heapam.h File Reference

#include "access/relation.h"
#include "access/relscan.h"
#include "access/sdir.h"
#include "access/skey.h"
#include "access/table.h"
#include "access/tableam.h"
#include "nodes/lockoptions.h"
#include "nodes/primnodes.h"
#include "storage/bufpage.h"
#include "storage/dsm.h"
#include "storage/lockdefs.h"
#include "storage/read_stream.h"
#include "storage/shm_toc.h"
#include "utils/relcache.h"
#include "utils/snapshot.h"

Include dependency graph for heapam.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	HeapScanDescData
struct	IndexFetchHeapData
struct	HeapTupleFreeze
struct	HeapPageFreeze
struct	PruneFreezeResult

Macros
#define	HEAP_INSERT_SKIP_FSM   TABLE_INSERT_SKIP_FSM
#define	HEAP_INSERT_FROZEN   TABLE_INSERT_FROZEN
#define	HEAP_INSERT_NO_LOGICAL   TABLE_INSERT_NO_LOGICAL
#define	HEAP_INSERT_SPECULATIVE   0x0010
#define	HEAP_PAGE_PRUNE_MARK_UNUSED_NOW   (1 << 0)
#define	HEAP_PAGE_PRUNE_FREEZE   (1 << 1)
#define	MaxLockTupleMode   LockTupleExclusive
#define	HEAP_FREEZE_CHECK_XMIN_COMMITTED   0x01
#define	HEAP_FREEZE_CHECK_XMAX_ABORTED   0x02
#define	HeapScanIsValid(scan)   PointerIsValid(scan)

Typedefs
typedef struct BulkInsertStateData *	BulkInsertState
typedef struct HeapScanDescData	HeapScanDescData
typedef struct HeapScanDescData *	HeapScanDesc
typedef struct IndexFetchHeapData	IndexFetchHeapData
typedef struct HeapTupleFreeze	HeapTupleFreeze
typedef struct HeapPageFreeze	HeapPageFreeze
typedef struct PruneFreezeResult	PruneFreezeResult

Enumerations
enum	HTSV_Result {   HEAPTUPLE_DEAD , HEAPTUPLE_LIVE , HEAPTUPLE_RECENTLY_DEAD , HEAPTUPLE_INSERT_IN_PROGRESS ,   HEAPTUPLE_DELETE_IN_PROGRESS }
enum	PruneReason { PRUNE_ON_ACCESS , PRUNE_VACUUM_SCAN , PRUNE_VACUUM_CLEANUP }

Functions
TableScanDesc	heap_beginscan (Relation relation, Snapshot snapshot, int nkeys, ScanKey key, ParallelTableScanDesc parallel_scan, uint32 flags)
void	heap_setscanlimits (TableScanDesc sscan, BlockNumber startBlk, BlockNumber numBlks)
void	heap_prepare_pagescan (TableScanDesc sscan)
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, struct 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)
BulkInsertState	GetBulkInsertState (void)
void	FreeBulkInsertState (BulkInsertState)
void	ReleaseBulkInsertStatePin (BulkInsertState bistate)
void	heap_insert (Relation relation, HeapTuple tup, CommandId cid, int options, BulkInsertState bistate)
void	heap_multi_insert (Relation relation, struct TupleTableSlot **slots, int ntuples, CommandId cid, int options, BulkInsertState bistate)
TM_Result	heap_delete (Relation relation, ItemPointer tid, CommandId cid, Snapshot crosscheck, bool wait, struct TM_FailureData *tmfd, bool changingPart)
void	heap_finish_speculative (Relation relation, ItemPointer tid)
void	heap_abort_speculative (Relation relation, ItemPointer tid)
TM_Result	heap_update (Relation relation, ItemPointer otid, HeapTuple newtup, CommandId cid, Snapshot crosscheck, bool wait, struct TM_FailureData *tmfd, LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes)
TM_Result	heap_lock_tuple (Relation relation, HeapTuple tuple, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, bool follow_updates, Buffer *buffer, struct TM_FailureData *tmfd)
void	heap_inplace_update (Relation relation, HeapTuple tuple)
bool	heap_prepare_freeze_tuple (HeapTupleHeader tuple, const struct VacuumCutoffs *cutoffs, HeapPageFreeze *pagefrz, HeapTupleFreeze *frz, bool *totally_frozen)
void	heap_pre_freeze_checks (Buffer buffer, HeapTupleFreeze *tuples, int ntuples)
void	heap_freeze_prepared_tuples (Buffer buffer, HeapTupleFreeze *tuples, int ntuples)
bool	heap_freeze_tuple (HeapTupleHeader tuple, TransactionId relfrozenxid, TransactionId relminmxid, TransactionId FreezeLimit, TransactionId MultiXactCutoff)
bool	heap_tuple_should_freeze (HeapTupleHeader tuple, const struct VacuumCutoffs *cutoffs, TransactionId *NoFreezePageRelfrozenXid, MultiXactId *NoFreezePageRelminMxid)
bool	heap_tuple_needs_eventual_freeze (HeapTupleHeader tuple)
void	simple_heap_insert (Relation relation, HeapTuple tup)
void	simple_heap_delete (Relation relation, ItemPointer tid)
void	simple_heap_update (Relation relation, ItemPointer otid, HeapTuple tup, TU_UpdateIndexes *update_indexes)
TransactionId	heap_index_delete_tuples (Relation rel, TM_IndexDeleteOp *delstate)
void	heap_page_prune_opt (Relation relation, Buffer buffer)
void	heap_page_prune_and_freeze (Relation relation, Buffer buffer, struct GlobalVisState *vistest, int options, struct VacuumCutoffs *cutoffs, PruneFreezeResult *presult, PruneReason reason, OffsetNumber *off_loc, TransactionId *new_relfrozen_xid, MultiXactId *new_relmin_mxid)
void	heap_page_prune_execute (Buffer buffer, bool lp_truncate_only, OffsetNumber *redirected, int nredirected, OffsetNumber *nowdead, int ndead, OffsetNumber *nowunused, int nunused)
void	heap_get_root_tuples (Page page, OffsetNumber *root_offsets)
void	log_heap_prune_and_freeze (Relation relation, Buffer buffer, TransactionId conflict_xid, bool cleanup_lock, PruneReason reason, HeapTupleFreeze *frozen, int nfrozen, OffsetNumber *redirected, int nredirected, OffsetNumber *dead, int ndead, OffsetNumber *unused, int nunused)
void	heap_vacuum_rel (Relation rel, struct VacuumParams *params, BufferAccessStrategy bstrategy)
bool	HeapTupleSatisfiesVisibility (HeapTuple htup, Snapshot snapshot, Buffer buffer)
TM_Result	HeapTupleSatisfiesUpdate (HeapTuple htup, CommandId curcid, Buffer buffer)
HTSV_Result	HeapTupleSatisfiesVacuum (HeapTuple htup, TransactionId OldestXmin, Buffer buffer)
HTSV_Result	HeapTupleSatisfiesVacuumHorizon (HeapTuple htup, Buffer buffer, TransactionId *dead_after)
void	HeapTupleSetHintBits (HeapTupleHeader tuple, Buffer buffer, uint16 infomask, TransactionId xid)
bool	HeapTupleHeaderIsOnlyLocked (HeapTupleHeader tuple)
bool	HeapTupleIsSurelyDead (HeapTuple htup, struct GlobalVisState *vistest)
bool	ResolveCminCmaxDuringDecoding (struct HTAB *tuplecid_data, Snapshot snapshot, HeapTuple htup, Buffer buffer, CommandId *cmin, CommandId *cmax)
void	HeapCheckForSerializableConflictOut (bool visible, Relation relation, HeapTuple tuple, Buffer buffer, Snapshot snapshot)

Macro Definition Documentation

HEAP_FREEZE_CHECK_XMAX_ABORTED

#define HEAP_FREEZE_CHECK_XMAX_ABORTED   0x02

Definition at line 137 of file heapam.h.

HEAP_FREEZE_CHECK_XMIN_COMMITTED

#define HEAP_FREEZE_CHECK_XMIN_COMMITTED   0x01

Definition at line 136 of file heapam.h.

HEAP_INSERT_FROZEN

#define HEAP_INSERT_FROZEN   TABLE_INSERT_FROZEN

Definition at line 36 of file heapam.h.

HEAP_INSERT_NO_LOGICAL

#define HEAP_INSERT_NO_LOGICAL   TABLE_INSERT_NO_LOGICAL

Definition at line 37 of file heapam.h.

HEAP_INSERT_SKIP_FSM

#define HEAP_INSERT_SKIP_FSM   TABLE_INSERT_SKIP_FSM

Definition at line 35 of file heapam.h.

HEAP_INSERT_SPECULATIVE

#define HEAP_INSERT_SPECULATIVE   0x0010

Definition at line 38 of file heapam.h.

HEAP_PAGE_PRUNE_FREEZE

#define HEAP_PAGE_PRUNE_FREEZE   (1 << 1)

Definition at line 42 of file heapam.h.

HEAP_PAGE_PRUNE_MARK_UNUSED_NOW

#define HEAP_PAGE_PRUNE_MARK_UNUSED_NOW   (1 << 0)

Definition at line 41 of file heapam.h.

HeapScanIsValid

#define HeapScanIsValid

(

scan

)

PointerIsValid(scan)

Definition at line 287 of file heapam.h.

MaxLockTupleMode

#define MaxLockTupleMode   LockTupleExclusive

Definition at line 48 of file heapam.h.

Typedef Documentation

BulkInsertState

typedef struct BulkInsertStateData* BulkInsertState

Definition at line 44 of file heapam.h.

HeapPageFreeze

typedef struct HeapPageFreeze HeapPageFreeze

HeapScanDesc

typedef struct HeapScanDescData* HeapScanDesc

Definition at line 109 of file heapam.h.

HeapScanDescData

typedef struct HeapScanDescData HeapScanDescData

HeapTupleFreeze

typedef struct HeapTupleFreeze HeapTupleFreeze

IndexFetchHeapData

typedef struct IndexFetchHeapData IndexFetchHeapData

PruneFreezeResult

typedef struct PruneFreezeResult PruneFreezeResult

Enumeration Type Documentation

HTSV_Result

enum HTSV_Result

Enumerator
HEAPTUPLE_DEAD
HEAPTUPLE_LIVE
HEAPTUPLE_RECENTLY_DEAD
HEAPTUPLE_INSERT_IN_PROGRESS
HEAPTUPLE_DELETE_IN_PROGRESS

Definition at line 123 of file heapam.h.

{
    HEAPTUPLE_DEAD,             /* tuple is dead and deletable */
    HEAPTUPLE_LIVE,             /* tuple is live (committed, no deleter) */
    HEAPTUPLE_RECENTLY_DEAD,    /* tuple is dead, but not deletable yet */
    HEAPTUPLE_INSERT_IN_PROGRESS,   /* inserting xact is still in progress */
    HEAPTUPLE_DELETE_IN_PROGRESS,   /* deleting xact is still in progress */
} HTSV_Result;

PruneReason

enum PruneReason

Enumerator
PRUNE_ON_ACCESS
PRUNE_VACUUM_SCAN
PRUNE_VACUUM_CLEANUP

Definition at line 267 of file heapam.h.

{
    PRUNE_ON_ACCESS,            /* on-access pruning */
    PRUNE_VACUUM_SCAN,          /* VACUUM 1st heap pass */
    PRUNE_VACUUM_CLEANUP,       /* VACUUM 2nd heap pass */
} PruneReason;

Function Documentation

FreeBulkInsertState()

void FreeBulkInsertState

(

BulkInsertState

bistate

)

Definition at line 1944 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().

GetBulkInsertState()

BulkInsertState GetBulkInsertState

(

void

)

Definition at line 1927 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().

heap_abort_speculative()

void heap_abort_speculative	(	Relation	relation,
		ItemPointer	tid
	)

Definition at line 5906 of file heapam.c.

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

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

Definition at line 1038 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 */
    scan->rs_vmbuffer = InvalidBuffer;
    scan->rs_empty_tuples_pending = 0;
 
    /*
     * 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);
 
    scan->rs_read_stream = NULL;
 
    /*
     * Set up a read stream for sequential scans and TID range scans. This
     * should be done after initscan() because initscan() allocates the
     * BufferAccessStrategy object passed to the read stream API.
     */
    if (scan->rs_base.rs_flags & SO_TYPE_SEQSCAN ||
        scan->rs_base.rs_flags & SO_TYPE_TIDRANGESCAN)
    {
        ReadStreamBlockNumberCB cb;
 
        if (scan->rs_base.rs_parallel)
            cb = heap_scan_stream_read_next_parallel;
        else
            cb = heap_scan_stream_read_next_serial;
 
        scan->rs_read_stream = read_stream_begin_relation(READ_STREAM_SEQUENTIAL,
                                                          scan->rs_strategy,
                                                          scan->rs_base.rs_rd,
                                                          MAIN_FORKNUM,
                                                          cb,
                                                          scan,
                                                          0);
    }
 
 
    return (TableScanDesc) scan;
}

References Assert, heap_scan_stream_read_next_parallel(), heap_scan_stream_read_next_serial(), if(), initscan(), InvalidBuffer, IsMVCCSnapshot, sort-test::key, MAIN_FORKNUM, palloc(), PredicateLockRelation(), read_stream_begin_relation(), READ_STREAM_SEQUENTIAL, RelationGetRelid, RelationIncrementReferenceCount(), HeapScanDescData::rs_base, HeapScanDescData::rs_ctup, HeapScanDescData::rs_empty_tuples_pending, TableScanDescData::rs_flags, TableScanDescData::rs_key, TableScanDescData::rs_nkeys, TableScanDescData::rs_parallel, HeapScanDescData::rs_parallelworkerdata, TableScanDescData::rs_rd, HeapScanDescData::rs_read_stream, TableScanDescData::rs_snapshot, HeapScanDescData::rs_strategy, HeapScanDescData::rs_vmbuffer, SO_ALLOW_PAGEMODE, SO_TYPE_SAMPLESCAN, SO_TYPE_SEQSCAN, SO_TYPE_TIDRANGESCAN, and HeapTupleData::t_tableOid.

heap_delete()

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

Definition at line 2683 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;
    }
 
    /* sanity check the result HeapTupleSatisfiesUpdate() and the logic above */
    if (result != TM_Ok)
    {
        Assert(result == TM_SelfModified ||
               result == TM_Updated ||
               result == TM_Deleted ||
               result == TM_BeingModified);
        Assert(!(tp.t_data->t_infomask & HEAP_XMAX_INVALID));
        Assert(result != TM_Updated ||
               !ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid));
    }
 
    if (crosscheck != InvalidSnapshot && result == TM_Ok)
    {
        /* Perform additional check for transaction-snapshot mode RI updates */
        if (!HeapTupleSatisfiesVisibility(&tp, crosscheck, buffer))
            result = TM_Updated;
    }
 
    if (result != TM_Ok)
    {
        tmfd->ctid = tp.t_data->t_ctid;
        tmfd->xmax = HeapTupleHeaderGetUpdateXid(tp.t_data);
        if (result == TM_SelfModified)
            tmfd->cmax = HeapTupleHeaderGetCmax(tp.t_data);
        else
            tmfd->cmax = InvalidCommandId;
        UnlockReleaseBuffer(buffer);
        if (have_tuple_lock)
            UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive);
        if (vmbuffer != InvalidBuffer)
            ReleaseBuffer(vmbuffer);
        return result;
    }
 
    /*
     * We're about to do the actual delete -- check for conflict first, to
     * avoid possibly having to roll back work we've just done.
     *
     * This is safe without a recheck as long as there is no possibility of
     * another process scanning the page between this check and the delete
     * being visible to the scan (i.e., an exclusive buffer content lock is
     * continuously held from this point until the tuple delete is visible).
     */
    CheckForSerializableConflictIn(relation, tid, BufferGetBlockNumber(buffer));
 
    /* replace cid with a combo CID if necessary */
    HeapTupleHeaderAdjustCmax(tp.t_data, &cid, &iscombo);
 
    /*
     * Compute replica identity tuple before entering the critical section so
     * we don't PANIC upon a memory allocation failure.
     */
    old_key_tuple = ExtractReplicaIdentity(relation, &tp, true, &old_key_copied);
 
    /*
     * If this is the first possibly-multixact-able operation in the current
     * transaction, set my per-backend OldestMemberMXactId setting. We can be
     * certain that the transaction will never become a member of any older
     * MultiXactIds than that.  (We have to do this even if we end up just
     * using our own TransactionId below, since some other backend could
     * incorporate our XID into a MultiXact immediately afterwards.)
     */
    MultiXactIdSetOldestMember();
 
    compute_new_xmax_infomask(HeapTupleHeaderGetRawXmax(tp.t_data),
                              tp.t_data->t_infomask, tp.t_data->t_infomask2,
                              xid, LockTupleExclusive, true,
                              &new_xmax, &new_infomask, &new_infomask2);
 
    START_CRIT_SECTION();
 
    /*
     * If this transaction commits, the tuple will become DEAD sooner or
     * later.  Set flag that this page is a candidate for pruning once our xid
     * falls below the OldestXmin horizon.  If the transaction finally aborts,
     * the subsequent page pruning will be a no-op and the hint will be
     * cleared.
     */
    PageSetPrunable(page, xid);
 
    if (PageIsAllVisible(page))
    {
        all_visible_cleared = true;
        PageClearAllVisible(page);
        visibilitymap_clear(relation, BufferGetBlockNumber(buffer),
                            vmbuffer, VISIBILITYMAP_VALID_BITS);
    }
 
    /* store transaction information of xact deleting the tuple */
    tp.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
    tp.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    tp.t_data->t_infomask |= new_infomask;
    tp.t_data->t_infomask2 |= new_infomask2;
    HeapTupleHeaderClearHotUpdated(tp.t_data);
    HeapTupleHeaderSetXmax(tp.t_data, new_xmax);
    HeapTupleHeaderSetCmax(tp.t_data, cid, iscombo);
    /* Make sure there is no forward chain link in t_ctid */
    tp.t_data->t_ctid = tp.t_self;
 
    /* Signal that this is actually a move into another partition */
    if (changingPart)
        HeapTupleHeaderSetMovedPartitions(tp.t_data);
 
    MarkBufferDirty(buffer);
 
    /*
     * XLOG stuff
     *
     * NB: heap_abort_speculative() uses the same xlog record and replay
     * routines.
     */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_delete xlrec;
        xl_heap_header xlhdr;
        XLogRecPtr  recptr;
 
        /*
         * For logical decode we need combo CIDs to properly decode the
         * catalog
         */
        if (RelationIsAccessibleInLogicalDecoding(relation))
            log_heap_new_cid(relation, &tp);
 
        xlrec.flags = 0;
        if (all_visible_cleared)
            xlrec.flags |= XLH_DELETE_ALL_VISIBLE_CLEARED;
        if (changingPart)
            xlrec.flags |= XLH_DELETE_IS_PARTITION_MOVE;
        xlrec.infobits_set = compute_infobits(tp.t_data->t_infomask,
                                              tp.t_data->t_infomask2);
        xlrec.offnum = ItemPointerGetOffsetNumber(&tp.t_self);
        xlrec.xmax = new_xmax;
 
        if (old_key_tuple != NULL)
        {
            if (relation->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
                xlrec.flags |= XLH_DELETE_CONTAINS_OLD_TUPLE;
            else
                xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
        }
 
        XLogBeginInsert();
        XLogRegisterData((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 1210 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);
 
    if (BufferIsValid(scan->rs_vmbuffer))
        ReleaseBuffer(scan->rs_vmbuffer);
 
    /*
     * Must free the read stream before freeing the BufferAccessStrategy.
     */
    if (scan->rs_read_stream)
        read_stream_end(scan->rs_read_stream);
 
    /*
     * decrement relation reference count and free scan descriptor storage
     */
    RelationDecrementReferenceCount(scan->rs_base.rs_rd);
 
    if (scan->rs_base.rs_key)
        pfree(scan->rs_base.rs_key);
 
    if (scan->rs_strategy != NULL)
        FreeAccessStrategy(scan->rs_strategy);
 
    if (scan->rs_parallelworkerdata != NULL)
        pfree(scan->rs_parallelworkerdata);
 
    if (scan->rs_base.rs_flags & SO_TEMP_SNAPSHOT)
        UnregisterSnapshot(scan->rs_base.rs_snapshot);
 
    pfree(scan);
}

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

heap_fetch()

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

Definition at line 1511 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 5819 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_prepared_tuples()

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

Definition at line 6900 of file heapam.c.

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

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

Referenced by heap_page_prune_and_freeze().

heap_freeze_tuple()

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

Definition at line 6922 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 1783 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_get_root_tuples()

void heap_get_root_tuples	(	Page	page,
		OffsetNumber *	root_offsets
	)

Definition at line 1785 of file pruneheap.c.

{
    OffsetNumber offnum,
                maxoff;
 
    MemSet(root_offsets, InvalidOffsetNumber,
           MaxHeapTuplesPerPage * sizeof(OffsetNumber));
 
    maxoff = PageGetMaxOffsetNumber(page);
    for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
    {
        ItemId      lp = PageGetItemId(page, offnum);
        HeapTupleHeader htup;
        OffsetNumber nextoffnum;
        TransactionId priorXmax;
 
        /* skip unused and dead items */
        if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
            continue;
 
        if (ItemIdIsNormal(lp))
        {
            htup = (HeapTupleHeader) PageGetItem(page, lp);
 
            /*
             * Check if this tuple is part of a HOT-chain rooted at some other
             * tuple. If so, skip it for now; we'll process it when we find
             * its root.
             */
            if (HeapTupleHeaderIsHeapOnly(htup))
                continue;
 
            /*
             * This is either a plain tuple or the root of a HOT-chain.
             * Remember it in the mapping.
             */
            root_offsets[offnum - 1] = offnum;
 
            /* If it's not the start of a HOT-chain, we're done with it */
            if (!HeapTupleHeaderIsHotUpdated(htup))
                continue;
 
            /* Set up to scan the HOT-chain */
            nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
            priorXmax = HeapTupleHeaderGetUpdateXid(htup);
        }
        else
        {
            /* Must be a redirect item. We do not set its root_offsets entry */
            Assert(ItemIdIsRedirected(lp));
            /* Set up to scan the HOT-chain */
            nextoffnum = ItemIdGetRedirect(lp);
            priorXmax = InvalidTransactionId;
        }
 
        /*
         * Now follow the HOT-chain and collect other tuples in the chain.
         *
         * Note: Even though this is a nested loop, the complexity of the
         * function is O(N) because a tuple in the page should be visited not
         * more than twice, once in the outer loop and once in HOT-chain
         * chases.
         */
        for (;;)
        {
            /* 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, nextoffnum);
 
            /* Check for broken chains */
            if (!ItemIdIsNormal(lp))
                break;
 
            htup = (HeapTupleHeader) PageGetItem(page, lp);
 
            if (TransactionIdIsValid(priorXmax) &&
                !TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
                break;
 
            /* Remember the root line pointer for this item */
            root_offsets[nextoffnum - 1] = offnum;
 
            /* Advance to next chain member, if any */
            if (!HeapTupleHeaderIsHotUpdated(htup))
                break;
 
            /* HOT implies it can't have moved to different partition */
            Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
 
            nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
            priorXmax = HeapTupleHeaderGetUpdateXid(htup);
        }
    }
}

References Assert, FirstOffsetNumber, HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleHeaderIndicatesMovedPartitions, HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, InvalidOffsetNumber, InvalidTransactionId, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetOffsetNumber(), MaxHeapTuplesPerPage, MemSet, OffsetNumberNext, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.

Referenced by heapam_index_build_range_scan(), and heapam_index_validate_scan().

heap_getnext()

HeapTuple heap_getnext	(	TableScanDesc	sscan,
		ScanDirection	direction
	)

Definition at line 1252 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,
		struct TupleTableSlot *	slot
	)

Definition at line 1301 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 1404 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 1631 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 7636 of file heapam.c.

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

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

heap_inplace_update()

void heap_inplace_update	(	Relation	relation,
		HeapTuple	tuple
	)

Definition at line 6063 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")));
 
    INJECTION_POINT("inplace-before-pin");
    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, INJECTION_POINT, 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(), EventTriggerOnLogin(), 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 1994 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,
		struct TM_FailureData *	tmfd
	)

Definition at line 4310 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)
                {
                    result = res;
                    /* recovery code expects to have buffer lock held */
                    LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
                    goto failed;
                }
            }
 
            LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
 
            /*
             * xwait is done, but if xwait had just locked the tuple then some
             * other xact could update this tuple before we get to this point.
             * Check for xmax change, and start over if so.
             */
            if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) ||
                !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data),
                                     xwait))
                goto l3;
 
            if (!(infomask & HEAP_XMAX_IS_MULTI))
            {
                /*
                 * Otherwise check if it committed or aborted.  Note we cannot
                 * be here if the tuple was only locked by somebody who didn't
                 * conflict with us; that would have been handled above.  So
                 * that transaction must necessarily be gone by now.  But
                 * don't check for this in the multixact case, because some
                 * locker transactions might still be running.
                 */
                UpdateXmaxHintBits(tuple->t_data, *buffer, xwait);
            }
        }
 
        /* By here, we're certain that we hold buffer exclusive lock again */
 
        /*
         * We may lock if previous xmax aborted, or if it committed but only
         * locked the tuple without updating it; or if we didn't have to wait
         * at all for whatever reason.
         */
        if (!require_sleep ||
            (tuple->t_data->t_infomask & HEAP_XMAX_INVALID) ||
            HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_data->t_infomask) ||
            HeapTupleHeaderIsOnlyLocked(tuple->t_data))
            result = TM_Ok;
        else if (!ItemPointerEquals(&tuple->t_self, &tuple->t_data->t_ctid))
            result = TM_Updated;
        else
            result = TM_Deleted;
    }
 
failed:
    if (result != TM_Ok)
    {
        Assert(result == TM_SelfModified || result == TM_Updated ||
               result == TM_Deleted || result == TM_WouldBlock);
 
        /*
         * When locking a tuple under LockWaitSkip semantics and we fail with
         * TM_WouldBlock above, it's possible for concurrent transactions to
         * release the lock and set HEAP_XMAX_INVALID in the meantime.  So
         * this assert is slightly different from the equivalent one in
         * heap_delete and heap_update.
         */
        Assert((result == TM_WouldBlock) ||
               !(tuple->t_data->t_infomask & HEAP_XMAX_INVALID));
        Assert(result != TM_Updated ||
               !ItemPointerEquals(&tuple->t_self, &tuple->t_data->t_ctid));
        tmfd->ctid = tuple->t_data->t_ctid;
        tmfd->xmax = HeapTupleHeaderGetUpdateXid(tuple->t_data);
        if (result == TM_SelfModified)
            tmfd->cmax = HeapTupleHeaderGetCmax(tuple->t_data);
        else
            tmfd->cmax = InvalidCommandId;
        goto out_locked;
    }
 
    /*
     * If we didn't pin the visibility map page and the page has become all
     * visible while we were busy locking the buffer, or during some
     * subsequent window during which we had it unlocked, we'll have to unlock
     * and re-lock, to avoid holding the buffer lock across I/O.  That's a bit
     * unfortunate, especially since we'll now have to recheck whether the
     * tuple has been locked or updated under us, but hopefully it won't
     * happen very often.
     */
    if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
    {
        LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
        visibilitymap_pin(relation, block, &vmbuffer);
        LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
        goto l3;
    }
 
    xmax = HeapTupleHeaderGetRawXmax(tuple->t_data);
    old_infomask = tuple->t_data->t_infomask;
 
    /*
     * If this is the first possibly-multixact-able operation in the current
     * transaction, set my per-backend OldestMemberMXactId setting. We can be
     * certain that the transaction will never become a member of any older
     * MultiXactIds than that.  (We have to do this even if we end up just
     * using our own TransactionId below, since some other backend could
     * incorporate our XID into a MultiXact immediately afterwards.)
     */
    MultiXactIdSetOldestMember();
 
    /*
     * Compute the new xmax and infomask to store into the tuple.  Note we do
     * not modify the tuple just yet, because that would leave it in the wrong
     * state if multixact.c elogs.
     */
    compute_new_xmax_infomask(xmax, old_infomask, tuple->t_data->t_infomask2,
                              GetCurrentTransactionId(), mode, false,
                              &xid, &new_infomask, &new_infomask2);
 
    START_CRIT_SECTION();
 
    /*
     * Store transaction information of xact locking the tuple.
     *
     * Note: Cmax is meaningless in this context, so don't set it; this avoids
     * possibly generating a useless combo CID.  Moreover, if we're locking a
     * previously updated tuple, it's important to preserve the Cmax.
     *
     * Also reset the HOT UPDATE bit, but only if there's no update; otherwise
     * we would break the HOT chain.
     */
    tuple->t_data->t_infomask &= ~HEAP_XMAX_BITS;
    tuple->t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
    tuple->t_data->t_infomask |= new_infomask;
    tuple->t_data->t_infomask2 |= new_infomask2;
    if (HEAP_XMAX_IS_LOCKED_ONLY(new_infomask))
        HeapTupleHeaderClearHotUpdated(tuple->t_data);
    HeapTupleHeaderSetXmax(tuple->t_data, xid);
 
    /*
     * Make sure there is no forward chain link in t_ctid.  Note that in the
     * cases where the tuple has been updated, we must not overwrite t_ctid,
     * because it was set by the updater.  Moreover, if the tuple has been
     * updated, we need to follow the update chain to lock the new versions of
     * the tuple as well.
     */
    if (HEAP_XMAX_IS_LOCKED_ONLY(new_infomask))
        tuple->t_data->t_ctid = *tid;
 
    /* Clear only the all-frozen bit on visibility map if needed */
    if (PageIsAllVisible(page) &&
        visibilitymap_clear(relation, block, vmbuffer,
                            VISIBILITYMAP_ALL_FROZEN))
        cleared_all_frozen = true;
 
 
    MarkBufferDirty(*buffer);
 
    /*
     * XLOG stuff.  You might think that we don't need an XLOG record because
     * there is no state change worth restoring after a crash.  You would be
     * wrong however: we have just written either a TransactionId or a
     * MultiXactId that may never have been seen on disk before, and we need
     * to make sure that there are XLOG entries covering those ID numbers.
     * Else the same IDs might be re-used after a crash, which would be
     * disastrous if this page made it to disk before the crash.  Essentially
     * we have to enforce the WAL log-before-data rule even in this case.
     * (Also, in a PITR log-shipping or 2PC environment, we have to have XLOG
     * entries for everything anyway.)
     */
    if (RelationNeedsWAL(relation))
    {
        xl_heap_lock xlrec;
        XLogRecPtr  recptr;
 
        XLogBeginInsert();
        XLogRegisterBuffer(0, *buffer, REGBUF_STANDARD);
 
        xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self);
        xlrec.xmax = xid;
        xlrec.infobits_set = compute_infobits(new_infomask,
                                              tuple->t_data->t_infomask2);
        xlrec.flags = cleared_all_frozen ? XLH_LOCK_ALL_FROZEN_CLEARED : 0;
        XLogRegisterData((char *) &xlrec, SizeOfHeapLock);
 
        /* we don't decode row locks atm, so no need to log the origin */
 
        recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK);
 
        PageSetLSN(page, recptr);
    }
 
    END_CRIT_SECTION();
 
    result = TM_Ok;
 
out_locked:
    LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
 
out_unlocked:
    if (BufferIsValid(vmbuffer))
        ReleaseBuffer(vmbuffer);
 
    /*
     * Don't update the visibility map here. Locking a tuple doesn't change
     * visibility info.
     */
 
    /*
     * Now that we have successfully marked the tuple as locked, we can
     * release the lmgr tuple lock, if we had it.
     */
    if (have_tuple_lock)
        UnlockTupleTuplock(relation, tid, mode);
 
    return result;
}

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

Referenced by heapam_tuple_lock().

heap_multi_insert()

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

Definition at line 2263 of file heapam.c.

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

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

Referenced by CatalogTuplesMultiInsertWithInfo().

heap_page_prune_and_freeze()

void heap_page_prune_and_freeze	(	Relation	relation,
		Buffer	buffer,
		struct GlobalVisState *	vistest,
		int	options,
		struct VacuumCutoffs *	cutoffs,
		PruneFreezeResult *	presult,
		PruneReason	reason,
		OffsetNumber *	off_loc,
		TransactionId *	new_relfrozen_xid,
		MultiXactId *	new_relmin_mxid
	)

Definition at line 350 of file pruneheap.c.

{
    Page        page = BufferGetPage(buffer);
    BlockNumber blockno = BufferGetBlockNumber(buffer);
    OffsetNumber offnum,
                maxoff;
    PruneState  prstate;
    HeapTupleData tup;
    bool        do_freeze;
    bool        do_prune;
    bool        do_hint;
    bool        hint_bit_fpi;
    int64       fpi_before = pgWalUsage.wal_fpi;
 
    /* Copy parameters to prstate */
    prstate.vistest = vistest;
    prstate.mark_unused_now = (options & HEAP_PAGE_PRUNE_MARK_UNUSED_NOW) != 0;
    prstate.freeze = (options & HEAP_PAGE_PRUNE_FREEZE) != 0;
    prstate.cutoffs = cutoffs;
 
    /*
     * Our strategy is to scan the page and make lists of items to change,
     * then apply the changes within a critical section.  This keeps as much
     * logic as possible out of the critical section, and also ensures that
     * WAL replay will work the same as the normal case.
     *
     * First, initialize the new pd_prune_xid value to zero (indicating no
     * prunable tuples).  If we find any tuples which may soon become
     * prunable, we will save the lowest relevant XID in new_prune_xid. Also
     * initialize the rest of our working state.
     */
    prstate.new_prune_xid = InvalidTransactionId;
    prstate.latest_xid_removed = InvalidTransactionId;
    prstate.nredirected = prstate.ndead = prstate.nunused = prstate.nfrozen = 0;
    prstate.nroot_items = 0;
    prstate.nheaponly_items = 0;
 
    /* initialize page freezing working state */
    prstate.pagefrz.freeze_required = false;
    if (prstate.freeze)
    {
        Assert(new_relfrozen_xid && new_relmin_mxid);
        prstate.pagefrz.FreezePageRelfrozenXid = *new_relfrozen_xid;
        prstate.pagefrz.NoFreezePageRelfrozenXid = *new_relfrozen_xid;
        prstate.pagefrz.FreezePageRelminMxid = *new_relmin_mxid;
        prstate.pagefrz.NoFreezePageRelminMxid = *new_relmin_mxid;
    }
    else
    {
        Assert(new_relfrozen_xid == NULL && new_relmin_mxid == NULL);
        prstate.pagefrz.FreezePageRelminMxid = InvalidMultiXactId;
        prstate.pagefrz.NoFreezePageRelminMxid = InvalidMultiXactId;
        prstate.pagefrz.FreezePageRelfrozenXid = InvalidTransactionId;
        prstate.pagefrz.NoFreezePageRelfrozenXid = InvalidTransactionId;
    }
 
    prstate.ndeleted = 0;
    prstate.live_tuples = 0;
    prstate.recently_dead_tuples = 0;
    prstate.hastup = false;
    prstate.lpdead_items = 0;
    prstate.deadoffsets = presult->deadoffsets;
 
    /*
     * Caller may update the VM after we're done.  We can keep track of
     * whether the page will be all-visible and all-frozen after pruning and
     * freezing to help the caller to do that.
     *
     * Currently, only VACUUM sets the VM bits.  To save the effort, only do
     * the bookkeeping if the caller needs it.  Currently, that's tied to
     * HEAP_PAGE_PRUNE_FREEZE, but it could be a separate flag if you wanted
     * to update the VM bits without also freezing or freeze without also
     * setting the VM bits.
     *
     * In addition to telling the caller whether it can set the VM bit, we
     * also use 'all_visible' and 'all_frozen' for our own decision-making. If
     * the whole page would become frozen, we consider opportunistically
     * freezing tuples.  We will not be able to freeze the whole page if there
     * are tuples present that are not visible to everyone or if there are
     * dead tuples which are not yet removable.  However, dead tuples which
     * will be removed by the end of vacuuming should not preclude us from
     * opportunistically freezing.  Because of that, we do not clear
     * all_visible when we see LP_DEAD items.  We fix that at the end of the
     * function, when we return the value to the caller, so that the caller
     * doesn't set the VM bit incorrectly.
     */
    if (prstate.freeze)
    {
        prstate.all_visible = true;
        prstate.all_frozen = true;
    }
    else
    {
        /*
         * Initializing to false allows skipping the work to update them in
         * heap_prune_record_unchanged_lp_normal().
         */
        prstate.all_visible = false;
        prstate.all_frozen = false;
    }
 
    /*
     * The visibility cutoff xid is the newest xmin of live tuples on the
     * page.  In the common case, this will be set as the conflict horizon the
     * caller can use for updating the VM.  If, at the end of freezing and
     * pruning, the page is all-frozen, there is no possibility that any
     * running transaction on the standby does not see tuples on the page as
     * all-visible, so the conflict horizon remains InvalidTransactionId.
     */
    prstate.visibility_cutoff_xid = InvalidTransactionId;
 
    maxoff = PageGetMaxOffsetNumber(page);
    tup.t_tableOid = RelationGetRelid(relation);
 
    /*
     * Determine HTSV for all tuples, and queue them up for processing as HOT
     * chain roots or as heap-only items.
     *
     * Determining HTSV only once for each tuple is required for correctness,
     * to deal with cases where running HTSV twice could result in different
     * results.  For example, RECENTLY_DEAD can turn to DEAD if another
     * checked item causes GlobalVisTestIsRemovableFullXid() to update the
     * horizon, or INSERT_IN_PROGRESS can change to DEAD if the inserting
     * transaction aborts.
     *
     * It's also good for performance. Most commonly tuples within a page are
     * stored at decreasing offsets (while the items are stored at increasing
     * offsets). When processing all tuples on a page this leads to reading
     * memory at decreasing offsets within a page, with a variable stride.
     * That's hard for CPU prefetchers to deal with. Processing the items in
     * reverse order (and thus the tuples in increasing order) increases
     * prefetching efficiency significantly / decreases the number of cache
     * misses.
     */
    for (offnum = maxoff;
         offnum >= FirstOffsetNumber;
         offnum = OffsetNumberPrev(offnum))
    {
        ItemId      itemid = PageGetItemId(page, offnum);
        HeapTupleHeader htup;
 
        /*
         * Set the offset number so that we can display it along with any
         * error that occurred while processing this tuple.
         */
        *off_loc = offnum;
 
        prstate.processed[offnum] = false;
        prstate.htsv[offnum] = -1;
 
        /* Nothing to do if slot doesn't contain a tuple */
        if (!ItemIdIsUsed(itemid))
        {
            heap_prune_record_unchanged_lp_unused(page, &prstate, offnum);
            continue;
        }
 
        if (ItemIdIsDead(itemid))
        {
            /*
             * If the caller set mark_unused_now true, we can set dead line
             * pointers LP_UNUSED now.
             */
            if (unlikely(prstate.mark_unused_now))
                heap_prune_record_unused(&prstate, offnum, false);
            else
                heap_prune_record_unchanged_lp_dead(page, &prstate, offnum);
            continue;
        }
 
        if (ItemIdIsRedirected(itemid))
        {
            /* This is the start of a HOT chain */
            prstate.root_items[prstate.nroot_items++] = offnum;
            continue;
        }
 
        Assert(ItemIdIsNormal(itemid));
 
        /*
         * Get the tuple's visibility status and queue it up for processing.
         */
        htup = (HeapTupleHeader) PageGetItem(page, itemid);
        tup.t_data = htup;
        tup.t_len = ItemIdGetLength(itemid);
        ItemPointerSet(&tup.t_self, blockno, offnum);
 
        prstate.htsv[offnum] = heap_prune_satisfies_vacuum(&prstate, &tup,
                                                           buffer);
 
        if (!HeapTupleHeaderIsHeapOnly(htup))
            prstate.root_items[prstate.nroot_items++] = offnum;
        else
            prstate.heaponly_items[prstate.nheaponly_items++] = offnum;
    }
 
    /*
     * If checksums are enabled, heap_prune_satisfies_vacuum() may have caused
     * an FPI to be emitted.
     */
    hint_bit_fpi = fpi_before != pgWalUsage.wal_fpi;
 
    /*
     * Process HOT chains.
     *
     * We added the items to the array starting from 'maxoff', so by
     * processing the array in reverse order, we process the items in
     * ascending offset number order.  The order doesn't matter for
     * correctness, but some quick micro-benchmarking suggests that this is
     * faster.  (Earlier PostgreSQL versions, which scanned all the items on
     * the page instead of using the root_items array, also did it in
     * ascending offset number order.)
     */
    for (int i = prstate.nroot_items - 1; i >= 0; i--)
    {
        offnum = prstate.root_items[i];
 
        /* Ignore items already processed as part of an earlier chain */
        if (prstate.processed[offnum])
            continue;
 
        /* see preceding loop */
        *off_loc = offnum;
 
        /* Process this item or chain of items */
        heap_prune_chain(page, blockno, maxoff, offnum, &prstate);
    }
 
    /*
     * Process any heap-only tuples that were not already processed as part of
     * a HOT chain.
     */
    for (int i = prstate.nheaponly_items - 1; i >= 0; i--)
    {
        offnum = prstate.heaponly_items[i];
 
        if (prstate.processed[offnum])
            continue;
 
        /* see preceding loop */
        *off_loc = offnum;
 
        /*
         * If the tuple is DEAD and doesn't chain to anything else, mark it
         * unused.  (If it does chain, we can only remove it as part of
         * pruning its chain.)
         *
         * We need this primarily to handle aborted HOT updates, that is,
         * XMIN_INVALID heap-only tuples.  Those might not be linked to by any
         * chain, since the parent tuple might be re-updated before any
         * pruning occurs.  So we have to be able to reap them separately from
         * chain-pruning.  (Note that HeapTupleHeaderIsHotUpdated will never
         * return true for an XMIN_INVALID tuple, so this code will work even
         * when there were sequential updates within the aborted transaction.)
         */
        if (prstate.htsv[offnum] == HEAPTUPLE_DEAD)
        {
            ItemId      itemid = PageGetItemId(page, offnum);
            HeapTupleHeader htup = (HeapTupleHeader) PageGetItem(page, itemid);
 
            if (likely(!HeapTupleHeaderIsHotUpdated(htup)))
            {
                HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                      &prstate.latest_xid_removed);
                heap_prune_record_unused(&prstate, offnum, true);
            }
            else
            {
                /*
                 * This tuple should've been processed and removed as part of
                 * a HOT chain, so something's wrong.  To preserve evidence,
                 * we don't dare to remove it.  We cannot leave behind a DEAD
                 * tuple either, because that will cause VACUUM to error out.
                 * Throwing an error with a distinct error message seems like
                 * the least bad option.
                 */
                elog(ERROR, "dead heap-only tuple (%u, %d) is not linked to from any HOT chain",
                     blockno, offnum);
            }
        }
        else
            heap_prune_record_unchanged_lp_normal(page, &prstate, offnum);
    }
 
    /* We should now have processed every tuple exactly once  */
#ifdef USE_ASSERT_CHECKING
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        *off_loc = offnum;
 
        Assert(prstate.processed[offnum]);
    }
#endif
 
    /* Clear the offset information once we have processed the given page. */
    *off_loc = InvalidOffsetNumber;
 
    do_prune = prstate.nredirected > 0 ||
        prstate.ndead > 0 ||
        prstate.nunused > 0;
 
    /*
     * Even if we don't prune anything, if we found a new value for the
     * pd_prune_xid field or the page was marked full, we will update the hint
     * bit.
     */
    do_hint = ((PageHeader) page)->pd_prune_xid != prstate.new_prune_xid ||
        PageIsFull(page);
 
    /*
     * Decide if we want to go ahead with freezing according to the freeze
     * plans we prepared, or not.
     */
    do_freeze = false;
    if (prstate.freeze)
    {
        if (prstate.pagefrz.freeze_required)
        {
            /*
             * heap_prepare_freeze_tuple indicated that at least one XID/MXID
             * from before FreezeLimit/MultiXactCutoff is present.  Must
             * freeze to advance relfrozenxid/relminmxid.
             */
            do_freeze = true;
        }
        else
        {
            /*
             * Opportunistically freeze the page if we are generating an FPI
             * anyway and if doing so means that we can set the page
             * all-frozen afterwards (might not happen until VACUUM's final
             * heap pass).
             *
             * XXX: Previously, we knew if pruning emitted an FPI by checking
             * pgWalUsage.wal_fpi before and after pruning.  Once the freeze
             * and prune records were combined, this heuristic couldn't be
             * used anymore.  The opportunistic freeze heuristic must be
             * improved; however, for now, try to approximate the old logic.
             */
            if (prstate.all_visible && prstate.all_frozen && prstate.nfrozen > 0)
            {
                /*
                 * Freezing would make the page all-frozen.  Have already
                 * emitted an FPI or will do so anyway?
                 */
                if (RelationNeedsWAL(relation))
                {
                    if (hint_bit_fpi)
                        do_freeze = true;
                    else if (do_prune)
                    {
                        if (XLogCheckBufferNeedsBackup(buffer))
                            do_freeze = true;
                    }
                    else if (do_hint)
                    {
                        if (XLogHintBitIsNeeded() && XLogCheckBufferNeedsBackup(buffer))
                            do_freeze = true;
                    }
                }
            }
        }
    }
 
    if (do_freeze)
    {
        /*
         * Validate the tuples we will be freezing before entering the
         * critical section.
         */
        heap_pre_freeze_checks(buffer, prstate.frozen, prstate.nfrozen);
    }
    else if (prstate.nfrozen > 0)
    {
        /*
         * The page contained some tuples that were not already frozen, and we
         * chose not to freeze them now.  The page won't be all-frozen then.
         */
        Assert(!prstate.pagefrz.freeze_required);
 
        prstate.all_frozen = false;
        prstate.nfrozen = 0;    /* avoid miscounts in instrumentation */
    }
    else
    {
        /*
         * We have no freeze plans to execute.  The page might already be
         * all-frozen (perhaps only following pruning), though.  Such pages
         * can be marked all-frozen in the VM by our caller, even though none
         * of its tuples were newly frozen here.
         */
    }
 
    /* Any error while applying the changes is critical */
    START_CRIT_SECTION();
 
    if (do_hint)
    {
        /*
         * Update the page's pd_prune_xid field to either zero, or the lowest
         * XID of any soon-prunable tuple.
         */
        ((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
 
        /*
         * Also clear the "page is full" flag, since there's no point in
         * repeating the prune/defrag process until something else happens to
         * the page.
         */
        PageClearFull(page);
 
        /*
         * If that's all we had to do to the page, this is a non-WAL-logged
         * hint.  If we are going to freeze or prune the page, we will mark
         * the buffer dirty below.
         */
        if (!do_freeze && !do_prune)
            MarkBufferDirtyHint(buffer, true);
    }
 
    if (do_prune || do_freeze)
    {
        /* Apply the planned item changes and repair page fragmentation. */
        if (do_prune)
        {
            heap_page_prune_execute(buffer, false,
                                    prstate.redirected, prstate.nredirected,
                                    prstate.nowdead, prstate.ndead,
                                    prstate.nowunused, prstate.nunused);
        }
 
        if (do_freeze)
            heap_freeze_prepared_tuples(buffer, prstate.frozen, prstate.nfrozen);
 
        MarkBufferDirty(buffer);
 
        /*
         * Emit a WAL XLOG_HEAP2_PRUNE_FREEZE record showing what we did
         */
        if (RelationNeedsWAL(relation))
        {
            /*
             * The snapshotConflictHorizon for the whole record should be the
             * most conservative of all the horizons calculated for any of the
             * possible modifications.  If this record will prune tuples, any
             * transactions on the standby older than the youngest xmax of the
             * most recently removed tuple this record will prune will
             * conflict.  If this record will freeze tuples, any transactions
             * on the standby with xids older than the youngest tuple this
             * record will freeze will conflict.
             */
            TransactionId frz_conflict_horizon = InvalidTransactionId;
            TransactionId conflict_xid;
 
            /*
             * We can use the visibility_cutoff_xid as our cutoff for
             * conflicts when the whole page is eligible to become all-frozen
             * in the VM once we're done with it.  Otherwise we generate a
             * conservative cutoff by stepping back from OldestXmin.
             */
            if (do_freeze)
            {
                if (prstate.all_visible && prstate.all_frozen)
                    frz_conflict_horizon = prstate.visibility_cutoff_xid;
                else
                {
                    /* Avoids false conflicts when hot_standby_feedback in use */
                    frz_conflict_horizon = prstate.cutoffs->OldestXmin;
                    TransactionIdRetreat(frz_conflict_horizon);
                }
            }
 
            if (TransactionIdFollows(frz_conflict_horizon, prstate.latest_xid_removed))
                conflict_xid = frz_conflict_horizon;
            else
                conflict_xid = prstate.latest_xid_removed;
 
            log_heap_prune_and_freeze(relation, buffer,
                                      conflict_xid,
                                      true, reason,
                                      prstate.frozen, prstate.nfrozen,
                                      prstate.redirected, prstate.nredirected,
                                      prstate.nowdead, prstate.ndead,
                                      prstate.nowunused, prstate.nunused);
        }
    }
 
    END_CRIT_SECTION();
 
    /* Copy information back for caller */
    presult->ndeleted = prstate.ndeleted;
    presult->nnewlpdead = prstate.ndead;
    presult->nfrozen = prstate.nfrozen;
    presult->live_tuples = prstate.live_tuples;
    presult->recently_dead_tuples = prstate.recently_dead_tuples;
 
    /*
     * It was convenient to ignore LP_DEAD items in all_visible earlier on to
     * make the choice of whether or not to freeze the page unaffected by the
     * short-term presence of LP_DEAD items.  These LP_DEAD items were
     * effectively assumed to be LP_UNUSED items in the making.  It doesn't
     * matter which vacuum heap pass (initial pass or final pass) ends up
     * setting the page all-frozen, as long as the ongoing VACUUM does it.
     *
     * Now that freezing has been finalized, unset all_visible if there are
     * any LP_DEAD items on the page.  It needs to reflect the present state
     * of the page, as expected by our caller.
     */
    if (prstate.all_visible && prstate.lpdead_items == 0)
    {
        presult->all_visible = prstate.all_visible;
        presult->all_frozen = prstate.all_frozen;
    }
    else
    {
        presult->all_visible = false;
        presult->all_frozen = false;
    }
 
    presult->hastup = prstate.hastup;
 
    /*
     * For callers planning to update the visibility map, the conflict horizon
     * for that record must be the newest xmin on the page.  However, if the
     * page is completely frozen, there can be no conflict and the
     * vm_conflict_horizon should remain InvalidTransactionId.  This includes
     * the case that we just froze all the tuples; the prune-freeze record
     * included the conflict XID already so the caller doesn't need it.
     */
    if (presult->all_frozen)
        presult->vm_conflict_horizon = InvalidTransactionId;
    else
        presult->vm_conflict_horizon = prstate.visibility_cutoff_xid;
 
    presult->lpdead_items = prstate.lpdead_items;
    /* the presult->deadoffsets array was already filled in */
 
    if (prstate.freeze)
    {
        if (presult->nfrozen > 0)
        {
            *new_relfrozen_xid = prstate.pagefrz.FreezePageRelfrozenXid;
            *new_relmin_mxid = prstate.pagefrz.FreezePageRelminMxid;
        }
        else
        {
            *new_relfrozen_xid = prstate.pagefrz.NoFreezePageRelfrozenXid;
            *new_relmin_mxid = prstate.pagefrz.NoFreezePageRelminMxid;
        }
    }
}

References PruneState::all_frozen, PruneFreezeResult::all_frozen, PruneState::all_visible, PruneFreezeResult::all_visible, Assert, BufferGetBlockNumber(), BufferGetPage(), PruneState::cutoffs, PruneState::deadoffsets, PruneFreezeResult::deadoffsets, elog, END_CRIT_SECTION, ERROR, FirstOffsetNumber, PruneState::freeze, HeapPageFreeze::freeze_required, HeapPageFreeze::FreezePageRelfrozenXid, HeapPageFreeze::FreezePageRelminMxid, PruneState::frozen, PruneState::hastup, PruneFreezeResult::hastup, heap_freeze_prepared_tuples(), heap_page_prune_execute(), HEAP_PAGE_PRUNE_FREEZE, HEAP_PAGE_PRUNE_MARK_UNUSED_NOW, heap_pre_freeze_checks(), heap_prune_chain(), heap_prune_record_unchanged_lp_dead(), heap_prune_record_unchanged_lp_normal(), heap_prune_record_unchanged_lp_unused(), heap_prune_record_unused(), heap_prune_satisfies_vacuum(), PruneState::heaponly_items, HEAPTUPLE_DEAD, HeapTupleHeaderAdvanceConflictHorizon(), HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, PruneState::htsv, i, InvalidMultiXactId, InvalidOffsetNumber, InvalidTransactionId, ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerSet(), PruneState::latest_xid_removed, likely, PruneState::live_tuples, PruneFreezeResult::live_tuples, log_heap_prune_and_freeze(), PruneState::lpdead_items, PruneFreezeResult::lpdead_items, PruneState::mark_unused_now, MarkBufferDirty(), MarkBufferDirtyHint(), PruneState::ndead, PruneState::ndeleted, PruneFreezeResult::ndeleted, PruneState::new_prune_xid, PruneState::nfrozen, PruneFreezeResult::nfrozen, PruneState::nheaponly_items, PruneFreezeResult::nnewlpdead, HeapPageFreeze::NoFreezePageRelfrozenXid, HeapPageFreeze::NoFreezePageRelminMxid, PruneState::nowdead, PruneState::nowunused, PruneState::nredirected, PruneState::nroot_items, PruneState::nunused, OffsetNumberNext, OffsetNumberPrev, VacuumCutoffs::OldestXmin, PageClearFull(), PruneState::pagefrz, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PageIsFull(), pgWalUsage, PruneState::processed, PruneState::recently_dead_tuples, PruneFreezeResult::recently_dead_tuples, PruneState::redirected, RelationGetRelid, RelationNeedsWAL, PruneState::root_items, START_CRIT_SECTION, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TransactionIdFollows(), TransactionIdRetreat, unlikely, PruneState::visibility_cutoff_xid, PruneState::vistest, PruneFreezeResult::vm_conflict_horizon, WalUsage::wal_fpi, XLogCheckBufferNeedsBackup(), and XLogHintBitIsNeeded.

Referenced by heap_page_prune_opt(), and lazy_scan_prune().

heap_page_prune_execute()

void heap_page_prune_execute	(	Buffer	buffer,
		bool	lp_truncate_only,
		OffsetNumber *	redirected,
		int	nredirected,
		OffsetNumber *	nowdead,
		int	ndead,
		OffsetNumber *	nowunused,
		int	nunused
	)

Definition at line 1561 of file pruneheap.c.

{
    Page        page = (Page) BufferGetPage(buffer);
    OffsetNumber *offnum;
    HeapTupleHeader htup PG_USED_FOR_ASSERTS_ONLY;
 
    /* Shouldn't be called unless there's something to do */
    Assert(nredirected > 0 || ndead > 0 || nunused > 0);
 
    /* If 'lp_truncate_only', we can only remove already-dead line pointers */
    Assert(!lp_truncate_only || (nredirected == 0 && ndead == 0));
 
    /* Update all redirected line pointers */
    offnum = redirected;
    for (int i = 0; i < nredirected; i++)
    {
        OffsetNumber fromoff = *offnum++;
        OffsetNumber tooff = *offnum++;
        ItemId      fromlp = PageGetItemId(page, fromoff);
        ItemId      tolp PG_USED_FOR_ASSERTS_ONLY;
 
#ifdef USE_ASSERT_CHECKING
 
        /*
         * Any existing item that we set as an LP_REDIRECT (any 'from' item)
         * must be the first item from a HOT chain.  If the item has tuple
         * storage then it can't be a heap-only tuple.  Otherwise we are just
         * maintaining an existing LP_REDIRECT from an existing HOT chain that
         * has been pruned at least once before now.
         */
        if (!ItemIdIsRedirected(fromlp))
        {
            Assert(ItemIdHasStorage(fromlp) && ItemIdIsNormal(fromlp));
 
            htup = (HeapTupleHeader) PageGetItem(page, fromlp);
            Assert(!HeapTupleHeaderIsHeapOnly(htup));
        }
        else
        {
            /* We shouldn't need to redundantly set the redirect */
            Assert(ItemIdGetRedirect(fromlp) != tooff);
        }
 
        /*
         * The item that we're about to set as an LP_REDIRECT (the 'from'
         * item) will point to an existing item (the 'to' item) that is
         * already a heap-only tuple.  There can be at most one LP_REDIRECT
         * item per HOT chain.
         *
         * We need to keep around an LP_REDIRECT item (after original
         * non-heap-only root tuple gets pruned away) so that it's always
         * possible for VACUUM to easily figure out what TID to delete from
         * indexes when an entire HOT chain becomes dead.  A heap-only tuple
         * can never become LP_DEAD; an LP_REDIRECT item or a regular heap
         * tuple can.
         *
         * This check may miss problems, e.g. the target of a redirect could
         * be marked as unused subsequently. The page_verify_redirects() check
         * below will catch such problems.
         */
        tolp = PageGetItemId(page, tooff);
        Assert(ItemIdHasStorage(tolp) && ItemIdIsNormal(tolp));
        htup = (HeapTupleHeader) PageGetItem(page, tolp);
        Assert(HeapTupleHeaderIsHeapOnly(htup));
#endif
 
        ItemIdSetRedirect(fromlp, tooff);
    }
 
    /* Update all now-dead line pointers */
    offnum = nowdead;
    for (int i = 0; i < ndead; i++)
    {
        OffsetNumber off = *offnum++;
        ItemId      lp = PageGetItemId(page, off);
 
#ifdef USE_ASSERT_CHECKING
 
        /*
         * An LP_DEAD line pointer must be left behind when the original item
         * (which is dead to everybody) could still be referenced by a TID in
         * an index.  This should never be necessary with any individual
         * heap-only tuple item, though. (It's not clear how much of a problem
         * that would be, but there is no reason to allow it.)
         */
        if (ItemIdHasStorage(lp))
        {
            Assert(ItemIdIsNormal(lp));
            htup = (HeapTupleHeader) PageGetItem(page, lp);
            Assert(!HeapTupleHeaderIsHeapOnly(htup));
        }
        else
        {
            /* Whole HOT chain becomes dead */
            Assert(ItemIdIsRedirected(lp));
        }
#endif
 
        ItemIdSetDead(lp);
    }
 
    /* Update all now-unused line pointers */
    offnum = nowunused;
    for (int i = 0; i < nunused; i++)
    {
        OffsetNumber off = *offnum++;
        ItemId      lp = PageGetItemId(page, off);
 
#ifdef USE_ASSERT_CHECKING
 
        if (lp_truncate_only)
        {
            /* Setting LP_DEAD to LP_UNUSED in vacuum's second pass */
            Assert(ItemIdIsDead(lp) && !ItemIdHasStorage(lp));
        }
        else
        {
            /*
             * When heap_page_prune_and_freeze() was called, mark_unused_now
             * may have been passed as true, which allows would-be LP_DEAD
             * items to be made LP_UNUSED instead.  This is only possible if
             * the relation has no indexes.  If there are any dead items, then
             * mark_unused_now was not true and every item being marked
             * LP_UNUSED must refer to a heap-only tuple.
             */
            if (ndead > 0)
            {
                Assert(ItemIdHasStorage(lp) && ItemIdIsNormal(lp));
                htup = (HeapTupleHeader) PageGetItem(page, lp);
                Assert(HeapTupleHeaderIsHeapOnly(htup));
            }
            else
                Assert(ItemIdIsUsed(lp));
        }
 
#endif
 
        ItemIdSetUnused(lp);
    }
 
    if (lp_truncate_only)
        PageTruncateLinePointerArray(page);
    else
    {
        /*
         * Finally, repair any fragmentation, and update the page's hint bit
         * about whether it has free pointers.
         */
        PageRepairFragmentation(page);
 
        /*
         * Now that the page has been modified, assert that redirect items
         * still point to valid targets.
         */
        page_verify_redirects(page);
    }
}

References Assert, BufferGetPage(), HeapTupleHeaderIsHeapOnly, i, ItemIdGetRedirect, ItemIdHasStorage, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemIdSetDead, ItemIdSetRedirect, ItemIdSetUnused, page_verify_redirects(), PageGetItem(), PageGetItemId(), PageRepairFragmentation(), PageTruncateLinePointerArray(), and PG_USED_FOR_ASSERTS_ONLY.

Referenced by heap_page_prune_and_freeze(), and heap_xlog_prune_freeze().

heap_page_prune_opt()

void heap_page_prune_opt	(	Relation	relation,
		Buffer	buffer
	)

Definition at line 193 of file pruneheap.c.

{
    Page        page = BufferGetPage(buffer);
    TransactionId prune_xid;
    GlobalVisState *vistest;
    Size        minfree;
 
    /*
     * We can't write WAL in recovery mode, so there's no point trying to
     * clean the page. The primary will likely issue a cleaning WAL record
     * soon anyway, so this is no particular loss.
     */
    if (RecoveryInProgress())
        return;
 
    /*
     * First check whether there's any chance there's something to prune,
     * determining the appropriate horizon is a waste if there's no prune_xid
     * (i.e. no updates/deletes left potentially dead tuples around).
     */
    prune_xid = ((PageHeader) page)->pd_prune_xid;
    if (!TransactionIdIsValid(prune_xid))
        return;
 
    /*
     * Check whether prune_xid indicates that there may be dead rows that can
     * be cleaned up.
     */
    vistest = GlobalVisTestFor(relation);
 
    if (!GlobalVisTestIsRemovableXid(vistest, prune_xid))
        return;
 
    /*
     * We prune when a previous UPDATE failed to find enough space on the page
     * for a new tuple version, or when free space falls below the relation's
     * fill-factor target (but not less than 10%).
     *
     * Checking free space here is questionable since we aren't holding any
     * lock on the buffer; in the worst case we could get a bogus answer. It's
     * unlikely to be *seriously* wrong, though, since reading either pd_lower
     * or pd_upper is probably atomic.  Avoiding taking a lock seems more
     * important than sometimes getting a wrong answer in what is after all
     * just a heuristic estimate.
     */
    minfree = RelationGetTargetPageFreeSpace(relation,
                                             HEAP_DEFAULT_FILLFACTOR);
    minfree = Max(minfree, BLCKSZ / 10);
 
    if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
    {
        /* OK, try to get exclusive buffer lock */
        if (!ConditionalLockBufferForCleanup(buffer))
            return;
 
        /*
         * Now that we have buffer lock, get accurate information about the
         * page's free space, and recheck the heuristic about whether to
         * prune.
         */
        if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
        {
            OffsetNumber dummy_off_loc;
            PruneFreezeResult presult;
 
            /*
             * For now, pass mark_unused_now as false regardless of whether or
             * not the relation has indexes, since we cannot safely determine
             * that during on-access pruning with the current implementation.