heapam.c File Reference

#include "postgres.h"
#include "access/bufmask.h"
#include "access/genam.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/heaptoast.h"
#include "access/hio.h"
#include "access/multixact.h"
#include "access/parallel.h"
#include "access/relscan.h"
#include "access/subtrans.h"
#include "access/syncscan.h"
#include "access/sysattr.h"
#include "access/tableam.h"
#include "access/transam.h"
#include "access/valid.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "port/atomics.h"
#include "port/pg_bitutils.h"
#include "storage/bufmgr.h"
#include "storage/freespace.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "storage/procarray.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "storage/standby.h"
#include "utils/datum.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/relcache.h"
#include "utils/snapmgr.h"
#include "utils/spccache.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)    ConditionalLockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
#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 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 int	heap_log_freeze_plan (HeapTupleFreeze *tuples, int ntuples, xl_heap_freeze_plan *plans_out, OffsetNumber *offsets_out)
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)
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	initscan (HeapScanDesc scan, ScanKey key, bool keep_startblock)
void	heap_setscanlimits (TableScanDesc sscan, BlockNumber startBlk, BlockNumber numBlks)
void	heapgetpage (TableScanDesc sscan, BlockNumber block)
static BlockNumber	heapgettup_initial_block (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 BlockNumber	heapgettup_advance_block (HeapScanDesc scan, BlockNumber block, ScanDirection dir)
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)
void	heap_inplace_update (Relation relation, HeapTuple tuple)
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)
static void	heap_execute_freeze_tuple (HeapTupleHeader tuple, HeapTupleFreeze *frz)
void	heap_freeze_execute_prepared (Relation rel, Buffer buffer, TransactionId snapshotConflictHorizon, HeapTupleFreeze *tuples, int ntuples)
static int	heap_log_freeze_cmp (const void *arg1, const void *arg2)
static bool	heap_log_freeze_eq (xl_heap_freeze_plan *plan, HeapTupleFreeze *frz)
static void	heap_log_freeze_new_plan (xl_heap_freeze_plan *plan, HeapTupleFreeze *frz)
bool	heap_freeze_tuple (HeapTupleHeader tuple, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId FreezeLimit, TransactionId MultiXactCutoff)
TransactionId	HeapTupleGetUpdateXid (HeapTupleHeader tuple)
static bool	Do_MultiXactIdWait (MultiXactId multi, MultiXactStatus status, uint16 infomask, bool nowait, Relation rel, ItemPointer ctid, XLTW_Oper oper, int *remaining)
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)
static void	heap_xlog_prune (XLogReaderState *record)
static void	heap_xlog_vacuum (XLogReaderState *record)
static void	heap_xlog_visible (XLogReaderState *record)
static void	heap_xlog_freeze_page (XLogReaderState *record)
static void	fix_infomask_from_infobits (uint8 infobits, uint16 *infomask, uint16 *infomask2)
static void	heap_xlog_delete (XLogReaderState *record)
static void	heap_xlog_insert (XLogReaderState *record)
static void	heap_xlog_multi_insert (XLogReaderState *record)
static void	heap_xlog_update (XLogReaderState *record, bool hot_update)
static void	heap_xlog_confirm (XLogReaderState *record)
static void	heap_xlog_lock (XLogReaderState *record)
static void	heap_xlog_lock_updated (XLogReaderState *record)
static void	heap_xlog_inplace (XLogReaderState *record)
void	heap_redo (XLogReaderState *record)
void	heap2_redo (XLogReaderState *record)
void	heap_mask (char *pagedata, BlockNumber blkno)
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 191 of file heapam.c.

BOTTOMUP_TOLERANCE_NBLOCKS

#define BOTTOMUP_TOLERANCE_NBLOCKS   3

Definition at line 192 of file heapam.c.

ConditionalLockTupleTuplock

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

Definition at line 173 of file heapam.c.

FRM_INVALIDATE_XMAX

#define FRM_INVALIDATE_XMAX   0x0002

Definition at line 5959 of file heapam.c.

FRM_MARK_COMMITTED

#define FRM_MARK_COMMITTED   0x0010

Definition at line 5962 of file heapam.c.

FRM_NOOP

#define FRM_NOOP   0x0001

Definition at line 5958 of file heapam.c.

FRM_RETURN_IS_MULTI

#define FRM_RETURN_IS_MULTI   0x0008

Definition at line 5961 of file heapam.c.

FRM_RETURN_IS_XID

#define FRM_RETURN_IS_XID   0x0004

Definition at line 5960 of file heapam.c.

LOCKMODE_from_mxstatus

#define LOCKMODE_from_mxstatus

(

status

)

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

Definition at line 161 of file heapam.c.

LockTupleTuplock

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

Definition at line 169 of file heapam.c.

TUPLOCK_from_mxstatus

#define TUPLOCK_from_mxstatus

(

status

)

(MultiXactStatusLock[(status)])

Definition at line 220 of file heapam.c.

UnlockTupleTuplock

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

Definition at line 171 of file heapam.c.

Typedef Documentation

IndexDeleteCounts

typedef struct IndexDeleteCounts IndexDeleteCounts

Function Documentation

bottomup_nblocksfavorable()

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

static

Definition at line 8071 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 8187 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 8114 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 2461 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 4873 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  )

static

Definition at line 7307 of file heapam.c.

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

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  )

static

Definition at line 7207 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);
                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 7108 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_lock_tuple(), and heap_update().

ExtractReplicaIdentity()

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

static

Definition at line 8653 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().

fix_infomask_from_infobits()

static void fix_infomask_from_infobits ( uint8  infobits, uint16 *  infomask, uint16 *  infomask2  )

static

Definition at line 9113 of file heapam.c.

{
    *infomask &= ~(HEAP_XMAX_IS_MULTI | HEAP_XMAX_LOCK_ONLY |
                   HEAP_XMAX_KEYSHR_LOCK | HEAP_XMAX_EXCL_LOCK);
    *infomask2 &= ~HEAP_KEYS_UPDATED;
 
    if (infobits & XLHL_XMAX_IS_MULTI)
        *infomask |= HEAP_XMAX_IS_MULTI;
    if (infobits & XLHL_XMAX_LOCK_ONLY)
        *infomask |= HEAP_XMAX_LOCK_ONLY;
    if (infobits & XLHL_XMAX_EXCL_LOCK)
        *infomask |= HEAP_XMAX_EXCL_LOCK;
    /* note HEAP_XMAX_SHR_LOCK isn't considered here */
    if (infobits & XLHL_XMAX_KEYSHR_LOCK)
        *infomask |= HEAP_XMAX_KEYSHR_LOCK;
 
    if (infobits & XLHL_KEYS_UPDATED)
        *infomask2 |= HEAP_KEYS_UPDATED;
}

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_xlog_delete(), heap_xlog_lock(), heap_xlog_lock_updated(), and heap_xlog_update().

FreeBulkInsertState()

void FreeBulkInsertState

(

BulkInsertState

bistate

)

Definition at line 1778 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 6011 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 4078 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 1761 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 6959 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().

heap2_redo()

void heap2_redo

(

XLogReaderState *

record

)

Definition at line 10000 of file heapam.c.

{
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
 
    switch (info & XLOG_HEAP_OPMASK)
    {
        case XLOG_HEAP2_PRUNE:
            heap_xlog_prune(record);
            break;
        case XLOG_HEAP2_VACUUM:
            heap_xlog_vacuum(record);
            break;
        case XLOG_HEAP2_FREEZE_PAGE:
            heap_xlog_freeze_page(record);
            break;
        case XLOG_HEAP2_VISIBLE:
            heap_xlog_visible(record);
            break;
        case XLOG_HEAP2_MULTI_INSERT:
            heap_xlog_multi_insert(record);
            break;
        case XLOG_HEAP2_LOCK_UPDATED:
            heap_xlog_lock_updated(record);
            break;
        case XLOG_HEAP2_NEW_CID:
 
            /*
             * Nothing to do on a real replay, only used during logical
             * decoding.
             */
            break;
        case XLOG_HEAP2_REWRITE:
            heap_xlog_logical_rewrite(record);
            break;
        default:
            elog(PANIC, "heap2_redo: unknown op code %u", info);
    }
}

References elog(), heap_xlog_freeze_page(), heap_xlog_lock_updated(), heap_xlog_logical_rewrite(), heap_xlog_multi_insert(), heap_xlog_prune(), heap_xlog_vacuum(), heap_xlog_visible(), PANIC, XLOG_HEAP2_FREEZE_PAGE, XLOG_HEAP2_LOCK_UPDATED, XLOG_HEAP2_MULTI_INSERT, XLOG_HEAP2_NEW_CID, XLOG_HEAP2_PRUNE, XLOG_HEAP2_REWRITE, XLOG_HEAP2_VACUUM, XLOG_HEAP2_VISIBLE, XLOG_HEAP_OPMASK, XLogRecGetInfo, and XLR_INFO_MASK.

heap_abort_speculative()

void heap_abort_speculative	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 5722 of file heapam.c.

{
    TransactionId xid = GetCurrentTransactionId();
    ItemId      lp;
    HeapTupleData tp;
    Page        page;
    BlockNumber block;
    Buffer      buffer;
    TransactionId prune_xid;
 
    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));
    if (TransactionIdPrecedes(TransactionXmin, relation->rd_rel->relfrozenxid))
        prune_xid = relation->rd_rel->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((char *) &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_KEYS_UPDATED, 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 4824 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))
                return false;
            break;
 
        case LockWaitError:
            if (!ConditionalLockTupleTuplock(relation, tid, mode))
                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, 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 3896 of file heapam.c.

{
    Form_pg_attribute att;
 
    /*
     * 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
    {
        Assert(attrnum <= tupdesc->natts);
        att = TupleDescAttr(tupdesc, attrnum - 1);
        return datumIsEqual(value1, value2, att->attbyval, att->attlen);
    }
}

References Assert(), DatumGetObjectId(), datumIsEqual(), and TupleDescAttr.

Referenced by HeapDetermineColumnsInfo().

heap_beginscan()

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

Definition at line 931 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
     */
    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 */
 
    /*
     * 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;
 
    /*
     * 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);
 
    return (TableScanDesc) scan;
}

References Assert(), if(), initscan(), IsMVCCSnapshot, sort-test::key, palloc(), PredicateLockRelation(), RelationGetRelid, RelationIncrementReferenceCount(), HeapScanDescData::rs_base, HeapScanDescData::rs_ctup, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_nkeys, TableScanDescData::rs_parallel, HeapScanDescData::rs_parallelworkerdata, TableScanDescData::rs_rd, TableScanDescData::rs_snapshot, HeapScanDescData::rs_strategy, SO_ALLOW_PAGEMODE, SO_TYPE_SAMPLESCAN, SO_TYPE_SEQSCAN, 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 2506 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));
 
    /*
     * 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;
    }
 
    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)
    {
        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));
        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((char *) &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((char *) &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(), 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_KEYS_UPDATED, 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 1053 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);
 
    /*
     * 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(), RelationDecrementReferenceCount(), ReleaseBuffer(), HeapScanDescData::rs_base, HeapScanDescData::rs_cbuf, TableScanDescData::rs_flags, TableScanDescData::rs_key, HeapScanDescData::rs_parallelworkerdata, TableScanDescData::rs_rd, TableScanDescData::rs_snapshot, HeapScanDescData::rs_strategy, SO_TEMP_SNAPSHOT, and UnregisterSnapshot().

heap_execute_freeze_tuple()

static void heap_execute_freeze_tuple ( HeapTupleHeader  tuple, HeapTupleFreeze *  frz  )

inlinestatic

Definition at line 6635 of file heapam.c.

{
    HeapTupleHeaderSetXmax(tuple, frz->xmax);
 
    if (frz->frzflags & XLH_FREEZE_XVAC)
        HeapTupleHeaderSetXvac(tuple, FrozenTransactionId);
 
    if (frz->frzflags & XLH_INVALID_XVAC)
        HeapTupleHeaderSetXvac(tuple, InvalidTransactionId);
 
    tuple->t_infomask = frz->t_infomask;
    tuple->t_infomask2 = frz->t_infomask2;
}

References FrozenTransactionId, HeapTupleFreeze::frzflags, HeapTupleHeaderSetXmax, HeapTupleHeaderSetXvac, InvalidTransactionId, HeapTupleFreeze::t_infomask, HeapTupleHeaderData::t_infomask, HeapTupleFreeze::t_infomask2, HeapTupleHeaderData::t_infomask2, XLH_FREEZE_XVAC, XLH_INVALID_XVAC, and HeapTupleFreeze::xmax.

Referenced by heap_freeze_execute_prepared(), heap_freeze_tuple(), and heap_xlog_freeze_page().

heap_fetch()

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

Definition at line 1345 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_finish_speculative()

void heap_finish_speculative	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 5635 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 = (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((char *) &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_execute_prepared()

void heap_freeze_execute_prepared	(	Relation	rel,
		Buffer	buffer,
		TransactionId	snapshotConflictHorizon,
		HeapTupleFreeze *	tuples,
		int	ntuples
	)

Definition at line 6664 of file heapam.c.

{
    Page        page = BufferGetPage(buffer);
 
    Assert(ntuples > 0);
 
    /*
     * Perform xmin/xmax XID status sanity checks before critical section.
     *
     * heap_prepare_freeze_tuple doesn't perform these checks directly because
     * pg_xact lookups are relatively expensive.  They shouldn't be repeated
     * by successive VACUUMs that each decide against freezing the same page.
     */
    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)));
        }
    }
 
    START_CRIT_SECTION();
 
    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);
    }
 
    MarkBufferDirty(buffer);
 
    /* Now WAL-log freezing if necessary */
    if (RelationNeedsWAL(rel))
    {
        xl_heap_freeze_plan plans[MaxHeapTuplesPerPage];
        OffsetNumber offsets[MaxHeapTuplesPerPage];
        int         nplans;
        xl_heap_freeze_page xlrec;
        XLogRecPtr  recptr;
 
        /* Prepare deduplicated representation for use in WAL record */
        nplans = heap_log_freeze_plan(tuples, ntuples, plans, offsets);
 
        xlrec.snapshotConflictHorizon = snapshotConflictHorizon;
        xlrec.isCatalogRel = RelationIsAccessibleInLogicalDecoding(rel);
        xlrec.nplans = nplans;
 
        XLogBeginInsert();
        XLogRegisterData((char *) &xlrec, SizeOfHeapFreezePage);
 
        /*
         * The freeze plan array and offset array are not actually in the
         * buffer, but pretend that they are.  When XLogInsert stores the
         * whole buffer, the arrays need not be stored too.
         */
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
        XLogRegisterBufData(0, (char *) plans,
                            nplans * sizeof(xl_heap_freeze_plan));
        XLogRegisterBufData(0, (char *) offsets,
                            ntuples * sizeof(OffsetNumber));
 
        recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_FREEZE_PAGE);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
}

References Assert(), BufferGetPage(), HeapTupleFreeze::checkflags, END_CRIT_SECTION, ereport, errcode(), ERRCODE_DATA_CORRUPTED, errmsg_internal(), ERROR, heap_execute_freeze_tuple(), HEAP_FREEZE_CHECK_XMAX_ABORTED, HEAP_FREEZE_CHECK_XMIN_COMMITTED, heap_log_freeze_plan(), HeapTupleHeaderGetRawXmax, HeapTupleHeaderGetRawXmin, HeapTupleHeaderXminFrozen, i, xl_heap_freeze_page::isCatalogRel, MarkBufferDirty(), MaxHeapTuplesPerPage, xl_heap_freeze_page::nplans, HeapTupleFreeze::offset, PageGetItem(), PageGetItemId(), PageSetLSN(), REGBUF_STANDARD, RelationIsAccessibleInLogicalDecoding, RelationNeedsWAL, SizeOfHeapFreezePage, xl_heap_freeze_page::snapshotConflictHorizon, START_CRIT_SECTION, TransactionIdDidCommit(), TransactionIdIsNormal, unlikely, XLOG_HEAP2_FREEZE_PAGE, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by lazy_scan_prune().

heap_freeze_tuple()

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

Definition at line 6915 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 1617 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 1086 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(), index_update_stats(), 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 1135 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 1238 of file heapam.c.

{
    HeapScanDesc scan = (HeapScanDesc) sscan;
    ItemPointer mintid = &sscan->rs_mintid;
    ItemPointer maxtid = &sscan->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, HeapTupleData::t_data, and HeapTupleData::t_self.

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 1465 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 heap_index_delete_tuples(), heapam_index_fetch_tuple(), and heapam_scan_bitmap_next_block().

heap_index_delete_tuples()

TransactionId heap_index_delete_tuples	(	Relation	rel,
		TM_IndexDeleteOp *	delstate
	)

Definition at line 7629 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 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_update()

void heap_inplace_update	(	Relation	relation,
		HeapTuple	tuple
	)

Definition at line 5875 of file heapam.c.

{
    Buffer      buffer;
    Page        page;
    OffsetNumber offnum;
    ItemId      lp = NULL;
    HeapTupleHeader htup;
    uint32      oldlen;
    uint32      newlen;
 
    /*
     * For now, we don't allow parallel updates.  Unlike a regular update,
     * this should never create a combo CID, so it might be possible to relax
     * this restriction, but not without more thought and testing.  It's not
     * clear that it would be useful, anyway.
     */
    if (IsInParallelMode())
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TRANSACTION_STATE),
                 errmsg("cannot update tuples during a parallel operation")));
 
    buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(&(tuple->t_self)));
    LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
    page = (Page) BufferGetPage(buffer);
 
    offnum = ItemPointerGetOffsetNumber(&(tuple->t_self));
    if (PageGetMaxOffsetNumber(page) >= offnum)
        lp = PageGetItemId(page, offnum);
 
    if (PageGetMaxOffsetNumber(page) < offnum || !ItemIdIsNormal(lp))
        elog(ERROR, "invalid lp");
 
    htup = (HeapTupleHeader) PageGetItem(page, lp);
 
    oldlen = ItemIdGetLength(lp) - 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");
 
    /* NO EREPORT(ERROR) from here till changes are logged */
    START_CRIT_SECTION();
 
    memcpy((char *) htup + htup->t_hoff,
           (char *) tuple->t_data + tuple->t_data->t_hoff,
           newlen);
 
    MarkBufferDirty(buffer);
 
    /* XLOG stuff */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_inplace xlrec;
        XLogRecPtr  recptr;
 
        xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self);
 
        XLogBeginInsert();
        XLogRegisterData((char *) &xlrec, SizeOfHeapInplace);
 
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
        XLogRegisterBufData(0, (char *) htup + htup->t_hoff, newlen);
 
        /* inplace updates aren't decoded atm, don't log the origin */
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_INPLACE);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    UnlockReleaseBuffer(buffer);
 
    /*
     * Send out shared cache inval if necessary.  Note that because we only
     * pass the new version of the tuple, this mustn't be used for any
     * operations that could change catcache lookup keys.  But we aren't
     * bothering with index updates either, so that's true a fortiori.
     */
    if (!IsBootstrapProcessingMode())
        CacheInvalidateHeapTuple(relation, tuple, NULL);
}

References BUFFER_LOCK_EXCLUSIVE, BufferGetPage(), CacheInvalidateHeapTuple(), elog(), END_CRIT_SECTION, ereport, errcode(), errmsg(), ERROR, IsBootstrapProcessingMode, IsInParallelMode(), ItemIdGetLength, ItemIdIsNormal, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), LockBuffer(), MarkBufferDirty(), xl_heap_inplace::offnum, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PageSetLSN(), ReadBuffer(), REGBUF_STANDARD, RelationNeedsWAL, SizeOfHeapInplace, START_CRIT_SECTION, HeapTupleData::t_data, HeapTupleHeaderData::t_hoff, HeapTupleData::t_len, HeapTupleData::t_self, UnlockReleaseBuffer(), XLOG_HEAP_INPLACE, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by create_toast_table(), dropdb(), index_update_stats(), vac_update_datfrozenxid(), and vac_update_relstats().

heap_insert()

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

Definition at line 1817 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));
 
    /*
     * 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((char *) &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, (char *) &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(), 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 4126 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))
                        {
                            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))
                            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))
                        {
                            result = TM_WouldBlock;
                            /* recovery code expects to have buffer lock held */
                            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                            goto failed;
                        }
                        break;
                    case LockWaitError:
                        if (!ConditionalXactLockTableWait(xwait))
                            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)