
        return true;
 
    /*
     * We do simple binary comparison of the two datums.  This may be overly
     * strict because there can be multiple binary representations for the
     * same logical value.  But we should be OK as long as there are no false
     * positives.  Using a type-specific equality operator is messy because
     * there could be multiple notions of equality in different operator
     * classes; furthermore, we cannot safely invoke user-defined functions
     * while holding exclusive buffer lock.
     */
    if (attrnum <= 0)
    {
        /* The only allowed system columns are OIDs, so do this */
        return (DatumGetObjectId(value1) == DatumGetObjectId(value2));
    }
    else
    {
        CompactAttribute *att;
 
        Assert(attrnum <= tupdesc->natts);
        att = TupleDescCompactAttr(tupdesc, attrnum - 1);
        return datumIsEqual(value1, value2, att->attbyval, att->attlen);
    }
}

References Assert(), CompactAttribute::attbyval, CompactAttribute::attlen, DatumGetObjectId(), datumIsEqual(), and TupleDescCompactAttr().

Referenced by HeapDetermineColumnsInfo().

heap_beginscan()

TableScanDesc heap_beginscan	(	Relation	relation,
		Snapshot	snapshot,
		int	nkeys,
		ScanKey	key,
		ParallelTableScanDesc	parallel_scan,
		uint32	flags
	)

Definition at line 1100 of file heapam.c.

{
    HeapScanDesc scan;
 
    /*
     * increment relation ref count while scanning relation
     *
     * This is just to make really sure the relcache entry won't go away while
     * the scan has a pointer to it.  Caller should be holding the rel open
     * anyway, so this is redundant in all normal scenarios...
     */
    RelationIncrementReferenceCount(relation);
 
    /*
     * allocate and initialize scan descriptor
     */
    if (flags & SO_TYPE_BITMAPSCAN)
    {
        BitmapHeapScanDesc bscan = palloc(sizeof(BitmapHeapScanDescData));
 
        /*
         * Bitmap Heap scans do not have any fields that a normal Heap Scan
         * does not have, so no special initializations required here.
         */
        scan = (HeapScanDesc) bscan;
    }
    else
        scan = (HeapScanDesc) palloc(sizeof(HeapScanDescData));
 
    scan->rs_base.rs_rd = relation;
    scan->rs_base.rs_snapshot = snapshot;
    scan->rs_base.rs_nkeys = nkeys;
    scan->rs_base.rs_flags = flags;
    scan->rs_base.rs_parallel = parallel_scan;
    scan->rs_strategy = NULL;   /* set in initscan */
    scan->rs_cbuf = InvalidBuffer;
 
    /*
     * Disable page-at-a-time mode if it's not a MVCC-safe snapshot.
     */
    if (!(snapshot && IsMVCCSnapshot(snapshot)))
        scan->rs_base.rs_flags &= ~SO_ALLOW_PAGEMODE;
 
    /* Check that a historic snapshot is not used for non-catalog tables */
    if (snapshot &&
        IsHistoricMVCCSnapshot(snapshot) &&
        !RelationIsAccessibleInLogicalDecoding(relation))
    {
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TRANSACTION_STATE),
                 errmsg("cannot query non-catalog table \"%s\" during logical decoding",
                        RelationGetRelationName(relation))));
    }
 
    /*
     * For seqscan and sample scans in a serializable transaction, acquire a
     * predicate lock on the entire relation. This is required not only to
     * lock all the matching tuples, but also to conflict with new insertions
     * into the table. In an indexscan, we take page locks on the index pages
     * covering the range specified in the scan qual, but in a heap scan there
     * is nothing more fine-grained to lock. A bitmap scan is a different
     * story, there we have already scanned the index and locked the index
     * pages covering the predicate. But in that case we still have to lock
     * any matching heap tuples. For sample scan we could optimize the locking
     * to be at least page-level granularity, but we'd need to add per-tuple
     * locking for that.
     */
    if (scan->rs_base.rs_flags & (SO_TYPE_SEQSCAN | SO_TYPE_SAMPLESCAN))
    {
        /*
         * Ensure a missing snapshot is noticed reliably, even if the
         * isolation mode means predicate locking isn't performed (and
         * therefore the snapshot isn't used here).
         */
        Assert(snapshot);
        PredicateLockRelation(relation, snapshot);
    }
 
    /* we only need to set this up once */
    scan->rs_ctup.t_tableOid = RelationGetRelid(relation);
 
    /*
     * Allocate memory to keep track of page allocation for parallel workers
     * when doing a parallel scan.
     */
    if (parallel_scan != NULL)
        scan->rs_parallelworkerdata = palloc(sizeof(ParallelBlockTableScanWorkerData));
    else
        scan->rs_parallelworkerdata = NULL;
 
    /*
     * we do this here instead of in initscan() because heap_rescan also calls
     * initscan() and we don't want to allocate memory again
     */
    if (nkeys > 0)
        scan->rs_base.rs_key = (ScanKey) palloc(sizeof(ScanKeyData) * nkeys);
    else
        scan->rs_base.rs_key = NULL;
 
    initscan(scan, key, false);
 
    scan->rs_read_stream = NULL;
 
    /*
     * Set up a read stream for sequential scans and TID range scans. This
     * should be done after initscan() because initscan() allocates the
     * BufferAccessStrategy object passed to the read stream API.
     */
    if (scan->rs_base.rs_flags & SO_TYPE_SEQSCAN ||
        scan->rs_base.rs_flags & SO_TYPE_TIDRANGESCAN)
    {
        ReadStreamBlockNumberCB cb;
 
        if (scan->rs_base.rs_parallel)
            cb = heap_scan_stream_read_next_parallel;
        else
            cb = heap_scan_stream_read_next_serial;
 
        /* ---
         * It is safe to use batchmode as the only locks taken by `cb`
         * are never taken while waiting for IO:
         * - SyncScanLock is used in the non-parallel case
         * - in the parallel case, only spinlocks and atomics are used
         * ---
         */
        scan->rs_read_stream = read_stream_begin_relation(READ_STREAM_SEQUENTIAL |
                                                          READ_STREAM_USE_BATCHING,
                                                          scan->rs_strategy,
                                                          scan->rs_base.rs_rd,
                                                          MAIN_FORKNUM,
                                                          cb,
                                                          scan,
                                                          0);
    }
    else if (scan->rs_base.rs_flags & SO_TYPE_BITMAPSCAN)
    {
        scan->rs_read_stream = read_stream_begin_relation(READ_STREAM_DEFAULT |
                                                          READ_STREAM_USE_BATCHING,
                                                          scan->rs_strategy,
                                                          scan->rs_base.rs_rd,
                                                          MAIN_FORKNUM,
                                                          bitmapheap_stream_read_next,
                                                          scan,
                                                          sizeof(TBMIterateResult));
    }
 
 
    return (TableScanDesc) scan;
}

References Assert(), bitmapheap_stream_read_next(), ereport, errcode(), errmsg(), ERROR, heap_scan_stream_read_next_parallel(), heap_scan_stream_read_next_serial(), initscan(), InvalidBuffer, IsHistoricMVCCSnapshot, IsMVCCSnapshot, sort-test::key, MAIN_FORKNUM, palloc(), PredicateLockRelation(), read_stream_begin_relation(), READ_STREAM_DEFAULT, READ_STREAM_SEQUENTIAL, READ_STREAM_USE_BATCHING, RelationGetRelationName, RelationGetRelid, RelationIncrementReferenceCount(), RelationIsAccessibleInLogicalDecoding, HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_ctup, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_nkeys, TableScanDescData::rs_parallel, HeapScanDescData::rs_parallelworkerdata, TableScanDescData::rs_rd, HeapScanDescData::rs_read_stream, TableScanDescData::rs_snapshot, HeapScanDescData::rs_strategy, SO_TYPE_BITMAPSCAN, SO_TYPE_SAMPLESCAN, SO_TYPE_SEQSCAN, SO_TYPE_TIDRANGESCAN, and HeapTupleData::t_tableOid.

heap_delete()

TM_Result heap_delete	(	Relation	relation,
		ItemPointer	tid,
		CommandId	cid,
		Snapshot	crosscheck,
		bool	wait,
		TM_FailureData *	tmfd,
		bool	changingPart
	)

Definition at line 2778 of file heapam.c.

{
    TM_Result   result;
    TransactionId xid = GetCurrentTransactionId();
    ItemId      lp;
    HeapTupleData tp;
    Page        page;
    BlockNumber block;
    Buffer      buffer;
    Buffer      vmbuffer = InvalidBuffer;
    TransactionId new_xmax;
    uint16      new_infomask,
                new_infomask2;
    bool        have_tuple_lock = false;
    bool        iscombo;
    bool        all_visible_cleared = false;
    HeapTuple   old_key_tuple = NULL;   /* replica identity of the tuple */
    bool        old_key_copied = false;
 
    Assert(ItemPointerIsValid(tid));
 
    AssertHasSnapshotForToast(relation);
 
    /*
     * Forbid this during a parallel operation, lest it allocate a combo CID.
     * Other workers might need that combo CID for visibility checks, and we
     * have no provision for broadcasting it to them.
     */
    if (IsInParallelMode())
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TRANSACTION_STATE),
                 errmsg("cannot delete tuples during a parallel operation")));
 
    block = ItemPointerGetBlockNumber(tid);
    buffer = ReadBuffer(relation, block);
    page = BufferGetPage(buffer);
 
    /*
     * Before locking the buffer, pin the visibility map page if it appears to
     * be necessary.  Since we haven't got the lock yet, someone else might be
     * in the middle of changing this, so we'll need to recheck after we have
     * the lock.
     */
    if (PageIsAllVisible(page))
        visibilitymap_pin(relation, block, &vmbuffer);
 
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
    lp = PageGetItemId(page, ItemPointerGetOffsetNumber(tid));
    Assert(ItemIdIsNormal(lp));
 
    tp.t_tableOid = RelationGetRelid(relation);
    tp.t_data = (HeapTupleHeader) PageGetItem(page, lp);
    tp.t_len = ItemIdGetLength(lp);
    tp.t_self = *tid;
 
l1:
 
    /*
     * If we didn't pin the visibility map page and the page has become all
     * visible while we were busy locking the buffer, we'll have to unlock and
     * re-lock, to avoid holding the buffer lock across an I/O.  That's a bit
     * unfortunate, but hopefully shouldn't happen often.
     */
    if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
    {
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
        visibilitymap_pin(relation, block, &vmbuffer);
        LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
    }
 
    result = HeapTupleSatisfiesUpdate(&tp, cid, buffer);
 
    if (result == TM_Invisible)
    {
        UnlockReleaseBuffer(buffer);
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("attempted to delete invisible tuple")));
    }
    else if (result == TM_BeingModified && wait)
    {
        TransactionId xwait;
        uint16      infomask;
 
        /* must copy state data before unlocking buffer */
        xwait = HeapTupleHeaderGetRawXmax(tp.t_data);
        infomask = tp.t_data->t_infomask;
 
        /*
         * Sleep until concurrent transaction ends -- except when there's a
         * single locker and it's our own transaction.  Note we don't care
         * which lock mode the locker has, because we need the strongest one.
         *
         * Before sleeping, we need to acquire tuple lock to establish our
         * priority for the tuple (see heap_lock_tuple).  LockTuple will
         * release us when we are next-in-line for the tuple.
         *
         * If we are forced to "start over" below, we keep the tuple lock;
         * this arranges that we stay at the head of the line while rechecking
         * tuple state.
         */
        if (infomask & HEAP_XMAX_IS_MULTI)
        {
            bool        current_is_member = false;
 
            if (DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
                                        LockTupleExclusive, &current_is_member))
            {
                LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
                /*
                 * Acquire the lock, if necessary (but skip it when we're
                 * requesting a lock and already have one; avoids deadlock).
                 */
                if (!current_is_member)
                    heap_acquire_tuplock(relation, &(tp.t_self), LockTupleExclusive,
                                         LockWaitBlock, &have_tuple_lock);
 
                /* wait for multixact */
                MultiXactIdWait((MultiXactId) xwait, MultiXactStatusUpdate, infomask,
                                relation, &(tp.t_self), XLTW_Delete,
                                NULL);
                LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
                /*
                 * If xwait had just locked the tuple then some other xact
                 * could update this tuple before we get to this point.  Check
                 * for xmax change, and start over if so.
                 *
                 * We also must start over if we didn't pin the VM page, and
                 * the page has become all visible.
                 */
                if ((vmbuffer == InvalidBuffer && PageIsAllVisible(page)) ||
                    xmax_infomask_changed(tp.t_data->t_infomask, infomask) ||
                    !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tp.t_data),
                                         xwait))
                    goto l1;
            }
 
            /*
             * You might think the multixact is necessarily done here, but not
             * so: it could have surviving members, namely our own xact or
             * other subxacts of this backend.  It is legal for us to delete
             * the tuple in either case, however (the latter case is
             * essentially a situation of upgrading our former shared lock to
             * exclusive).  We don't bother changing the on-disk hint bits
             * since we are about to overwrite the xmax altogether.
             */
        }
        else if (!TransactionIdIsCurrentTransactionId(xwait))
        {
            /*
             * Wait for regular transaction to end; but first, acquire tuple
             * lock.
             */
            LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            heap_acquire_tuplock(relation, &(tp.t_self), LockTupleExclusive,
                                 LockWaitBlock, &have_tuple_lock);
            XactLockTableWait(xwait, relation, &(tp.t_self), XLTW_Delete);
            LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
            /*
             * xwait is done, but if xwait had just locked the tuple then some
             * other xact could update this tuple before we get to this point.
             * Check for xmax change, and start over if so.
             *
             * We also must start over if we didn't pin the VM page, and the
             * page has become all visible.
             */
            if ((vmbuffer == InvalidBuffer && PageIsAllVisible(page)) ||
                xmax_infomask_changed(tp.t_data->t_infomask, infomask) ||
                !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tp.t_data),
                                     xwait))
                goto l1;
 
            /* Otherwise check if it committed or aborted */
            UpdateXmaxHintBits(tp.t_data, buffer, xwait);
        }
 
        /*
         * We may overwrite if previous xmax aborted, or if it committed but
         * only locked the tuple without updating it.
         */
        if ((tp.t_data->t_infomask & HEAP_XMAX_INVALID) ||
            HEAP_XMAX_IS_LOCKED_ONLY(tp.t_data->t_infomask) ||
            HeapTupleHeaderIsOnlyLocked(tp.t_data))
            result = TM_Ok;
        else if (!ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid))
            result = TM_Updated;
        else
            result = TM_Deleted;
    }
 
    /* sanity check the result HeapTupleSatisfiesUpdate() and the logic above */
    if (result != TM_Ok)
    {
        Assert(result == TM_SelfModified ||
               result == TM_Updated ||
               result == TM_Deleted ||
               result == TM_BeingModified);
        Assert(!(tp.t_data->t_infomask & HEAP_XMAX_INVALID));
        Assert(result != TM_Updated ||
               !ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid));
    }
 
    if (crosscheck != InvalidSnapshot && result == TM_Ok)
    {
        /* Perform additional check for transaction-snapshot mode RI updates */
        if (!HeapTupleSatisfiesVisibility(&tp, crosscheck, buffer))
            result = TM_Updated;
    }
 
    if (result != TM_Ok)
    {
        tmfd->ctid = tp.t_data->t_ctid;
        tmfd->xmax = HeapTupleHeaderGetUpdateXid(tp.t_data);
        if (result == TM_SelfModified)
            tmfd->cmax = HeapTupleHeaderGetCmax(tp.t_data);
        else
            tmfd->cmax = InvalidCommandId;
        UnlockReleaseBuffer(buffer);
        if (have_tuple_lock)
            UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive);
        if (vmbuffer != InvalidBuffer)
            ReleaseBuffer(vmbuffer);
        return result;
    }
 
    /*
     * We're about to do the actual delete -- check for conflict first, to
     * avoid possibly having to roll back work we've just done.
     *
     * This is safe without a recheck as long as there is no possibility of
     * another process scanning the page between this check and the delete
     * being visible to the scan (i.e., an exclusive buffer content lock is
     * continuously held from this point until the tuple delete is visible).
     */
    CheckForSerializableConflictIn(relation, tid, BufferGetBlockNumber(buffer));
 
    /* replace cid with a combo CID if necessary */
    HeapTupleHeaderAdjustCmax(tp.t_data, &cid, &iscombo);
 
    /*
     * Compute replica identity tuple before entering the critical section so
     * we don't PANIC upon a memory allocation failure.
     */
    old_key_tuple = ExtractReplicaIdentity(relation, &tp, true, &old_key_copied);
 
    /*
     * If this is the first possibly-multixact-able operation in the current
     * transaction, set my per-backend OldestMemberMXactId setting. We can be
     * certain that the transaction will never become a member of any older
     * MultiXactIds than that.  (We have to do this even if we end up just
     * using our own TransactionId below, since some other backend could
     * incorporate our XID into a MultiXact immediately afterwards.)
     */
    MultiXactIdSetOldestMember();
 
    compute_new_xmax_infomask(HeapTupleHeaderGetRawXmax(tp.t_data),
                              tp.t_data->t_infomask, tp.t_data->t_infomask2,
                              xid, LockTupleExclusive, true,
                              &new_xmax, &new_infomask, &new_infomask2);
 
    START_CRIT_SECTION();
 
    /*
     * If this transaction commits, the tuple will become DEAD sooner or
     * later.  Set flag that this page is a candidate for pruning once our xid
     * falls below the OldestXmin horizon.  If the transaction finally aborts,
     * the subsequent page pruning will be a no-op and the hint will be
     * cleared.
     */
    PageSetPrunable(page, xid);
 
    if (PageIsAllVisible(page))
    {
        all_visible_cleared = true;
        PageClearAllVisible(page);
        visibilitymap_clear(relation, BufferGetBlockNumber(buffer),
                            vmbuffer, VISIBILITYMAP_VALID_BITS);
    }
 
    /* store transaction information of xact deleting the tuple */
    tp.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
    tp.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    tp.t_data->t_infomask |= new_infomask;
    tp.t_data->t_infomask2 |= new_infomask2;
    HeapTupleHeaderClearHotUpdated(tp.t_data);
    HeapTupleHeaderSetXmax(tp.t_data, new_xmax);
    HeapTupleHeaderSetCmax(tp.t_data, cid, iscombo);
    /* Make sure there is no forward chain link in t_ctid */
    tp.t_data->t_ctid = tp.t_self;
 
    /* Signal that this is actually a move into another partition */
    if (changingPart)
        HeapTupleHeaderSetMovedPartitions(tp.t_data);
 
    MarkBufferDirty(buffer);
 
    /*
     * XLOG stuff
     *
     * NB: heap_abort_speculative() uses the same xlog record and replay
     * routines.
     */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_delete xlrec;
        xl_heap_header xlhdr;
        XLogRecPtr  recptr;
 
        /*
         * For logical decode we need combo CIDs to properly decode the
         * catalog
         */
        if (RelationIsAccessibleInLogicalDecoding(relation))
            log_heap_new_cid(relation, &tp);
 
        xlrec.flags = 0;
        if (all_visible_cleared)
            xlrec.flags |= XLH_DELETE_ALL_VISIBLE_CLEARED;
        if (changingPart)
            xlrec.flags |= XLH_DELETE_IS_PARTITION_MOVE;
        xlrec.infobits_set = compute_infobits(tp.t_data->t_infomask,
                                              tp.t_data->t_infomask2);
        xlrec.offnum = ItemPointerGetOffsetNumber(&tp.t_self);
        xlrec.xmax = new_xmax;
 
        if (old_key_tuple != NULL)
        {
            if (relation->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
                xlrec.flags |= XLH_DELETE_CONTAINS_OLD_TUPLE;
            else
                xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
        }
 
        XLogBeginInsert();
        XLogRegisterData(&xlrec, SizeOfHeapDelete);
 
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 
        /*
         * Log replica identity of the deleted tuple if there is one
         */
        if (old_key_tuple != NULL)
        {
            xlhdr.t_infomask2 = old_key_tuple->t_data->t_infomask2;
            xlhdr.t_infomask = old_key_tuple->t_data->t_infomask;
            xlhdr.t_hoff = old_key_tuple->t_data->t_hoff;
 
            XLogRegisterData(&xlhdr, SizeOfHeapHeader);
            XLogRegisterData((char *) old_key_tuple->t_data
                             + SizeofHeapTupleHeader,
                             old_key_tuple->t_len
                             - SizeofHeapTupleHeader);
        }
 
        /* filtering by origin on a row level is much more efficient */
        XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
    if (vmbuffer != InvalidBuffer)
        ReleaseBuffer(vmbuffer);
 
    /*
     * If the tuple has toasted out-of-line attributes, we need to delete
     * those items too.  We have to do this before releasing the buffer
     * because we need to look at the contents of the tuple, but it's OK to
     * release the content lock on the buffer first.
     */
    if (relation->rd_rel->relkind != RELKIND_RELATION &&
        relation->rd_rel->relkind != RELKIND_MATVIEW)
    {
        /* toast table entries should never be recursively toasted */
        Assert(!HeapTupleHasExternal(&tp));
    }
    else if (HeapTupleHasExternal(&tp))
        heap_toast_delete(relation, &tp, false);
 
    /*
     * Mark tuple for invalidation from system caches at next command
     * boundary. We have to do this before releasing the buffer because we
     * need to look at the contents of the tuple.
     */
    CacheInvalidateHeapTuple(relation, &tp, NULL);
 
    /* Now we can release the buffer */
    ReleaseBuffer(buffer);
 
    /*
     * Release the lmgr tuple lock, if we had it.
     */
    if (have_tuple_lock)
        UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive);
 
    pgstat_count_heap_delete(relation);
 
    if (old_key_tuple != NULL && old_key_copied)
        heap_freetuple(old_key_tuple);
 
    return TM_Ok;
}

References Assert(), AssertHasSnapshotForToast(), BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage(), CacheInvalidateHeapTuple(), CheckForSerializableConflictIn(), TM_FailureData::cmax, compute_infobits(), compute_new_xmax_infomask(), TM_FailureData::ctid, DoesMultiXactIdConflict(), END_CRIT_SECTION, ereport, errcode(), errmsg(), ERROR, ExtractReplicaIdentity(), xl_heap_delete::flags, GetCurrentTransactionId(), heap_acquire_tuplock(), heap_freetuple(), HEAP_MOVED, heap_toast_delete(), HEAP_XMAX_BITS, HEAP_XMAX_INVALID, HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HeapTupleHasExternal(), HeapTupleHeaderAdjustCmax(), HeapTupleHeaderClearHotUpdated(), HeapTupleHeaderGetCmax(), HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderIsOnlyLocked(), HeapTupleHeaderSetCmax(), HeapTupleHeaderSetMovedPartitions(), HeapTupleHeaderSetXmax(), HeapTupleSatisfiesUpdate(), HeapTupleSatisfiesVisibility(), xl_heap_delete::infobits_set, InvalidBuffer, InvalidCommandId, InvalidSnapshot, IsInParallelMode(), ItemIdGetLength, ItemIdIsNormal, ItemPointerEquals(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), ItemPointerIsValid(), LockBuffer(), LockTupleExclusive, LockWaitBlock, log_heap_new_cid(), MarkBufferDirty(), MultiXactIdSetOldestMember(), MultiXactIdWait(), MultiXactStatusUpdate, xl_heap_delete::offnum, PageClearAllVisible(), PageGetItem(), PageGetItemId(), PageIsAllVisible(), PageSetLSN(), PageSetPrunable, pgstat_count_heap_delete(), RelationData::rd_rel, ReadBuffer(), REGBUF_STANDARD, RelationGetRelid, RelationIsAccessibleInLogicalDecoding, RelationNeedsWAL, ReleaseBuffer(), SizeOfHeapDelete, SizeOfHeapHeader, SizeofHeapTupleHeader, START_CRIT_SECTION, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, xl_heap_header::t_hoff, HeapTupleHeaderData::t_hoff, xl_heap_header::t_infomask, HeapTupleHeaderData::t_infomask, xl_heap_header::t_infomask2, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TM_BeingModified, TM_Deleted, TM_Invisible, TM_Ok, TM_SelfModified, TM_Updated, TransactionIdEquals, TransactionIdIsCurrentTransactionId(), UnlockReleaseBuffer(), UnlockTupleTuplock, UpdateXmaxHintBits(), visibilitymap_clear(), visibilitymap_pin(), VISIBILITYMAP_VALID_BITS, XactLockTableWait(), XLH_DELETE_ALL_VISIBLE_CLEARED, XLH_DELETE_CONTAINS_OLD_KEY, XLH_DELETE_CONTAINS_OLD_TUPLE, XLH_DELETE_IS_PARTITION_MOVE, XLOG_HEAP_DELETE, XLOG_INCLUDE_ORIGIN, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), XLogSetRecordFlags(), XLTW_Delete, xl_heap_delete::xmax, TM_FailureData::xmax, and xmax_infomask_changed().

Referenced by heapam_tuple_delete(), and simple_heap_delete().

heap_endscan()

void heap_endscan

(

TableScanDesc

sscan

)

Definition at line 1307 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
 
    /* Note: no locking manipulations needed */
 
    /*
     * unpin scan buffers
     */
    if (BufferIsValid(scan->rs_cbuf))
        ReleaseBuffer(scan->rs_cbuf);
 
    /*
     * Must free the read stream before freeing the BufferAccessStrategy.
     */
    if (scan->rs_read_stream)
        read_stream_end(scan->rs_read_stream);
 
    /*
     * decrement relation reference count and free scan descriptor storage
     */
    RelationDecrementReferenceCount(scan->rs_base.rs_rd);
 
    if (scan->rs_base.rs_key)
        pfree(scan->rs_base.rs_key);
 
    if (scan->rs_strategy != NULL)
        FreeAccessStrategy(scan->rs_strategy);
 
    if (scan->rs_parallelworkerdata != NULL)
        pfree(scan->rs_parallelworkerdata);
 
    if (scan->rs_base.rs_flags & SO_TEMP_SNAPSHOT)
        UnregisterSnapshot(scan->rs_base.rs_snapshot);
 
    pfree(scan);
}

References BufferIsValid(), FreeAccessStrategy(), pfree(), read_stream_end(), RelationDecrementReferenceCount(), ReleaseBuffer(), HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, TableScanDescData::rs_flags, TableScanDescData::rs_key, HeapScanDescData::rs_parallelworkerdata, TableScanDescData::rs_rd, HeapScanDescData::rs_read_stream, TableScanDescData::rs_snapshot, HeapScanDescData::rs_strategy, SO_TEMP_SNAPSHOT, and UnregisterSnapshot().

heap_fetch()

bool heap_fetch	(	Relation	relation,
		Snapshot	snapshot,
		HeapTuple	tuple,
		Buffer *	userbuf,
		bool	keep_buf
	)

Definition at line 1605 of file heapam.c.

{
    ItemPointer tid = &(tuple->t_self);
    ItemId      lp;
    Buffer      buffer;
    Page        page;
    OffsetNumber offnum;
    bool        valid;
 
    /*
     * Fetch and pin the appropriate page of the relation.
     */
    buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
 
    /*
     * Need share lock on buffer to examine tuple commit status.
     */
    LockBuffer(buffer, BUFFER_LOCK_SHARE);
    page = BufferGetPage(buffer);
 
    /*
     * We'd better check for out-of-range offnum in case of VACUUM since the
     * TID was obtained.
     */
    offnum = ItemPointerGetOffsetNumber(tid);
    if (offnum < FirstOffsetNumber || offnum > PageGetMaxOffsetNumber(page))
    {
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
        ReleaseBuffer(buffer);
        *userbuf = InvalidBuffer;
        tuple->t_data = NULL;
        return false;
    }
 
    /*
     * get the item line pointer corresponding to the requested tid
     */
    lp = PageGetItemId(page, offnum);
 
    /*
     * Must check for deleted tuple.
     */
    if (!ItemIdIsNormal(lp))
    {
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
        ReleaseBuffer(buffer);
        *userbuf = InvalidBuffer;
        tuple->t_data = NULL;
        return false;
    }
 
    /*
     * fill in *tuple fields
     */
    tuple->t_data = (HeapTupleHeader) PageGetItem(page, lp);
    tuple->t_len = ItemIdGetLength(lp);
    tuple->t_tableOid = RelationGetRelid(relation);
 
    /*
     * check tuple visibility, then release lock
     */
    valid = HeapTupleSatisfiesVisibility(tuple, snapshot, buffer);
 
    if (valid)
        PredicateLockTID(relation, &(tuple->t_self), snapshot,
                         HeapTupleHeaderGetXmin(tuple->t_data));
 
    HeapCheckForSerializableConflictOut(valid, relation, tuple, buffer, snapshot);
 
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
    if (valid)
    {
        /*
         * All checks passed, so return the tuple as valid. Caller is now
         * responsible for releasing the buffer.
         */
        *userbuf = buffer;
 
        return true;
    }
 
    /* Tuple failed time qual, but maybe caller wants to see it anyway. */
    if (keep_buf)
        *userbuf = buffer;
    else
    {
        ReleaseBuffer(buffer);
        *userbuf = InvalidBuffer;
        tuple->t_data = NULL;
    }
 
    return false;
}

References BUFFER_LOCK_SHARE, BUFFER_LOCK_UNLOCK, BufferGetPage(), HeapCheckForSerializableConflictOut(), HeapTupleHeaderGetXmin(), HeapTupleSatisfiesVisibility(), InvalidBuffer, ItemIdGetLength, ItemIdIsNormal, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), LockBuffer(), PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PredicateLockTID(), ReadBuffer(), RelationGetRelid, ReleaseBuffer(), HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, and HeapTupleData::t_tableOid.

Referenced by heap_lock_updated_tuple_rec(), heapam_fetch_row_version(), and heapam_tuple_lock().

heap_fetch_next_buffer()

static void heap_fetch_next_buffer ( HeapScanDesc  scan, ScanDirection  dir  )

inlinestatic

Definition at line 643 of file heapam.c.

{
    Assert(scan->rs_read_stream);
 
    /* release previous scan buffer, if any */
    if (BufferIsValid(scan->rs_cbuf))
    {
        ReleaseBuffer(scan->rs_cbuf);
        scan->rs_cbuf = InvalidBuffer;
    }
 
    /*
     * Be sure to check for interrupts at least once per page.  Checks at
     * higher code levels won't be able to stop a seqscan that encounters many
     * pages' worth of consecutive dead tuples.
     */
    CHECK_FOR_INTERRUPTS();
 
    /*
     * If the scan direction is changing, reset the prefetch block to the
     * current block. Otherwise, we will incorrectly prefetch the blocks
     * between the prefetch block and the current block again before
     * prefetching blocks in the new, correct scan direction.
     */
    if (unlikely(scan->rs_dir != dir))
    {
        scan->rs_prefetch_block = scan->rs_cblock;
        read_stream_reset(scan->rs_read_stream);
    }
 
    scan->rs_dir = dir;
 
    scan->rs_cbuf = read_stream_next_buffer(scan->rs_read_stream, NULL);
    if (BufferIsValid(scan->rs_cbuf))
        scan->rs_cblock = BufferGetBlockNumber(scan->rs_cbuf);
}

References Assert(), BufferGetBlockNumber(), BufferIsValid(), CHECK_FOR_INTERRUPTS, InvalidBuffer, read_stream_next_buffer(), read_stream_reset(), ReleaseBuffer(), HeapScanDescData::rs_cblock, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_dir, HeapScanDescData::rs_prefetch_block, HeapScanDescData::rs_read_stream, and unlikely.

Referenced by heapgettup(), and heapgettup_pagemode().

heap_finish_speculative()

void heap_finish_speculative	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 6088 of file heapam.c.

{
    Buffer      buffer;
    Page        page;
    OffsetNumber offnum;
    ItemId      lp = NULL;
    HeapTupleHeader htup;
 
    buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
    page = BufferGetPage(buffer);
 
    offnum = ItemPointerGetOffsetNumber(tid);
    if (PageGetMaxOffsetNumber(page) >= offnum)
        lp = PageGetItemId(page, offnum);
 
    if (PageGetMaxOffsetNumber(page) < offnum || !ItemIdIsNormal(lp))
        elog(ERROR, "invalid lp");
 
    htup = (HeapTupleHeader) PageGetItem(page, lp);
 
    /* NO EREPORT(ERROR) from here till changes are logged */
    START_CRIT_SECTION();
 
    Assert(HeapTupleHeaderIsSpeculative(htup));
 
    MarkBufferDirty(buffer);
 
    /*
     * Replace the speculative insertion token with a real t_ctid, pointing to
     * itself like it does on regular tuples.
     */
    htup->t_ctid = *tid;
 
    /* XLOG stuff */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_confirm xlrec;
        XLogRecPtr  recptr;
 
        xlrec.offnum = ItemPointerGetOffsetNumber(tid);
 
        XLogBeginInsert();
 
        /* We want the same filtering on this as on a plain insert */
        XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
 
        XLogRegisterData(&xlrec, SizeOfHeapConfirm);
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_CONFIRM);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    UnlockReleaseBuffer(buffer);
}

References Assert(), BUFFER_LOCK_EXCLUSIVE, BufferGetPage(), elog, END_CRIT_SECTION, ERROR, HeapTupleHeaderIsSpeculative(), ItemIdIsNormal, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), LockBuffer(), MarkBufferDirty(), xl_heap_confirm::offnum, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PageSetLSN(), ReadBuffer(), REGBUF_STANDARD, RelationNeedsWAL, SizeOfHeapConfirm, START_CRIT_SECTION, HeapTupleHeaderData::t_ctid, UnlockReleaseBuffer(), XLOG_HEAP_CONFIRM, XLOG_INCLUDE_ORIGIN, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), and XLogSetRecordFlags().

Referenced by heapam_tuple_complete_speculative().

heap_freeze_prepared_tuples()

void heap_freeze_prepared_tuples	(	Buffer	buffer,
		HeapTupleFreeze *	tuples,
		int	ntuples
	)

Definition at line 7380 of file heapam.c.

{
    Page        page = BufferGetPage(buffer);
 
    for (int i = 0; i < ntuples; i++)
    {
        HeapTupleFreeze *frz = tuples + i;
        ItemId      itemid = PageGetItemId(page, frz->offset);
        HeapTupleHeader htup;
 
        htup = (HeapTupleHeader) PageGetItem(page, itemid);
        heap_execute_freeze_tuple(htup, frz);
    }
}

References BufferGetPage(), heap_execute_freeze_tuple(), i, HeapTupleFreeze::offset, PageGetItem(), and PageGetItemId().

Referenced by heap_page_prune_and_freeze().

heap_freeze_tuple()

bool heap_freeze_tuple	(	HeapTupleHeader	tuple,
		TransactionId	relfrozenxid,
		TransactionId	relminmxid,
		TransactionId	FreezeLimit,
		TransactionId	MultiXactCutoff
	)

Definition at line 7402 of file heapam.c.

{
    HeapTupleFreeze frz;
    bool        do_freeze;
    bool        totally_frozen;
    struct VacuumCutoffs cutoffs;
    HeapPageFreeze pagefrz;
 
    cutoffs.relfrozenxid = relfrozenxid;
    cutoffs.relminmxid = relminmxid;
    cutoffs.OldestXmin = FreezeLimit;
    cutoffs.OldestMxact = MultiXactCutoff;
    cutoffs.FreezeLimit = FreezeLimit;
    cutoffs.MultiXactCutoff = MultiXactCutoff;
 
    pagefrz.freeze_required = true;
    pagefrz.FreezePageRelfrozenXid = FreezeLimit;
    pagefrz.FreezePageRelminMxid = MultiXactCutoff;
    pagefrz.NoFreezePageRelfrozenXid = FreezeLimit;
    pagefrz.NoFreezePageRelminMxid = MultiXactCutoff;
 
    do_freeze = heap_prepare_freeze_tuple(tuple, &cutoffs,
                                          &pagefrz, &frz, &totally_frozen);
 
    /*
     * Note that because this is not a WAL-logged operation, we don't need to
     * fill in the offset in the freeze record.
     */
 
    if (do_freeze)
        heap_execute_freeze_tuple(tuple, &frz);
    return do_freeze;
}

References VacuumCutoffs::FreezeLimit, heap_execute_freeze_tuple(), heap_prepare_freeze_tuple(), VacuumCutoffs::MultiXactCutoff, VacuumCutoffs::OldestMxact, VacuumCutoffs::OldestXmin, VacuumCutoffs::relfrozenxid, and VacuumCutoffs::relminmxid.

Referenced by rewrite_heap_tuple().

heap_get_latest_tid()

void heap_get_latest_tid	(	TableScanDesc	sscan,
		ItemPointer	tid
	)

Definition at line 1877 of file heapam.c.

{
    Relation    relation = sscan->rs_rd;
    Snapshot    snapshot = sscan->rs_snapshot;
    ItemPointerData ctid;
    TransactionId priorXmax;
 
    /*
     * table_tuple_get_latest_tid() verified that the passed in tid is valid.
     * Assume that t_ctid links are valid however - there shouldn't be invalid
     * ones in the table.
     */
    Assert(ItemPointerIsValid(tid));
 
    /*
     * Loop to chase down t_ctid links.  At top of loop, ctid is the tuple we
     * need to examine, and *tid is the TID we will return if ctid turns out
     * to be bogus.
     *
     * Note that we will loop until we reach the end of the t_ctid chain.
     * Depending on the snapshot passed, there might be at most one visible
     * version of the row, but we don't try to optimize for that.
     */
    ctid = *tid;
    priorXmax = InvalidTransactionId;   /* cannot check first XMIN */
    for (;;)
    {
        Buffer      buffer;
        Page        page;
        OffsetNumber offnum;
        ItemId      lp;
        HeapTupleData tp;
        bool        valid;
 
        /*
         * Read, pin, and lock the page.
         */
        buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(&ctid));
        LockBuffer(buffer, BUFFER_LOCK_SHARE);
        page = BufferGetPage(buffer);
 
        /*
         * Check for bogus item number.  This is not treated as an error
         * condition because it can happen while following a t_ctid link. We
         * just assume that the prior tid is OK and return it unchanged.
         */
        offnum = ItemPointerGetOffsetNumber(&ctid);
        if (offnum < FirstOffsetNumber || offnum > PageGetMaxOffsetNumber(page))
        {
            UnlockReleaseBuffer(buffer);
            break;
        }
        lp = PageGetItemId(page, offnum);
        if (!ItemIdIsNormal(lp))
        {
            UnlockReleaseBuffer(buffer);
            break;
        }
 
        /* OK to access the tuple */
        tp.t_self = ctid;
        tp.t_data = (HeapTupleHeader) PageGetItem(page, lp);
        tp.t_len = ItemIdGetLength(lp);
        tp.t_tableOid = RelationGetRelid(relation);
 
        /*
         * After following a t_ctid link, we might arrive at an unrelated
         * tuple.  Check for XMIN match.
         */
        if (TransactionIdIsValid(priorXmax) &&
            !TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(tp.t_data)))
        {
            UnlockReleaseBuffer(buffer);
            break;
        }
 
        /*
         * Check tuple visibility; if visible, set it as the new result
         * candidate.
         */
        valid = HeapTupleSatisfiesVisibility(&tp, snapshot, buffer);
        HeapCheckForSerializableConflictOut(valid, relation, &tp, buffer, snapshot);
        if (valid)
            *tid = ctid;
 
        /*
         * If there's a valid t_ctid link, follow it, else we're done.
         */
        if ((tp.t_data->t_infomask & HEAP_XMAX_INVALID) ||
            HeapTupleHeaderIsOnlyLocked(tp.t_data) ||
            HeapTupleHeaderIndicatesMovedPartitions(tp.t_data) ||
            ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid))
        {
            UnlockReleaseBuffer(buffer);
            break;
        }
 
        ctid = tp.t_data->t_ctid;
        priorXmax = HeapTupleHeaderGetUpdateXid(tp.t_data);
        UnlockReleaseBuffer(buffer);
    }                           /* end of loop */
}

References Assert(), BUFFER_LOCK_SHARE, BufferGetPage(), HEAP_XMAX_INVALID, HeapCheckForSerializableConflictOut(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderIndicatesMovedPartitions(), HeapTupleHeaderIsOnlyLocked(), HeapTupleSatisfiesVisibility(), InvalidTransactionId, ItemIdGetLength, ItemIdIsNormal, ItemPointerEquals(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), ItemPointerIsValid(), LockBuffer(), PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), ReadBuffer(), RelationGetRelid, TableScanDescData::rs_rd, TableScanDescData::rs_snapshot, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TransactionIdEquals, TransactionIdIsValid, and UnlockReleaseBuffer().

heap_getnext()

HeapTuple heap_getnext	(	TableScanDesc	sscan,
		ScanDirection	direction
	)

Definition at line 1346 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
 
    /*
     * This is still widely used directly, without going through table AM, so
     * add a safety check.  It's possible we should, at a later point,
     * downgrade this to an assert. The reason for checking the AM routine,
     * rather than the AM oid, is that this allows to write regression tests
     * that create another AM reusing the heap handler.
     */
    if (unlikely(sscan->rs_rd->rd_tableam != GetHeapamTableAmRoutine()))
        ereport(ERROR,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg_internal("only heap AM is supported")));
 
    /*
     * We don't expect direct calls to heap_getnext with valid CheckXidAlive
     * for catalog or regular tables.  See detailed comments in xact.c where
     * these variables are declared.  Normally we have such a check at tableam
     * level API but this is called from many places so we need to ensure it
     * here.
     */
    if (unlikely(TransactionIdIsValid(CheckXidAlive) && !bsysscan))
        elog(ERROR, "unexpected heap_getnext call during logical decoding");
 
    /* Note: no locking manipulations needed */
 
    if (scan->rs_base.rs_flags & SO_ALLOW_PAGEMODE)
        heapgettup_pagemode(scan, direction,
                            scan->rs_base.rs_nkeys, scan->rs_base.rs_key);
    else
        heapgettup(scan, direction,
                   scan->rs_base.rs_nkeys, scan->rs_base.rs_key);
 
    if (scan->rs_ctup.t_data == NULL)
        return NULL;
 
    /*
     * if we get here it means we have a new current scan tuple, so point to
     * the proper return buffer and return the tuple.
     */
 
    pgstat_count_heap_getnext(scan->rs_base.rs_rd);
 
    return &scan->rs_ctup;
}

References bsysscan, CheckXidAlive, elog, ereport, errcode(), errmsg_internal(), ERROR, GetHeapamTableAmRoutine(), heapgettup(), heapgettup_pagemode(), pgstat_count_heap_getnext, RelationData::rd_tableam, HeapScanDescData::rs_base, HeapScanDescData::rs_ctup, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_nkeys, TableScanDescData::rs_rd, SO_ALLOW_PAGEMODE, HeapTupleData::t_data, TransactionIdIsValid, and unlikely.

Referenced by AlterTableMoveAll(), AlterTableSpaceOptions(), check_db_file_conflict(), CreateDatabaseUsingFileCopy(), do_autovacuum(), DropSetting(), DropTableSpace(), find_typed_table_dependencies(), get_all_vacuum_rels(), get_database_list(), get_subscription_list(), get_tables_to_cluster(), get_tablespace_name(), get_tablespace_oid(), GetAllTablesPublicationRelations(), getRelationsInNamespace(), GetSchemaPublicationRelations(), heapam_index_build_range_scan(), heapam_index_validate_scan(), objectsInSchemaToOids(), pgrowlocks(), pgstat_heap(), populate_typ_list(), ReindexMultipleTables(), remove_dbtablespaces(), RemoveSubscriptionRel(), RenameTableSpace(), ThereIsAtLeastOneRole(), and vac_truncate_clog().

heap_getnextslot()

bool heap_getnextslot	(	TableScanDesc	sscan,
		ScanDirection	direction,
		TupleTableSlot *	slot
	)

Definition at line 1395 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
 
    /* Note: no locking manipulations needed */
 
    if (sscan->rs_flags & SO_ALLOW_PAGEMODE)
        heapgettup_pagemode(scan, direction, sscan->rs_nkeys, sscan->rs_key);
    else
        heapgettup(scan, direction, sscan->rs_nkeys, sscan->rs_key);
 
    if (scan->rs_ctup.t_data == NULL)
    {
        ExecClearTuple(slot);
        return false;
    }
 
    /*
     * if we get here it means we have a new current scan tuple, so point to
     * the proper return buffer and return the tuple.
     */
 
    pgstat_count_heap_getnext(scan->rs_base.rs_rd);
 
    ExecStoreBufferHeapTuple(&scan->rs_ctup, slot,
                             scan->rs_cbuf);
    return true;
}

References ExecClearTuple(), ExecStoreBufferHeapTuple(), heapgettup(), heapgettup_pagemode(), pgstat_count_heap_getnext, HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_ctup, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_nkeys, TableScanDescData::rs_rd, SO_ALLOW_PAGEMODE, and HeapTupleData::t_data.

heap_getnextslot_tidrange()

bool heap_getnextslot_tidrange	(	TableScanDesc	sscan,
		ScanDirection	direction,
		TupleTableSlot *	slot
	)

Definition at line 1498 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
    ItemPointer mintid = &sscan->st.tidrange.rs_mintid;
    ItemPointer maxtid = &sscan->st.tidrange.rs_maxtid;
 
    /* Note: no locking manipulations needed */
    for (;;)
    {
        if (sscan->rs_flags & SO_ALLOW_PAGEMODE)
            heapgettup_pagemode(scan, direction, sscan->rs_nkeys, sscan->rs_key);
        else
            heapgettup(scan, direction, sscan->rs_nkeys, sscan->rs_key);
 
        if (scan->rs_ctup.t_data == NULL)
        {
            ExecClearTuple(slot);
            return false;
        }
 
        /*
         * heap_set_tidrange will have used heap_setscanlimits to limit the
         * range of pages we scan to only ones that can contain the TID range
         * we're scanning for.  Here we must filter out any tuples from these
         * pages that are outside of that range.
         */
        if (ItemPointerCompare(&scan->rs_ctup.t_self, mintid) < 0)
        {
            ExecClearTuple(slot);
 
            /*
             * When scanning backwards, the TIDs will be in descending order.
             * Future tuples in this direction will be lower still, so we can
             * just return false to indicate there will be no more tuples.
             */
            if (ScanDirectionIsBackward(direction))
                return false;
 
            continue;
        }
 
        /*
         * Likewise for the final page, we must filter out TIDs greater than
         * maxtid.
         */
        if (ItemPointerCompare(&scan->rs_ctup.t_self, maxtid) > 0)
        {
            ExecClearTuple(slot);
 
            /*
             * When scanning forward, the TIDs will be in ascending order.
             * Future tuples in this direction will be higher still, so we can
             * just return false to indicate there will be no more tuples.
             */
            if (ScanDirectionIsForward(direction))
                return false;
            continue;
        }
 
        break;
    }
 
    /*
     * if we get here it means we have a new current scan tuple, so point to
     * the proper return buffer and return the tuple.
     */
    pgstat_count_heap_getnext(scan->rs_base.rs_rd);
 
    ExecStoreBufferHeapTuple(&scan->rs_ctup, slot, scan->rs_cbuf);
    return true;
}

References ExecClearTuple(), ExecStoreBufferHeapTuple(), heapgettup(), heapgettup_pagemode(), ItemPointerCompare(), pgstat_count_heap_getnext, HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_ctup, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_maxtid, TableScanDescData::rs_mintid, TableScanDescData::rs_nkeys, TableScanDescData::rs_rd, ScanDirectionIsBackward, ScanDirectionIsForward, SO_ALLOW_PAGEMODE, TableScanDescData::st, HeapTupleData::t_data, HeapTupleData::t_self, and TableScanDescData::tidrange.

heap_hot_search_buffer()

bool heap_hot_search_buffer	(	ItemPointer	tid,
		Relation	relation,
		Buffer	buffer,
		Snapshot	snapshot,
		HeapTuple	heapTuple,
		bool *	all_dead,
		bool	first_call
	)

Definition at line 1725 of file heapam.c.

{
    Page        page = BufferGetPage(buffer);
    TransactionId prev_xmax = InvalidTransactionId;
    BlockNumber blkno;
    OffsetNumber offnum;
    bool        at_chain_start;
    bool        valid;
    bool        skip;
    GlobalVisState *vistest = NULL;
 
    /* If this is not the first call, previous call returned a (live!) tuple */
    if (all_dead)
        *all_dead = first_call;
 
    blkno = ItemPointerGetBlockNumber(tid);
    offnum = ItemPointerGetOffsetNumber(tid);
    at_chain_start = first_call;
    skip = !first_call;
 
    /* XXX: we should assert that a snapshot is pushed or registered */
    Assert(TransactionIdIsValid(RecentXmin));
    Assert(BufferGetBlockNumber(buffer) == blkno);
 
    /* Scan through possible multiple members of HOT-chain */
    for (;;)
    {
        ItemId      lp;
 
        /* check for bogus TID */
        if (offnum < FirstOffsetNumber || offnum > PageGetMaxOffsetNumber(page))
            break;
 
        lp = PageGetItemId(page, offnum);
 
        /* check for unused, dead, or redirected items */
        if (!ItemIdIsNormal(lp))
        {
            /* We should only see a redirect at start of chain */
            if (ItemIdIsRedirected(lp) && at_chain_start)
            {
                /* Follow the redirect */
                offnum = ItemIdGetRedirect(lp);
                at_chain_start = false;
                continue;
            }
            /* else must be end of chain */
            break;
        }
 
        /*
         * Update heapTuple to point to the element of the HOT chain we're
         * currently investigating. Having t_self set correctly is important
         * because the SSI checks and the *Satisfies routine for historical
         * MVCC snapshots need the correct tid to decide about the visibility.
         */
        heapTuple->t_data = (HeapTupleHeader) PageGetItem(page, lp);
        heapTuple->t_len = ItemIdGetLength(lp);
        heapTuple->t_tableOid = RelationGetRelid(relation);
        ItemPointerSet(&heapTuple->t_self, blkno, offnum);
 
        /*
         * Shouldn't see a HEAP_ONLY tuple at chain start.
         */
        if (at_chain_start && HeapTupleIsHeapOnly(heapTuple))
            break;
 
        /*
         * The xmin should match the previous xmax value, else chain is
         * broken.
         */
        if (TransactionIdIsValid(prev_xmax) &&
            !TransactionIdEquals(prev_xmax,
                                 HeapTupleHeaderGetXmin(heapTuple->t_data)))
            break;
 
        /*
         * When first_call is true (and thus, skip is initially false) we'll
         * return the first tuple we find.  But on later passes, heapTuple
         * will initially be pointing to the tuple we returned last time.
         * Returning it again would be incorrect (and would loop forever), so
         * we skip it and return the next match we find.
         */
        if (!skip)
        {
            /* If it's visible per the snapshot, we must return it */
            valid = HeapTupleSatisfiesVisibility(heapTuple, snapshot, buffer);
            HeapCheckForSerializableConflictOut(valid, relation, heapTuple,
                                                buffer, snapshot);
 
            if (valid)
            {
                ItemPointerSetOffsetNumber(tid, offnum);
                PredicateLockTID(relation, &heapTuple->t_self, snapshot,
                                 HeapTupleHeaderGetXmin(heapTuple->t_data));
                if (all_dead)
                    *all_dead = false;
                return true;
            }
        }
        skip = false;
 
        /*
         * If we can't see it, maybe no one else can either.  At caller
         * request, check whether all chain members are dead to all
         * transactions.
         *
         * Note: if you change the criterion here for what is "dead", fix the
         * planner's get_actual_variable_range() function to match.
         */
        if (all_dead && *all_dead)
        {
            if (!vistest)
                vistest = GlobalVisTestFor(relation);
 
            if (!HeapTupleIsSurelyDead(heapTuple, vistest))
                *all_dead = false;
        }
 
        /*
         * Check to see if HOT chain continues past this tuple; if so fetch
         * the next offnum and loop around.
         */
        if (HeapTupleIsHotUpdated(heapTuple))
        {
            Assert(ItemPointerGetBlockNumber(&heapTuple->t_data->t_ctid) ==
                   blkno);
            offnum = ItemPointerGetOffsetNumber(&heapTuple->t_data->t_ctid);
            at_chain_start = false;
            prev_xmax = HeapTupleHeaderGetUpdateXid(heapTuple->t_data);
        }
        else
            break;              /* end of chain */
    }
 
    return false;
}

References Assert(), BufferGetBlockNumber(), BufferGetPage(), GlobalVisTestFor(), HeapCheckForSerializableConflictOut(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleIsHeapOnly(), HeapTupleIsHotUpdated(), HeapTupleIsSurelyDead(), HeapTupleSatisfiesVisibility(), InvalidTransactionId, ItemIdGetLength, ItemIdGetRedirect, ItemIdIsNormal, ItemIdIsRedirected, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), ItemPointerSet(), ItemPointerSetOffsetNumber(), PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PredicateLockTID(), RecentXmin, RelationGetRelid, skip, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TransactionIdEquals, and TransactionIdIsValid.

Referenced by BitmapHeapScanNextBlock(), heap_index_delete_tuples(), and heapam_index_fetch_tuple().

heap_index_delete_tuples()

TransactionId heap_index_delete_tuples	(	Relation	rel,
		TM_IndexDeleteOp *	delstate
	)

Definition at line 8118 of file heapam.c.

{
    /* Initial assumption is that earlier pruning took care of conflict */
    TransactionId snapshotConflictHorizon = InvalidTransactionId;
    BlockNumber blkno = InvalidBlockNumber;
    Buffer      buf = InvalidBuffer;
    Page        page = NULL;
    OffsetNumber maxoff = InvalidOffsetNumber;
    TransactionId priorXmax;
#ifdef USE_PREFETCH
    IndexDeletePrefetchState prefetch_state;
    int         prefetch_distance;
#endif
    SnapshotData SnapshotNonVacuumable;
    int         finalndeltids = 0,
                nblocksaccessed = 0;
 
    /* State that's only used in bottom-up index deletion case */
    int         nblocksfavorable = 0;
    int         curtargetfreespace = delstate->bottomupfreespace,
                lastfreespace = 0,
                actualfreespace = 0;
    bool        bottomup_final_block = false;
 
    InitNonVacuumableSnapshot(SnapshotNonVacuumable, GlobalVisTestFor(rel));
 
    /* Sort caller's deltids array by TID for further processing */
    index_delete_sort(delstate);
 
    /*
     * Bottom-up case: resort deltids array in an order attuned to where the
     * greatest number of promising TIDs are to be found, and determine how
     * many blocks from the start of sorted array should be considered
     * favorable.  This will also shrink the deltids array in order to
     * eliminate completely unfavorable blocks up front.
     */
    if (delstate->bottomup)
        nblocksfavorable = bottomup_sort_and_shrink(delstate);
 
#ifdef USE_PREFETCH
    /* Initialize prefetch state. */
    prefetch_state.cur_hblkno = InvalidBlockNumber;
    prefetch_state.next_item = 0;
    prefetch_state.ndeltids = delstate->ndeltids;
    prefetch_state.deltids = delstate->deltids;
 
    /*
     * Determine the prefetch distance that we will attempt to maintain.
     *
     * Since the caller holds a buffer lock somewhere in rel, we'd better make
     * sure that isn't a catalog relation before we call code that does
     * syscache lookups, to avoid risk of deadlock.
     */
    if (IsCatalogRelation(rel))
        prefetch_distance = maintenance_io_concurrency;
    else
        prefetch_distance =
            get_tablespace_maintenance_io_concurrency(rel->rd_rel->reltablespace);
 
    /* Cap initial prefetch distance for bottom-up deletion caller */
    if (delstate->bottomup)
    {
        Assert(nblocksfavorable >= 1);
        Assert(nblocksfavorable <= BOTTOMUP_MAX_NBLOCKS);
        prefetch_distance = Min(prefetch_distance, nblocksfavorable);
    }
 
    /* Start prefetching. */
    index_delete_prefetch_buffer(rel, &prefetch_state, prefetch_distance);
#endif
 
    /* Iterate over deltids, determine which to delete, check their horizon */
    Assert(delstate->ndeltids > 0);
    for (int i = 0; i < delstate->ndeltids; i++)
    {
        TM_IndexDelete *ideltid = &delstate->deltids[i];
        TM_IndexStatus *istatus = delstate->status + ideltid->id;
        ItemPointer htid = &ideltid->tid;
        OffsetNumber offnum;
 
        /*
         * Read buffer, and perform required extra steps each time a new block
         * is encountered.  Avoid refetching if it's the same block as the one
         * from the last htid.
         */
        if (blkno == InvalidBlockNumber ||
            ItemPointerGetBlockNumber(htid) != blkno)
        {
            /*
             * Consider giving up early for bottom-up index deletion caller
             * first. (Only prefetch next-next block afterwards, when it
             * becomes clear that we're at least going to access the next
             * block in line.)
             *
             * Sometimes the first block frees so much space for bottom-up
             * caller that the deletion process can end without accessing any
             * more blocks.  It is usually necessary to access 2 or 3 blocks
             * per bottom-up deletion operation, though.
             */
            if (delstate->bottomup)
            {
                /*
                 * We often allow caller to delete a few additional items
                 * whose entries we reached after the point that space target
                 * from caller was satisfied.  The cost of accessing the page
                 * was already paid at that point, so it made sense to finish
                 * it off.  When that happened, we finalize everything here
                 * (by finishing off the whole bottom-up deletion operation
                 * without needlessly paying the cost of accessing any more
                 * blocks).
                 */
                if (bottomup_final_block)
                    break;
 
                /*
                 * Give up when we didn't enable our caller to free any
                 * additional space as a result of processing the page that we
                 * just finished up with.  This rule is the main way in which
                 * we keep the cost of bottom-up deletion under control.
                 */
                if (nblocksaccessed >= 1 && actualfreespace == lastfreespace)
                    break;
                lastfreespace = actualfreespace;    /* for next time */
 
                /*
                 * Deletion operation (which is bottom-up) will definitely
                 * access the next block in line.  Prepare for that now.
                 *
                 * Decay target free space so that we don't hang on for too
                 * long with a marginal case. (Space target is only truly
                 * helpful when it allows us to recognize that we don't need
                 * to access more than 1 or 2 blocks to satisfy caller due to
                 * agreeable workload characteristics.)
                 *
                 * We are a bit more patient when we encounter contiguous
                 * blocks, though: these are treated as favorable blocks.  The
                 * decay process is only applied when the next block in line
                 * is not a favorable/contiguous block.  This is not an
                 * exception to the general rule; we still insist on finding
                 * at least one deletable item per block accessed.  See
                 * bottomup_nblocksfavorable() for full details of the theory
                 * behind favorable blocks and heap block locality in general.
                 *
                 * Note: The first block in line is always treated as a
                 * favorable block, so the earliest possible point that the
                 * decay can be applied is just before we access the second
                 * block in line.  The Assert() verifies this for us.
                 */
                Assert(nblocksaccessed > 0 || nblocksfavorable > 0);
                if (nblocksfavorable > 0)
                    nblocksfavorable--;
                else
                    curtargetfreespace /= 2;
            }
 
            /* release old buffer */
            if (BufferIsValid(buf))
                UnlockReleaseBuffer(buf);
 
            blkno = ItemPointerGetBlockNumber(htid);
            buf = ReadBuffer(rel, blkno);
            nblocksaccessed++;
            Assert(!delstate->bottomup ||
                   nblocksaccessed <= BOTTOMUP_MAX_NBLOCKS);
 
#ifdef USE_PREFETCH
 
            /*
             * To maintain the prefetch distance, prefetch one more page for
             * each page we read.
             */
            index_delete_prefetch_buffer(rel, &prefetch_state, 1);
#endif
 
            LockBuffer(buf, BUFFER_LOCK_SHARE);
 
            page = BufferGetPage(buf);
            maxoff = PageGetMaxOffsetNumber(page);
        }
 
        /*
         * In passing, detect index corruption involving an index page with a
         * TID that points to a location in the heap that couldn't possibly be
         * correct.  We only do this with actual TIDs from caller's index page
         * (not items reached by traversing through a HOT chain).
         */
        index_delete_check_htid(delstate, page, maxoff, htid, istatus);
 
        if (istatus->knowndeletable)
            Assert(!delstate->bottomup && !istatus->promising);
        else
        {
            ItemPointerData tmp = *htid;
            HeapTupleData heapTuple;
 
            /* Are any tuples from this HOT chain non-vacuumable? */
            if (heap_hot_search_buffer(&tmp, rel, buf, &SnapshotNonVacuumable,
                                       &heapTuple, NULL, true))
                continue;       /* can't delete entry */
 
            /* Caller will delete, since whole HOT chain is vacuumable */
            istatus->knowndeletable = true;
 
            /* Maintain index free space info for bottom-up deletion case */
            if (delstate->bottomup)
            {
                Assert(istatus->freespace > 0);
                actualfreespace += istatus->freespace;
                if (actualfreespace >= curtargetfreespace)
                    bottomup_final_block = true;
            }
        }
 
        /*
         * Maintain snapshotConflictHorizon value for deletion operation as a
         * whole by advancing current value using heap tuple headers.  This is
         * loosely based on the logic for pruning a HOT chain.
         */
        offnum = ItemPointerGetOffsetNumber(htid);
        priorXmax = InvalidTransactionId;   /* cannot check first XMIN */
        for (;;)
        {
            ItemId      lp;
            HeapTupleHeader htup;
 
            /* Sanity check (pure paranoia) */
            if (offnum < FirstOffsetNumber)
                break;
 
            /*
             * An offset past the end of page's line pointer array is possible
             * when the array was truncated
             */
            if (offnum > maxoff)
                break;
 
            lp = PageGetItemId(page, offnum);
            if (ItemIdIsRedirected(lp))
            {
                offnum = ItemIdGetRedirect(lp);
                continue;
            }
 
            /*
             * We'll often encounter LP_DEAD line pointers (especially with an
             * entry marked knowndeletable by our caller up front).  No heap
             * tuple headers get examined for an htid that leads us to an
             * LP_DEAD item.  This is okay because the earlier pruning
             * operation that made the line pointer LP_DEAD in the first place
             * must have considered the original tuple header as part of
             * generating its own snapshotConflictHorizon value.
             *
             * Relying on XLOG_HEAP2_PRUNE_VACUUM_SCAN records like this is
             * the same strategy that index vacuuming uses in all cases. Index
             * VACUUM WAL records don't even have a snapshotConflictHorizon
             * field of their own for this reason.
             */
            if (!ItemIdIsNormal(lp))
                break;
 
            htup = (HeapTupleHeader) PageGetItem(page, lp);
 
            /*
             * Check the tuple XMIN against prior XMAX, if any
             */
            if (TransactionIdIsValid(priorXmax) &&
                !TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
                break;
 
            HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                  &snapshotConflictHorizon);
 
            /*
             * If the tuple is not HOT-updated, then we are at the end of this
             * HOT-chain.  No need to visit later tuples from the same update
             * chain (they get their own index entries) -- just move on to
             * next htid from index AM caller.
             */
            if (!HeapTupleHeaderIsHotUpdated(htup))
                break;
 
            /* Advance to next HOT chain member */
            Assert(ItemPointerGetBlockNumber(&htup->t_ctid) == blkno);
            offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
            priorXmax = HeapTupleHeaderGetUpdateXid(htup);
        }
 
        /* Enable further/final shrinking of deltids for caller */
        finalndeltids = i + 1;
    }
 
    UnlockReleaseBuffer(buf);
 
    /*
     * Shrink deltids array to exclude non-deletable entries at the end.  This
     * is not just a minor optimization.  Final deltids array size might be
     * zero for a bottom-up caller.  Index AM is explicitly allowed to rely on
     * ndeltids being zero in all cases with zero total deletable entries.
     */
    Assert(finalndeltids > 0 || delstate->bottomup);
    delstate->ndeltids = finalndeltids;
 
    return snapshotConflictHorizon;
}

References Assert(), TM_IndexDeleteOp::bottomup, BOTTOMUP_MAX_NBLOCKS, bottomup_sort_and_shrink(), TM_IndexDeleteOp::bottomupfreespace, buf, BUFFER_LOCK_SHARE, BufferGetPage(), BufferIsValid(), TM_IndexDeleteOp::deltids, FirstOffsetNumber, TM_IndexStatus::freespace, get_tablespace_maintenance_io_concurrency(), GlobalVisTestFor(), heap_hot_search_buffer(), HeapTupleHeaderAdvanceConflictHorizon(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderIsHotUpdated(), i, TM_IndexDelete::id, index_delete_check_htid(), index_delete_sort(), InitNonVacuumableSnapshot, InvalidBlockNumber, InvalidBuffer, InvalidOffsetNumber, InvalidTransactionId, IsCatalogRelation(), ItemIdGetRedirect, ItemIdIsNormal, ItemIdIsRedirected, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), TM_IndexStatus::knowndeletable, LockBuffer(), maintenance_io_concurrency, Min, TM_IndexDeleteOp::ndeltids, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), TM_IndexStatus::promising, RelationData::rd_rel, ReadBuffer(), TM_IndexDeleteOp::status, HeapTupleHeaderData::t_ctid, TM_IndexDelete::tid, TransactionIdEquals, TransactionIdIsValid, and UnlockReleaseBuffer().

heap_inplace_lock()

bool heap_inplace_lock	(	Relation	relation,
		HeapTuple	oldtup_ptr,
		Buffer	buffer,
		void(*)(void *)	release_callback,
		void *	arg
	)

Definition at line 6354 of file heapam.c.

{
    HeapTupleData oldtup = *oldtup_ptr; /* minimize diff vs. heap_update() */
    TM_Result   result;
    bool        ret;
 
#ifdef USE_ASSERT_CHECKING
    if (RelationGetRelid(relation) == RelationRelationId)
        check_inplace_rel_lock(oldtup_ptr);
#endif
 
    Assert(BufferIsValid(buffer));
 
    /*
     * Construct shared cache inval if necessary.  Because we pass a tuple
     * version without our own inplace changes or inplace changes other
     * sessions complete while we wait for locks, inplace update mustn't
     * change catcache lookup keys.  But we aren't bothering with index
     * updates either, so that's true a fortiori.  After LockBuffer(), it
     * would be too late, because this might reach a
     * CatalogCacheInitializeCache() that locks "buffer".
     */
    CacheInvalidateHeapTupleInplace(relation, oldtup_ptr, NULL);
 
    LockTuple(relation, &oldtup.t_self, InplaceUpdateTupleLock);
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
    /*----------
     * Interpret HeapTupleSatisfiesUpdate() like heap_update() does, except:
     *
     * - wait unconditionally
     * - already locked tuple above, since inplace needs that unconditionally
     * - don't recheck header after wait: simpler to defer to next iteration
     * - don't try to continue even if the updater aborts: likewise
     * - no crosscheck
     */
    result = HeapTupleSatisfiesUpdate(&oldtup, GetCurrentCommandId(false),
                                      buffer);
 
    if (result == TM_Invisible)
    {
        /* no known way this can happen */
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg_internal("attempted to overwrite invisible tuple")));
    }
    else if (result == TM_SelfModified)
    {
        /*
         * CREATE INDEX might reach this if an expression is silly enough to
         * call e.g. SELECT ... FROM pg_class FOR SHARE.  C code of other SQL
         * statements might get here after a heap_update() of the same row, in
         * the absence of an intervening CommandCounterIncrement().
         */
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("tuple to be updated was already modified by an operation triggered by the current command")));
    }
    else if (result == TM_BeingModified)
    {
        TransactionId xwait;
        uint16      infomask;
 
        xwait = HeapTupleHeaderGetRawXmax(oldtup.t_data);
        infomask = oldtup.t_data->t_infomask;
 
        if (infomask & HEAP_XMAX_IS_MULTI)
        {
            LockTupleMode lockmode = LockTupleNoKeyExclusive;
            MultiXactStatus mxact_status = MultiXactStatusNoKeyUpdate;
            int         remain;
 
            if (DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
                                        lockmode, NULL))
            {
                LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
                release_callback(arg);
                ret = false;
                MultiXactIdWait((MultiXactId) xwait, mxact_status, infomask,
                                relation, &oldtup.t_self, XLTW_Update,
                                &remain);
            }
            else
                ret = true;
        }
        else if (TransactionIdIsCurrentTransactionId(xwait))
            ret = true;
        else if (HEAP_XMAX_IS_KEYSHR_LOCKED(infomask))
            ret = true;
        else
        {
            LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            release_callback(arg);
            ret = false;
            XactLockTableWait(xwait, relation, &oldtup.t_self,
                              XLTW_Update);
        }
    }
    else
    {
        ret = (result == TM_Ok);
        if (!ret)
        {
            LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            release_callback(arg);
        }
    }
 
    /*
     * GetCatalogSnapshot() relies on invalidation messages to know when to
     * take a new snapshot.  COMMIT of xwait is responsible for sending the
     * invalidation.  We're not acquiring heavyweight locks sufficient to
     * block if not yet sent, so we must take a new snapshot to ensure a later
     * attempt has a fair chance.  While we don't need this if xwait aborted,
     * don't bother optimizing that.
     */
    if (!ret)
    {
        UnlockTuple(relation, &oldtup.t_self, InplaceUpdateTupleLock);
        ForgetInplace_Inval();
        InvalidateCatalogSnapshot();
    }
    return ret;
}

References arg, Assert(), BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferIsValid(), CacheInvalidateHeapTupleInplace(), DoesMultiXactIdConflict(), ereport, errcode(), errmsg(), errmsg_internal(), ERROR, ForgetInplace_Inval(), GetCurrentCommandId(), HEAP_XMAX_IS_KEYSHR_LOCKED(), HEAP_XMAX_IS_MULTI, HeapTupleHeaderGetRawXmax(), HeapTupleSatisfiesUpdate(), InplaceUpdateTupleLock, InvalidateCatalogSnapshot(), LockBuffer(), LockTuple(), LockTupleNoKeyExclusive, MultiXactIdWait(), MultiXactStatusNoKeyUpdate, RelationGetRelid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleData::t_self, TM_BeingModified, TM_Invisible, TM_Ok, TM_SelfModified, TransactionIdIsCurrentTransactionId(), UnlockTuple(), XactLockTableWait(), and XLTW_Update.

Referenced by systable_inplace_update_begin().

heap_inplace_unlock()

void heap_inplace_unlock	(	Relation	relation,
		HeapTuple	oldtup,
		Buffer	buffer
	)

Definition at line 6643 of file heapam.c.

{
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
    UnlockTuple(relation, &oldtup->t_self, InplaceUpdateTupleLock);
    ForgetInplace_Inval();
}

References BUFFER_LOCK_UNLOCK, ForgetInplace_Inval(), InplaceUpdateTupleLock, LockBuffer(), HeapTupleData::t_self, and UnlockTuple().

Referenced by systable_inplace_update_cancel().

heap_inplace_update_and_unlock()

void heap_inplace_update_and_unlock	(	Relation	relation,
		HeapTuple	oldtup,
		HeapTuple	tuple,
		Buffer	buffer
	)

Definition at line 6490 of file heapam.c.

{
    HeapTupleHeader htup = oldtup->t_data;
    uint32      oldlen;
    uint32      newlen;
    char       *dst;
    char       *src;
    int         nmsgs = 0;
    SharedInvalidationMessage *invalMessages = NULL;
    bool        RelcacheInitFileInval = false;
 
    Assert(ItemPointerEquals(&oldtup->t_self, &tuple->t_self));
    oldlen = oldtup->t_len - htup->t_hoff;
    newlen = tuple->t_len - tuple->t_data->t_hoff;
    if (oldlen != newlen || htup->t_hoff != tuple->t_data->t_hoff)
        elog(ERROR, "wrong tuple length");
 
    dst = (char *) htup + htup->t_hoff;
    src = (char *) tuple->t_data + tuple->t_data->t_hoff;
 
    /* Like RecordTransactionCommit(), log only if needed */
    if (XLogStandbyInfoActive())
        nmsgs = inplaceGetInvalidationMessages(&invalMessages,
                                               &RelcacheInitFileInval);
 
    /*
     * Unlink relcache init files as needed.  If unlinking, acquire
     * RelCacheInitLock until after associated invalidations.  By doing this
     * in advance, if we checkpoint and then crash between inplace
     * XLogInsert() and inval, we don't rely on StartupXLOG() ->
     * RelationCacheInitFileRemove().  That uses elevel==LOG, so replay would
     * neglect to PANIC on EIO.
     */
    PreInplace_Inval();
 
    /*----------
     * NO EREPORT(ERROR) from here till changes are complete
     *
     * Our buffer lock won't stop a reader having already pinned and checked
     * visibility for this tuple.  Hence, we write WAL first, then mutate the
     * buffer.  Like in MarkBufferDirtyHint() or RecordTransactionCommit(),
     * checkpoint delay makes that acceptable.  With the usual order of
     * changes, a crash after memcpy() and before XLogInsert() could allow
     * datfrozenxid to overtake relfrozenxid:
     *
     * ["D" is a VACUUM (ONLY_DATABASE_STATS)]
     * ["R" is a VACUUM tbl]
     * D: vac_update_datfrozenxid() -> systable_beginscan(pg_class)
     * D: systable_getnext() returns pg_class tuple of tbl
     * R: memcpy() into pg_class tuple of tbl
     * D: raise pg_database.datfrozenxid, XLogInsert(), finish
     * [crash]
     * [recovery restores datfrozenxid w/o relfrozenxid]
     *
     * Mimic MarkBufferDirtyHint() subroutine XLogSaveBufferForHint().
     * Specifically, use DELAY_CHKPT_START, and copy the buffer to the stack.
     * The stack copy facilitates a FPI of the post-mutation block before we
     * accept other sessions seeing it.  DELAY_CHKPT_START allows us to
     * XLogInsert() before MarkBufferDirty().  Since XLogSaveBufferForHint()
     * can operate under BUFFER_LOCK_SHARED, it can't avoid DELAY_CHKPT_START.
     * This function, however, likely could avoid it with the following order
     * of operations: MarkBufferDirty(), XLogInsert(), memcpy().  Opt to use
     * DELAY_CHKPT_START here, too, as a way to have fewer distinct code
     * patterns to analyze.  Inplace update isn't so frequent that it should
     * pursue the small optimization of skipping DELAY_CHKPT_START.
     */
    Assert((MyProc->delayChkptFlags & DELAY_CHKPT_START) == 0);
    START_CRIT_SECTION();
    MyProc->delayChkptFlags |= DELAY_CHKPT_START;
 
    /* XLOG stuff */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_inplace xlrec;
        PGAlignedBlock copied_buffer;
        char       *origdata = (char *) BufferGetBlock(buffer);
        Page        page = BufferGetPage(buffer);
        uint16      lower = ((PageHeader) page)->pd_lower;
        uint16      upper = ((PageHeader) page)->pd_upper;
        uintptr_t   dst_offset_in_block;
        RelFileLocator rlocator;
        ForkNumber  forkno;
        BlockNumber blkno;
        XLogRecPtr  recptr;
 
        xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self);
        xlrec.dbId = MyDatabaseId;
        xlrec.tsId = MyDatabaseTableSpace;
        xlrec.relcacheInitFileInval = RelcacheInitFileInval;
        xlrec.nmsgs = nmsgs;
 
        XLogBeginInsert();
        XLogRegisterData(&xlrec, MinSizeOfHeapInplace);
        if (nmsgs != 0)
            XLogRegisterData(invalMessages,
                             nmsgs * sizeof(SharedInvalidationMessage));
 
        /* register block matching what buffer will look like after changes */
        memcpy(copied_buffer.data, origdata, lower);
        memcpy(copied_buffer.data + upper, origdata + upper, BLCKSZ - upper);
        dst_offset_in_block = dst - origdata;
        memcpy(copied_buffer.data + dst_offset_in_block, src, newlen);
        BufferGetTag(buffer, &rlocator, &forkno, &blkno);
        Assert(forkno == MAIN_FORKNUM);
        XLogRegisterBlock(0, &rlocator, forkno, blkno, copied_buffer.data,
                          REGBUF_STANDARD);
        XLogRegisterBufData(0, src, newlen);
 
        /* inplace updates aren't decoded atm, don't log the origin */
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_INPLACE);
 
        PageSetLSN(page, recptr);
    }
 
    memcpy(dst, src, newlen);
 
    MarkBufferDirty(buffer);
 
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
    /*
     * Send invalidations to shared queue.  SearchSysCacheLocked1() assumes we
     * do this before UnlockTuple().
     *
     * If we're mutating a tuple visible only to this transaction, there's an
     * equivalent transactional inval from the action that created the tuple,
     * and this inval is superfluous.
     */
    AtInplace_Inval();
 
    MyProc->delayChkptFlags &= ~DELAY_CHKPT_START;
    END_CRIT_SECTION();
    UnlockTuple(relation, &tuple->t_self, InplaceUpdateTupleLock);
 
    AcceptInvalidationMessages();   /* local processing of just-sent inval */
 
    /*
     * Queue a transactional inval.  The immediate invalidation we just sent
     * is the only one known to be necessary.  To reduce risk from the
     * transition to immediate invalidation, continue sending a transactional
     * invalidation like we've long done.  Third-party code might rely on it.
     */
    if (!IsBootstrapProcessingMode())
        CacheInvalidateHeapTuple(relation, tuple, NULL);
}

References AcceptInvalidationMessages(), Assert(), AtInplace_Inval(), BUFFER_LOCK_UNLOCK, BufferGetBlock(), BufferGetPage(), BufferGetTag(), CacheInvalidateHeapTuple(), PGAlignedBlock::data, xl_heap_inplace::dbId, DELAY_CHKPT_START, PGPROC::delayChkptFlags, elog, END_CRIT_SECTION, ERROR, inplaceGetInvalidationMessages(), InplaceUpdateTupleLock, IsBootstrapProcessingMode, ItemPointerEquals(), ItemPointerGetOffsetNumber(), LockBuffer(), lower(), MAIN_FORKNUM, MarkBufferDirty(), MinSizeOfHeapInplace, MyDatabaseId, MyDatabaseTableSpace, MyProc, xl_heap_inplace::nmsgs, xl_heap_inplace::offnum, PageSetLSN(), PreInplace_Inval(), REGBUF_STANDARD, RelationNeedsWAL, xl_heap_inplace::relcacheInitFileInval, START_CRIT_SECTION, HeapTupleData::t_data, HeapTupleHeaderData::t_hoff, HeapTupleData::t_len, HeapTupleData::t_self, xl_heap_inplace::tsId, UnlockTuple(), upper(), XLOG_HEAP_INPLACE, XLogBeginInsert(), XLogInsert(), XLogRegisterBlock(), XLogRegisterBufData(), XLogRegisterData(), and XLogStandbyInfoActive.

Referenced by systable_inplace_update_finish().

heap_insert()

void heap_insert	(	Relation	relation,
		HeapTuple	tup,
		CommandId	cid,
		int	options,
		BulkInsertState	bistate
	)

Definition at line 2088 of file heapam.c.

{
    TransactionId xid = GetCurrentTransactionId();
    HeapTuple   heaptup;
    Buffer      buffer;
    Buffer      vmbuffer = InvalidBuffer;
    bool        all_visible_cleared = false;
 
    /* Cheap, simplistic check that the tuple matches the rel's rowtype. */
    Assert(HeapTupleHeaderGetNatts(tup->t_data) <=
           RelationGetNumberOfAttributes(relation));
 
    AssertHasSnapshotForToast(relation);
 
    /*
     * Fill in tuple header fields and toast the tuple if necessary.
     *
     * Note: below this point, heaptup is the data we actually intend to store
     * into the relation; tup is the caller's original untoasted data.
     */
    heaptup = heap_prepare_insert(relation, tup, xid, cid, options);
 
    /*
     * Find buffer to insert this tuple into.  If the page is all visible,
     * this will also pin the requisite visibility map page.
     */
    buffer = RelationGetBufferForTuple(relation, heaptup->t_len,
                                       InvalidBuffer, options, bistate,
                                       &vmbuffer, NULL,
                                       0);
 
    /*
     * We're about to do the actual insert -- but check for conflict first, to
     * avoid possibly having to roll back work we've just done.
     *
     * This is safe without a recheck as long as there is no possibility of
     * another process scanning the page between this check and the insert
     * being visible to the scan (i.e., an exclusive buffer content lock is
     * continuously held from this point until the tuple insert is visible).
     *
     * For a heap insert, we only need to check for table-level SSI locks. Our
     * new tuple can't possibly conflict with existing tuple locks, and heap
     * page locks are only consolidated versions of tuple locks; they do not
     * lock "gaps" as index page locks do.  So we don't need to specify a
     * buffer when making the call, which makes for a faster check.
     */
    CheckForSerializableConflictIn(relation, NULL, InvalidBlockNumber);
 
    /* NO EREPORT(ERROR) from here till changes are logged */
    START_CRIT_SECTION();
 
    RelationPutHeapTuple(relation, buffer, heaptup,
                         (options & HEAP_INSERT_SPECULATIVE) != 0);
 
    if (PageIsAllVisible(BufferGetPage(buffer)))
    {
        all_visible_cleared = true;
        PageClearAllVisible(BufferGetPage(buffer));
        visibilitymap_clear(relation,
                            ItemPointerGetBlockNumber(&(heaptup->t_self)),
                            vmbuffer, VISIBILITYMAP_VALID_BITS);
    }
 
    /*
     * XXX Should we set PageSetPrunable on this page ?
     *
     * The inserting transaction may eventually abort thus making this tuple
     * DEAD and hence available for pruning. Though we don't want to optimize
     * for aborts, if no other tuple in this page is UPDATEd/DELETEd, the
     * aborted tuple will never be pruned until next vacuum is triggered.
     *
     * If you do add PageSetPrunable here, add it in heap_xlog_insert too.
     */
 
    MarkBufferDirty(buffer);
 
    /* XLOG stuff */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_insert xlrec;
        xl_heap_header xlhdr;
        XLogRecPtr  recptr;
        Page        page = BufferGetPage(buffer);
        uint8       info = XLOG_HEAP_INSERT;
        int         bufflags = 0;
 
        /*
         * If this is a catalog, we need to transmit combo CIDs to properly
         * decode, so log that as well.
         */
        if (RelationIsAccessibleInLogicalDecoding(relation))
            log_heap_new_cid(relation, heaptup);
 
        /*
         * If this is the single and first tuple on page, we can reinit the
         * page instead of restoring the whole thing.  Set flag, and hide
         * buffer references from XLogInsert.
         */
        if (ItemPointerGetOffsetNumber(&(heaptup->t_self)) == FirstOffsetNumber &&
            PageGetMaxOffsetNumber(page) == FirstOffsetNumber)
        {
            info |= XLOG_HEAP_INIT_PAGE;
            bufflags |= REGBUF_WILL_INIT;
        }
 
        xlrec.offnum = ItemPointerGetOffsetNumber(&heaptup->t_self);
        xlrec.flags = 0;
        if (all_visible_cleared)
            xlrec.flags |= XLH_INSERT_ALL_VISIBLE_CLEARED;
        if (options & HEAP_INSERT_SPECULATIVE)
            xlrec.flags |= XLH_INSERT_IS_SPECULATIVE;
        Assert(ItemPointerGetBlockNumber(&heaptup->t_self) == BufferGetBlockNumber(buffer));
 
        /*
         * For logical decoding, we need the tuple even if we're doing a full
         * page write, so make sure it's included even if we take a full-page
         * image. (XXX We could alternatively store a pointer into the FPW).
         */
        if (RelationIsLogicallyLogged(relation) &&
            !(options & HEAP_INSERT_NO_LOGICAL))
        {
            xlrec.flags |= XLH_INSERT_CONTAINS_NEW_TUPLE;
            bufflags |= REGBUF_KEEP_DATA;
 
            if (IsToastRelation(relation))
                xlrec.flags |= XLH_INSERT_ON_TOAST_RELATION;
        }
 
        XLogBeginInsert();
        XLogRegisterData(&xlrec, SizeOfHeapInsert);
 
        xlhdr.t_infomask2 = heaptup->t_data->t_infomask2;
        xlhdr.t_infomask = heaptup->t_data->t_infomask;
        xlhdr.t_hoff = heaptup->t_data->t_hoff;
 
        /*
         * note we mark xlhdr as belonging to buffer; if XLogInsert decides to
         * write the whole page to the xlog, we don't need to store
         * xl_heap_header in the xlog.
         */
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD | bufflags);
        XLogRegisterBufData(0, &xlhdr, SizeOfHeapHeader);
        /* PG73FORMAT: write bitmap [+ padding] [+ oid] + data */
        XLogRegisterBufData(0,
                            (char *) heaptup->t_data + SizeofHeapTupleHeader,
                            heaptup->t_len - SizeofHeapTupleHeader);
 
        /* filtering by origin on a row level is much more efficient */
        XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
 
        recptr = XLogInsert(RM_HEAP_ID, info);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    UnlockReleaseBuffer(buffer);
    if (vmbuffer != InvalidBuffer)
        ReleaseBuffer(vmbuffer);
 
    /*
     * If tuple is cachable, mark it for invalidation from the caches in case
     * we abort.  Note it is OK to do this after releasing the buffer, because
     * the heaptup data structure is all in local memory, not in the shared
     * buffer.
     */
    CacheInvalidateHeapTuple(relation, heaptup, NULL);
 
    /* Note: speculative insertions are counted too, even if aborted later */
    pgstat_count_heap_insert(relation, 1);
 
    /*
     * If heaptup is a private copy, release it.  Don't forget to copy t_self
     * back to the caller's image, too.
     */
    if (heaptup != tup)
    {
        tup->t_self = heaptup->t_self;
        heap_freetuple(heaptup);
    }
}

References Assert(), AssertHasSnapshotForToast(), BufferGetBlockNumber(), BufferGetPage(), CacheInvalidateHeapTuple(), CheckForSerializableConflictIn(), END_CRIT_SECTION, FirstOffsetNumber, xl_heap_insert::flags, GetCurrentTransactionId(), heap_freetuple(), HEAP_INSERT_NO_LOGICAL, HEAP_INSERT_SPECULATIVE, heap_prepare_insert(), HeapTupleHeaderGetNatts, InvalidBlockNumber, InvalidBuffer, IsToastRelation(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), log_heap_new_cid(), MarkBufferDirty(), xl_heap_insert::offnum, PageClearAllVisible(), PageGetMaxOffsetNumber(), PageIsAllVisible(), PageSetLSN(), pgstat_count_heap_insert(), REGBUF_KEEP_DATA, REGBUF_STANDARD, REGBUF_WILL_INIT, RelationGetBufferForTuple(), RelationGetNumberOfAttributes, RelationIsAccessibleInLogicalDecoding, RelationIsLogicallyLogged, RelationNeedsWAL, RelationPutHeapTuple(), ReleaseBuffer(), SizeOfHeapHeader, SizeOfHeapInsert, SizeofHeapTupleHeader, START_CRIT_SECTION, HeapTupleData::t_data, xl_heap_header::t_hoff, HeapTupleHeaderData::t_hoff, xl_heap_header::t_infomask, HeapTupleHeaderData::t_infomask, xl_heap_header::t_infomask2, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, UnlockReleaseBuffer(), visibilitymap_clear(), VISIBILITYMAP_VALID_BITS, XLH_INSERT_ALL_VISIBLE_CLEARED, XLH_INSERT_CONTAINS_NEW_TUPLE, XLH_INSERT_IS_SPECULATIVE, XLH_INSERT_ON_TOAST_RELATION, XLOG_HEAP_INIT_PAGE, XLOG_HEAP_INSERT, XLOG_INCLUDE_ORIGIN, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), XLogRegisterData(), and XLogSetRecordFlags().

Referenced by heapam_tuple_insert(), heapam_tuple_insert_speculative(), simple_heap_insert(), and toast_save_datum().

heap_lock_tuple()

TM_Result heap_lock_tuple	(	Relation	relation,
		HeapTuple	tuple,
		CommandId	cid,
		LockTupleMode	mode,
		LockWaitPolicy	wait_policy,
		bool	follow_updates,
		Buffer *	buffer,
		TM_FailureData *	tmfd
	)

Definition at line 4579 of file heapam.c.

{
    TM_Result   result;
    ItemPointer tid = &(tuple->t_self);
    ItemId      lp;
    Page        page;
    Buffer      vmbuffer = InvalidBuffer;
    BlockNumber block;
    TransactionId xid,
                xmax;
    uint16      old_infomask,
                new_infomask,
                new_infomask2;
    bool        first_time = true;
    bool        skip_tuple_lock = false;
    bool        have_tuple_lock = false;
    bool        cleared_all_frozen = false;
 
    *buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
    block = ItemPointerGetBlockNumber(tid);
 
    /*
     * Before locking the buffer, pin the visibility map page if it appears to
     * be necessary.  Since we haven't got the lock yet, someone else might be
     * in the middle of changing this, so we'll need to recheck after we have
     * the lock.
     */
    if (PageIsAllVisible(BufferGetPage(*buffer)))
        visibilitymap_pin(relation, block, &vmbuffer);
 
    LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
    page = BufferGetPage(*buffer);
    lp = PageGetItemId(page, ItemPointerGetOffsetNumber(tid));
    Assert(ItemIdIsNormal(lp));
 
    tuple->t_data = (HeapTupleHeader) PageGetItem(page, lp);
    tuple->t_len = ItemIdGetLength(lp);
    tuple->t_tableOid = RelationGetRelid(relation);
 
l3:
    result = HeapTupleSatisfiesUpdate(tuple, cid, *buffer);
 
    if (result == TM_Invisible)
    {
        /*
         * This is possible, but only when locking a tuple for ON CONFLICT
         * UPDATE.  We return this value here rather than throwing an error in
         * order to give that case the opportunity to throw a more specific
         * error.
         */
        result = TM_Invisible;
        goto out_locked;
    }
    else if (result == TM_BeingModified ||
             result == TM_Updated ||
             result == TM_Deleted)
    {
        TransactionId xwait;
        uint16      infomask;
        uint16      infomask2;
        bool        require_sleep;
        ItemPointerData t_ctid;
 
        /* must copy state data before unlocking buffer */
        xwait = HeapTupleHeaderGetRawXmax(tuple->t_data);
        infomask = tuple->t_data->t_infomask;
        infomask2 = tuple->t_data->t_infomask2;
        ItemPointerCopy(&tuple->t_data->t_ctid, &t_ctid);
 
        LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
 
        /*
         * If any subtransaction of the current top transaction already holds
         * a lock as strong as or stronger than what we're requesting, we
         * effectively hold the desired lock already.  We *must* succeed
         * without trying to take the tuple lock, else we will deadlock
         * against anyone wanting to acquire a stronger lock.
         *
         * Note we only do this the first time we loop on the HTSU result;
         * there is no point in testing in subsequent passes, because
         * evidently our own transaction cannot have acquired a new lock after
         * the first time we checked.
         */
        if (first_time)
        {
            first_time = false;
 
            if (infomask & HEAP_XMAX_IS_MULTI)
            {
                int         i;
                int         nmembers;
                MultiXactMember *members;
 
                /*
                 * We don't need to allow old multixacts here; if that had
                 * been the case, HeapTupleSatisfiesUpdate would have returned
                 * MayBeUpdated and we wouldn't be here.
                 */
                nmembers =
                    GetMultiXactIdMembers(xwait, &members, false,
                                          HEAP_XMAX_IS_LOCKED_ONLY(infomask));
 
                for (i = 0; i < nmembers; i++)
                {
                    /* only consider members of our own transaction */
                    if (!TransactionIdIsCurrentTransactionId(members[i].xid))
                        continue;
 
                    if (TUPLOCK_from_mxstatus(members[i].status) >= mode)
                    {
                        pfree(members);
                        result = TM_Ok;
                        goto out_unlocked;
                    }
                    else
                    {
                        /*
                         * Disable acquisition of the heavyweight tuple lock.
                         * Otherwise, when promoting a weaker lock, we might
                         * deadlock with another locker that has acquired the
                         * heavyweight tuple lock and is waiting for our
                         * transaction to finish.
                         *
                         * Note that in this case we still need to wait for
                         * the multixact if required, to avoid acquiring
                         * conflicting locks.
                         */
                        skip_tuple_lock = true;
                    }
                }
 
                if (members)
                    pfree(members);
            }
            else if (TransactionIdIsCurrentTransactionId(xwait))
            {
                switch (mode)
                {
                    case LockTupleKeyShare:
                        Assert(HEAP_XMAX_IS_KEYSHR_LOCKED(infomask) ||
                               HEAP_XMAX_IS_SHR_LOCKED(infomask) ||
                               HEAP_XMAX_IS_EXCL_LOCKED(infomask));
                        result = TM_Ok;
                        goto out_unlocked;
                    case LockTupleShare:
                        if (HEAP_XMAX_IS_SHR_LOCKED(infomask) ||
                            HEAP_XMAX_IS_EXCL_LOCKED(infomask))
                        {
                            result = TM_Ok;
                            goto out_unlocked;
                        }
                        break;
                    case LockTupleNoKeyExclusive:
                        if (HEAP_XMAX_IS_EXCL_LOCKED(infomask))
                        {
                            result = TM_Ok;
                            goto out_unlocked;
                        }
                        break;
                    case LockTupleExclusive:
                        if (HEAP_XMAX_IS_EXCL_LOCKED(infomask) &&
                            infomask2 & HEAP_KEYS_UPDATED)
                        {
                            result = TM_Ok;
                            goto out_unlocked;
                        }
                        break;
                }
            }
        }
 
        /*
         * Initially assume that we will have to wait for the locking
         * transaction(s) to finish.  We check various cases below in which
         * this can be turned off.
         */
        require_sleep = true;
        if (mode == LockTupleKeyShare)
        {
            /*
             * If we're requesting KeyShare, and there's no update present, we
             * don't need to wait.  Even if there is an update, we can still
             * continue if the key hasn't been modified.
             *
             * However, if there are updates, we need to walk the update chain
             * to mark future versions of the row as locked, too.  That way,
             * if somebody deletes that future version, we're protected
             * against the key going away.  This locking of future versions
             * could block momentarily, if a concurrent transaction is
             * deleting a key; or it could return a value to the effect that
             * the transaction deleting the key has already committed.  So we
             * do this before re-locking the buffer; otherwise this would be
             * prone to deadlocks.
             *
             * Note that the TID we're locking was grabbed before we unlocked
             * the buffer.  For it to change while we're not looking, the
             * other properties we're testing for below after re-locking the
             * buffer would also change, in which case we would restart this
             * loop above.
             */
            if (!(infomask2 & HEAP_KEYS_UPDATED))
            {
                bool        updated;
 
                updated = !HEAP_XMAX_IS_LOCKED_ONLY(infomask);
 
                /*
                 * If there are updates, follow the update chain; bail out if
                 * that cannot be done.
                 */
                if (follow_updates && updated)
                {
                    TM_Result   res;
 
                    res = heap_lock_updated_tuple(relation, tuple, &t_ctid,
                                                  GetCurrentTransactionId(),
                                                  mode);
                    if (res != TM_Ok)
                    {
                        result = res;
                        /* recovery code expects to have buffer lock held */
                        LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                        goto failed;
                    }
                }
 
                LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
                /*
                 * Make sure it's still an appropriate lock, else start over.
                 * Also, if it wasn't updated before we released the lock, but
                 * is updated now, we start over too; the reason is that we
                 * now need to follow the update chain to lock the new
                 * versions.
                 */
                if (!HeapTupleHeaderIsOnlyLocked(tuple->t_data) &&
                    ((tuple->t_data->t_infomask2 & HEAP_KEYS_UPDATED) ||
                     !updated))
                    goto l3;
 
                /* Things look okay, so we can skip sleeping */
                require_sleep = false;
 
                /*
                 * Note we allow Xmax to change here; other updaters/lockers
                 * could have modified it before we grabbed the buffer lock.
                 * However, this is not a problem, because with the recheck we
                 * just did we ensure that they still don't conflict with the
                 * lock we want.
                 */
            }
        }
        else if (mode == LockTupleShare)
        {
            /*
             * If we're requesting Share, we can similarly avoid sleeping if
             * there's no update and no exclusive lock present.
             */
            if (HEAP_XMAX_IS_LOCKED_ONLY(infomask) &&
                !HEAP_XMAX_IS_EXCL_LOCKED(infomask))
            {
                LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
                /*
                 * Make sure it's still an appropriate lock, else start over.
                 * See above about allowing xmax to change.
                 */
                if (!HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_data->t_infomask) ||
                    HEAP_XMAX_IS_EXCL_LOCKED(tuple->t_data->t_infomask))
                    goto l3;
                require_sleep = false;
            }
        }
        else if (mode == LockTupleNoKeyExclusive)
        {
            /*
             * If we're requesting NoKeyExclusive, we might also be able to
             * avoid sleeping; just ensure that there no conflicting lock
             * already acquired.
             */
            if (infomask & HEAP_XMAX_IS_MULTI)
            {
                if (!DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
                                             mode, NULL))
                {
                    /*
                     * No conflict, but if the xmax changed under us in the
                     * meantime, start over.
                     */
                    LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                    if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) ||
                        !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data),
                                             xwait))
                        goto l3;
 
                    /* otherwise, we're good */
                    require_sleep = false;
                }
            }
            else if (HEAP_XMAX_IS_KEYSHR_LOCKED(infomask))
            {
                LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
                /* if the xmax changed in the meantime, start over */
                if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) ||
                    !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data),
                                         xwait))
                    goto l3;
                /* otherwise, we're good */
                require_sleep = false;
            }
        }
 
        /*
         * As a check independent from those above, we can also avoid sleeping
         * if the current transaction is the sole locker of the tuple.  Note
         * that the strength of the lock already held is irrelevant; this is
         * not about recording the lock in Xmax (which will be done regardless
         * of this optimization, below).  Also, note that the cases where we
         * hold a lock stronger than we are requesting are already handled
         * above by not doing anything.
         *
         * Note we only deal with the non-multixact case here; MultiXactIdWait
         * is well equipped to deal with this situation on its own.
         */
        if (require_sleep && !(infomask & HEAP_XMAX_IS_MULTI) &&
            TransactionIdIsCurrentTransactionId(xwait))
        {
            /* ... but if the xmax changed in the meantime, start over */
            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
            if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) ||
                !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data),
                                     xwait))
                goto l3;
            Assert(HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_data->t_infomask));
            require_sleep = false;
        }
 
        /*
         * Time to sleep on the other transaction/multixact, if necessary.
         *
         * If the other transaction is an update/delete that's already
         * committed, then sleeping cannot possibly do any good: if we're
         * required to sleep, get out to raise an error instead.
         *
         * By here, we either have already acquired the buffer exclusive lock,
         * or we must wait for the locking transaction or multixact; so below
         * we ensure that we grab buffer lock after the sleep.
         */
        if (require_sleep && (result == TM_Updated || result == TM_Deleted))
        {
            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
            goto failed;
        }
        else if (require_sleep)
        {
            /*
             * Acquire tuple lock to establish our priority for the tuple, or
             * die trying.  LockTuple will release us when we are next-in-line
             * for the tuple.  We must do this even if we are share-locking,
             * but not if we already have a weaker lock on the tuple.
             *
             * If we are forced to "start over" below, we keep the tuple lock;
             * this arranges that we stay at the head of the line while
             * rechecking tuple state.
             */
            if (!skip_tuple_lock &&
                !heap_acquire_tuplock(relation, tid, mode, wait_policy,
                                      &have_tuple_lock))
            {
                /*
                 * This can only happen if wait_policy is Skip and the lock
                 * couldn't be obtained.
                 */
                result = TM_WouldBlock;
                /* recovery code expects to have buffer lock held */
                LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                goto failed;
            }
 
            if (infomask & HEAP_XMAX_IS_MULTI)
            {
                MultiXactStatus status = get_mxact_status_for_lock(mode, false);
 
                /* We only ever lock tuples, never update them */
                if (status >= MultiXactStatusNoKeyUpdate)
                    elog(ERROR, "invalid lock mode in heap_lock_tuple");
 
                /* wait for multixact to end, or die trying  */
                switch (wait_policy)
                {
                    case LockWaitBlock:
                        MultiXactIdWait((MultiXactId) xwait, status, infomask,
                                        relation, &tuple->t_self, XLTW_Lock, NULL);
                        break;
                    case LockWaitSkip:
                        if (!ConditionalMultiXactIdWait((MultiXactId) xwait,
                                                        status, infomask, relation,
                                                        NULL, false))
                        {
                            result = TM_WouldBlock;
                            /* recovery code expects to have buffer lock held */
                            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                            goto failed;
                        }
                        break;
                    case LockWaitError:
                        if (!ConditionalMultiXactIdWait((MultiXactId) xwait,
                                                        status, infomask, relation,
                                                        NULL, log_lock_failures))
                            ereport(ERROR,
                                    (errcode(ERRCODE_LOCK_NOT_AVAILABLE),
                                     errmsg("could not obtain lock on row in relation \"%s\"",
                                            RelationGetRelationName(relation))));
 
                        break;
                }
 
                /*
                 * Of course, the multixact might not be done here: if we're
                 * requesting a light lock mode, other transactions with light
                 * locks could still be alive, as well as locks owned by our
                 * own xact or other subxacts of this backend.  We need to
                 * preserve the surviving MultiXact members.  Note that it
                 * isn't absolutely necessary in the latter case, but doing so
                 * is simpler.
                 */
            }
            else
            {
                /* wait for regular transaction to end, or die trying */
                switch (wait_policy)
                {
                    case LockWaitBlock:
                        XactLockTableWait(xwait, relation, &tuple->t_self,
                                          XLTW_Lock);
                        break;
                    case LockWaitSkip:
                        if (!ConditionalXactLockTableWait(xwait, false))
                        {
                            result = TM_WouldBlock;
                            /* recovery code expects to have buffer lock held */
                            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                            goto failed;
                        }
                        break;
                    case LockWaitError:
                        if (!ConditionalXactLockTableWait(xwait, log_lock_failures))
                            ereport(ERROR,
                                    (errcode(ERRCODE_LOCK_NOT_AVAILABLE),
                                     errmsg("could not obtain lock on row in relation \"%s\"",
                                            RelationGetRelationName(relation))));
                        break;
                }
            }
 
            /* if there are updates, follow the update chain */
            if (follow_updates && !HEAP_XMAX_IS_LOCKED_ONLY(infomask))
            {
                TM_Result   res;
 
                res = heap_lock_updated_tuple(relation, tuple, &t_ctid,
                                              GetCurrentTransactionId(),
                                              mode);
                if (res != TM_Ok)
                {
                    result = res;
                    /* recovery code expects to have buffer lock held */
                    LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                    goto failed;
                }
            }
 
            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
            /*
             * xwait is done, but if xwait had just locked the tuple then some
             * other xact could update this tuple before we get to this point.
             * Check for xmax change, and start over if so.
             */
            if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) ||
                !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data),
                                     xwait))
                goto l3;
 
            if (!(infomask & HEAP_XMAX_IS_MULTI))
            {
                /*
                 * Otherwise check if it committed or aborted.  Note we cannot
                 * be here if the tuple was only locked by somebody who didn't
                 * conflict with us; that would have been handled above.  So
                 * that transaction must necessarily be gone by now.  But
                 * don't check for this in the multixact case, because some
                 * locker transactions might still be running.
                 */
                UpdateXmaxHintBits(tuple->t_data, *buffer, xwait);
            }
        }
 
        /* By here, we're certain that we hold buffer exclusive lock again */
 
        /*
         * We may lock if previous xmax aborted, or if it committed but only
         * locked the tuple without updating it; or if we didn't have to wait
         * at all for whatever reason.
         */
        if (!require_sleep ||
            (tuple->t_data->t_infomask & HEAP_XMAX_INVALID) ||
            HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_data->t_infomask) ||
            HeapTupleHeaderIsOnlyLocked(tuple->t_data))
            result = TM_Ok;
        else if (!ItemPointerEquals(&tuple->t_self, &tuple->t_data->t_ctid))
            result = TM_Updated;
        else
            result = TM_Deleted;
    }
 
failed:
    if (result != TM_Ok)
    {
        Assert(result == TM_SelfModified || result == TM_Updated ||
               result == TM_Deleted || result == TM_WouldBlock);
 
        /*
         * When locking a tuple under LockWaitSkip semantics and we fail with
         * TM_WouldBlock above, it's possible for concurrent transactions to
         * release the lock and set HEAP_XMAX_INVALID in the meantime.  So
         * this assert is slightly different from the equivalent one in
         * heap_delete and heap_update.
         */
        Assert((result == TM_WouldBlock) ||
               !(tuple->t_data->t_infomask & HEAP_XMAX_INVALID));
        Assert(result != TM_Updated ||
               !ItemPointerEquals(&tuple->t_self, &tuple->t_data->t_ctid));
        tmfd->ctid = tuple->t_data->t_ctid;
        tmfd->xmax = HeapTupleHeaderGetUpdateXid(tuple->t_data);
        if (result == TM_SelfModified)
            tmfd->cmax = HeapTupleHeaderGetCmax(tuple->t_data);
        else
            tmfd->cmax = InvalidCommandId;
        goto out_locked;
    }
 
    /*
     * If we didn't pin the visibility map page and the page has become all
     * visible while we were busy locking the buffer, or during some
     * subsequent window during which we had it unlocked, we'll have to unlock
     * and re-lock, to avoid holding the buffer lock across I/O.  That's a bit
     * unfortunate, especially since we'll now have to recheck whether the
     * tuple has been locked or updated under us, but hopefully it won't
     * happen very often.
     */
    if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
    {
        LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
        visibilitymap_pin(relation, block, &vmbuffer);
        LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
        goto l3;
    }
 
    xmax = HeapTupleHeaderGetRawXmax(tuple->t_data);
    old_infomask = tuple->t_data->t_infomask;
 
    /*
     * If this is the first possibly-multixact-able operation in the current
     * transaction, set my per-backend OldestMemberMXactId setting. We can be
     * certain that the transaction will never become a member of any older
     * MultiXactIds than that.  (We have to do this even if we end up just
     * using our own TransactionId below, since some other backend could
     * incorporate our XID into a MultiXact immediately afterwards.)
     */
    MultiXactIdSetOldestMember();
 
    /*
     * Compute the new xmax and infomask to store into the tuple.  Note we do
     * not modify the tuple just yet, because that would leave it in the wrong
     * state if multixact.c elogs.
     */
    compute_new_xmax_infomask(xmax, old_infomask, tuple->t_data->t_infomask2,
                              GetCurrentTransactionId(), mode, false,
                              &xid, &new_infomask, &new_infomask2);
 
    START_CRIT_SECTION();
 
    /*
     * Store transaction information of xact locking the tuple.
     *
     * Note: Cmax is meaningless in this context, so don't set it; this avoids
     * possibly generating a useless combo CID.  Moreover, if we're locking a
     * previously updated tuple, it's important to preserve the Cmax.
     *
     * Also reset the HOT UPDATE bit, but only if there's no update; otherwise
     * we would break the HOT chain.
     */
    tuple->t_data->t_infomask &= ~HEAP_XMAX_BITS;
    tuple->t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    tuple->t_data->t_infomask |= new_infomask;
    tuple->t_data->t_infomask2 |= new_infomask2;
    if (HEAP_XMAX_IS_LOCKED_ONLY(new_infomask))
        HeapTupleHeaderClearHotUpdated(tuple->t_data);
    HeapTupleHeaderSetXmax(tuple->t_data, xid);
 
    /*
     * Make sure there is no forward chain link in t_ctid.  Note that in the
     * cases where the tuple has been updated, we must not overwrite t_ctid,
     * because it was set by the updater.  Moreover, if the tuple has been
     * updated, we need to follow the update chain to lock the new versions of
     * the tuple as well.
     */
    if (HEAP_XMAX_IS_LOCKED_ONLY(new_infomask))
        tuple->t_data->t_ctid = *tid;
 
    /* Clear only the all-frozen bit on visibility map if needed */
    if (PageIsAllVisible(page) &&
        visibilitymap_clear(relation, block, vmbuffer,
                            VISIBILITYMAP_ALL_FROZEN))
        cleared_all_frozen = true;
 
 
    MarkBufferDirty(*buffer);
 
    /*
     * XLOG stuff.  You might think that we don't need an XLOG record because
     * there is no state change worth restoring after a crash.  You would be
     * wrong however: we have just written either a TransactionId or a
     * MultiXactId that may never have been seen on disk before, and we need
     * to make sure that there are XLOG entries covering those ID numbers.
     * Else the same IDs might be re-used after a crash, which would be
     * disastrous if this page made it to disk before the crash.  Essentially
     * we have to enforce the WAL log-before-data rule even in this case.
     * (Also, in a PITR log-shipping or 2PC environment, we have to have XLOG
     * entries for everything anyway.)
     */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_lock xlrec;
        XLogRecPtr  recptr;
 
        XLogBeginInsert();
        XLogRegisterBuffer(0, *buffer, REGBUF_STANDARD);
 
        xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self);
        xlrec.xmax = xid;
        xlrec.infobits_set = compute_infobits(new_infomask,
                                              tuple->t_data->t_infomask2);
        xlrec.flags = cleared_all_frozen ? XLH_LOCK_ALL_FROZEN_CLEARED : 0;
        XLogRegisterData(&xlrec, SizeOfHeapLock);
 
        /* we don't decode row locks atm, so no need to log the origin */
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    result = TM_Ok;
 
out_locked:
    LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
 
out_unlocked:
    if (BufferIsValid(vmbuffer))
        ReleaseBuffer(vmbuffer);
 
    /*
     * Don't update the visibility map here. Locking a tuple doesn't change
     * visibility info.
     */
 
    /*
     * Now that we have successfully marked the tuple as locked, we can
     * release the lmgr tuple lock, if we had it.
     */
    if (have_tuple_lock)
        UnlockTupleTuplock(relation, tid, mode);
 
    return result;
}

References Assert(), BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetPage(), BufferIsValid(), TM_FailureData::cmax, compute_infobits(), compute_new_xmax_infomask(), ConditionalMultiXactIdWait(), ConditionalXactLockTableWait(), TM_FailureData::ctid, DoesMultiXactIdConflict(), elog, END_CRIT_SECTION, ereport, errcode(), errmsg(), ERROR, xl_heap_lock::flags, get_mxact_status_for_lock(), GetCurrentTransactionId(), GetMultiXactIdMembers(), heap_acquire_tuplock(), HEAP_KEYS_UPDATED, heap_lock_updated_tuple(), HEAP_XMAX_INVALID, HEAP_XMAX_IS_EXCL_LOCKED(), HEAP_XMAX_IS_KEYSHR_LOCKED(), HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HEAP_XMAX_IS_SHR_LOCKED(), HeapTupleHeaderClearHotUpdated(), HeapTupleHeaderGetCmax(), HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderIsOnlyLocked(), HeapTupleHeaderSetXmax(), HeapTupleSatisfiesUpdate(), i, xl_heap_lock::infobits_set, InvalidBuffer, InvalidCommandId, ItemIdGetLength, ItemIdIsNormal, ItemPointerCopy(), ItemPointerEquals(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), LockBuffer(), LockTupleExclusive, LockTupleKeyShare, LockTupleNoKeyExclusive, LockTupleShare, LockWaitBlock, LockWaitError, LockWaitSkip, log_lock_failures, MarkBufferDirty(), mode, MultiXactIdSetOldestMember(), MultiXactIdWait(), MultiXactStatusNoKeyUpdate, xl_heap_lock::offnum, PageGetItem(), PageGetItemId(), PageIsAllVisible(), PageSetLSN(), pfree(), ReadBuffer(), REGBUF_STANDARD, RelationGetRelationName, RelationGetRelid, RelationNeedsWAL, ReleaseBuffer(), SizeOfHeapLock, START_CRIT_SECTION, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TM_BeingModified, TM_Deleted, TM_Invisible, TM_Ok, TM_SelfModified, TM_Updated, TM_WouldBlock, TransactionIdEquals, TransactionIdIsCurrentTransactionId(), TUPLOCK_from_mxstatus, UnlockTupleTuplock, UpdateXmaxHintBits(), VISIBILITYMAP_ALL_FROZEN, visibilitymap_clear(), visibilitymap_pin(), XactLockTableWait(), XLH_LOCK_ALL_FROZEN_CLEARED, XLOG_HEAP_LOCK, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), XLTW_Lock, xl_heap_lock::xmax, TM_FailureData::xmax, and xmax_infomask_changed().

Referenced by heapam_tuple_lock().

heap_lock_updated_tuple()

static TM_Result heap_lock_updated_tuple ( Relation  rel, HeapTuple  tuple, ItemPointer  ctid, TransactionId  xid, LockTupleMode  mode  )

static

Definition at line 6043 of file heapam.c.

{
    /*
     * If the tuple has not been updated, or has moved into another partition
     * (effectively a delete) stop here.
     */
    if (!HeapTupleHeaderIndicatesMovedPartitions(tuple->t_data) &&
        !ItemPointerEquals(&tuple->t_self, ctid))
    {
        /*
         * If this is the first possibly-multixact-able operation in the
         * current transaction, set my per-backend OldestMemberMXactId
         * setting. We can be certain that the transaction will never become a
         * member of any older MultiXactIds than that.  (We have to do this
         * even if we end up just using our own TransactionId below, since
         * some other backend could incorporate our XID into a MultiXact
         * immediately afterwards.)
         */
        MultiXactIdSetOldestMember();
 
        return heap_lock_updated_tuple_rec(rel, ctid, xid, mode);
    }
 
    /* nothing to lock */
    return TM_Ok;
}

References heap_lock_updated_tuple_rec(), HeapTupleHeaderIndicatesMovedPartitions(), ItemPointerEquals(), mode, MultiXactIdSetOldestMember(), HeapTupleData::t_data, HeapTupleData::t_self, and TM_Ok.

Referenced by heap_lock_tuple().

heap_lock_updated_tuple_rec()

static TM_Result heap_lock_updated_tuple_rec ( Relation  rel, ItemPointer  tid, TransactionId  xid, LockTupleMode  mode  )

static

Definition at line 5698 of file heapam.c.

{
    TM_Result   result;
    ItemPointerData tupid;
    HeapTupleData mytup;
    Buffer      buf;
    uint16      new_infomask,
                new_infomask2,
                old_infomask,
                old_infomask2;
    TransactionId xmax,
                new_xmax;
    TransactionId priorXmax = InvalidTransactionId;
    bool        cleared_all_frozen = false;
    bool        pinned_desired_page;
    Buffer      vmbuffer = InvalidBuffer;
    BlockNumber block;
 
    ItemPointerCopy(tid, &tupid);
 
    for (;;)
    {
        new_infomask = 0;
        new_xmax = InvalidTransactionId;
        block = ItemPointerGetBlockNumber(&tupid);
        ItemPointerCopy(&tupid, &(mytup.t_self));
 
        if (!heap_fetch(rel, SnapshotAny, &mytup, &buf, false))
        {
            /*
             * if we fail to find the updated version of the tuple, it's
             * because it was vacuumed/pruned away after its creator
             * transaction aborted.  So behave as if we got to the end of the
             * chain, and there's no further tuple to lock: return success to
             * caller.
             */
            result = TM_Ok;
            goto out_unlocked;
        }
 
l4:
        CHECK_FOR_INTERRUPTS();
 
        /*
         * Before locking the buffer, pin the visibility map page if it
         * appears to be necessary.  Since we haven't got the lock yet,
         * someone else might be in the middle of changing this, so we'll need
         * to recheck after we have the lock.
         */
        if (PageIsAllVisible(BufferGetPage(buf)))
        {
            visibilitymap_pin(rel, block, &vmbuffer);
            pinned_desired_page = true;
        }
        else
            pinned_desired_page = false;
 
        LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
        /*
         * If we didn't pin the visibility map page and the page has become
         * all visible while we were busy locking the buffer, we'll have to
         * unlock and re-lock, to avoid holding the buffer lock across I/O.
         * That's a bit unfortunate, but hopefully shouldn't happen often.
         *
         * Note: in some paths through this function, we will reach here
         * holding a pin on a vm page that may or may not be the one matching
         * this page.  If this page isn't all-visible, we won't use the vm
         * page, but we hold onto such a pin till the end of the function.
         */
        if (!pinned_desired_page && PageIsAllVisible(BufferGetPage(buf)))
        {
            LockBuffer(buf, BUFFER_LOCK_UNLOCK);
            visibilitymap_pin(rel, block, &vmbuffer);
            LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
        }
 
        /*
         * Check the tuple XMIN against prior XMAX, if any.  If we reached the
         * end of the chain, we're done, so return success.
         */
        if (TransactionIdIsValid(priorXmax) &&
            !TransactionIdEquals(HeapTupleHeaderGetXmin(mytup.t_data),
                                 priorXmax))
        {
            result = TM_Ok;
            goto out_locked;
        }
 
        /*
         * Also check Xmin: if this tuple was created by an aborted
         * (sub)transaction, then we already locked the last live one in the
         * chain, thus we're done, so return success.
         */
        if (TransactionIdDidAbort(HeapTupleHeaderGetXmin(mytup.t_data)))
        {
            result = TM_Ok;
            goto out_locked;
        }
 
        old_infomask = mytup.t_data->t_infomask;
        old_infomask2 = mytup.t_data->t_infomask2;
        xmax = HeapTupleHeaderGetRawXmax(mytup.t_data);
 
        /*
         * If this tuple version has been updated or locked by some concurrent
         * transaction(s), what we do depends on whether our lock mode
         * conflicts with what those other transactions hold, and also on the
         * status of them.
         */
        if (!(old_infomask & HEAP_XMAX_INVALID))
        {
            TransactionId rawxmax;
            bool        needwait;
 
            rawxmax = HeapTupleHeaderGetRawXmax(mytup.t_data);
            if (old_infomask & HEAP_XMAX_IS_MULTI)
            {
                int         nmembers;
                int         i;
                MultiXactMember *members;
 
                /*
                 * We don't need a test for pg_upgrade'd tuples: this is only
                 * applied to tuples after the first in an update chain.  Said
                 * first tuple in the chain may well be locked-in-9.2-and-
                 * pg_upgraded, but that one was already locked by our caller,
                 * not us; and any subsequent ones cannot be because our
                 * caller must necessarily have obtained a snapshot later than
                 * the pg_upgrade itself.
                 */
                Assert(!HEAP_LOCKED_UPGRADED(mytup.t_data->t_infomask));
 
                nmembers = GetMultiXactIdMembers(rawxmax, &members, false,
                                                 HEAP_XMAX_IS_LOCKED_ONLY(old_infomask));
                for (i = 0; i < nmembers; i++)
                {
                    result = test_lockmode_for_conflict(members[i].status,
                                                        members[i].xid,
                                                        mode,
                                                        &mytup,
                                                        &needwait);
 
                    /*
                     * If the tuple was already locked by ourselves in a
                     * previous iteration of this (say heap_lock_tuple was
                     * forced to restart the locking loop because of a change
                     * in xmax), then we hold the lock already on this tuple
                     * version and we don't need to do anything; and this is
                     * not an error condition either.  We just need to skip
                     * this tuple and continue locking the next version in the
                     * update chain.
                     */
                    if (result == TM_SelfModified)
                    {
                        pfree(members);
                        goto next;
                    }
 
                    if (needwait)
                    {
                        LockBuffer(buf, BUFFER_LOCK_UNLOCK);
                        XactLockTableWait(members[i].xid, rel,
                                          &mytup.t_self,
                                          XLTW_LockUpdated);
                        pfree(members);
                        goto l4;
                    }
                    if (result != TM_Ok)
                    {
                        pfree(members);
                        goto out_locked;
                    }
                }
                if (members)
                    pfree(members);
            }
            else
            {
                MultiXactStatus status;
 
                /*
                 * For a non-multi Xmax, we first need to compute the
                 * corresponding MultiXactStatus by using the infomask bits.
                 */
                if (HEAP_XMAX_IS_LOCKED_ONLY(old_infomask))
                {
                    if (HEAP_XMAX_IS_KEYSHR_LOCKED(old_infomask))
                        status = MultiXactStatusForKeyShare;
                    else if (HEAP_XMAX_IS_SHR_LOCKED(old_infomask))
                        status = MultiXactStatusForShare;
                    else if (HEAP_XMAX_IS_EXCL_LOCKED(old_infomask))
                    {
                        if (old_infomask2 & HEAP_KEYS_UPDATED)
                            status = MultiXactStatusForUpdate;
                        else
                            status = MultiXactStatusForNoKeyUpdate;
                    }
                    else
                    {
                        /*
                         * LOCK_ONLY present alone (a pg_upgraded tuple marked
                         * as share-locked in the old cluster) shouldn't be
                         * seen in the middle of an update chain.
                         */
                        elog(ERROR, "invalid lock status in tuple");
                    }
                }
                else
                {
                    /* it's an update, but which kind? */
                    if (old_infomask2 & HEAP_KEYS_UPDATED)
                        status = MultiXactStatusUpdate;
                    else
                        status = MultiXactStatusNoKeyUpdate;
                }
 
                result = test_lockmode_for_conflict(status, rawxmax, mode,
                                                    &mytup, &needwait);
 
                /*
                 * If the tuple was already locked by ourselves in a previous
                 * iteration of this (say heap_lock_tuple was forced to
                 * restart the locking loop because of a change in xmax), then
                 * we hold the lock already on this tuple version and we don't
                 * need to do anything; and this is not an error condition
                 * either.  We just need to skip this tuple and continue
                 * locking the next version in the update chain.
                 */
                if (result == TM_SelfModified)
                    goto next;
 
                if (needwait)
                {
                    LockBuffer(buf, BUFFER_LOCK_UNLOCK);
                    XactLockTableWait(rawxmax, rel, &mytup.t_self,
                                      XLTW_LockUpdated);
                    goto l4;
                }
                if (result != TM_Ok)
                {
                    goto out_locked;
                }
            }
        }
 
        /* compute the new Xmax and infomask values for the tuple ... */
        compute_new_xmax_infomask(xmax, old_infomask, mytup.t_data->t_infomask2,
                                  xid, mode, false,
                                  &new_xmax, &new_infomask, &new_infomask2);
 
        if (PageIsAllVisible(BufferGetPage(buf)) &&
            visibilitymap_clear(rel, block, vmbuffer,
                                VISIBILITYMAP_ALL_FROZEN))
            cleared_all_frozen = true;
 
        START_CRIT_SECTION();
 
        /* ... and set them */
        HeapTupleHeaderSetXmax(mytup.t_data, new_xmax);
        mytup.t_data->t_infomask &= ~HEAP_XMAX_BITS;
        mytup.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
        mytup.t_data->t_infomask |= new_infomask;
        mytup.t_data->t_infomask2 |= new_infomask2;
 
        MarkBufferDirty(buf);
 
        /* XLOG stuff */
        if (RelationNeedsWAL(rel))
        {
            xl_heap_lock_updated xlrec;
            XLogRecPtr  recptr;
            Page        page = BufferGetPage(buf);
 
            XLogBeginInsert();
            XLogRegisterBuffer(0, buf, REGBUF_STANDARD);
 
            xlrec.offnum = ItemPointerGetOffsetNumber(&mytup.t_self);
            xlrec.xmax = new_xmax;
            xlrec.infobits_set = compute_infobits(new_infomask, new_infomask2);
            xlrec.flags =
                cleared_all_frozen ? XLH_LOCK_ALL_FROZEN_CLEARED : 0;
 
            XLogRegisterData(&xlrec, SizeOfHeapLockUpdated);
 
            recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_LOCK_UPDATED);
 
            PageSetLSN(page, recptr);
        }
 
        END_CRIT_SECTION();
 
next:
        /* if we find the end of update chain, we're done. */
        if (mytup.t_data->t_infomask & HEAP_XMAX_INVALID ||
            HeapTupleHeaderIndicatesMovedPartitions(mytup.t_data) ||
            ItemPointerEquals(&mytup.t_self, &mytup.t_data->t_ctid) ||
            HeapTupleHeaderIsOnlyLocked(mytup.t_data))
        {
            result = TM_Ok;
            goto out_locked;
        }
 
        /* tail recursion */
        priorXmax = HeapTupleHeaderGetUpdateXid(mytup.t_data);
        ItemPointerCopy(&(mytup.t_data->t_ctid), &tupid);
        UnlockReleaseBuffer(buf);
    }
 
    result = TM_Ok;
 
out_locked:
    UnlockReleaseBuffer(buf);
 
out_unlocked:
    if (vmbuffer != InvalidBuffer)
        ReleaseBuffer(vmbuffer);
 
    return result;
}

References Assert(), buf, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetPage(), CHECK_FOR_INTERRUPTS, compute_infobits(), compute_new_xmax_infomask(), elog, END_CRIT_SECTION, ERROR, xl_heap_lock_updated::flags, GetMultiXactIdMembers(), heap_fetch(), HEAP_KEYS_UPDATED, HEAP_LOCKED_UPGRADED(), HEAP_XMAX_INVALID, HEAP_XMAX_IS_EXCL_LOCKED(), HEAP_XMAX_IS_KEYSHR_LOCKED(), HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HEAP_XMAX_IS_SHR_LOCKED(), HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderIndicatesMovedPartitions(), HeapTupleHeaderIsOnlyLocked(), HeapTupleHeaderSetXmax(), i, xl_heap_lock_updated::infobits_set, InvalidBuffer, InvalidTransactionId, ItemPointerCopy(), ItemPointerEquals(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), LockBuffer(), MarkBufferDirty(), mode, MultiXactStatusForKeyShare, MultiXactStatusForNoKeyUpdate, MultiXactStatusForShare, MultiXactStatusForUpdate, MultiXactStatusNoKeyUpdate, MultiXactStatusUpdate, next, xl_heap_lock_updated::offnum, PageIsAllVisible(), PageSetLSN(), pfree(), REGBUF_STANDARD, RelationNeedsWAL, ReleaseBuffer(), SizeOfHeapLockUpdated, SnapshotAny, START_CRIT_SECTION, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_self, test_lockmode_for_conflict(), TM_Ok, TM_SelfModified, TransactionIdDidAbort(), TransactionIdEquals, TransactionIdIsValid, UnlockReleaseBuffer(), VISIBILITYMAP_ALL_FROZEN, visibilitymap_clear(), visibilitymap_pin(), XactLockTableWait(), XLH_LOCK_ALL_FROZEN_CLEARED, XLOG_HEAP2_LOCK_UPDATED, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), XLTW_LockUpdated, and xl_heap_lock_updated::xmax.

Referenced by heap_lock_updated_tuple().

heap_multi_insert()

void heap_multi_insert	(	Relation	relation,
		TupleTableSlot **	slots,
		int	ntuples,
		CommandId	cid,
		int	options,
		BulkInsertState	bistate
	)

Definition at line 2359 of file heapam.c.

{
    TransactionId xid = GetCurrentTransactionId();
    HeapTuple  *heaptuples;
    int         i;
    int         ndone;
    PGAlignedBlock scratch;
    Page        page;
    Buffer      vmbuffer = InvalidBuffer;
    bool        needwal;
    Size        saveFreeSpace;
    bool        need_tuple_data = RelationIsLogicallyLogged(relation);
    bool        need_cids = RelationIsAccessibleInLogicalDecoding(relation);
    bool        starting_with_empty_page = false;
    int         npages = 0;
    int         npages_used = 0;
 
    /* currently not needed (thus unsupported) for heap_multi_insert() */
    Assert(!(options & HEAP_INSERT_NO_LOGICAL));
 
    AssertHasSnapshotForToast(relation);
 
    needwal = RelationNeedsWAL(relation);
    saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
                                                   HEAP_DEFAULT_FILLFACTOR);
 
    /* Toast and set header data in all the slots */
    heaptuples = palloc(ntuples * sizeof(HeapTuple));
    for (i = 0; i < ntuples; i++)
    {
        HeapTuple   tuple;
 
        tuple = ExecFetchSlotHeapTuple(slots[i], true, NULL);
        slots[i]->tts_tableOid = RelationGetRelid(relation);
        tuple->t_tableOid = slots[i]->tts_tableOid;
        heaptuples[i] = heap_prepare_insert(relation, tuple, xid, cid,
                                            options);
    }
 
    /*
     * We're about to do the actual inserts -- but check for conflict first,
     * to minimize the possibility of having to roll back work we've just
     * done.
     *
     * A check here does not definitively prevent a serialization anomaly;
     * that check MUST be done at least past the point of acquiring an
     * exclusive buffer content lock on every buffer that will be affected,
     * and MAY be done after all inserts are reflected in the buffers and
     * those locks are released; otherwise there is a race condition.  Since
     * multiple buffers can be locked and unlocked in the loop below, and it
     * would not be feasible to identify and lock all of those buffers before
     * the loop, we must do a final check at the end.
     *
     * The check here could be omitted with no loss of correctness; it is
     * present strictly as an optimization.
     *
     * For heap inserts, we only need to check for table-level SSI locks. Our
     * new tuples can't possibly conflict with existing tuple locks, and heap
     * page locks are only consolidated versions of tuple locks; they do not
     * lock "gaps" as index page locks do.  So we don't need to specify a
     * buffer when making the call, which makes for a faster check.
     */
    CheckForSerializableConflictIn(relation, NULL, InvalidBlockNumber);
 
    ndone = 0;
    while (ndone < ntuples)
    {
        Buffer      buffer;
        bool        all_visible_cleared = false;
        bool        all_frozen_set = false;
        int         nthispage;
 
        CHECK_FOR_INTERRUPTS();
 
        /*
         * Compute number of pages needed to fit the to-be-inserted tuples in
         * the worst case.  This will be used to determine how much to extend
         * the relation by in RelationGetBufferForTuple(), if needed.  If we
         * filled a prior page from scratch, we can just update our last
         * computation, but if we started with a partially filled page,
         * recompute from scratch, the number of potentially required pages
         * can vary due to tuples needing to fit onto the page, page headers
         * etc.
         */
        if (ndone == 0 || !starting_with_empty_page)
        {
            npages = heap_multi_insert_pages(heaptuples, ndone, ntuples,
                                             saveFreeSpace);
            npages_used = 0;
        }
        else
            npages_used++;
 
        /*
         * Find buffer where at least the next tuple will fit.  If the page is
         * all-visible, this will also pin the requisite visibility map page.
         *
         * Also pin visibility map page if COPY FREEZE inserts tuples into an
         * empty page. See all_frozen_set below.
         */
        buffer = RelationGetBufferForTuple(relation, heaptuples[ndone]->t_len,
                                           InvalidBuffer, options, bistate,
                                           &vmbuffer, NULL,
                                           npages - npages_used);
        page = BufferGetPage(buffer);
 
        starting_with_empty_page = PageGetMaxOffsetNumber(page) == 0;
 
        if (starting_with_empty_page && (options & HEAP_INSERT_FROZEN))
            all_frozen_set = true;
 
        /* NO EREPORT(ERROR) from here till changes are logged */
        START_CRIT_SECTION();
 
        /*
         * RelationGetBufferForTuple has ensured that the first tuple fits.
         * Put that on the page, and then as many other tuples as fit.
         */
        RelationPutHeapTuple(relation, buffer, heaptuples[ndone], false);
 
        /*
         * For logical decoding we need combo CIDs to properly decode the
         * catalog.
         */
        if (needwal && need_cids)
            log_heap_new_cid(relation, heaptuples[ndone]);
 
        for (nthispage = 1; ndone + nthispage < ntuples; nthispage++)
        {
            HeapTuple   heaptup = heaptuples[ndone + nthispage];
 
            if (PageGetHeapFreeSpace(page) < MAXALIGN(heaptup->t_len) + saveFreeSpace)
                break;
 
            RelationPutHeapTuple(relation, buffer, heaptup, false);
 
            /*
             * For logical decoding we need combo CIDs to properly decode the
             * catalog.
             */
            if (needwal && need_cids)
                log_heap_new_cid(relation, heaptup);
        }
 
        /*
         * If the page is all visible, need to clear that, unless we're only
         * going to add further frozen rows to it.
         *
         * If we're only adding already frozen rows to a previously empty
         * page, mark it as all-visible.
         */
        if (PageIsAllVisible(page) && !(options & HEAP_INSERT_FROZEN))
        {
            all_visible_cleared = true;
            PageClearAllVisible(page);
            visibilitymap_clear(relation,
                                BufferGetBlockNumber(buffer),
                                vmbuffer, VISIBILITYMAP_VALID_BITS);
        }
        else if (all_frozen_set)
            PageSetAllVisible(page);
 
        /*
         * XXX Should we set PageSetPrunable on this page ? See heap_insert()
         */
 
        MarkBufferDirty(buffer);
 
        /* XLOG stuff */
        if (needwal)
        {
            XLogRecPtr  recptr;
            xl_heap_multi_insert *xlrec;
            uint8       info = XLOG_HEAP2_MULTI_INSERT;
            char       *tupledata;
            int         totaldatalen;
            char       *scratchptr = scratch.data;
            bool        init;
            int         bufflags = 0;
 
            /*
             * If the page was previously empty, we can reinit the page
             * instead of restoring the whole thing.
             */
            init = starting_with_empty_page;
 
            /* allocate xl_heap_multi_insert struct from the scratch area */
            xlrec = (xl_heap_multi_insert *) scratchptr;
            scratchptr += SizeOfHeapMultiInsert;
 
            /*
             * Allocate offsets array. Unless we're reinitializing the page,
             * in that case the tuples are stored in order starting at
             * FirstOffsetNumber and we don't need to store the offsets
             * explicitly.
             */
            if (!init)
                scratchptr += nthispage * sizeof(OffsetNumber);
 
            /* the rest of the scratch space is used for tuple data */
            tupledata = scratchptr;
 
            /* check that the mutually exclusive flags are not both set */
            Assert(!(all_visible_cleared && all_frozen_set));
 
            xlrec->flags = 0;
            if (all_visible_cleared)
                xlrec->flags = XLH_INSERT_ALL_VISIBLE_CLEARED;
            if (all_frozen_set)
                xlrec->flags = XLH_INSERT_ALL_FROZEN_SET;
 
            xlrec->ntuples = nthispage;
 
            /*
             * Write out an xl_multi_insert_tuple and the tuple data itself
             * for each tuple.
             */
            for (i = 0; i < nthispage; i++)
            {
                HeapTuple   heaptup = heaptuples[ndone + i];
                xl_multi_insert_tuple *tuphdr;
                int         datalen;
 
                if (!init)
                    xlrec->offsets[i] = ItemPointerGetOffsetNumber(&heaptup->t_self);
                /* xl_multi_insert_tuple needs two-byte alignment. */
                tuphdr = (xl_multi_insert_tuple *) SHORTALIGN(scratchptr);
                scratchptr = ((char *) tuphdr) + SizeOfMultiInsertTuple;
 
                tuphdr->t_infomask2 = heaptup->t_data->t_infomask2;
                tuphdr->t_infomask = heaptup->t_data->t_infomask;
                tuphdr->t_hoff = heaptup->t_data->t_hoff;
 
                /* write bitmap [+ padding] [+ oid] + data */
                datalen = heaptup->t_len - SizeofHeapTupleHeader;
                memcpy(scratchptr,
                       (char *) heaptup->t_data + SizeofHeapTupleHeader,
                       datalen);
                tuphdr->datalen = datalen;
                scratchptr += datalen;
            }
            totaldatalen = scratchptr - tupledata;
            Assert((scratchptr - scratch.data) < BLCKSZ);
 
            if (need_tuple_data)
                xlrec->flags |= XLH_INSERT_CONTAINS_NEW_TUPLE;
 
            /*
             * Signal that this is the last xl_heap_multi_insert record
             * emitted by this call to heap_multi_insert(). Needed for logical
             * decoding so it knows when to cleanup temporary data.
             */
            if (ndone + nthispage == ntuples)
                xlrec->flags |= XLH_INSERT_LAST_IN_MULTI;
 
            if (init)
            {
                info |= XLOG_HEAP_INIT_PAGE;
                bufflags |= REGBUF_WILL_INIT;
            }
 
            /*
             * If we're doing logical decoding, include the new tuple data
             * even if we take a full-page image of the page.
             */
            if (need_tuple_data)
                bufflags |= REGBUF_KEEP_DATA;
 
            XLogBeginInsert();
            XLogRegisterData(xlrec, tupledata - scratch.data);
            XLogRegisterBuffer(0, buffer, REGBUF_STANDARD | bufflags);
 
            XLogRegisterBufData(0, tupledata, totaldatalen);
 
            /* filtering by origin on a row level is much more efficient */
            XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
 
            recptr = XLogInsert(RM_HEAP2_ID, info);
 
            PageSetLSN(page, recptr);
        }
 
        END_CRIT_SECTION();
 
        /*
         * If we've frozen everything on the page, update the visibilitymap.
         * We're already holding pin on the vmbuffer.
         */
        if (all_frozen_set)
        {
            /*
             * It's fine to use InvalidTransactionId here - this is only used
             * when HEAP_INSERT_FROZEN is specified, which intentionally
             * violates visibility rules.
             */
            visibilitymap_set(relation, BufferGetBlockNumber(buffer), buffer,
                              InvalidXLogRecPtr, vmbuffer,
                              InvalidTransactionId,
                              VISIBILITYMAP_ALL_VISIBLE | VISIBILITYMAP_ALL_FROZEN);
        }
 
        UnlockReleaseBuffer(buffer);
        ndone += nthispage;
 
        /*
         * NB: Only release vmbuffer after inserting all tuples - it's fairly
         * likely that we'll insert into subsequent heap pages that are likely
         * to use the same vm page.
         */
    }
 
    /* We're done with inserting all tuples, so release the last vmbuffer. */
    if (vmbuffer != InvalidBuffer)
        ReleaseBuffer(vmbuffer);
 
    /*
     * We're done with the actual inserts.  Check for conflicts again, to
     * ensure that all rw-conflicts in to these inserts are detected.  Without
     * this final check, a sequential scan of the heap may have locked the
     * table after the "before" check, missing one opportunity to detect the
     * conflict, and then scanned the table before the new tuples were there,
     * missing the other chance to detect the conflict.
     *
     * For heap inserts, we only need to check for table-level SSI locks. Our
     * new tuples can't possibly conflict with existing tuple locks, and heap
     * page locks are only consolidated versions of tuple locks; they do not
     * lock "gaps" as index page locks do.  So we don't need to specify a
     * buffer when making the call.
     */
    CheckForSerializableConflictIn(relation, NULL, InvalidBlockNumber);
 
    /*
     * If tuples are cachable, mark them for invalidation from the caches in
     * case we abort.  Note it is OK to do this after releasing the buffer,
     * because the heaptuples data structure is all in local memory, not in
     * the shared buffer.
     */
    if (IsCatalogRelation(relation))
    {
        for (i = 0; i < ntuples; i++)
            CacheInvalidateHeapTuple(relation, heaptuples[i], NULL);
    }
 
    /* copy t_self fields back to the caller's slots */
    for (i = 0; i < ntuples; i++)
        slots[i]->tts_tid = heaptuples[i]->t_self;
 
    pgstat_count_heap_insert(relation, ntuples);
}

References Assert(), AssertHasSnapshotForToast(), BufferGetBlockNumber(), BufferGetPage(), CacheInvalidateHeapTuple(), CHECK_FOR_INTERRUPTS, CheckForSerializableConflictIn(), PGAlignedBlock::data, xl_multi_insert_tuple::datalen, END_CRIT_SECTION, ExecFetchSlotHeapTuple(), xl_heap_multi_insert::flags, GetCurrentTransactionId(), HEAP_DEFAULT_FILLFACTOR, HEAP_INSERT_FROZEN, HEAP_INSERT_NO_LOGICAL, heap_multi_insert_pages(), heap_prepare_insert(), i, init, InvalidBlockNumber, InvalidBuffer, InvalidTransactionId, InvalidXLogRecPtr, IsCatalogRelation(), ItemPointerGetOffsetNumber(), log_heap_new_cid(), MarkBufferDirty(), MAXALIGN, xl_heap_multi_insert::ntuples, xl_heap_multi_insert::offsets, PageClearAllVisible(), PageGetHeapFreeSpace(), PageGetMaxOffsetNumber(), PageIsAllVisible(), PageSetAllVisible(), PageSetLSN(), palloc(), pgstat_count_heap_insert(), REGBUF_KEEP_DATA, REGBUF_STANDARD, REGBUF_WILL_INIT, RelationGetBufferForTuple(), RelationGetRelid, RelationGetTargetPageFreeSpace, RelationIsAccessibleInLogicalDecoding, RelationIsLogicallyLogged, RelationNeedsWAL, RelationPutHeapTuple(), ReleaseBuffer(), SHORTALIGN, SizeOfHeapMultiInsert, SizeofHeapTupleHeader, SizeOfMultiInsertTuple, START_CRIT_SECTION, HeapTupleData::t_data, xl_multi_insert_tuple::t_hoff, HeapTupleHeaderData::t_hoff, xl_multi_insert_tuple::t_infomask, HeapTupleHeaderData::t_infomask, xl_multi_insert_tuple::t_infomask2, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TupleTableSlot::tts_tableOid, UnlockReleaseBuffer(), VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, visibilitymap_clear(), visibilitymap_set(), VISIBILITYMAP_VALID_BITS, XLH_INSERT_ALL_FROZEN_SET, XLH_INSERT_ALL_VISIBLE_CLEARED, XLH_INSERT_CONTAINS_NEW_TUPLE, XLH_INSERT_LAST_IN_MULTI, XLOG_HEAP2_MULTI_INSERT, XLOG_HEAP_INIT_PAGE, XLOG_INCLUDE_ORIGIN, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), XLogRegisterData(), and XLogSetRecordFlags().

Referenced by CatalogTuplesMultiInsertWithInfo().

heap_multi_insert_pages()

static int heap_multi_insert_pages ( HeapTuple *  heaptuples, int  done, int  ntuples, Size  saveFreeSpace  )

static

Definition at line 2327 of file heapam.c.

{
    size_t      page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
    int         npages = 1;
 
    for (int i = done; i < ntuples; i++)
    {
        size_t      tup_sz = sizeof(ItemIdData) + MAXALIGN(heaptuples[i]->t_len);
 
        if (page_avail < tup_sz)
        {
            npages++;
            page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
        }
        page_avail -= tup_sz;
    }
 
    return npages;
}

References i, MAXALIGN, and SizeOfPageHeaderData.

Referenced by heap_multi_insert().

heap_pre_freeze_checks()

void heap_pre_freeze_checks	(	Buffer	buffer,
		HeapTupleFreeze *	tuples,
		int	ntuples
	)

Definition at line 7327 of file heapam.c.

{
    Page        page = BufferGetPage(buffer);
 
    for (int i = 0; i < ntuples; i++)
    {
        HeapTupleFreeze *frz = tuples + i;
        ItemId      itemid = PageGetItemId(page, frz->offset);
        HeapTupleHeader htup;
 
        htup = (HeapTupleHeader) PageGetItem(page, itemid);
 
        /* Deliberately avoid relying on tuple hint bits here */
        if (frz->checkflags & HEAP_FREEZE_CHECK_XMIN_COMMITTED)
        {
            TransactionId xmin = HeapTupleHeaderGetRawXmin(htup);
 
            Assert(!HeapTupleHeaderXminFrozen(htup));
            if (unlikely(!TransactionIdDidCommit(xmin)))
                ereport(ERROR,
                        (errcode(ERRCODE_DATA_CORRUPTED),
                         errmsg_internal("uncommitted xmin %u needs to be frozen",
                                         xmin)));
        }
 
        /*
         * TransactionIdDidAbort won't work reliably in the presence of XIDs
         * left behind by transactions that were in progress during a crash,
         * so we can only check that xmax didn't commit
         */
        if (frz->checkflags & HEAP_FREEZE_CHECK_XMAX_ABORTED)
        {
            TransactionId xmax = HeapTupleHeaderGetRawXmax(htup);
 
            Assert(TransactionIdIsNormal(xmax));
            if (unlikely(TransactionIdDidCommit(xmax)))
                ereport(ERROR,
                        (errcode(ERRCODE_DATA_CORRUPTED),
                         errmsg_internal("cannot freeze committed xmax %u",
                                         xmax)));
        }
    }
}

References Assert(), BufferGetPage(), HeapTupleFreeze::checkflags, ereport, errcode(), ERRCODE_DATA_CORRUPTED, errmsg_internal(), ERROR, HEAP_FREEZE_CHECK_XMAX_ABORTED, HEAP_FREEZE_CHECK_XMIN_COMMITTED, HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetRawXmin(), HeapTupleHeaderXminFrozen(), i, HeapTupleFreeze::offset, PageGetItem(), PageGetItemId(), TransactionIdDidCommit(), TransactionIdIsNormal, and unlikely.

Referenced by heap_page_prune_and_freeze().

heap_prepare_freeze_tuple()

bool heap_prepare_freeze_tuple	(	HeapTupleHeader	tuple,
		const struct VacuumCutoffs *	cutoffs,
		HeapPageFreeze *	pagefrz,
		HeapTupleFreeze *	frz,
		bool *	totally_frozen
	)

Definition at line 7054 of file heapam.c.

{
    bool        xmin_already_frozen = false,
                xmax_already_frozen = false;
    bool        freeze_xmin = false,
                replace_xvac = false,
                replace_xmax = false,
                freeze_xmax = false;
    TransactionId xid;
 
    frz->xmax = HeapTupleHeaderGetRawXmax(tuple);
    frz->t_infomask2 = tuple->t_infomask2;
    frz->t_infomask = tuple->t_infomask;
    frz->frzflags = 0;
    frz->checkflags = 0;
 
    /*
     * Process xmin, while keeping track of whether it's already frozen, or
     * will become frozen iff our freeze plan is executed by caller (could be
     * neither).
     */
    xid = HeapTupleHeaderGetXmin(tuple);
    if (!TransactionIdIsNormal(xid))
        xmin_already_frozen = true;
    else
    {
        if (TransactionIdPrecedes(xid, cutoffs->relfrozenxid))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("found xmin %u from before relfrozenxid %u",
                                     xid, cutoffs->relfrozenxid)));
 
        /* Will set freeze_xmin flags in freeze plan below */
        freeze_xmin = TransactionIdPrecedes(xid, cutoffs->OldestXmin);
 
        /* Verify that xmin committed if and when freeze plan is executed */
        if (freeze_xmin)
            frz->checkflags |= HEAP_FREEZE_CHECK_XMIN_COMMITTED;
    }
 
    /*
     * Old-style VACUUM FULL is gone, but we have to process xvac for as long
     * as we support having MOVED_OFF/MOVED_IN tuples in the database
     */
    xid = HeapTupleHeaderGetXvac(tuple);
    if (TransactionIdIsNormal(xid))
    {
        Assert(TransactionIdPrecedesOrEquals(cutoffs->relfrozenxid, xid));
        Assert(TransactionIdPrecedes(xid, cutoffs->OldestXmin));
 
        /*
         * For Xvac, we always freeze proactively.  This allows totally_frozen
         * tracking to ignore xvac.
         */
        replace_xvac = pagefrz->freeze_required = true;
 
        /* Will set replace_xvac flags in freeze plan below */
    }
 
    /* Now process xmax */
    xid = frz->xmax;
    if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
    {
        /* Raw xmax is a MultiXactId */
        TransactionId newxmax;
        uint16      flags;
 
        /*
         * We will either remove xmax completely (in the "freeze_xmax" path),
         * process xmax by replacing it (in the "replace_xmax" path), or
         * perform no-op xmax processing.  The only constraint is that the
         * FreezeLimit/MultiXactCutoff postcondition must never be violated.
         */
        newxmax = FreezeMultiXactId(xid, tuple->t_infomask, cutoffs,
                                    &flags, pagefrz);
 
        if (flags & FRM_NOOP)
        {
            /*
             * xmax is a MultiXactId, and nothing about it changes for now.
             * This is the only case where 'freeze_required' won't have been
             * set for us by FreezeMultiXactId, as well as the only case where
             * neither freeze_xmax nor replace_xmax are set (given a multi).
             *
             * This is a no-op, but the call to FreezeMultiXactId might have
             * ratcheted back NewRelfrozenXid and/or NewRelminMxid trackers
             * for us (the "freeze page" variants, specifically).  That'll
             * make it safe for our caller to freeze the page later on, while
             * leaving this particular xmax undisturbed.
             *
             * FreezeMultiXactId is _not_ responsible for the "no freeze"
             * NewRelfrozenXid/NewRelminMxid trackers, though -- that's our
             * job.  A call to heap_tuple_should_freeze for this same tuple
             * will take place below if 'freeze_required' isn't set already.
             * (This repeats work from FreezeMultiXactId, but allows "no
             * freeze" tracker maintenance to happen in only one place.)
             */
            Assert(!MultiXactIdPrecedes(newxmax, cutoffs->MultiXactCutoff));
            Assert(MultiXactIdIsValid(newxmax) && xid == newxmax);
        }
        else if (flags & FRM_RETURN_IS_XID)
        {
            /*
             * xmax will become an updater Xid (original MultiXact's updater
             * member Xid will be carried forward as a simple Xid in Xmax).
             */
            Assert(!TransactionIdPrecedes(newxmax, cutoffs->OldestXmin));
 
            /*
             * NB -- some of these transformations are only valid because we
             * know the return Xid is a tuple updater (i.e. not merely a
             * locker.) Also note that the only reason we don't explicitly
             * worry about HEAP_KEYS_UPDATED is because it lives in
             * t_infomask2 rather than t_infomask.
             */
            frz->t_infomask &= ~HEAP_XMAX_BITS;
            frz->xmax = newxmax;
            if (flags & FRM_MARK_COMMITTED)
                frz->t_infomask |= HEAP_XMAX_COMMITTED;
            replace_xmax = true;
        }
        else if (flags & FRM_RETURN_IS_MULTI)
        {
            uint16      newbits;
            uint16      newbits2;
 
            /*
             * xmax is an old MultiXactId that we have to replace with a new
             * MultiXactId, to carry forward two or more original member XIDs.
             */
            Assert(!MultiXactIdPrecedes(newxmax, cutoffs->OldestMxact));
 
            /*
             * We can't use GetMultiXactIdHintBits directly on the new multi
             * here; that routine initializes the masks to all zeroes, which
             * would lose other bits we need.  Doing it this way ensures all
             * unrelated bits remain untouched.
             */
            frz->t_infomask &= ~HEAP_XMAX_BITS;
            frz->t_infomask2 &= ~HEAP_KEYS_UPDATED;
            GetMultiXactIdHintBits(newxmax, &newbits, &newbits2);
            frz->t_infomask |= newbits;
            frz->t_infomask2 |= newbits2;
            frz->xmax = newxmax;
            replace_xmax = true;
        }
        else
        {
            /*
             * Freeze plan for tuple "freezes xmax" in the strictest sense:
             * it'll leave nothing in xmax (neither an Xid nor a MultiXactId).
             */
            Assert(flags & FRM_INVALIDATE_XMAX);
            Assert(!TransactionIdIsValid(newxmax));
 
            /* Will set freeze_xmax flags in freeze plan below */
            freeze_xmax = true;
        }
 
        /* MultiXactId processing forces freezing (barring FRM_NOOP case) */
        Assert(pagefrz->freeze_required || (!freeze_xmax && !replace_xmax));
    }
    else if (TransactionIdIsNormal(xid))
    {
        /* Raw xmax is normal XID */
        if (TransactionIdPrecedes(xid, cutoffs->relfrozenxid))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg_internal("found xmax %u from before relfrozenxid %u",
                                     xid, cutoffs->relfrozenxid)));
 
        /* Will set freeze_xmax flags in freeze plan below */
        freeze_xmax = TransactionIdPrecedes(xid, cutoffs->OldestXmin);
 
        /*
         * Verify that xmax aborted if and when freeze plan is executed,
         * provided it's from an update. (A lock-only xmax can be removed
         * independent of this, since the lock is released at xact end.)
         */
        if (freeze_xmax && !HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask))
            frz->checkflags |= HEAP_FREEZE_CHECK_XMAX_ABORTED;
    }
    else if (!TransactionIdIsValid(xid))
    {
        /* Raw xmax is InvalidTransactionId XID */
        Assert((tuple->t_infomask & HEAP_XMAX_IS_MULTI) == 0);
        xmax_already_frozen = true;
    }
    else
        ereport(ERROR,
                (errcode(ERRCODE_DATA_CORRUPTED),
                 errmsg_internal("found raw xmax %u (infomask 0x%04x) not invalid and not multi",
                                 xid, tuple->t_infomask)));
 
    if (freeze_xmin)
    {
        Assert(!xmin_already_frozen);
 
        frz->t_infomask |= HEAP_XMIN_FROZEN;
    }
    if (replace_xvac)
    {
        /*
         * If a MOVED_OFF tuple is not dead, the xvac transaction must have
         * failed; whereas a non-dead MOVED_IN tuple must mean the xvac
         * transaction succeeded.
         */
        Assert(pagefrz->freeze_required);
        if (tuple->t_infomask & HEAP_MOVED_OFF)
            frz->frzflags |= XLH_INVALID_XVAC;
        else
            frz->frzflags |= XLH_FREEZE_XVAC;
    }
    if (replace_xmax)
    {
        Assert(!xmax_already_frozen && !freeze_xmax);
        Assert(pagefrz->freeze_required);
 
        /* Already set replace_xmax flags in freeze plan earlier */
    }
    if (freeze_xmax)
    {
        Assert(!xmax_already_frozen && !replace_xmax);
 
        frz->xmax = InvalidTransactionId;
 
        /*
         * The tuple might be marked either XMAX_INVALID or XMAX_COMMITTED +
         * LOCKED.  Normalize to INVALID just to be sure no one gets confused.
         * Also get rid of the HEAP_KEYS_UPDATED bit.
         */
        frz->t_infomask &= ~HEAP_XMAX_BITS;
        frz->t_infomask |= HEAP_XMAX_INVALID;
        frz->t_infomask2 &= ~HEAP_HOT_UPDATED;
        frz->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    }
 
    /*
     * Determine if this tuple is already totally frozen, or will become
     * totally frozen (provided caller executes freeze plans for the page)
     */
    *totally_frozen = ((freeze_xmin || xmin_already_frozen) &&
                       (freeze_xmax || xmax_already_frozen));
 
    if (!pagefrz->freeze_required && !(xmin_already_frozen &&
                                       xmax_already_frozen))
    {
        /*
         * So far no previous tuple from the page made freezing mandatory.
         * Does this tuple force caller to freeze the entire page?
         */
        pagefrz->freeze_required =
            heap_tuple_should_freeze(tuple, cutoffs,
                                     &pagefrz->NoFreezePageRelfrozenXid,
                                     &pagefrz->NoFreezePageRelminMxid);
    }
 
    /* Tell caller if this tuple has a usable freeze plan set in *frz */
    return freeze_xmin || replace_xvac || replace_xmax || freeze_xmax;
}

References Assert(), HeapTupleFreeze::checkflags, ereport, errcode(), ERRCODE_DATA_CORRUPTED, errmsg_internal(), ERROR, HeapPageFreeze::freeze_required, FreezeMultiXactId(), FRM_INVALIDATE_XMAX, FRM_MARK_COMMITTED, FRM_NOOP, FRM_RETURN_IS_MULTI, FRM_RETURN_IS_XID, HeapTupleFreeze::frzflags, GetMultiXactIdHintBits(), HEAP_FREEZE_CHECK_XMAX_ABORTED, HEAP_FREEZE_CHECK_XMIN_COMMITTED, HEAP_MOVED_OFF, heap_tuple_should_freeze(), HEAP_XMAX_COMMITTED, HEAP_XMAX_INVALID, HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HEAP_XMIN_FROZEN, HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetXmin(), HeapTupleHeaderGetXvac(), InvalidTransactionId, VacuumCutoffs::MultiXactCutoff, MultiXactIdIsValid, MultiXactIdPrecedes(), HeapPageFreeze::NoFreezePageRelfrozenXid, HeapPageFreeze::NoFreezePageRelminMxid, VacuumCutoffs::OldestMxact, VacuumCutoffs::OldestXmin, VacuumCutoffs::relfrozenxid, HeapTupleFreeze::t_infomask, HeapTupleHeaderData::t_infomask, HeapTupleFreeze::t_infomask2, HeapTupleHeaderData::t_infomask2, TransactionIdIsNormal, TransactionIdIsValid, TransactionIdPrecedes(), TransactionIdPrecedesOrEquals(), XLH_FREEZE_XVAC, XLH_INVALID_XVAC, and HeapTupleFreeze::xmax.

Referenced by heap_freeze_tuple(), and heap_prune_record_unchanged_lp_normal().

heap_prepare_insert()

static HeapTuple heap_prepare_insert ( Relation  relation, HeapTuple  tup, TransactionId  xid, CommandId  cid, int  options  )

static

Definition at line 2279 of file heapam.c.

{
    /*
     * To allow parallel inserts, we need to ensure that they are safe to be
     * performed in workers. We have the infrastructure to allow parallel
     * inserts in general except for the cases where inserts generate a new
     * CommandId (eg. inserts into a table having a foreign key column).
     */
    if (IsParallelWorker())
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TRANSACTION_STATE),
                 errmsg("cannot insert tuples in a parallel worker")));
 
    tup->t_data->t_infomask &= ~(HEAP_XACT_MASK);
    tup->t_data->t_infomask2 &= ~(HEAP2_XACT_MASK);
    tup->t_data->t_infomask |= HEAP_XMAX_INVALID;
    HeapTupleHeaderSetXmin(tup->t_data, xid);
    if (options & HEAP_INSERT_FROZEN)
        HeapTupleHeaderSetXminFrozen(tup->t_data);
 
    HeapTupleHeaderSetCmin(tup->t_data, cid);
    HeapTupleHeaderSetXmax(tup->t_data, 0); /* for cleanliness */
    tup->t_tableOid = RelationGetRelid(relation);
 
    /*
     * If the new tuple is too big for storage or contains already toasted
     * out-of-line attributes from some other relation, invoke the toaster.
     */
    if (relation->rd_rel->relkind != RELKIND_RELATION &&
        relation->rd_rel->relkind != RELKIND_MATVIEW)
    {
        /* toast table entries should never be recursively toasted */
        Assert(!HeapTupleHasExternal(tup));
        return tup;
    }
    else if (HeapTupleHasExternal(tup) || tup->t_len > TOAST_TUPLE_THRESHOLD)
        return heap_toast_insert_or_update(relation, tup, NULL, options);
    else
        return tup;
}

References Assert(), ereport, errcode(), errmsg(), ERROR, HEAP2_XACT_MASK, HEAP_INSERT_FROZEN, heap_toast_insert_or_update(), HEAP_XACT_MASK, HEAP_XMAX_INVALID, HeapTupleHasExternal(), HeapTupleHeaderSetCmin(), HeapTupleHeaderSetXmax(), HeapTupleHeaderSetXmin(), HeapTupleHeaderSetXminFrozen(), IsParallelWorker, RelationData::rd_rel, RelationGetRelid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_tableOid, and TOAST_TUPLE_THRESHOLD.

Referenced by heap_insert(), and heap_multi_insert().

heap_prepare_pagescan()

void heap_prepare_pagescan

(

TableScanDesc

sscan

)

Definition at line 552 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
    Buffer      buffer = scan->rs_cbuf;
    BlockNumber block = scan->rs_cblock;
    Snapshot    snapshot;
    Page        page;
    int         lines;
    bool        all_visible;
    bool        check_serializable;
 
    Assert(BufferGetBlockNumber(buffer) == block);
 
    /* ensure we're not accidentally being used when not in pagemode */
    Assert(scan->rs_base.rs_flags & SO_ALLOW_PAGEMODE);
    snapshot = scan->rs_base.rs_snapshot;
 
    /*
     * Prune and repair fragmentation for the whole page, if possible.
     */
    heap_page_prune_opt(scan->rs_base.rs_rd, buffer);
 
    /*
     * We must hold share lock on the buffer content while examining tuple
     * visibility.  Afterwards, however, the tuples we have found to be
     * visible are guaranteed good as long as we hold the buffer pin.
     */
    LockBuffer(buffer, BUFFER_LOCK_SHARE);
 
    page = BufferGetPage(buffer);
    lines = PageGetMaxOffsetNumber(page);
 
    /*
     * If the all-visible flag indicates that all tuples on the page are
     * visible to everyone, we can skip the per-tuple visibility tests.
     *
     * Note: In hot standby, a tuple that's already visible to all
     * transactions on the primary might still be invisible to a read-only
     * transaction in the standby. We partly handle this problem by tracking
     * the minimum xmin of visible tuples as the cut-off XID while marking a
     * page all-visible on the primary and WAL log that along with the
     * visibility map SET operation. In hot standby, we wait for (or abort)
     * all transactions that can potentially may not see one or more tuples on
     * the page. That's how index-only scans work fine in hot standby. A
     * crucial difference between index-only scans and heap scans is that the
     * index-only scan completely relies on the visibility map where as heap
     * scan looks at the page-level PD_ALL_VISIBLE flag. We are not sure if
     * the page-level flag can be trusted in the same way, because it might
     * get propagated somehow without being explicitly WAL-logged, e.g. via a
     * full page write. Until we can prove that beyond doubt, let's check each
     * tuple for visibility the hard way.
     */
    all_visible = PageIsAllVisible(page) && !snapshot->takenDuringRecovery;
    check_serializable =
        CheckForSerializableConflictOutNeeded(scan->rs_base.rs_rd, snapshot);
 
    /*
     * We call page_collect_tuples() with constant arguments, to get the
     * compiler to constant fold the constant arguments. Separate calls with
     * constant arguments, rather than variables, are needed on several
     * compilers to actually perform constant folding.
     */
    if (likely(all_visible))
    {
        if (likely(!check_serializable))
            scan->rs_ntuples = page_collect_tuples(scan, snapshot, page, buffer,
                                                   block, lines, true, false);
        else
            scan->rs_ntuples = page_collect_tuples(scan, snapshot, page, buffer,
                                                   block, lines, true, true);
    }
    else
    {
        if (likely(!check_serializable))
            scan->rs_ntuples = page_collect_tuples(scan, snapshot, page, buffer,
                                                   block, lines, false, false);
        else
            scan->rs_ntuples = page_collect_tuples(scan, snapshot, page, buffer,
                                                   block, lines, false, true);
    }
 
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
}

References Assert(), BUFFER_LOCK_SHARE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage(), CheckForSerializableConflictOutNeeded(), heap_page_prune_opt(), likely, LockBuffer(), page_collect_tuples(), PageGetMaxOffsetNumber(), PageIsAllVisible(), HeapScanDescData::rs_base, HeapScanDescData::rs_cblock, HeapScanDescData::rs_cbuf, TableScanDescData::rs_flags, HeapScanDescData::rs_ntuples, TableScanDescData::rs_rd, TableScanDescData::rs_snapshot, SO_ALLOW_PAGEMODE, and SnapshotData::takenDuringRecovery.

Referenced by heapam_scan_sample_next_block(), and heapgettup_pagemode().

heap_rescan()

void heap_rescan	(	TableScanDesc	sscan,
		ScanKey	key,
		bool	set_params,
		bool	allow_strat,
		bool	allow_sync,
		bool	allow_pagemode
	)

Definition at line 1254 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
 
    if (set_params)
    {
        if (allow_strat)
            scan->rs_base.rs_flags |= SO_ALLOW_STRAT;
        else
            scan->rs_base.rs_flags &= ~SO_ALLOW_STRAT;
 
        if (allow_sync)
            scan->rs_base.rs_flags |= SO_ALLOW_SYNC;
        else
            scan->rs_base.rs_flags &= ~SO_ALLOW_SYNC;
 
        if (allow_pagemode && scan->rs_base.rs_snapshot &&
            IsMVCCSnapshot(scan->rs_base.rs_snapshot))
            scan->rs_base.rs_flags |= SO_ALLOW_PAGEMODE;
        else
            scan->rs_base.rs_flags &= ~SO_ALLOW_PAGEMODE;
    }
 
    /*
     * unpin scan buffers
     */
    if (BufferIsValid(scan->rs_cbuf))
    {
        ReleaseBuffer(scan->rs_cbuf);
        scan->rs_cbuf = InvalidBuffer;
    }
 
    /*
     * SO_TYPE_BITMAPSCAN would be cleaned up here, but it does not hold any
     * additional data vs a normal HeapScan
     */
 
    /*
     * The read stream is reset on rescan. This must be done before
     * initscan(), as some state referred to by read_stream_reset() is reset
     * in initscan().
     */
    if (scan->rs_read_stream)
        read_stream_reset(scan->rs_read_stream);
 
    /*
     * reinitialize scan descriptor
     */
    initscan(scan, key, true);
}

References BufferIsValid(), initscan(), InvalidBuffer, IsMVCCSnapshot, sort-test::key, read_stream_reset(), ReleaseBuffer(), HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, TableScanDescData::rs_flags, HeapScanDescData::rs_read_stream, TableScanDescData::rs_snapshot, SO_ALLOW_PAGEMODE, SO_ALLOW_STRAT, and SO_ALLOW_SYNC.

heap_scan_stream_read_next_parallel()

static BlockNumber heap_scan_stream_read_next_parallel ( ReadStream *  stream, void *  callback_private_data, void *  per_buffer_data  )

static

Definition at line 247 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) callback_private_data;
 
    Assert(ScanDirectionIsForward(scan->rs_dir));
    Assert(scan->rs_base.rs_parallel);
 
    if (unlikely(!scan->rs_inited))
    {
        /* parallel scan */
        table_block_parallelscan_startblock_init(scan->rs_base.rs_rd,
                                                 scan->rs_parallelworkerdata,
                                                 (ParallelBlockTableScanDesc) scan->rs_base.rs_parallel);
 
        /* may return InvalidBlockNumber if there are no more blocks */
        scan->rs_prefetch_block = table_block_parallelscan_nextpage(scan->rs_base.rs_rd,
                                                                    scan->rs_parallelworkerdata,
                                                                    (ParallelBlockTableScanDesc) scan->rs_base.rs_parallel);
        scan->rs_inited = true;
    }
    else
    {
        scan->rs_prefetch_block = table_block_parallelscan_nextpage(scan->rs_base.rs_rd,
                                                                    scan->rs_parallelworkerdata, (ParallelBlockTableScanDesc)
                                                                    scan->rs_base.rs_parallel);
    }
 
    return scan->rs_prefetch_block;
}

References Assert(), HeapScanDescData::rs_base, HeapScanDescData::rs_dir, HeapScanDescData::rs_inited, TableScanDescData::rs_parallel, HeapScanDescData::rs_parallelworkerdata, HeapScanDescData::rs_prefetch_block, TableScanDescData::rs_rd, ScanDirectionIsForward, table_block_parallelscan_nextpage(), table_block_parallelscan_startblock_init(), and unlikely.

Referenced by heap_beginscan().

heap_scan_stream_read_next_serial()

static BlockNumber heap_scan_stream_read_next_serial ( ReadStream *  stream, void *  callback_private_data, void *  per_buffer_data  )

static

Definition at line 285 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) callback_private_data;
 
    if (unlikely(!scan->rs_inited))
    {
        scan->rs_prefetch_block = heapgettup_initial_block(scan, scan->rs_dir);
        scan->rs_inited = true;
    }
    else
        scan->rs_prefetch_block = heapgettup_advance_block(scan,
                                                           scan->rs_prefetch_block,
                                                           scan->rs_dir);
 
    return scan->rs_prefetch_block;
}

References heapgettup_advance_block(), heapgettup_initial_block(), HeapScanDescData::rs_dir, HeapScanDescData::rs_inited, HeapScanDescData::rs_prefetch_block, and unlikely.

Referenced by heap_beginscan().

heap_set_tidrange()

void heap_set_tidrange	(	TableScanDesc	sscan,
		ItemPointer	mintid,
		ItemPointer	maxtid
	)

Definition at line 1425 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
    BlockNumber startBlk;
    BlockNumber numBlks;
    ItemPointerData highestItem;
    ItemPointerData lowestItem;
 
    /*
     * For relations without any pages, we can simply leave the TID range
     * unset.  There will be no tuples to scan, therefore no tuples outside
     * the given TID range.
     */
    if (scan->rs_nblocks == 0)
        return;
 
    /*
     * Set up some ItemPointers which point to the first and last possible
     * tuples in the heap.
     */
    ItemPointerSet(&highestItem, scan->rs_nblocks - 1, MaxOffsetNumber);
    ItemPointerSet(&lowestItem, 0, FirstOffsetNumber);
 
    /*
     * If the given maximum TID is below the highest possible TID in the
     * relation, then restrict the range to that, otherwise we scan to the end
     * of the relation.
     */
    if (ItemPointerCompare(maxtid, &highestItem) < 0)
        ItemPointerCopy(maxtid, &highestItem);
 
    /*
     * If the given minimum TID is above the lowest possible TID in the
     * relation, then restrict the range to only scan for TIDs above that.
     */
    if (ItemPointerCompare(mintid, &lowestItem) > 0)
        ItemPointerCopy(mintid, &lowestItem);
 
    /*
     * Check for an empty range and protect from would be negative results
     * from the numBlks calculation below.
     */
    if (ItemPointerCompare(&highestItem, &lowestItem) < 0)
    {
        /* Set an empty range of blocks to scan */
        heap_setscanlimits(sscan, 0, 0);
        return;
    }
 
    /*
     * Calculate the first block and the number of blocks we must scan. We
     * could be more aggressive here and perform some more validation to try
     * and further narrow the scope of blocks to scan by checking if the
     * lowestItem has an offset above MaxOffsetNumber.  In this case, we could
     * advance startBlk by one.  Likewise, if highestItem has an offset of 0
     * we could scan one fewer blocks.  However, such an optimization does not
     * seem worth troubling over, currently.
     */
    startBlk = ItemPointerGetBlockNumberNoCheck(&lowestItem);
 
    numBlks = ItemPointerGetBlockNumberNoCheck(&highestItem) -
        ItemPointerGetBlockNumberNoCheck(&lowestItem) + 1;
 
    /* Set the start block and number of blocks to scan */
    heap_setscanlimits(sscan, startBlk, numBlks);
 
    /* Finally, set the TID range in sscan */
    ItemPointerCopy(&lowestItem, &sscan->st.tidrange.rs_mintid);
    ItemPointerCopy(&highestItem, &sscan->st.tidrange.rs_maxtid);
}

References FirstOffsetNumber, heap_setscanlimits(), ItemPointerCompare(), ItemPointerCopy(), ItemPointerGetBlockNumberNoCheck(), ItemPointerSet(), MaxOffsetNumber, TableScanDescData::rs_maxtid, TableScanDescData::rs_mintid, HeapScanDescData::rs_nblocks, TableScanDescData::st, and TableScanDescData::tidrange.

heap_setscanlimits()

void heap_setscanlimits	(	TableScanDesc	sscan,
		BlockNumber	startBlk,
		BlockNumber	numBlks
	)

Definition at line 480 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
 
    Assert(!scan->rs_inited);   /* else too late to change */
    /* else rs_startblock is significant */
    Assert(!(scan->rs_base.rs_flags & SO_ALLOW_SYNC));
 
    /* Check startBlk is valid (but allow case of zero blocks...) */
    Assert(startBlk == 0 || startBlk < scan->rs_nblocks);
 
    scan->rs_startblock = startBlk;
    scan->rs_numblocks = numBlks;
}

References Assert(), HeapScanDescData::rs_base, TableScanDescData::rs_flags, HeapScanDescData::rs_inited, HeapScanDescData::rs_numblocks, HeapScanDescData::rs_startblock, and SO_ALLOW_SYNC.

Referenced by heap_set_tidrange(), and heapam_index_build_range_scan().

heap_tuple_needs_eventual_freeze()

bool heap_tuple_needs_eventual_freeze

(

HeapTupleHeader

tuple

)

Definition at line 7810 of file heapam.c.

{
    TransactionId xid;
 
    /*
     * If xmin is a normal transaction ID, this tuple is definitely not
     * frozen.
     */
    xid = HeapTupleHeaderGetXmin(tuple);
    if (TransactionIdIsNormal(xid))
        return true;
 
    /*
     * If xmax is a valid xact or multixact, this tuple is also not frozen.
     */
    if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
    {
        MultiXactId multi;
 
        multi = HeapTupleHeaderGetRawXmax(tuple);
        if (MultiXactIdIsValid(multi))
            return true;
    }
    else
    {
        xid = HeapTupleHeaderGetRawXmax(tuple);
        if (TransactionIdIsNormal(xid))
            return true;
    }
 
    if (tuple->t_infomask & HEAP_MOVED)
    {
        xid = HeapTupleHeaderGetXvac(tuple);
        if (TransactionIdIsNormal(xid))
            return true;
    }
 
    return false;
}

References HEAP_MOVED, HEAP_XMAX_IS_MULTI, HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetXmin(), HeapTupleHeaderGetXvac(), MultiXactIdIsValid, HeapTupleHeaderData::t_infomask, and TransactionIdIsNormal.

Referenced by collect_corrupt_items(), and heap_page_is_all_visible().

heap_tuple_should_freeze()

bool heap_tuple_should_freeze	(	HeapTupleHeader	tuple,
		const struct VacuumCutoffs *	cutoffs,
		TransactionId *	NoFreezePageRelfrozenXid,
		MultiXactId *	NoFreezePageRelminMxid
	)

Definition at line 7865 of file heapam.c.

{
    TransactionId xid;
    MultiXactId multi;
    bool        freeze = false;
 
    /* First deal with xmin */
    xid = HeapTupleHeaderGetXmin(tuple);
    if (TransactionIdIsNormal(xid))
    {
        Assert(TransactionIdPrecedesOrEquals(cutoffs->relfrozenxid, xid));
        if (TransactionIdPrecedes(xid, *NoFreezePageRelfrozenXid))
            *NoFreezePageRelfrozenXid = xid;
        if (TransactionIdPrecedes(xid, cutoffs->FreezeLimit))
            freeze = true;
    }
 
    /* Now deal with xmax */
    xid = InvalidTransactionId;
    multi = InvalidMultiXactId;
    if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
        multi = HeapTupleHeaderGetRawXmax(tuple);
    else
        xid = HeapTupleHeaderGetRawXmax(tuple);
 
    if (TransactionIdIsNormal(xid))
    {
        Assert(TransactionIdPrecedesOrEquals(cutoffs->relfrozenxid, xid));
        /* xmax is a non-permanent XID */
        if (TransactionIdPrecedes(xid, *NoFreezePageRelfrozenXid))
            *NoFreezePageRelfrozenXid = xid;
        if (TransactionIdPrecedes(xid, cutoffs->FreezeLimit))
            freeze = true;
    }
    else if (!MultiXactIdIsValid(multi))
    {
        /* xmax is a permanent XID or invalid MultiXactId/XID */
    }
    else if (HEAP_LOCKED_UPGRADED(tuple->t_infomask))
    {
        /* xmax is a pg_upgrade'd MultiXact, which can't have updater XID */
        if (MultiXactIdPrecedes(multi, *NoFreezePageRelminMxid))
            *NoFreezePageRelminMxid = multi;
        /* heap_prepare_freeze_tuple always freezes pg_upgrade'd xmax */
        freeze = true;
    }
    else
    {
        /* xmax is a MultiXactId that may have an updater XID */
        MultiXactMember *members;
        int         nmembers;
 
        Assert(MultiXactIdPrecedesOrEquals(cutoffs->relminmxid, multi));
        if (MultiXactIdPrecedes(multi, *NoFreezePageRelminMxid))
            *NoFreezePageRelminMxid = multi;
        if (MultiXactIdPrecedes(multi, cutoffs->MultiXactCutoff))
            freeze = true;
 
        /* need to check whether any member of the mxact is old */
        nmembers = GetMultiXactIdMembers(multi, &members, false,
                                         HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask));
 
        for (int i = 0; i < nmembers; i++)
        {
            xid = members[i].xid;
            Assert(TransactionIdPrecedesOrEquals(cutoffs->relfrozenxid, xid));
            if (TransactionIdPrecedes(xid, *NoFreezePageRelfrozenXid))
                *NoFreezePageRelfrozenXid = xid;
            if (TransactionIdPrecedes(xid, cutoffs->FreezeLimit))
                freeze = true;
        }
        if (nmembers > 0)
            pfree(members);
    }
 
    if (tuple->t_infomask & HEAP_MOVED)
    {
        xid = HeapTupleHeaderGetXvac(tuple);
        if (TransactionIdIsNormal(xid))
        {
            Assert(TransactionIdPrecedesOrEquals(cutoffs->relfrozenxid, xid));
            if (TransactionIdPrecedes(xid, *NoFreezePageRelfrozenXid))
                *NoFreezePageRelfrozenXid = xid;
            /* heap_prepare_freeze_tuple forces xvac freezing */
            freeze = true;
        }
    }
 
    return freeze;
}

References Assert(), VacuumCutoffs::FreezeLimit, GetMultiXactIdMembers(), HEAP_LOCKED_UPGRADED(), HEAP_MOVED, HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetXmin(), HeapTupleHeaderGetXvac(), i, InvalidMultiXactId, InvalidTransactionId, VacuumCutoffs::MultiXactCutoff, MultiXactIdIsValid, MultiXactIdPrecedes(), MultiXactIdPrecedesOrEquals(), pfree(), VacuumCutoffs::relfrozenxid, VacuumCutoffs::relminmxid, HeapTupleHeaderData::t_infomask, TransactionIdIsNormal, TransactionIdPrecedes(), TransactionIdPrecedesOrEquals(), and MultiXactMember::xid.

Referenced by heap_prepare_freeze_tuple(), and lazy_scan_noprune().

heap_update()

TM_Result heap_update	(	Relation	relation,
		ItemPointer	otid,
		HeapTuple	newtup,
		CommandId	cid,
		Snapshot	crosscheck,
		bool	wait,
		TM_FailureData *	tmfd,
		LockTupleMode *	lockmode,
		TU_UpdateIndexes *	update_indexes
	)

Definition at line 3247 of file heapam.c.

{
    TM_Result   result;
    TransactionId xid = GetCurrentTransactionId();
    Bitmapset  *hot_attrs;
    Bitmapset  *sum_attrs;
    Bitmapset  *key_attrs;
    Bitmapset  *id_attrs;
    Bitmapset  *interesting_attrs;
    Bitmapset  *modified_attrs;
    ItemId      lp;
    HeapTupleData oldtup;
    HeapTuple   heaptup;
    HeapTuple   old_key_tuple = NULL;
    bool        old_key_copied = false;
    Page        page;
    BlockNumber block;
    MultiXactStatus mxact_status;
    Buffer      buffer,
                newbuf,
                vmbuffer = InvalidBuffer,
                vmbuffer_new = InvalidBuffer;
    bool        need_toast;
    Size        newtupsize,
                pagefree;
    bool        have_tuple_lock = false;
    bool        iscombo;
    bool        use_hot_update = false;
    bool        summarized_update = false;
    bool        key_intact;
    bool        all_visible_cleared = false;
    bool        all_visible_cleared_new = false;
    bool        checked_lockers;
    bool        locker_remains;
    bool        id_has_external = false;
    TransactionId xmax_new_tuple,
                xmax_old_tuple;
    uint16      infomask_old_tuple,
                infomask2_old_tuple,
                infomask_new_tuple,
                infomask2_new_tuple;
 
    Assert(ItemPointerIsValid(otid));
 
    /* Cheap, simplistic check that the tuple matches the rel's rowtype. */
    Assert(HeapTupleHeaderGetNatts(newtup->t_data) <=
           RelationGetNumberOfAttributes(relation));
 
    AssertHasSnapshotForToast(relation);
 
    /*
     * Forbid this during a parallel operation, lest it allocate a combo CID.
     * Other workers might need that combo CID for visibility checks, and we
     * have no provision for broadcasting it to them.
     */
    if (IsInParallelMode())
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TRANSACTION_STATE),
                 errmsg("cannot update tuples during a parallel operation")));
 
#ifdef USE_ASSERT_CHECKING
    check_lock_if_inplace_updateable_rel(relation, otid, newtup);
#endif
 
    /*
     * Fetch the list of attributes to be checked for various operations.
     *
     * For HOT considerations, this is wasted effort if we fail to update or
     * have to put the new tuple on a different page.  But we must compute the
     * list before obtaining buffer lock --- in the worst case, if we are
     * doing an update on one of the relevant system catalogs, we could
     * deadlock if we try to fetch the list later.  In any case, the relcache
     * caches the data so this is usually pretty cheap.
     *
     * We also need columns used by the replica identity and columns that are
     * considered the "key" of rows in the table.
     *
     * Note that we get copies of each bitmap, so we need not worry about
     * relcache flush happening midway through.
     */
    hot_attrs = RelationGetIndexAttrBitmap(relation,
                                           INDEX_ATTR_BITMAP_HOT_BLOCKING);
    sum_attrs = RelationGetIndexAttrBitmap(relation,
                                           INDEX_ATTR_BITMAP_SUMMARIZED);
    key_attrs = RelationGetIndexAttrBitmap(relation, INDEX_ATTR_BITMAP_KEY);
    id_attrs = RelationGetIndexAttrBitmap(relation,
                                          INDEX_ATTR_BITMAP_IDENTITY_KEY);
    interesting_attrs = NULL;
    interesting_attrs = bms_add_members(interesting_attrs, hot_attrs);
    interesting_attrs = bms_add_members(interesting_attrs, sum_attrs);
    interesting_attrs = bms_add_members(interesting_attrs, key_attrs);
    interesting_attrs = bms_add_members(interesting_attrs, id_attrs);
 
    block = ItemPointerGetBlockNumber(otid);
    INJECTION_POINT("heap_update-before-pin", NULL);
    buffer = ReadBuffer(relation, block);
    page = BufferGetPage(buffer);
 
    /*
     * Before locking the buffer, pin the visibility map page if it appears to
     * be necessary.  Since we haven't got the lock yet, someone else might be
     * in the middle of changing this, so we'll need to recheck after we have
     * the lock.
     */
    if (PageIsAllVisible(page))
        visibilitymap_pin(relation, block, &vmbuffer);
 
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
    lp = PageGetItemId(page, ItemPointerGetOffsetNumber(otid));
 
    /*
     * Usually, a buffer pin and/or snapshot blocks pruning of otid, ensuring
     * we see LP_NORMAL here.  When the otid origin is a syscache, we may have
     * neither a pin nor a snapshot.  Hence, we may see other LP_ states, each
     * of which indicates concurrent pruning.
     *
     * Failing with TM_Updated would be most accurate.  However, unlike other
     * TM_Updated scenarios, we don't know the successor ctid in LP_UNUSED and
     * LP_DEAD cases.  While the distinction between TM_Updated and TM_Deleted
     * does matter to SQL statements UPDATE and MERGE, those SQL statements
     * hold a snapshot that ensures LP_NORMAL.  Hence, the choice between
     * TM_Updated and TM_Deleted affects only the wording of error messages.
     * Settle on TM_Deleted, for two reasons.  First, it avoids complicating
     * the specification of when tmfd->ctid is valid.  Second, it creates
     * error log evidence that we took this branch.
     *
     * Since it's possible to see LP_UNUSED at otid, it's also possible to see
     * LP_NORMAL for a tuple that replaced LP_UNUSED.  If it's a tuple for an
     * unrelated row, we'll fail with "duplicate key value violates unique".
     * XXX if otid is the live, newer version of the newtup row, we'll discard
     * changes originating in versions of this catalog row after the version
     * the caller got from syscache.  See syscache-update-pruned.spec.
     */
    if (!ItemIdIsNormal(lp))
    {
        Assert(RelationSupportsSysCache(RelationGetRelid(relation)));
 
        UnlockReleaseBuffer(buffer);
        Assert(!have_tuple_lock);
        if (vmbuffer != InvalidBuffer)
            ReleaseBuffer(vmbuffer);
        tmfd->ctid = *otid;
        tmfd->xmax = InvalidTransactionId;
        tmfd->cmax = InvalidCommandId;
        *update_indexes = TU_None;
 
        bms_free(hot_attrs);
        bms_free(sum_attrs);
        bms_free(key_attrs);
        bms_free(id_attrs);
        /* modified_attrs not yet initialized */
        bms_free(interesting_attrs);
        return TM_Deleted;
    }
 
    /*
     * Fill in enough data in oldtup for HeapDetermineColumnsInfo to work
     * properly.
     */
    oldtup.t_tableOid = RelationGetRelid(relation);
    oldtup.t_data = (HeapTupleHeader) PageGetItem(page, lp);
    oldtup.t_len = ItemIdGetLength(lp);
    oldtup.t_self = *otid;
 
    /* the new tuple is ready, except for this: */
    newtup->t_tableOid = RelationGetRelid(relation);
 
    /*
     * Determine columns modified by the update.  Additionally, identify
     * whether any of the unmodified replica identity key attributes in the
     * old tuple is externally stored or not.  This is required because for
     * such attributes the flattened value won't be WAL logged as part of the
     * new tuple so we must include it as part of the old_key_tuple.  See
     * ExtractReplicaIdentity.
     */
    modified_attrs = HeapDetermineColumnsInfo(relation, interesting_attrs,
                                              id_attrs, &oldtup,
                                              newtup, &id_has_external);
 
    /*
     * If we're not updating any "key" column, we can grab a weaker lock type.
     * This allows for more concurrency when we are running simultaneously
     * with foreign key checks.
     *
     * Note that if a column gets detoasted while executing the update, but
     * the value ends up being the same, this test will fail and we will use
     * the stronger lock.  This is acceptable; the important case to optimize
     * is updates that don't manipulate key columns, not those that
     * serendipitously arrive at the same key values.
     */
    if (!bms_overlap(modified_attrs, key_attrs))
    {
        *lockmode = LockTupleNoKeyExclusive;
        mxact_status = MultiXactStatusNoKeyUpdate;
        key_intact = true;
 
        /*
         * If this is the first possibly-multixact-able operation in the
         * current transaction, set my per-backend OldestMemberMXactId
         * setting. We can be certain that the transaction will never become a
         * member of any older MultiXactIds than that.  (We have to do this
         * even if we end up just using our own TransactionId below, since
         * some other backend could incorporate our XID into a MultiXact
         * immediately afterwards.)
         */
        MultiXactIdSetOldestMember();
    }
    else
    {
        *lockmode = LockTupleExclusive;
        mxact_status = MultiXactStatusUpdate;
        key_intact = false;
    }
 
    /*
     * Note: beyond this point, use oldtup not otid to refer to old tuple.
     * otid may very well point at newtup->t_self, which we will overwrite
     * with the new tuple's location, so there's great risk of confusion if we
     * use otid anymore.
     */
 
l2:
    checked_lockers = false;
    locker_remains = false;
    result = HeapTupleSatisfiesUpdate(&oldtup, cid, buffer);
 
    /* see below about the "no wait" case */
    Assert(result != TM_BeingModified || wait);
 
    if (result == TM_Invisible)
    {
        UnlockReleaseBuffer(buffer);
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("attempted to update invisible tuple")));
    }
    else if (result == TM_BeingModified && wait)
    {
        TransactionId xwait;
        uint16      infomask;
        bool        can_continue = false;
 
        /*
         * XXX note that we don't consider the "no wait" case here.  This
         * isn't a problem currently because no caller uses that case, but it
         * should be fixed if such a caller is introduced.  It wasn't a
         * problem previously because this code would always wait, but now
         * that some tuple locks do not conflict with one of the lock modes we
         * use, it is possible that this case is interesting to handle
         * specially.
         *
         * This may cause failures with third-party code that calls
         * heap_update directly.
         */
 
        /* must copy state data before unlocking buffer */
        xwait = HeapTupleHeaderGetRawXmax(oldtup.t_data);
        infomask = oldtup.t_data->t_infomask;
 
        /*
         * Now we have to do something about the existing locker.  If it's a
         * multi, sleep on it; we might be awakened before it is completely
         * gone (or even not sleep at all in some cases); we need to preserve
         * it as locker, unless it is gone completely.
         *
         * If it's not a multi, we need to check for sleeping conditions
         * before actually going to sleep.  If the update doesn't conflict
         * with the locks, we just continue without sleeping (but making sure
         * it is preserved).
         *
         * Before sleeping, we need to acquire tuple lock to establish our
         * priority for the tuple (see heap_lock_tuple).  LockTuple will
         * release us when we are next-in-line for the tuple.  Note we must
         * not acquire the tuple lock until we're sure we're going to sleep;
         * otherwise we're open for race conditions with other transactions
         * holding the tuple lock which sleep on us.
         *
         * If we are forced to "start over" below, we keep the tuple lock;
         * this arranges that we stay at the head of the line while rechecking
         * tuple state.
         */
        if (infomask & HEAP_XMAX_IS_MULTI)
        {
            TransactionId update_xact;
            int         remain;
            bool        current_is_member = false;
 
            if (DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
                                        *lockmode, &current_is_member))
            {
                LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
                /*
                 * Acquire the lock, if necessary (but skip it when we're
                 * requesting a lock and already have one; avoids deadlock).
                 */
                if (!current_is_member)
                    heap_acquire_tuplock(relation, &(oldtup.t_self), *lockmode,
                                         LockWaitBlock, &have_tuple_lock);
 
                /* wait for multixact */
                MultiXactIdWait((MultiXactId) xwait, mxact_status, infomask,
                                relation, &oldtup.t_self, XLTW_Update,
                                &remain);
                checked_lockers = true;
                locker_remains = remain != 0;
                LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
                /*
                 * If xwait had just locked the tuple then some other xact
                 * could update this tuple before we get to this point.  Check
                 * for xmax change, and start over if so.
                 */
                if (xmax_infomask_changed(oldtup.t_data->t_infomask,
                                          infomask) ||
                    !TransactionIdEquals(HeapTupleHeaderGetRawXmax(oldtup.t_data),
                                         xwait))
                    goto l2;
            }
 
            /*
             * Note that the multixact may not be done by now.  It could have
             * surviving members; our own xact or other subxacts of this
             * backend, and also any other concurrent transaction that locked
             * the tuple with LockTupleKeyShare if we only got
             * LockTupleNoKeyExclusive.  If this is the case, we have to be
             * careful to mark the updated tuple with the surviving members in
             * Xmax.
             *
             * Note that there could have been another update in the
             * MultiXact. In that case, we need to check whether it committed
             * or aborted. If it aborted we are safe to update it again;
             * otherwise there is an update conflict, and we have to return
             * TableTuple{Deleted, Updated} below.
             *
             * In the LockTupleExclusive case, we still need to preserve the
             * surviving members: those would include the tuple locks we had
             * before this one, which are important to keep in case this
             * subxact aborts.
             */
            if (!HEAP_XMAX_IS_LOCKED_ONLY(oldtup.t_data->t_infomask))
                update_xact = HeapTupleGetUpdateXid(oldtup.t_data);
            else
                update_xact = InvalidTransactionId;
 
            /*
             * There was no UPDATE in the MultiXact; or it aborted. No
             * TransactionIdIsInProgress() call needed here, since we called
             * MultiXactIdWait() above.
             */
            if (!TransactionIdIsValid(update_xact) ||
                TransactionIdDidAbort(update_xact))
                can_continue = true;
        }
        else if (TransactionIdIsCurrentTransactionId(xwait))
        {
            /*
             * The only locker is ourselves; we can avoid grabbing the tuple
             * lock here, but must preserve our locking information.
             */
            checked_lockers = true;
            locker_remains = true;
            can_continue = true;
        }
        else if (HEAP_XMAX_IS_KEYSHR_LOCKED(infomask) && key_intact)
        {
            /*
             * If it's just a key-share locker, and we're not changing the key
             * columns, we don't need to wait for it to end; but we need to
             * preserve it as locker.
             */
            checked_lockers = true;
            locker_remains = true;
            can_continue = true;
        }
        else
        {
            /*
             * Wait for regular transaction to end; but first, acquire tuple
             * lock.
             */
            LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            heap_acquire_tuplock(relation, &(oldtup.t_self), *lockmode,
                                 LockWaitBlock, &have_tuple_lock);
            XactLockTableWait(xwait, relation, &oldtup.t_self,
                              XLTW_Update);
            checked_lockers = true;
            LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
 
            /*
             * xwait is done, but if xwait had just locked the tuple then some
             * other xact could update this tuple before we get to this point.
             * Check for xmax change, and start over if so.
             */
            if (xmax_infomask_changed(oldtup.t_data->t_infomask, infomask) ||
                !TransactionIdEquals(xwait,
                                     HeapTupleHeaderGetRawXmax(oldtup.t_data)))
                goto l2;
 
            /* Otherwise check if it committed or aborted */
            UpdateXmaxHintBits(oldtup.t_data, buffer, xwait);
            if (oldtup.t_data->t_infomask & HEAP_XMAX_INVALID)
                can_continue = true;
        }
 
        if (can_continue)
            result = TM_Ok;
        else if (!ItemPointerEquals(&oldtup.t_self, &oldtup.t_data->t_ctid))
            result = TM_Updated;
        else
            result = TM_Deleted;
    }
 
    /* Sanity check the result HeapTupleSatisfiesUpdate() and the logic above */
    if (result != TM_Ok)
    {
        Assert(result == TM_SelfModified ||
               result == TM_Updated ||
               result == TM_Deleted ||
               result == TM_BeingModified);
        Assert(!(oldtup.t_data->t_infomask & HEAP_XMAX_INVALID));
        Assert(result != TM_Updated ||
               !ItemPointerEquals(&oldtup.t_self, &oldtup.t_data->t_ctid));
    }
 
    if (crosscheck != InvalidSnapshot && result == TM_Ok)
    {
        /* Perform additional check for transaction-snapshot mode RI updates */
        if (!HeapTupleSatisfiesVisibility(&oldtup, crosscheck, buffer))
            result = TM_Updated;
    }
 
    if (result != TM_Ok)
    {
        tmfd->ctid = oldtup.t_data->t_ctid;
        tmfd->xmax = HeapTupleHeaderGetUpdateXid(oldtup.t_data);
        if (result == TM_SelfModified)
            tmfd->cmax = HeapTupleHeaderGetCmax(oldtup.t_data);
        else
            tmfd->cmax = InvalidCommandId;
        UnlockReleaseBuffer(buffer);
        if (have_tuple_lock)
            UnlockTupleTuplock(relation, &(oldtup.t_self), *lockmode);
        if (vmbuffer != InvalidBuffer)
            ReleaseBuffer(vmbuffer);
        *update_indexes = TU_None;
 
        bms_free(hot_attrs);
        bms_free(sum_attrs);
        bms_free(key_attrs);
        bms_free(id_attrs);
        bms_free(modified_attrs);
        bms_free(interesting_attrs);
        return result;
    }
 
    /*
     * If we didn't pin the visibility map page and the page has become all
     * visible while we were busy locking the buffer, or during some
     * subsequent window during which we had it unlocked, we'll have to unlock
     * and re-lock, to avoid holding the buffer lock across an I/O.  That's a
     * bit unfortunate, especially since we'll now have to recheck whether the
     * tuple has been locked or updated under us, but hopefully it won't
     * happen very often.
     */
    if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
    {
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
        visibilitymap_pin(relation, block, &vmbuffer);
        LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
        goto l2;
    }
 
    /* Fill in transaction status data */
 
    /*
     * If the tuple we're updating is locked, we need to preserve the locking
     * info in the old tuple's Xmax.  Prepare a new Xmax value for this.
     */
    compute_new_xmax_infomask(HeapTupleHeaderGetRawXmax(oldtup.t_data),
                              oldtup.t_data->t_infomask,
                              oldtup.t_data->t_infomask2,
                              xid, *lockmode, true,
                              &xmax_old_tuple, &infomask_old_tuple,
                              &infomask2_old_tuple);
 
    /*
     * And also prepare an Xmax value for the new copy of the tuple.  If there
     * was no xmax previously, or there was one but all lockers are now gone,
     * then use InvalidTransactionId; otherwise, get the xmax from the old
     * tuple.  (In rare cases that might also be InvalidTransactionId and yet
     * not have the HEAP_XMAX_INVALID bit set; that's fine.)
     */
    if ((oldtup.t_data->t_infomask & HEAP_XMAX_INVALID) ||
        HEAP_LOCKED_UPGRADED(oldtup.t_data->t_infomask) ||
        (checked_lockers && !locker_remains))
        xmax_new_tuple = InvalidTransactionId;
    else
        xmax_new_tuple = HeapTupleHeaderGetRawXmax(oldtup.t_data);
 
    if (!TransactionIdIsValid(xmax_new_tuple))
    {
        infomask_new_tuple = HEAP_XMAX_INVALID;
        infomask2_new_tuple = 0;
    }
    else
    {
        /*
         * If we found a valid Xmax for the new tuple, then the infomask bits
         * to use on the new tuple depend on what was there on the old one.
         * Note that since we're doing an update, the only possibility is that
         * the lockers had FOR KEY SHARE lock.
         */
        if (oldtup.t_data->t_infomask & HEAP_XMAX_IS_MULTI)
        {
            GetMultiXactIdHintBits(xmax_new_tuple, &infomask_new_tuple,
                                   &infomask2_new_tuple);
        }
        else
        {
            infomask_new_tuple = HEAP_XMAX_KEYSHR_LOCK | HEAP_XMAX_LOCK_ONLY;
            infomask2_new_tuple = 0;
        }
    }
 
    /*
     * Prepare the new tuple with the appropriate initial values of Xmin and
     * Xmax, as well as initial infomask bits as computed above.
     */
    newtup->t_data->t_infomask &= ~(HEAP_XACT_MASK);
    newtup->t_data->t_infomask2 &= ~(HEAP2_XACT_MASK);
    HeapTupleHeaderSetXmin(newtup->t_data, xid);
    HeapTupleHeaderSetCmin(newtup->t_data, cid);
    newtup->t_data->t_infomask |= HEAP_UPDATED | infomask_new_tuple;
    newtup->t_data->t_infomask2 |= infomask2_new_tuple;
    HeapTupleHeaderSetXmax(newtup->t_data, xmax_new_tuple);
 
    /*
     * Replace cid with a combo CID if necessary.  Note that we already put
     * the plain cid into the new tuple.
     */
    HeapTupleHeaderAdjustCmax(oldtup.t_data, &cid, &iscombo);
 
    /*
     * If the toaster needs to be activated, OR if the new tuple will not fit
     * on the same page as the old, then we need to release the content lock
     * (but not the pin!) on the old tuple's buffer while we are off doing
     * TOAST and/or table-file-extension work.  We must mark the old tuple to
     * show that it's locked, else other processes may try to update it
     * themselves.
     *
     * We need to invoke the toaster if there are already any out-of-line
     * toasted values present, or if the new tuple is over-threshold.
     */
    if (relation->rd_rel->relkind != RELKIND_RELATION &&
        relation->rd_rel->relkind != RELKIND_MATVIEW)
    {
        /* toast table entries should never be recursively toasted */
        Assert(!HeapTupleHasExternal(&oldtup));
        Assert(!HeapTupleHasExternal(newtup));
        need_toast = false;
    }
    else
        need_toast = (HeapTupleHasExternal(&oldtup) ||
                      HeapTupleHasExternal(newtup) ||
                      newtup->t_len > TOAST_TUPLE_THRESHOLD);
 
    pagefree = PageGetHeapFreeSpace(page);
 
    newtupsize = MAXALIGN(newtup->t_len);
 
    if (need_toast || newtupsize > pagefree)
    {
        TransactionId xmax_lock_old_tuple;
        uint16      infomask_lock_old_tuple,
                    infomask2_lock_old_tuple;
        bool        cleared_all_frozen = false;
 
        /*
         * To prevent concurrent sessions from updating the tuple, we have to
         * temporarily mark it locked, while we release the page-level lock.
         *
         * To satisfy the rule that any xid potentially appearing in a buffer
         * written out to disk, we unfortunately have to WAL log this
         * temporary modification.  We can reuse xl_heap_lock for this
         * purpose.  If we crash/error before following through with the
         * actual update, xmax will be of an aborted transaction, allowing
         * other sessions to proceed.
         */
 
        /*
         * Compute xmax / infomask appropriate for locking the tuple. This has
         * to be done separately from the combo that's going to be used for
         * updating, because the potentially created multixact would otherwise
         * be wrong.
         */
        compute_new_xmax_infomask(HeapTupleHeaderGetRawXmax(oldtup.t_data),
                                  oldtup.t_data->t_infomask,
                                  oldtup.t_data->t_infomask2,
                                  xid, *lockmode, false,
                                  &xmax_lock_old_tuple, &infomask_lock_old_tuple,
                                  &infomask2_lock_old_tuple);
 
        Assert(HEAP_XMAX_IS_LOCKED_ONLY(infomask_lock_old_tuple));
 
        START_CRIT_SECTION();
 
        /* Clear obsolete visibility flags ... */
        oldtup.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
        oldtup.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
        HeapTupleClearHotUpdated(&oldtup);
        /* ... and store info about transaction updating this tuple */
        Assert(TransactionIdIsValid(xmax_lock_old_tuple));
        HeapTupleHeaderSetXmax(oldtup.t_data, xmax_lock_old_tuple);
        oldtup.t_data->t_infomask |= infomask_lock_old_tuple;
        oldtup.t_data->t_infomask2 |= infomask2_lock_old_tuple;
        HeapTupleHeaderSetCmax(oldtup.t_data, cid, iscombo);
 
        /* temporarily make it look not-updated, but locked */
        oldtup.t_data->t_ctid = oldtup.t_self;
 
        /*
         * Clear all-frozen bit on visibility map if needed. We could
         * immediately reset ALL_VISIBLE, but given that the WAL logging
         * overhead would be unchanged, that doesn't seem necessarily
         * worthwhile.
         */
        if (PageIsAllVisible(page) &&
            visibilitymap_clear(relation, block, vmbuffer,
                                VISIBILITYMAP_ALL_FROZEN))
            cleared_all_frozen = true;
 
        MarkBufferDirty(buffer);
 
        if (RelationNeedsWAL(relation))
        {
            xl_heap_lock xlrec;
            XLogRecPtr  recptr;
 
            XLogBeginInsert();
            XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 
            xlrec.offnum = ItemPointerGetOffsetNumber(&oldtup.t_self);
            xlrec.xmax = xmax_lock_old_tuple;
            xlrec.infobits_set = compute_infobits(oldtup.t_data->t_infomask,
                                                  oldtup.t_data->t_infomask2);
            xlrec.flags =
                cleared_all_frozen ? XLH_LOCK_ALL_FROZEN_CLEARED : 0;
            XLogRegisterData(&xlrec, SizeOfHeapLock);
            recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK);
            PageSetLSN(page, recptr);
        }
 
        END_CRIT_SECTION();
 
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
        /*
         * Let the toaster do its thing, if needed.
         *
         * Note: below this point, heaptup is the data we actually intend to
         * store into the relation; newtup is the caller's original untoasted
         * data.
         */
        if (need_toast)
        {
            /* Note we always use WAL and FSM during updates */
            heaptup = heap_toast_insert_or_update(relation, newtup, &oldtup, 0);
            newtupsize = MAXALIGN(heaptup->t_len);
        }
        else
            heaptup = newtup;
 
        /*
         * Now, do we need a new page for the tuple, or not?  This is a bit
         * tricky since someone else could have added tuples to the page while
         * we weren't looking.  We have to recheck the available space after
         * reacquiring the buffer lock.  But don't bother to do that if the
         * former amount of free space is still not enough; it's unlikely
         * there's more free now than before.
         *
         * What's more, if we need to get a new page, we will need to acquire
         * buffer locks on both old and new pages.  To avoid deadlock against
         * some other backend trying to get the same two locks in the other
         * order, we must be consistent about the order we get the locks in.
         * We use the rule "lock the lower-numbered page of the relation
         * first".  To implement this, we must do RelationGetBufferForTuple
         * while not holding the lock on the old page, and we must rely on it
         * to get the locks on both pages in the correct order.
         *
         * Another consideration is that we need visibility map page pin(s) if
         * we will have to clear the all-visible flag on either page.  If we
         * call RelationGetBufferForTuple, we rely on it to acquire any such
         * pins; but if we don't, we have to handle that here.  Hence we need
         * a loop.
         */
        for (;;)
        {
            if (newtupsize > pagefree)
            {
                /* It doesn't fit, must use RelationGetBufferForTuple. */
                newbuf = RelationGetBufferForTuple(relation, heaptup->t_len,
                                                   buffer, 0, NULL,
                                                   &vmbuffer_new, &vmbuffer,
                                                   0);
                /* We're all done. */
                break;
            }
            /* Acquire VM page pin if needed and we don't have it. */
            if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
                visibilitymap_pin(relation, block, &vmbuffer);
            /* Re-acquire the lock on the old tuple's page. */
            LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
            /* Re-check using the up-to-date free space */
            pagefree = PageGetHeapFreeSpace(page);
            if (newtupsize > pagefree ||
                (vmbuffer == InvalidBuffer && PageIsAllVisible(page)))
            {
                /*
                 * Rats, it doesn't fit anymore, or somebody just now set the
                 * all-visible flag.  We must now unlock and loop to avoid
                 * deadlock.  Fortunately, this path should seldom be taken.
                 */
                LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            }
            else
            {
                /* We're all done. */
                newbuf = buffer;
                break;
            }
        }
    }
    else
    {
        /* No TOAST work needed, and it'll fit on same page */
        newbuf = buffer;
        heaptup = newtup;
    }
 
    /*
     * We're about to do the actual update -- check for conflict first, to
     * avoid possibly having to roll back work we've just done.
     *
     * This is safe without a recheck as long as there is no possibility of
     * another process scanning the pages between this check and the update
     * being visible to the scan (i.e., exclusive buffer content lock(s) are
     * continuously held from this point until the tuple update is visible).
     *
     * For the new tuple the only check needed is at the relation level, but
     * since both tuples are in the same relation and the check for oldtup
     * will include checking the relation level, there is no benefit to a
     * separate check for the new tuple.
     */
    CheckForSerializableConflictIn(relation, &oldtup.t_self,
                                   BufferGetBlockNumber(buffer));
 
    /*
     * At this point newbuf and buffer are both pinned and locked, and newbuf
     * has enough space for the new tuple.  If they are the same buffer, only
     * one pin is held.
     */
 
    if (newbuf == buffer)
    {
        /*
         * Since the new tuple is going into the same page, we might be able
         * to do a HOT update.  Check if any of the index columns have been
         * changed.
         */
        if (!bms_overlap(modified_attrs, hot_attrs))
        {
            use_hot_update = true;
 
            /*
             * If none of the columns that are used in hot-blocking indexes
             * were updated, we can apply HOT, but we do still need to check
             * if we need to update the summarizing indexes, and update those
             * indexes if the columns were updated, or we may fail to detect
             * e.g. value bound changes in BRIN minmax indexes.
             */
            if (bms_overlap(modified_attrs, sum_attrs))
                summarized_update = true;
        }
    }
    else
    {
        /* Set a hint that the old page could use prune/defrag */
        PageSetFull(page);
    }
 
    /*
     * Compute replica identity tuple before entering the critical section so
     * we don't PANIC upon a memory allocation failure.
     * ExtractReplicaIdentity() will return NULL if nothing needs to be
     * logged.  Pass old key required as true only if the replica identity key
     * columns are modified or it has external data.
     */
    old_key_tuple = ExtractReplicaIdentity(relation, &oldtup,
                                           bms_overlap(modified_attrs, id_attrs) ||
                                           id_has_external,
                                           &old_key_copied);
 
    /* NO EREPORT(ERROR) from here till changes are logged */
    START_CRIT_SECTION();
 
    /*
     * If this transaction commits, the old tuple will become DEAD sooner or
     * later.  Set flag that this page is a candidate for pruning once our xid
     * falls below the OldestXmin horizon.  If the transaction finally aborts,
     * the subsequent page pruning will be a no-op and the hint will be
     * cleared.
     *
     * XXX Should we set hint on newbuf as well?  If the transaction aborts,
     * there would be a prunable tuple in the newbuf; but for now we choose
     * not to optimize for aborts.  Note that heap_xlog_update must be kept in
     * sync if this decision changes.
     */
    PageSetPrunable(page, xid);
 
    if (use_hot_update)
    {
        /* Mark the old tuple as HOT-updated */
        HeapTupleSetHotUpdated(&oldtup);
        /* And mark the new tuple as heap-only */
        HeapTupleSetHeapOnly(heaptup);
        /* Mark the caller's copy too, in case different from heaptup */
        HeapTupleSetHeapOnly(newtup);
    }
    else
    {
        /* Make sure tuples are correctly marked as not-HOT */
        HeapTupleClearHotUpdated(&oldtup);
        HeapTupleClearHeapOnly(heaptup);
        HeapTupleClearHeapOnly(newtup);
    }
 
    RelationPutHeapTuple(relation, newbuf, heaptup, false); /* insert new tuple */
 
 
    /* Clear obsolete visibility flags, possibly set by ourselves above... */
    oldtup.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
    oldtup.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    /* ... and store info about transaction updating this tuple */
    Assert(TransactionIdIsValid(xmax_old_tuple));
    HeapTupleHeaderSetXmax(oldtup.t_data, xmax_old_tuple);
    oldtup.t_data->t_infomask |= infomask_old_tuple;
    oldtup.t_data->t_infomask2 |= infomask2_old_tuple;
    HeapTupleHeaderSetCmax(oldtup.t_data, cid, iscombo);
 
    /* record address of new tuple in t_ctid of old one */
    oldtup.t_data->t_ctid = heaptup->t_self;
 
    /* clear PD_ALL_VISIBLE flags, reset all visibilitymap bits */
    if (PageIsAllVisible(BufferGetPage(buffer)))
    {
        all_visible_cleared = true;
        PageClearAllVisible(BufferGetPage(buffer));
        visibilitymap_clear(relation, BufferGetBlockNumber(buffer),
                            vmbuffer, VISIBILITYMAP_VALID_BITS);
    }
    if (newbuf != buffer && PageIsAllVisible(BufferGetPage(newbuf)))
    {
        all_visible_cleared_new = true;
        PageClearAllVisible(BufferGetPage(newbuf));
        visibilitymap_clear(relation, BufferGetBlockNumber(newbuf),
                            vmbuffer_new, VISIBILITYMAP_VALID_BITS);
    }
 
    if (newbuf != buffer)
        MarkBufferDirty(newbuf);
    MarkBufferDirty(buffer);
 
    /* XLOG stuff */
    if (RelationNeedsWAL(relation))
    {
        XLogRecPtr  recptr;
 
        /*
         * For logical decoding we need combo CIDs to properly decode the
         * catalog.
         */
        if (RelationIsAccessibleInLogicalDecoding(relation))
        {
            log_heap_new_cid(relation, &oldtup);
            log_heap_new_cid(relation, heaptup);
        }
 
        recptr = log_heap_update(relation, buffer,
                                 newbuf, &oldtup, heaptup,
                                 old_key_tuple,
                                 all_visible_cleared,
                                 all_visible_cleared_new);
        if (newbuf != buffer)
        {
            PageSetLSN(BufferGetPage(newbuf), recptr);
        }
        PageSetLSN(BufferGetPage(buffer), recptr);
    }
 
    END_CRIT_SECTION();
 
    if (newbuf != buffer)
        LockBuffer(newbuf, BUFFER_LOCK_UNLOCK);
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
    /*
     * Mark old tuple for invalidation from system caches at next command
     * boundary, and mark the new tuple for invalidation in case we abort. We
     * have to do this before releasing the buffer because oldtup is in the
     * buffer.  (heaptup is all in local memory, but it's necessary to process
     * both tuple versions in one call to inval.c so we can avoid redundant
     * sinval messages.)
     */
    CacheInvalidateHeapTuple(relation, &oldtup, heaptup);
 
    /* Now we can release the buffer(s) */
    if (newbuf != buffer)
        ReleaseBuffer(newbuf);
    ReleaseBuffer(buffer);
    if (BufferIsValid(vmbuffer_new))
        ReleaseBuffer(vmbuffer_new);
    if (BufferIsValid(vmbuffer))
        ReleaseBuffer(vmbuffer);
 
    /*
     * Release the lmgr tuple lock, if we had it.
     */
    if (have_tuple_lock)
        UnlockTupleTuplock(relation, &(oldtup.t_self), *lockmode);
 
    pgstat_count_heap_update(relation, use_hot_update, newbuf != buffer);
 
    /*
     * If heaptup is a private copy, release it.  Don't forget to copy t_self
     * back to the caller's image, too.
     */
    if (heaptup != newtup)
    {
        newtup->t_self = heaptup->t_self;
        heap_freetuple(heaptup);
    }
 
    /*
     * If it is a HOT update, the update may still need to update summarized
     * indexes, lest we fail to update those summaries and get incorrect
     * results (for example, minmax bounds of the block may change with this
     * update).
     */
    if (use_hot_update)
    {
        if (summarized_update)
            *update_indexes = TU_Summarizing;
        else
            *update_indexes = TU_None;
    }
    else
        *update_indexes = TU_All;
 
    if (old_key_tuple != NULL && old_key_copied)
        heap_freetuple(old_key_tuple);
 
    bms_free(hot_attrs);
    bms_free(sum_attrs);
    bms_free(key_attrs);
    bms_free(id_attrs);
    bms_free(modified_attrs);
    bms_free(interesting_attrs);
 
    return TM_Ok;
}

References Assert(), AssertHasSnapshotForToast(), bms_add_members(), bms_free(), bms_overlap(), BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), CacheInvalidateHeapTuple(), CheckForSerializableConflictIn(), TM_FailureData::cmax, compute_infobits(), compute_new_xmax_infomask(), TM_FailureData::ctid, DoesMultiXactIdConflict(), END_CRIT_SECTION, ereport, errcode(), errmsg(), ERROR, ExtractReplicaIdentity(), xl_heap_lock::flags, GetCurrentTransactionId(), GetMultiXactIdHintBits(), HEAP2_XACT_MASK, heap_acquire_tuplock(), heap_freetuple(), HEAP_LOCKED_UPGRADED(), HEAP_MOVED, heap_toast_insert_or_update(), HEAP_UPDATED, HEAP_XACT_MASK, HEAP_XMAX_BITS, HEAP_XMAX_INVALID, HEAP_XMAX_IS_KEYSHR_LOCKED(), HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HEAP_XMAX_KEYSHR_LOCK, HEAP_XMAX_LOCK_ONLY, HeapDetermineColumnsInfo(), HeapTupleClearHeapOnly(), HeapTupleClearHotUpdated(), HeapTupleGetUpdateXid(), HeapTupleHasExternal(), HeapTupleHeaderAdjustCmax(), HeapTupleHeaderGetCmax(), HeapTupleHeaderGetNatts, HeapTupleHeaderGetRawXmax(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderSetCmax(), HeapTupleHeaderSetCmin(), HeapTupleHeaderSetXmax(), HeapTupleHeaderSetXmin(), HeapTupleSatisfiesUpdate(), HeapTupleSatisfiesVisibility(), HeapTupleSetHeapOnly(), HeapTupleSetHotUpdated(), INDEX_ATTR_BITMAP_HOT_BLOCKING, INDEX_ATTR_BITMAP_IDENTITY_KEY, INDEX_ATTR_BITMAP_KEY, INDEX_ATTR_BITMAP_SUMMARIZED, xl_heap_lock::infobits_set, INJECTION_POINT, InvalidBuffer, InvalidCommandId, InvalidSnapshot, InvalidTransactionId, IsInParallelMode(), ItemIdGetLength, ItemIdIsNormal, ItemPointerEquals(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), ItemPointerIsValid(), LockBuffer(), LockTupleExclusive, LockTupleNoKeyExclusive, LockWaitBlock, log_heap_new_cid(), log_heap_update(), MarkBufferDirty(), MAXALIGN, MultiXactIdSetOldestMember(), MultiXactIdWait(), MultiXactStatusNoKeyUpdate, MultiXactStatusUpdate, xl_heap_lock::offnum, PageClearAllVisible(), PageGetHeapFreeSpace(), PageGetItem(), PageGetItemId(), PageIsAllVisible(), PageSetFull(), PageSetLSN(), PageSetPrunable, pgstat_count_heap_update(), RelationData::rd_rel, ReadBuffer(), REGBUF_STANDARD, RelationGetBufferForTuple(), RelationGetIndexAttrBitmap(), RelationGetNumberOfAttributes, RelationGetRelid, RelationIsAccessibleInLogicalDecoding, RelationNeedsWAL, RelationPutHeapTuple(), RelationSupportsSysCache(), ReleaseBuffer(), SizeOfHeapLock, START_CRIT_SECTION, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TM_BeingModified, TM_Deleted, TM_Invisible, TM_Ok, TM_SelfModified, TM_Updated, TOAST_TUPLE_THRESHOLD, TransactionIdDidAbort(), TransactionIdEquals, TransactionIdIsCurrentTransactionId(), TransactionIdIsValid, TU_All, TU_None, TU_Summarizing, UnlockReleaseBuffer(), UnlockTupleTuplock, UpdateXmaxHintBits(), VISIBILITYMAP_ALL_FROZEN, visibilitymap_clear(), visibilitymap_pin(), VISIBILITYMAP_VALID_BITS, XactLockTableWait(), XLH_LOCK_ALL_FROZEN_CLEARED, XLOG_HEAP_LOCK, XLogBeginInsert(), XLogInsert(), XLogRegisterBuffer(), XLogRegisterData(), XLTW_Update, xl_heap_lock::xmax, TM_FailureData::xmax, and xmax_infomask_changed().

Referenced by heapam_tuple_update(), and simple_heap_update().

HeapCheckForSerializableConflictOut()

void HeapCheckForSerializableConflictOut	(	bool	visible,
		Relation	relation,
		HeapTuple	tuple,
		Buffer	buffer,
		Snapshot	snapshot
	)

Definition at line 9245 of file heapam.c.

{
    TransactionId xid;
    HTSV_Result htsvResult;
 
    if (!CheckForSerializableConflictOutNeeded(relation, snapshot))
        return;
 
    /*
     * Check to see whether the tuple has been written to by a concurrent
     * transaction, either to create it not visible to us, or to delete it
     * while it is visible to us.  The "visible" bool indicates whether the
     * tuple is visible to us, while HeapTupleSatisfiesVacuum checks what else
     * is going on with it.
     *
     * In the event of a concurrently inserted tuple that also happens to have
     * been concurrently updated (by a separate transaction), the xmin of the
     * tuple will be used -- not the updater's xid.
     */
    htsvResult = HeapTupleSatisfiesVacuum(tuple, TransactionXmin, buffer);
    switch (htsvResult)
    {
        case HEAPTUPLE_LIVE:
            if (visible)
                return;
            xid = HeapTupleHeaderGetXmin(tuple->t_data);
            break;
        case HEAPTUPLE_RECENTLY_DEAD:
        case HEAPTUPLE_DELETE_IN_PROGRESS:
            if (visible)
                xid = HeapTupleHeaderGetUpdateXid(tuple->t_data);
            else
                xid = HeapTupleHeaderGetXmin(tuple->t_data);
 
            if (TransactionIdPrecedes(xid, TransactionXmin))
            {
                /* This is like the HEAPTUPLE_DEAD case */
                Assert(!visible);
                return;
            }
            break;
        case HEAPTUPLE_INSERT_IN_PROGRESS:
            xid = HeapTupleHeaderGetXmin(tuple->t_data);
            break;
        case HEAPTUPLE_DEAD:
            Assert(!visible);
            return;
        default:
 
            /*
             * The only way to get to this default clause is if a new value is
             * added to the enum type without adding it to this switch
             * statement.  That's a bug, so elog.
             */
            elog(ERROR, "unrecognized return value from HeapTupleSatisfiesVacuum: %u", htsvResult);
 
            /*
             * In spite of having all enum values covered and calling elog on
             * this default, some compilers think this is a code path which
             * allows xid to be used below without initialization. Silence
             * that warning.
             */
            xid = InvalidTransactionId;
    }
 
    Assert(TransactionIdIsValid(xid));
    Assert(TransactionIdFollowsOrEquals(xid, TransactionXmin));
 
    /*
     * Find top level xid.  Bail out if xid is too early to be a conflict, or
     * if it's our own xid.
     */
    if (TransactionIdEquals(xid, GetTopTransactionIdIfAny()))
        return;
    xid = SubTransGetTopmostTransaction(xid);
    if (TransactionIdPrecedes(xid, TransactionXmin))
        return;
 
    CheckForSerializableConflictOut(relation, xid, snapshot);
}

References Assert(), CheckForSerializableConflictOut(), CheckForSerializableConflictOutNeeded(), elog, ERROR, GetTopTransactionIdIfAny(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleSatisfiesVacuum(), InvalidTransactionId, SubTransGetTopmostTransaction(), HeapTupleData::t_data, TransactionIdEquals, TransactionIdFollowsOrEquals(), TransactionIdIsValid, TransactionIdPrecedes(), and TransactionXmin.

Referenced by BitmapHeapScanNextBlock(), heap_fetch(), heap_get_latest_tid(), heap_hot_search_buffer(), heapam_scan_sample_next_tuple(), heapgettup(), and page_collect_tuples().

HeapDetermineColumnsInfo()

static Bitmapset * HeapDetermineColumnsInfo ( Relation  relation, Bitmapset *  interesting_cols, Bitmapset *  external_cols, HeapTuple  oldtup, HeapTuple  newtup, bool *  has_external  )

static

Definition at line 4401 of file heapam.c.

{
    int         attidx;
    Bitmapset  *modified = NULL;
    TupleDesc   tupdesc = RelationGetDescr(relation);
 
    attidx = -1;
    while ((attidx = bms_next_member(interesting_cols, attidx)) >= 0)
    {
        /* attidx is zero-based, attrnum is the normal attribute number */
        AttrNumber  attrnum = attidx + FirstLowInvalidHeapAttributeNumber;
        Datum       value1,
                    value2;
        bool        isnull1,
                    isnull2;
 
        /*
         * If it's a whole-tuple reference, say "not equal".  It's not really
         * worth supporting this case, since it could only succeed after a
         * no-op update, which is hardly a case worth optimizing for.
         */
        if (attrnum == 0)
        {
            modified = bms_add_member(modified, attidx);
            continue;
        }
 
        /*
         * Likewise, automatically say "not equal" for any system attribute
         * other than tableOID; we cannot expect these to be consistent in a
         * HOT chain, or even to be set correctly yet in the new tuple.
         */
        if (attrnum < 0)
        {
            if (attrnum != TableOidAttributeNumber)
            {
                modified = bms_add_member(modified, attidx);
                continue;
            }
        }
 
        /*
         * Extract the corresponding values.  XXX this is pretty inefficient
         * if there are many indexed columns.  Should we do a single
         * heap_deform_tuple call on each tuple, instead?   But that doesn't
         * work for system columns ...
         */
        value1 = heap_getattr(oldtup, attrnum, tupdesc, &isnull1);
        value2 = heap_getattr(newtup, attrnum, tupdesc, &isnull2);
 
        if (!heap_attr_equals(tupdesc, attrnum, value1,
                              value2, isnull1, isnull2))
        {
            modified = bms_add_member(modified, attidx);
            continue;
        }
 
        /*
         * No need to check attributes that can't be stored externally. Note
         * that system attributes can't be stored externally.
         */
        if (attrnum < 0 || isnull1 ||
            TupleDescCompactAttr(tupdesc, attrnum - 1)->attlen != -1)
            continue;
 
        /*
         * Check if the old tuple's attribute is stored externally and is a
         * member of external_cols.
         */
        if (VARATT_IS_EXTERNAL((struct varlena *) DatumGetPointer(value1)) &&
            bms_is_member(attidx, external_cols))
            *has_external = true;
    }
 
    return modified;
}

References attlen, bms_add_member(), bms_is_member(), bms_next_member(), DatumGetPointer(), FirstLowInvalidHeapAttributeNumber, heap_attr_equals(), heap_getattr(), RelationGetDescr, TableOidAttributeNumber, TupleDescCompactAttr(), and VARATT_IS_EXTERNAL().

Referenced by heap_update().

heapgettup()

static void heapgettup ( HeapScanDesc  scan, ScanDirection  dir, int  nkeys, ScanKey  key  )

static

Definition at line 896 of file heapam.c.

{
    HeapTuple   tuple = &(scan->rs_ctup);
    Page        page;
    OffsetNumber lineoff;
    int         linesleft;
 
    if (likely(scan->rs_inited))
    {
        /* continue from previously returned page/tuple */
        LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
        page = heapgettup_continue_page(scan, dir, &linesleft, &lineoff);
        goto continue_page;
    }
 
    /*
     * advance the scan until we find a qualifying tuple or run out of stuff
     * to scan
     */
    while (true)
    {
        heap_fetch_next_buffer(scan, dir);
 
        /* did we run out of blocks to scan? */
        if (!BufferIsValid(scan->rs_cbuf))
            break;
 
        Assert(BufferGetBlockNumber(scan->rs_cbuf) == scan->rs_cblock);
 
        LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
        page = heapgettup_start_page(scan, dir, &linesleft, &lineoff);
continue_page:
 
        /*
         * Only continue scanning the page while we have lines left.
         *
         * Note that this protects us from accessing line pointers past
         * PageGetMaxOffsetNumber(); both for forward scans when we resume the
         * table scan, and for when we start scanning a new page.
         */
        for (; linesleft > 0; linesleft--, lineoff += dir)
        {
            bool        visible;
            ItemId      lpp = PageGetItemId(page, lineoff);
 
            if (!ItemIdIsNormal(lpp))
                continue;
 
            tuple->t_data = (HeapTupleHeader) PageGetItem(page, lpp);
            tuple->t_len = ItemIdGetLength(lpp);
            ItemPointerSet(&(tuple->t_self), scan->rs_cblock, lineoff);
 
            visible = HeapTupleSatisfiesVisibility(tuple,
                                                   scan->rs_base.rs_snapshot,
                                                   scan->rs_cbuf);
 
            HeapCheckForSerializableConflictOut(visible, scan->rs_base.rs_rd,
                                                tuple, scan->rs_cbuf,
                                                scan->rs_base.rs_snapshot);
 
            /* skip tuples not visible to this snapshot */
            if (!visible)
                continue;
 
            /* skip any tuples that don't match the scan key */
            if (key != NULL &&
                !HeapKeyTest(tuple, RelationGetDescr(scan->rs_base.rs_rd),
                             nkeys, key))
                continue;
 
            LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
            scan->rs_coffset = lineoff;
            return;
        }
 
        /*
         * if we get here, it means we've exhausted the items on this page and
         * it's time to move to the next.
         */
        LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
    }
 
    /* end of scan */
    if (BufferIsValid(scan->rs_cbuf))
        ReleaseBuffer(scan->rs_cbuf);
 
    scan->rs_cbuf = InvalidBuffer;
    scan->rs_cblock = InvalidBlockNumber;
    scan->rs_prefetch_block = InvalidBlockNumber;
    tuple->t_data = NULL;
    scan->rs_inited = false;
}

References Assert(), BUFFER_LOCK_SHARE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferIsValid(), heap_fetch_next_buffer(), HeapCheckForSerializableConflictOut(), heapgettup_continue_page(), heapgettup_start_page(), HeapKeyTest(), HeapTupleSatisfiesVisibility(), InvalidBlockNumber, InvalidBuffer, ItemIdGetLength, ItemIdIsNormal, ItemPointerSet(), sort-test::key, likely, LockBuffer(), PageGetItem(), PageGetItemId(), RelationGetDescr, ReleaseBuffer(), HeapScanDescData::rs_base, HeapScanDescData::rs_cblock, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_coffset, HeapScanDescData::rs_ctup, HeapScanDescData::rs_inited, HeapScanDescData::rs_prefetch_block, TableScanDescData::rs_rd, TableScanDescData::rs_snapshot, HeapTupleData::t_data, HeapTupleData::t_len, and HeapTupleData::t_self.

Referenced by heap_getnext(), heap_getnextslot(), and heap_getnextslot_tidrange().

heapgettup_advance_block()

static BlockNumber heapgettup_advance_block ( HeapScanDesc  scan, BlockNumber  block, ScanDirection  dir  )

inlinestatic

Definition at line 812 of file heapam.c.

{
    Assert(scan->rs_base.rs_parallel == NULL);
 
    if (likely(ScanDirectionIsForward(dir)))
    {
        block++;
 
        /* wrap back to the start of the heap */
        if (block >= scan->rs_nblocks)
            block = 0;
 
        /*
         * Report our new scan position for synchronization purposes. We don't
         * do that when moving backwards, however. That would just mess up any
         * other forward-moving scanners.
         *
         * Note: we do this before checking for end of scan so that the final
         * state of the position hint is back at the start of the rel.  That's
         * not strictly necessary, but otherwise when you run the same query
         * multiple times the starting position would shift a little bit
         * backwards on every invocation, which is confusing. We don't
         * guarantee any specific ordering in general, though.
         */
        if (scan->rs_base.rs_flags & SO_ALLOW_SYNC)
            ss_report_location(scan->rs_base.rs_rd, block);
 
        /* we're done if we're back at where we started */
        if (block == scan->rs_startblock)
            return InvalidBlockNumber;
 
        /* check if the limit imposed by heap_setscanlimits() is met */
        if (scan->rs_numblocks != InvalidBlockNumber)
        {
            if (--scan->rs_numblocks == 0)
                return InvalidBlockNumber;
        }
 
        return block;
    }
    else
    {
        /* we're done if the last block is the start position */
        if (block == scan->rs_startblock)
            return InvalidBlockNumber;
 
        /* check if the limit imposed by heap_setscanlimits() is met */
        if (scan->rs_numblocks != InvalidBlockNumber)
        {
            if (--scan->rs_numblocks == 0)
                return InvalidBlockNumber;
        }
 
        /* wrap to the end of the heap when the last page was page 0 */
        if (block == 0)
            block = scan->rs_nblocks;
 
        block--;
 
        return block;
    }
}

References Assert(), InvalidBlockNumber, likely, HeapScanDescData::rs_base, TableScanDescData::rs_flags, HeapScanDescData::rs_nblocks, HeapScanDescData::rs_numblocks, TableScanDescData::rs_parallel, TableScanDescData::rs_rd, HeapScanDescData::rs_startblock, ScanDirectionIsForward, SO_ALLOW_SYNC, and ss_report_location().

Referenced by heap_scan_stream_read_next_serial().

heapgettup_continue_page()

static Page heapgettup_continue_page ( HeapScanDesc  scan, ScanDirection  dir, int *  linesleft, OffsetNumber *  lineoff  )

inlinestatic

Definition at line 766 of file heapam.c.

{
    Page        page;
 
    Assert(scan->rs_inited);
    Assert(BufferIsValid(scan->rs_cbuf));
 
    /* Caller is responsible for ensuring buffer is locked if needed */
    page = BufferGetPage(scan->rs_cbuf);
 
    if (ScanDirectionIsForward(dir))
    {
        *lineoff = OffsetNumberNext(scan->rs_coffset);
        *linesleft = PageGetMaxOffsetNumber(page) - (*lineoff) + 1;
    }
    else
    {
        /*
         * The previous returned tuple may have been vacuumed since the
         * previous scan when we use a non-MVCC snapshot, so we must
         * re-establish the lineoff <= PageGetMaxOffsetNumber(page) invariant
         */
        *lineoff = Min(PageGetMaxOffsetNumber(page), OffsetNumberPrev(scan->rs_coffset));
        *linesleft = *lineoff;
    }
 
    /* lineoff now references the physically previous or next tid */
    return page;
}

References Assert(), BufferGetPage(), BufferIsValid(), Min, OffsetNumberNext, OffsetNumberPrev, PageGetMaxOffsetNumber(), HeapScanDescData::rs_cbuf, HeapScanDescData::rs_coffset, HeapScanDescData::rs_inited, and ScanDirectionIsForward.

Referenced by heapgettup().

heapgettup_initial_block()

static pg_noinline BlockNumber heapgettup_initial_block ( HeapScanDesc  scan, ScanDirection  dir  )

static

Definition at line 688 of file heapam.c.

{
    Assert(!scan->rs_inited);
    Assert(scan->rs_base.rs_parallel == NULL);
 
    /* When there are no pages to scan, return InvalidBlockNumber */
    if (scan->rs_nblocks == 0 || scan->rs_numblocks == 0)
        return InvalidBlockNumber;
 
    if (ScanDirectionIsForward(dir))
    {
        return scan->rs_startblock;
    }
    else
    {
        /*
         * Disable reporting to syncscan logic in a backwards scan; it's not
         * very likely anyone else is doing the same thing at the same time,
         * and much more likely that we'll just bollix things for forward
         * scanners.
         */
        scan->rs_base.rs_flags &= ~SO_ALLOW_SYNC;
 
        /*
         * Start from last page of the scan.  Ensure we take into account
         * rs_numblocks if it's been adjusted by heap_setscanlimits().
         */
        if (scan->rs_numblocks != InvalidBlockNumber)
            return (scan->rs_startblock + scan->rs_numblocks - 1) % scan->rs_nblocks;
 
        if (scan->rs_startblock > 0)
            return scan->rs_startblock - 1;
 
        return scan->rs_nblocks - 1;
    }
}

References Assert(), InvalidBlockNumber, HeapScanDescData::rs_base, TableScanDescData::rs_flags, HeapScanDescData::rs_inited, HeapScanDescData::rs_nblocks, HeapScanDescData::rs_numblocks, TableScanDescData::rs_parallel, HeapScanDescData::rs_startblock, and ScanDirectionIsForward.

Referenced by heap_scan_stream_read_next_serial().

heapgettup_pagemode()

static void heapgettup_pagemode ( HeapScanDesc  scan, ScanDirection  dir, int  nkeys, ScanKey  key  )

static

Definition at line 1006 of file heapam.c.

{
    HeapTuple   tuple = &(scan->rs_ctup);
    Page        page;
    uint32      lineindex;
    uint32      linesleft;
 
    if (likely(scan->rs_inited))
    {
        /* continue from previously returned page/tuple */
        page = BufferGetPage(scan->rs_cbuf);
 
        lineindex = scan->rs_cindex + dir;
        if (ScanDirectionIsForward(dir))
            linesleft = scan->rs_ntuples - lineindex;
        else
            linesleft = scan->rs_cindex;
        /* lineindex now references the next or previous visible tid */
 
        goto continue_page;
    }
 
    /*
     * advance the scan until we find a qualifying tuple or run out of stuff
     * to scan
     */
    while (true)
    {
        heap_fetch_next_buffer(scan, dir);
 
        /* did we run out of blocks to scan? */
        if (!BufferIsValid(scan->rs_cbuf))
            break;
 
        Assert(BufferGetBlockNumber(scan->rs_cbuf) == scan->rs_cblock);
 
        /* prune the page and determine visible tuple offsets */
        heap_prepare_pagescan((TableScanDesc) scan);
        page = BufferGetPage(scan->rs_cbuf);
        linesleft = scan->rs_ntuples;
        lineindex = ScanDirectionIsForward(dir) ? 0 : linesleft - 1;
 
        /* block is the same for all tuples, set it once outside the loop */
        ItemPointerSetBlockNumber(&tuple->t_self, scan->rs_cblock);
 
        /* lineindex now references the next or previous visible tid */
continue_page:
 
        for (; linesleft > 0; linesleft--, lineindex += dir)
        {
            ItemId      lpp;
            OffsetNumber lineoff;
 
            Assert(lineindex <= scan->rs_ntuples);
            lineoff = scan->rs_vistuples[lineindex];
            lpp = PageGetItemId(page, lineoff);
            Assert(ItemIdIsNormal(lpp));
 
            tuple->t_data = (HeapTupleHeader) PageGetItem(page, lpp);
            tuple->t_len = ItemIdGetLength(lpp);
            ItemPointerSetOffsetNumber(&tuple->t_self, lineoff);
 
            /* skip any tuples that don't match the scan key */
            if (key != NULL &&
                !HeapKeyTest(tuple, RelationGetDescr(scan->rs_base.rs_rd),
                             nkeys, key))
                continue;
 
            scan->rs_cindex = lineindex;
            return;
        }
    }
 
    /* end of scan */
    if (BufferIsValid(scan->rs_cbuf))
        ReleaseBuffer(scan->rs_cbuf);
    scan->rs_cbuf = InvalidBuffer;
    scan->rs_cblock = InvalidBlockNumber;
    scan->rs_prefetch_block = InvalidBlockNumber;
    tuple->t_data = NULL;
    scan->rs_inited = false;
}

References Assert(), BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), heap_fetch_next_buffer(), heap_prepare_pagescan(), HeapKeyTest(), InvalidBlockNumber, InvalidBuffer, ItemIdGetLength, ItemIdIsNormal, ItemPointerSetBlockNumber(), ItemPointerSetOffsetNumber(), sort-test::key, likely, PageGetItem(), PageGetItemId(), RelationGetDescr, ReleaseBuffer(), HeapScanDescData::rs_cblock, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_cindex, HeapScanDescData::rs_ctup, HeapScanDescData::rs_inited, HeapScanDescData::rs_ntuples, HeapScanDescData::rs_prefetch_block, TableScanDescData::rs_rd, ScanDirectionIsForward, HeapTupleData::t_data, HeapTupleData::t_len, and HeapTupleData::t_self.

Referenced by heap_getnext(), heap_getnextslot(), and heap_getnextslot_tidrange().

heapgettup_start_page()

static Page heapgettup_start_page ( HeapScanDesc  scan, ScanDirection  dir, int *  linesleft, OffsetNumber *  lineoff  )

static

Definition at line 735 of file heapam.c.

{
    Page        page;
 
    Assert(scan->rs_inited);
    Assert(BufferIsValid(scan->rs_cbuf));
 
    /* Caller is responsible for ensuring buffer is locked if needed */
    page = BufferGetPage(scan->rs_cbuf);
 
    *linesleft = PageGetMaxOffsetNumber(page) - FirstOffsetNumber + 1;
 
    if (ScanDirectionIsForward(dir))
        *lineoff = FirstOffsetNumber;
    else
        *lineoff = (OffsetNumber) (*linesleft);
 
    /* lineoff now references the physically previous or next tid */
    return page;
}

References Assert(), BufferGetPage(), BufferIsValid(), FirstOffsetNumber, PageGetMaxOffsetNumber(), HeapScanDescData::rs_cbuf, HeapScanDescData::rs_inited, and ScanDirectionIsForward.

Referenced by heapgettup().

HeapTupleGetUpdateXid()

TransactionId HeapTupleGetUpdateXid

(

const HeapTupleHeaderData *

tup

)

Definition at line 7579 of file heapam.c.

{
    return MultiXactIdGetUpdateXid(HeapTupleHeaderGetRawXmax(tup),
                                   tup->t_infomask);
}

References HeapTupleHeaderGetRawXmax(), MultiXactIdGetUpdateXid(), and HeapTupleHeaderData::t_infomask.

Referenced by check_tuple_visibility(), heap_update(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderIsOnlyLocked(), HeapTupleSatisfiesDirty(), HeapTupleSatisfiesHistoricMVCC(), HeapTupleSatisfiesMVCC(), HeapTupleSatisfiesSelf(), HeapTupleSatisfiesUpdate(), and HeapTupleSatisfiesVacuumHorizon().

HeapTupleHeaderAdvanceConflictHorizon()

void HeapTupleHeaderAdvanceConflictHorizon	(	HeapTupleHeader	tuple,
		TransactionId *	snapshotConflictHorizon
	)

Definition at line 7973 of file heapam.c.

{
    TransactionId xmin = HeapTupleHeaderGetXmin(tuple);
    TransactionId xmax = HeapTupleHeaderGetUpdateXid(tuple);
    TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
 
    if (tuple->t_infomask & HEAP_MOVED)
    {
        if (TransactionIdPrecedes(*snapshotConflictHorizon, xvac))
            *snapshotConflictHorizon = xvac;
    }
 
    /*
     * Ignore tuples inserted by an aborted transaction or if the tuple was
     * updated/deleted by the inserting transaction.
     *
     * Look for a committed hint bit, or if no xmin bit is set, check clog.
     */
    if (HeapTupleHeaderXminCommitted(tuple) ||
        (!HeapTupleHeaderXminInvalid(tuple) && TransactionIdDidCommit(xmin)))
    {
        if (xmax != xmin &&
            TransactionIdFollows(xmax, *snapshotConflictHorizon))
            *snapshotConflictHorizon = xmax;
    }
}

References HEAP_MOVED, HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderGetXvac(), HeapTupleHeaderXminCommitted(), HeapTupleHeaderXminInvalid(), HeapTupleHeaderData::t_infomask, TransactionIdDidCommit(), TransactionIdFollows(), and TransactionIdPrecedes().

Referenced by heap_index_delete_tuples(), heap_page_prune_and_freeze(), and heap_prune_chain().

index_delete_check_htid()

static void index_delete_check_htid ( TM_IndexDeleteOp *  delstate, Page  page, OffsetNumber  maxoff, ItemPointer  htid, TM_IndexStatus *  istatus  )

inlinestatic

Definition at line 8058 of file heapam.c.

{
    OffsetNumber indexpagehoffnum = ItemPointerGetOffsetNumber(htid);
    ItemId      iid;
 
    Assert(OffsetNumberIsValid(istatus->idxoffnum));
 
    if (unlikely(indexpagehoffnum > maxoff))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("heap tid from index tuple (%u,%u) points past end of heap page line pointer array at offset %u of block %u in index \"%s\"",
                                 ItemPointerGetBlockNumber(htid),
                                 indexpagehoffnum,
                                 istatus->idxoffnum, delstate->iblknum,
                                 RelationGetRelationName(delstate->irel))));
 
    iid = PageGetItemId(page, indexpagehoffnum);
    if (unlikely(!ItemIdIsUsed(iid)))
        ereport(ERROR,
                (errcode(ERRCODE_INDEX_CORRUPTED),
                 errmsg_internal("heap tid from index tuple (%u,%u) points to unused heap page item at offset %u of block %u in index \"%s\"",
                                 ItemPointerGetBlockNumber(htid),
                                 indexpagehoffnum,
                                 istatus->idxoffnum, delstate->iblknum,
                                 RelationGetRelationName(delstate->irel))));
 
    if (ItemIdHasStorage(iid))
    {
        HeapTupleHeader htup;
 
        Assert(ItemIdIsNormal(iid));
        htup = (HeapTupleHeader) PageGetItem(page, iid);
 
        if (unlikely(HeapTupleHeaderIsHeapOnly(htup)))
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("heap tid from index tuple (%u,%u) points to heap-only tuple at offset %u of block %u in index \"%s\"",
                                     ItemPointerGetBlockNumber(htid),
                                     indexpagehoffnum,
                                     istatus->idxoffnum, delstate->iblknum,
                                     RelationGetRelationName(delstate->irel))));
    }
}

References Assert(), ereport, errcode(), errmsg_internal(), ERROR, HeapTupleHeaderIsHeapOnly(), TM_IndexDeleteOp::iblknum, TM_IndexStatus::idxoffnum, TM_IndexDeleteOp::irel, ItemIdHasStorage, ItemIdIsNormal, ItemIdIsUsed, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), OffsetNumberIsValid, PageGetItem(), PageGetItemId(), RelationGetRelationName, and unlikely.

Referenced by heap_index_delete_tuples().

index_delete_sort()

static void index_delete_sort ( TM_IndexDeleteOp *  delstate )

static

Definition at line 8463 of file heapam.c.

{
    TM_IndexDelete *deltids = delstate->deltids;
    int         ndeltids = delstate->ndeltids;
 
    /*
     * Shellsort gap sequence (taken from Sedgewick-Incerpi paper).
     *
     * This implementation is fast with array sizes up to ~4500.  This covers
     * all supported BLCKSZ values.
     */
    const int   gaps[9] = {1968, 861, 336, 112, 48, 21, 7, 3, 1};
 
    /* Think carefully before changing anything here -- keep swaps cheap */
    StaticAssertDecl(sizeof(TM_IndexDelete) <= 8,
                     "element size exceeds 8 bytes");
 
    for (int g = 0; g < lengthof(gaps); g++)
    {
        for (int hi = gaps[g], i = hi; i < ndeltids; i++)
        {
            TM_IndexDelete d = deltids[i];
            int         j = i;
 
            while (j >= hi && index_delete_sort_cmp(&deltids[j - hi], &d) >= 0)
            {
                deltids[j] = deltids[j - hi];
                j -= hi;
            }
            deltids[j] = d;
        }
    }
}

References TM_IndexDeleteOp::deltids, i, index_delete_sort_cmp(), j, lengthof, TM_IndexDeleteOp::ndeltids, and StaticAssertDecl.

Referenced by heap_index_delete_tuples().

index_delete_sort_cmp()

static int index_delete_sort_cmp ( TM_IndexDelete *  deltid1, TM_IndexDelete *  deltid2  )

inlinestatic

Definition at line 8427 of file heapam.c.

{
    ItemPointer tid1 = &deltid1->tid;
    ItemPointer tid2 = &deltid2->tid;
 
    {
        BlockNumber blk1 = ItemPointerGetBlockNumber(tid1);
        BlockNumber blk2 = ItemPointerGetBlockNumber(tid2);
 
        if (blk1 != blk2)
            return (blk1 < blk2) ? -1 : 1;
    }
    {
        OffsetNumber pos1 = ItemPointerGetOffsetNumber(tid1);
        OffsetNumber pos2 = ItemPointerGetOffsetNumber(tid2);
 
        if (pos1 != pos2)
            return (pos1 < pos2) ? -1 : 1;
    }
 
    Assert(false);
 
    return 0;
}

References Assert(), ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), and TM_IndexDelete::tid.

Referenced by index_delete_sort().

initscan()

static void initscan ( HeapScanDesc  scan, ScanKey  key, bool  keep_startblock  )

static

Definition at line 350 of file heapam.c.

{
    ParallelBlockTableScanDesc bpscan = NULL;
    bool        allow_strat;
    bool        allow_sync;
 
    /*
     * Determine the number of blocks we have to scan.
     *
     * It is sufficient to do this once at scan start, since any tuples added
     * while the scan is in progress will be invisible to my snapshot anyway.
     * (That is not true when using a non-MVCC snapshot.  However, we couldn't
     * guarantee to return tuples added after scan start anyway, since they
     * might go into pages we already scanned.  To guarantee consistent
     * results for a non-MVCC snapshot, the caller must hold some higher-level
     * lock that ensures the interesting tuple(s) won't change.)
     */
    if (scan->rs_base.rs_parallel != NULL)
    {
        bpscan = (ParallelBlockTableScanDesc) scan->rs_base.rs_parallel;
        scan->rs_nblocks = bpscan->phs_nblocks;
    }
    else
        scan->rs_nblocks = RelationGetNumberOfBlocks(scan->rs_base.rs_rd);
 
    /*
     * If the table is large relative to NBuffers, use a bulk-read access
     * strategy and enable synchronized scanning (see syncscan.c).  Although
     * the thresholds for these features could be different, we make them the
     * same so that there are only two behaviors to tune rather than four.
     * (However, some callers need to be able to disable one or both of these
     * behaviors, independently of the size of the table; also there is a GUC
     * variable that can disable synchronized scanning.)
     *
     * Note that table_block_parallelscan_initialize has a very similar test;
     * if you change this, consider changing that one, too.
     */
    if (!RelationUsesLocalBuffers(scan->rs_base.rs_rd) &&
        scan->rs_nblocks > NBuffers / 4)
    {
        allow_strat = (scan->rs_base.rs_flags & SO_ALLOW_STRAT) != 0;
        allow_sync = (scan->rs_base.rs_flags & SO_ALLOW_SYNC) != 0;
    }
    else
        allow_strat = allow_sync = false;
 
    if (allow_strat)
    {
        /* During a rescan, keep the previous strategy object. */
        if (scan->rs_strategy == NULL)
            scan->rs_strategy = GetAccessStrategy(BAS_BULKREAD);
    }
    else
    {
        if (scan->rs_strategy != NULL)
            FreeAccessStrategy(scan->rs_strategy);
        scan->rs_strategy = NULL;
    }
 
    if (scan->rs_base.rs_parallel != NULL)
    {
        /* For parallel scan, believe whatever ParallelTableScanDesc says. */
        if (scan->rs_base.rs_parallel->phs_syncscan)
            scan->rs_base.rs_flags |= SO_ALLOW_SYNC;
        else
            scan->rs_base.rs_flags &= ~SO_ALLOW_SYNC;
    }
    else if (keep_startblock)
    {
        /*
         * When rescanning, we want to keep the previous startblock setting,
         * so that rewinding a cursor doesn't generate surprising results.
         * Reset the active syncscan setting, though.
         */
        if (allow_sync && synchronize_seqscans)
            scan->rs_base.rs_flags |= SO_ALLOW_SYNC;
        else
            scan->rs_base.rs_flags &= ~SO_ALLOW_SYNC;
    }
    else if (allow_sync && synchronize_seqscans)
    {
        scan->rs_base.rs_flags |= SO_ALLOW_SYNC;
        scan->rs_startblock = ss_get_location(scan->rs_base.rs_rd, scan->rs_nblocks);
    }
    else
    {
        scan->rs_base.rs_flags &= ~SO_ALLOW_SYNC;
        scan->rs_startblock = 0;
    }
 
    scan->rs_numblocks = InvalidBlockNumber;
    scan->rs_inited = false;
    scan->rs_ctup.t_data = NULL;
    ItemPointerSetInvalid(&scan->rs_ctup.t_self);
    scan->rs_cbuf = InvalidBuffer;
    scan->rs_cblock = InvalidBlockNumber;
    scan->rs_ntuples = 0;
    scan->rs_cindex = 0;
 
    /*
     * Initialize to ForwardScanDirection because it is most common and
     * because heap scans go forward before going backward (e.g. CURSORs).
     */
    scan->rs_dir = ForwardScanDirection;
    scan->rs_prefetch_block = InvalidBlockNumber;
 
    /* page-at-a-time fields are always invalid when not rs_inited */
 
    /*
     * copy the scan key, if appropriate
     */
    if (key != NULL && scan->rs_base.rs_nkeys > 0)
        memcpy(scan->rs_base.rs_key, key, scan->rs_base.rs_nkeys * sizeof(ScanKeyData));
 
    /*
     * Currently, we only have a stats counter for sequential heap scans (but
     * e.g for bitmap scans the underlying bitmap index scans will be counted,
     * and for sample scans we update stats for tuple fetches).
     */
    if (scan->rs_base.rs_flags & SO_TYPE_SEQSCAN)
        pgstat_count_heap_scan(scan->rs_base.rs_rd);
}

References BAS_BULKREAD, ForwardScanDirection, FreeAccessStrategy(), GetAccessStrategy(), InvalidBlockNumber, InvalidBuffer, ItemPointerSetInvalid(), sort-test::key, NBuffers, pgstat_count_heap_scan, ParallelBlockTableScanDescData::phs_nblocks, ParallelTableScanDescData::phs_syncscan, RelationGetNumberOfBlocks, RelationUsesLocalBuffers, HeapScanDescData::rs_base, HeapScanDescData::rs_cblock, HeapScanDescData::rs_cbuf, HeapScanDescData::rs_cindex, HeapScanDescData::rs_ctup, HeapScanDescData::rs_dir, TableScanDescData::rs_flags, HeapScanDescData::rs_inited, TableScanDescData::rs_key, HeapScanDescData::rs_nblocks, TableScanDescData::rs_nkeys, HeapScanDescData::rs_ntuples, HeapScanDescData::rs_numblocks, TableScanDescData::rs_parallel, HeapScanDescData::rs_prefetch_block, TableScanDescData::rs_rd, HeapScanDescData::rs_startblock, HeapScanDescData::rs_strategy, SO_ALLOW_STRAT, SO_ALLOW_SYNC, SO_TYPE_SEQSCAN, ss_get_location(), synchronize_seqscans, HeapTupleData::t_data, and HeapTupleData::t_self.

Referenced by heap_beginscan(), and heap_rescan().

log_heap_new_cid()

static XLogRecPtr log_heap_new_cid ( Relation  relation, HeapTuple  tup  )

static

Definition at line 9060 of file heapam.c.

{
    xl_heap_new_cid xlrec;
 
    XLogRecPtr  recptr;
    HeapTupleHeader hdr = tup->t_data;
 
    Assert(ItemPointerIsValid(&tup->t_self));
    Assert(tup->t_tableOid != InvalidOid);
 
    xlrec.top_xid = GetTopTransactionId();
    xlrec.target_locator = relation->rd_locator;
    xlrec.target_tid = tup->t_self;
 
    /*
     * If the tuple got inserted & deleted in the same TX we definitely have a
     * combo CID, set cmin and cmax.
     */
    if (hdr->t_infomask & HEAP_COMBOCID)
    {
        Assert(!(hdr->t_infomask & HEAP_XMAX_INVALID));
        Assert(!HeapTupleHeaderXminInvalid(hdr));
        xlrec.cmin = HeapTupleHeaderGetCmin(hdr);
        xlrec.cmax = HeapTupleHeaderGetCmax(hdr);
        xlrec.combocid = HeapTupleHeaderGetRawCommandId(hdr);
    }
    /* No combo CID, so only cmin or cmax can be set by this TX */
    else
    {
        /*
         * Tuple inserted.
         *
         * We need to check for LOCK ONLY because multixacts might be
         * transferred to the new tuple in case of FOR KEY SHARE updates in
         * which case there will be an xmax, although the tuple just got
         * inserted.
         */
        if (hdr->t_infomask & HEAP_XMAX_INVALID ||
            HEAP_XMAX_IS_LOCKED_ONLY(hdr->t_infomask))
        {
            xlrec.cmin = HeapTupleHeaderGetRawCommandId(hdr);
            xlrec.cmax = InvalidCommandId;
        }
        /* Tuple from a different tx updated or deleted. */
        else
        {
            xlrec.cmin = InvalidCommandId;
            xlrec.cmax = HeapTupleHeaderGetRawCommandId(hdr);
        }
        xlrec.combocid = InvalidCommandId;
    }
 
    /*
     * Note that we don't need to register the buffer here, because this
     * operation does not modify the page. The insert/update/delete that
     * called us certainly did, but that's WAL-logged separately.
     */
    XLogBeginInsert();
    XLogRegisterData(&xlrec, SizeOfHeapNewCid);
 
    /* will be looked at irrespective of origin */
 
    recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_NEW_CID);
 
    return recptr;
}

References Assert(), xl_heap_new_cid::cmax, xl_heap_new_cid::cmin, xl_heap_new_cid::combocid, GetTopTransactionId(), HEAP_COMBOCID, HEAP_XMAX_INVALID, HEAP_XMAX_IS_LOCKED_ONLY(), HeapTupleHeaderGetCmax(), HeapTupleHeaderGetCmin(), HeapTupleHeaderGetRawCommandId(), HeapTupleHeaderXminInvalid(), InvalidCommandId, InvalidOid, ItemPointerIsValid(), RelationData::rd_locator, SizeOfHeapNewCid, HeapTupleData::t_data, HeapTupleHeaderData::t_infomask, HeapTupleData::t_self, HeapTupleData::t_tableOid, xl_heap_new_cid::target_locator, xl_heap_new_cid::target_tid, xl_heap_new_cid::top_xid, XLOG_HEAP2_NEW_CID, XLogBeginInsert(), XLogInsert(), and XLogRegisterData().

Referenced by heap_delete(), heap_insert(), heap_multi_insert(), and heap_update().

log_heap_update()

static XLogRecPtr log_heap_update ( Relation  reln, Buffer  oldbuf, Buffer  newbuf, HeapTuple  oldtup, HeapTuple  newtup, HeapTuple  old_key_tuple, bool  all_visible_cleared, bool  new_all_visible_cleared  )

static

Definition at line 8838 of file heapam.c.

{
    xl_heap_update xlrec;
    xl_heap_header xlhdr;
    xl_heap_header xlhdr_idx;
    uint8       info;
    uint16      prefix_suffix[2];
    uint16      prefixlen = 0,
                suffixlen = 0;
    XLogRecPtr  recptr;
    Page        page = BufferGetPage(newbuf);
    bool        need_tuple_data = RelationIsLogicallyLogged(reln);
    bool        init;
    int         bufflags;
 
    /* Caller should not call me on a non-WAL-logged relation */
    Assert(RelationNeedsWAL(reln));
 
    XLogBeginInsert();
 
    if (HeapTupleIsHeapOnly(newtup))
        info = XLOG_HEAP_HOT_UPDATE;
    else
        info = XLOG_HEAP_UPDATE;
 
    /*
     * If the old and new tuple are on the same page, we only need to log the
     * parts of the new tuple that were changed.  That saves on the amount of
     * WAL we need to write.  Currently, we just count any unchanged bytes in
     * the beginning and end of the tuple.  That's quick to check, and
     * perfectly covers the common case that only one field is updated.
     *
     * We could do this even if the old and new tuple are on different pages,
     * but only if we don't make a full-page image of the old page, which is
     * difficult to know in advance.  Also, if the old tuple is corrupt for
     * some reason, it would allow the corruption to propagate the new page,
     * so it seems best to avoid.  Under the general assumption that most
     * updates tend to create the new tuple version on the same page, there
     * isn't much to be gained by doing this across pages anyway.
     *
     * Skip this if we're taking a full-page image of the new page, as we
     * don't include the new tuple in the WAL record in that case.  Also
     * disable if wal_level='logical', as logical decoding needs to be able to
     * read the new tuple in whole from the WAL record alone.
     */
    if (oldbuf == newbuf && !need_tuple_data &&
        !XLogCheckBufferNeedsBackup(newbuf))
    {
        char       *oldp = (char *) oldtup->t_data + oldtup->t_data->t_hoff;
        char       *newp = (char *) newtup->t_data + newtup->t_data->t_hoff;
        int         oldlen = oldtup->t_len - oldtup->t_data->t_hoff;
        int         newlen = newtup->t_len - newtup->t_data->t_hoff;
 
        /* Check for common prefix between old and new tuple */
        for (prefixlen = 0; prefixlen < Min(oldlen, newlen); prefixlen++)
        {
            if (newp[prefixlen] != oldp[prefixlen])
                break;
        }
 
        /*
         * Storing the length of the prefix takes 2 bytes, so we need to save
         * at least 3 bytes or there's no point.
         */
        if (prefixlen < 3)
            prefixlen = 0;
 
        /* Same for suffix */
        for (suffixlen = 0; suffixlen < Min(oldlen, newlen) - prefixlen; suffixlen++)
        {
            if (newp[newlen - suffixlen - 1] != oldp[oldlen - suffixlen - 1])
                break;
        }
        if (suffixlen < 3)
            suffixlen = 0;
    }
 
    /* Prepare main WAL data chain */
    xlrec.flags = 0;
    if (all_visible_cleared)
        xlrec.flags |= XLH_UPDATE_OLD_ALL_VISIBLE_CLEARED;
    if (new_all_visible_cleared)
        xlrec.flags |= XLH_UPDATE_NEW_ALL_VISIBLE_CLEARED;
    if (prefixlen > 0)
        xlrec.flags |= XLH_UPDATE_PREFIX_FROM_OLD;
    if (suffixlen > 0)
        xlrec.flags |= XLH_UPDATE_SUFFIX_FROM_OLD;
    if (need_tuple_data)
    {
        xlrec.flags |= XLH_UPDATE_CONTAINS_NEW_TUPLE;
        if (old_key_tuple)
        {
            if (reln->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
                xlrec.flags |= XLH_UPDATE_CONTAINS_OLD_TUPLE;
            else
                xlrec.flags |= XLH_UPDATE_CONTAINS_OLD_KEY;
        }
    }
 
    /* If new tuple is the single and first tuple on page... */
    if (ItemPointerGetOffsetNumber(&(newtup->t_self)) == FirstOffsetNumber &&
        PageGetMaxOffsetNumber(page) == FirstOffsetNumber)
    {
        info |= XLOG_HEAP_INIT_PAGE;
        init = true;
    }
    else
        init = false;
 
    /* Prepare WAL data for the old page */
    xlrec.old_offnum = ItemPointerGetOffsetNumber(&oldtup->t_self);
    xlrec.old_xmax = HeapTupleHeaderGetRawXmax(oldtup->t_data);
    xlrec.old_infobits_set = compute_infobits(oldtup->t_data->t_infomask,
                                              oldtup->t_data->t_infomask2);
 
    /* Prepare WAL data for the new page */
    xlrec.new_offnum = ItemPointerGetOffsetNumber(&newtup->t_self);
    xlrec.new_xmax = HeapTupleHeaderGetRawXmax(newtup->t_data);
 
    bufflags = REGBUF_STANDARD;
    if (init)
        bufflags |= REGBUF_WILL_INIT;
    if (need_tuple_data)
        bufflags |= REGBUF_KEEP_DATA;
 
    XLogRegisterBuffer(0, newbuf, bufflags);
    if (oldbuf != newbuf)
        XLogRegisterBuffer(1, oldbuf, REGBUF_STANDARD);
 
    XLogRegisterData(&xlrec, SizeOfHeapUpdate);
 
    /*
     * Prepare WAL data for the new tuple.
     */
    if (prefixlen > 0 || suffixlen > 0)
    {
        if (prefixlen > 0 && suffixlen > 0)
        {
            prefix_suffix[0] = prefixlen;
            prefix_suffix[1] = suffixlen;
            XLogRegisterBufData(0, &prefix_suffix, sizeof(uint16) * 2);
        }
        else if (prefixlen > 0)
        {
            XLogRegisterBufData(0, &prefixlen, sizeof(uint16));
        }
        else
        {
            XLogRegisterBufData(0, &suffixlen, sizeof(uint16));
        }
    }
 
    xlhdr.t_infomask2 = newtup->t_data->t_infomask2;
    xlhdr.t_infomask = newtup->t_data->t_infomask;
    xlhdr.t_hoff = newtup->t_data->t_hoff;
    Assert(SizeofHeapTupleHeader + prefixlen + suffixlen <= newtup->t_len);
 
    /*
     * PG73FORMAT: write bitmap [+ padding] [+ oid] + data
     *
     * The 'data' doesn't include the common prefix or suffix.
     */
    XLogRegisterBufData(0, &xlhdr, SizeOfHeapHeader);
    if (prefixlen == 0)
    {
        XLogRegisterBufData(0,
                            (char *) newtup->t_data + SizeofHeapTupleHeader,
                            newtup->t_len - SizeofHeapTupleHeader - suffixlen);
    }
    else
    {
        /*
         * Have to write the null bitmap and data after the common prefix as
         * two separate rdata entries.
         */
        /* bitmap [+ padding] [+ oid] */
        if (newtup->t_data->t_hoff - SizeofHeapTupleHeader > 0)
        {
            XLogRegisterBufData(0,
                                (char *) newtup->t_data + SizeofHeapTupleHeader,
                                newtup->t_data->t_hoff - SizeofHeapTupleHeader);
        }
 
        /* data after common prefix */
        XLogRegisterBufData(0,
                            (char *) newtup->t_data + newtup->t_data->t_hoff + prefixlen,
                            newtup->t_len - newtup->t_data->t_hoff - prefixlen - suffixlen);
    }
 
    /* We need to log a tuple identity */
    if (need_tuple_data && old_key_tuple)
    {
        /* don't really need this, but its more comfy to decode */
        xlhdr_idx.t_infomask2 = old_key_tuple->t_data->t_infomask2;
        xlhdr_idx.t_infomask = old_key_tuple->t_data->t_infomask;
        xlhdr_idx.t_hoff = old_key_tuple->t_data->t_hoff;
 
        XLogRegisterData(&xlhdr_idx, SizeOfHeapHeader);
 
        /* PG73FORMAT: write bitmap [+ padding] [+ oid] + data */
        XLogRegisterData((char *) old_key_tuple->t_data + SizeofHeapTupleHeader,
                         old_key_tuple->t_len - SizeofHeapTupleHeader);
    }
 
    /* filtering by origin on a row level is much more efficient */
    XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
 
    recptr = XLogInsert(RM_HEAP_ID, info);
 
    return recptr;
}

References Assert(), BufferGetPage(), compute_infobits(), FirstOffsetNumber, xl_heap_update::flags, HeapTupleHeaderGetRawXmax(), HeapTupleIsHeapOnly(), init, ItemPointerGetOffsetNumber(), Min, xl_heap_update::new_offnum, xl_heap_update::new_xmax, xl_heap_update::old_infobits_set, xl_heap_update::old_offnum, xl_heap_update::old_xmax, PageGetMaxOffsetNumber(), RelationData::rd_rel, REGBUF_KEEP_DATA, REGBUF_STANDARD, REGBUF_WILL_INIT, RelationIsLogicallyLogged, RelationNeedsWAL, SizeOfHeapHeader, SizeofHeapTupleHeader, SizeOfHeapUpdate, HeapTupleData::t_data, xl_heap_header::t_hoff, HeapTupleHeaderData::t_hoff, xl_heap_header::t_infomask, HeapTupleHeaderData::t_infomask, xl_heap_header::t_infomask2, HeapTupleHeaderData::t_infomask2, HeapTupleData::t_len, HeapTupleData::t_self, XLH_UPDATE_CONTAINS_NEW_TUPLE, XLH_UPDATE_CONTAINS_OLD_KEY, XLH_UPDATE_CONTAINS_OLD_TUPLE, XLH_UPDATE_NEW_ALL_VISIBLE_CLEARED, XLH_UPDATE_OLD_ALL_VISIBLE_CLEARED, XLH_UPDATE_PREFIX_FROM_OLD, XLH_UPDATE_SUFFIX_FROM_OLD, XLOG_HEAP_HOT_UPDATE, XLOG_HEAP_INIT_PAGE, XLOG_HEAP_UPDATE, XLOG_INCLUDE_ORIGIN, XLogBeginInsert(), XLogCheckBufferNeedsBackup(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), XLogRegisterData(), and XLogSetRecordFlags().

Referenced by heap_update().

log_heap_visible()

XLogRecPtr log_heap_visible	(	Relation	rel,
		Buffer	heap_buffer,
		Buffer	vm_buffer,
		TransactionId	snapshotConflictHorizon,
		uint8	vmflags
	)

Definition at line 8804 of file heapam.c.

{
    xl_heap_visible xlrec;
    XLogRecPtr  recptr;
    uint8       flags;
 
    Assert(BufferIsValid(heap_buffer));
    Assert(BufferIsValid(vm_buffer));
 
    xlrec.snapshotConflictHorizon = snapshotConflictHorizon;
    xlrec.flags = vmflags;
    if (RelationIsAccessibleInLogicalDecoding(rel))
        xlrec.flags |= VISIBILITYMAP_XLOG_CATALOG_REL;
    XLogBeginInsert();
    XLogRegisterData(&xlrec, SizeOfHeapVisible);
 
    XLogRegisterBuffer(0, vm_buffer, 0);
 
    flags = REGBUF_STANDARD;
    if (!XLogHintBitIsNeeded())
        flags |= REGBUF_NO_IMAGE;
    XLogRegisterBuffer(1, heap_buffer, flags);
 
    recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_VISIBLE);
 
    return recptr;
}

References Assert(), BufferIsValid(), xl_heap_visible::flags, REGBUF_NO_IMAGE, REGBUF_STANDARD, RelationIsAccessibleInLogicalDecoding, SizeOfHeapVisible, xl_heap_visible::snapshotConflictHorizon, VISIBILITYMAP_XLOG_CATALOG_REL, XLOG_HEAP2_VISIBLE, XLogBeginInsert(), XLogHintBitIsNeeded, XLogInsert(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by visibilitymap_set().

MultiXactIdGetUpdateXid()

static TransactionId MultiXactIdGetUpdateXid ( TransactionId  xmax, uint16  t_infomask  )

static

Definition at line 7527 of file heapam.c.

{
    TransactionId update_xact = InvalidTransactionId;
    MultiXactMember *members;
    int         nmembers;
 
    Assert(!(t_infomask & HEAP_XMAX_LOCK_ONLY));
    Assert(t_infomask & HEAP_XMAX_IS_MULTI);
 
    /*
     * Since we know the LOCK_ONLY bit is not set, this cannot be a multi from
     * pre-pg_upgrade.
     */
    nmembers = GetMultiXactIdMembers(xmax, &members, false, false);
 
    if (nmembers > 0)
    {
        int         i;
 
        for (i = 0; i < nmembers; i++)
        {
            /* Ignore lockers */
            if (!ISUPDATE_from_mxstatus(members[i].status))
                continue;
 
            /* there can be at most one updater */
            Assert(update_xact == InvalidTransactionId);
            update_xact = members[i].xid;
#ifndef USE_ASSERT_CHECKING
 
            /*
             * in an assert-enabled build, walk the whole array to ensure
             * there's no other updater.
             */
            break;
#endif
        }
 
        pfree(members);
    }
 
    return update_xact;
}

References Assert(), GetMultiXactIdMembers(), HEAP_XMAX_IS_MULTI, HEAP_XMAX_LOCK_ONLY, i, InvalidTransactionId, ISUPDATE_from_mxstatus, pfree(), and MultiXactMember::xid.

Referenced by compute_new_xmax_infomask(), FreezeMultiXactId(), and HeapTupleGetUpdateXid().

MultiXactIdWait()

static void MultiXactIdWait ( MultiXactId  multi, MultiXactStatus  status, uint16  infomask, Relation  rel, ItemPointer  ctid, XLTW_Oper  oper, int *  remaining  )

static

Definition at line 7773 of file heapam.c.

{
    (void) Do_MultiXactIdWait(multi, status, infomask, false,
                              rel, ctid, oper, remaining, false);
}

References Do_MultiXactIdWait(), oper(), and remaining.

Referenced by heap_delete(), heap_inplace_lock(), heap_lock_tuple(), and heap_update().

page_collect_tuples()

static pg_attribute_always_inline int page_collect_tuples ( HeapScanDesc  scan, Snapshot  snapshot, Page  page, Buffer  buffer, BlockNumber  block, int  lines, bool  all_visible, bool  check_serializable  )

static

Definition at line 502 of file heapam.c.

{
    int         ntup = 0;
    OffsetNumber lineoff;
 
    for (lineoff = FirstOffsetNumber; lineoff <= lines; lineoff++)
    {
        ItemId      lpp = PageGetItemId(page, lineoff);
        HeapTupleData loctup;
        bool        valid;
 
        if (!ItemIdIsNormal(lpp))
            continue;
 
        loctup.t_data = (HeapTupleHeader) PageGetItem(page, lpp);
        loctup.t_len = ItemIdGetLength(lpp);
        loctup.t_tableOid = RelationGetRelid(scan->rs_base.rs_rd);
        ItemPointerSet(&(loctup.t_self), block, lineoff);
 
        if (all_visible)
            valid = true;
        else
            valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
 
        if (check_serializable)
            HeapCheckForSerializableConflictOut(valid, scan->rs_base.rs_rd,
                                                &loctup, buffer, snapshot);
 
        if (valid)
        {
            scan->rs_vistuples[ntup] = lineoff;
            ntup++;
        }
    }
 
    Assert(ntup <= MaxHeapTuplesPerPage);
 
    return ntup;
}

References Assert(), FirstOffsetNumber, HeapCheckForSerializableConflictOut(), HeapTupleSatisfiesVisibility(), ItemIdGetLength, ItemIdIsNormal, ItemPointerSet(), MaxHeapTuplesPerPage, PageGetItem(), PageGetItemId(), RelationGetRelid, HeapScanDescData::rs_base, TableScanDescData::rs_rd, HeapScanDescData::rs_vistuples, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, and HeapTupleData::t_tableOid.

Referenced by heap_prepare_pagescan().

ReleaseBulkInsertStatePin()

void ReleaseBulkInsertStatePin

(

BulkInsertState

bistate

)

Definition at line 2050 of file heapam.c.

{
    if (bistate->current_buf != InvalidBuffer)
        ReleaseBuffer(bistate->current_buf);
    bistate->current_buf = InvalidBuffer;
 
    /*
     * Despite the name, we also reset bulk relation extension state.
     * Otherwise we can end up erroring out due to looking for free space in
     * ->next_free of one partition, even though ->next_free was set when
     * extending another partition. It could obviously also be bad for
     * efficiency to look at existing blocks at offsets from another
     * partition, even if we don't error out.
     */
    bistate->next_free = InvalidBlockNumber;
    bistate->last_free = InvalidBlockNumber;
}

References BulkInsertStateData::current_buf, InvalidBlockNumber, InvalidBuffer, BulkInsertStateData::last_free, BulkInsertStateData::next_free, and ReleaseBuffer().

Referenced by CopyFrom().

simple_heap_delete()

void simple_heap_delete	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 3201 of file heapam.c.

{
    TM_Result   result;
    TM_FailureData tmfd;
 
    result = heap_delete(relation, tid,
                         GetCurrentCommandId(true), InvalidSnapshot,
                         true /* wait for commit */ ,
                         &tmfd, false /* changingPart */ );
    switch (result)
    {
        case TM_SelfModified:
            /* Tuple was already updated in current command? */
            elog(ERROR, "tuple already updated by self");
            break;
 
        case TM_Ok:
            /* done successfully */
            break;
 
        case TM_Updated:
            elog(ERROR, "tuple concurrently updated");
            break;
 
        case TM_Deleted:
            elog(ERROR, "tuple concurrently deleted");
            break;
 
        default:
            elog(ERROR, "unrecognized heap_delete status: %u", result);
            break;
    }
}

References elog, ERROR, GetCurrentCommandId(), heap_delete(), InvalidSnapshot, TM_Deleted, TM_Ok, TM_SelfModified, and TM_Updated.

Referenced by CatalogTupleDelete(), and toast_delete_datum().

simple_heap_insert()

void simple_heap_insert	(	Relation	relation,
		HeapTuple	tup
	)

Definition at line 2720 of file heapam.c.

{
    heap_insert(relation, tup, GetCurrentCommandId(true), 0, NULL);
}

References GetCurrentCommandId(), and heap_insert().

Referenced by CatalogTupleInsert(), CatalogTupleInsertWithInfo(), and InsertOneTuple().

simple_heap_update()

void simple_heap_update	(	Relation	relation,
		ItemPointer	otid,
		HeapTuple	tup,
		TU_UpdateIndexes *	update_indexes
	)

Definition at line 4491 of file heapam.c.

{
    TM_Result   result;
    TM_FailureData tmfd;
    LockTupleMode lockmode;
 
    result = heap_update(relation, otid, tup,
                         GetCurrentCommandId(true), InvalidSnapshot,
                         true /* wait for commit */ ,
                         &tmfd, &lockmode, update_indexes);
    switch (result)
    {
        case TM_SelfModified:
            /* Tuple was already updated in current command? */
            elog(ERROR, "tuple already updated by self");
            break;
 
        case TM_Ok:
            /* done successfully */
            break;
 
        case TM_Updated:
            elog(ERROR, "tuple concurrently updated");
            break;
 
        case TM_Deleted:
            elog(ERROR, "tuple concurrently deleted");
            break;
 
        default:
            elog(ERROR, "unrecognized heap_update status: %u", result);
            break;
    }
}

References elog, ERROR, GetCurrentCommandId(), heap_update(), InvalidSnapshot, TM_Deleted, TM_Ok, TM_SelfModified, and TM_Updated.

Referenced by CatalogTupleUpdate(), and CatalogTupleUpdateWithInfo().

test_lockmode_for_conflict()

static TM_Result test_lockmode_for_conflict ( MultiXactStatus  status, TransactionId  xid, LockTupleMode  mode, HeapTuple  tup, bool *  needwait  )

static

Definition at line 5607 of file heapam.c.

{
    MultiXactStatus wantedstatus;
 
    *needwait = false;
    wantedstatus = get_mxact_status_for_lock(mode, false);
 
    /*
     * Note: we *must* check TransactionIdIsInProgress before
     * TransactionIdDidAbort/Commit; see comment at top of heapam_visibility.c
     * for an explanation.
     */
    if (TransactionIdIsCurrentTransactionId(xid))
    {
        /*
         * The tuple has already been locked by our own transaction.  This is
         * very rare but can happen if multiple transactions are trying to
         * lock an ancient version of the same tuple.
         */
        return TM_SelfModified;
    }
    else if (TransactionIdIsInProgress(xid))
    {
        /*
         * If the locking transaction is running, what we do depends on
         * whether the lock modes conflict: if they do, then we must wait for
         * it to finish; otherwise we can fall through to lock this tuple
         * version without waiting.
         */
        if (DoLockModesConflict(LOCKMODE_from_mxstatus(status),
                                LOCKMODE_from_mxstatus(wantedstatus)))
        {
            *needwait = true;
        }
 
        /*
         * If we set needwait above, then this value doesn't matter;
         * otherwise, this value signals to caller that it's okay to proceed.
         */
        return TM_Ok;
    }
    else if (TransactionIdDidAbort(xid))
        return TM_Ok;
    else if (TransactionIdDidCommit(xid))
    {
        /*
         * The other transaction committed.  If it was only a locker, then the
         * lock is completely gone now and we can return success; but if it
         * was an update, then what we do depends on whether the two lock
         * modes conflict.  If they conflict, then we must report error to
         * caller. But if they don't, we can fall through to allow the current
         * transaction to lock the tuple.
         *
         * Note: the reason we worry about ISUPDATE here is because as soon as
         * a transaction ends, all its locks are gone and meaningless, and
         * thus we can ignore them; whereas its updates persist.  In the
         * TransactionIdIsInProgress case, above, we don't need to check
         * because we know the lock is still "alive" and thus a conflict needs
         * always be checked.
         */
        if (!ISUPDATE_from_mxstatus(status))
            return TM_Ok;
 
        if (DoLockModesConflict(LOCKMODE_from_mxstatus(status),
                                LOCKMODE_from_mxstatus(wantedstatus)))
        {
            /* bummer */
            if (!ItemPointerEquals(&tup->t_self, &tup->t_data->t_ctid))
                return TM_Updated;
            else
                return TM_Deleted;
        }
 
        return TM_Ok;
    }
 
    /* Not in progress, not aborted, not committed -- must have crashed */
    return TM_Ok;
}

References DoLockModesConflict(), get_mxact_status_for_lock(), ISUPDATE_from_mxstatus, ItemPointerEquals(), LOCKMODE_from_mxstatus, mode, HeapTupleHeaderData::t_ctid, HeapTupleData::t_data, HeapTupleData::t_self, TM_Deleted, TM_Ok, TM_SelfModified, TM_Updated, TransactionIdDidAbort(), TransactionIdDidCommit(), TransactionIdIsCurrentTransactionId(), and TransactionIdIsInProgress().

Referenced by heap_lock_updated_tuple_rec().

UpdateXmaxHintBits()

static void UpdateXmaxHintBits ( HeapTupleHeader  tuple, Buffer  buffer, TransactionId  xid  )

static

Definition at line 1999 of file heapam.c.

{
    Assert(TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple), xid));
    Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
 
    if (!(tuple->t_infomask & (HEAP_XMAX_COMMITTED | HEAP_XMAX_INVALID)))
    {
        if (!HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask) &&
            TransactionIdDidCommit(xid))
            HeapTupleSetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
                                 xid);
        else
            HeapTupleSetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
                                 InvalidTransactionId);
    }
}

References Assert(), HEAP_XMAX_COMMITTED, HEAP_XMAX_INVALID, HEAP_XMAX_IS_LOCKED_ONLY(), HEAP_XMAX_IS_MULTI, HeapTupleHeaderGetRawXmax(), HeapTupleSetHintBits(), InvalidTransactionId, HeapTupleHeaderData::t_infomask, TransactionIdDidCommit(), and TransactionIdEquals.

Referenced by heap_delete(), heap_lock_tuple(), and heap_update().

xmax_infomask_changed()

static bool xmax_infomask_changed ( uint16  new_infomask, uint16  old_infomask  )

inlinestatic

Definition at line 2755 of file heapam.c.

{
    const uint16 interesting =
        HEAP_XMAX_IS_MULTI | HEAP_XMAX_LOCK_ONLY | HEAP_LOCK_MASK;
 
    if ((new_infomask & interesting) != (old_infomask & interesting))
        return true;
 
    return false;
}

References HEAP_LOCK_MASK, HEAP_XMAX_IS_MULTI, and HEAP_XMAX_LOCK_ONLY.

Referenced by heap_delete(), heap_lock_tuple(), and heap_update().

Variable Documentation

hwlock

LOCKMODE hwlock

Definition at line 124 of file heapam.c.

lockstatus

int lockstatus

Definition at line 125 of file heapam.c.

MultiXactStatusLock

const int MultiXactStatusLock[MaxMultiXactStatus+1]

static

Initial value:

=
{
    LockTupleKeyShare,          
    LockTupleShare,             
    LockTupleNoKeyExclusive,    
    LockTupleExclusive,         
    LockTupleNoKeyExclusive,    
    LockTupleExclusive          
}

Definition at line 202 of file heapam.c.

const struct { ... } tupleLockExtraInfo[MaxLockTupleMode + 1]

Initial value:

=
{
    {                           
        AccessShareLock,
        MultiXactStatusForKeyShare,
        -1                      
    },
    {                           
        RowShareLock,
        MultiXactStatusForShare,
        -1                      
    },
    {                           
        ExclusiveLock,
        MultiXactStatusForNoKeyUpdate,
        MultiXactStatusNoKeyUpdate
    },
    {                           
        AccessExclusiveLock,
        MultiXactStatusForUpdate,
        MultiXactStatusUpdate
    }
}

Referenced by DoesMultiXactIdConflict(), and get_mxact_status_for_lock().

updstatus

int updstatus

Definition at line 126 of file heapam.c.