Permalink
Switch branches/tags
Find file Copy path
9463 lines (8354 sloc) 283 KB
/*-------------------------------------------------------------------------
*
* heapam.c
* heap access method code
*
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/access/heap/heapam.c
*
*
* INTERFACE ROUTINES
* relation_open - open any relation by relation OID
* relation_openrv - open any relation specified by a RangeVar
* relation_close - close any relation
* heap_open - open a heap relation by relation OID
* heap_openrv - open a heap relation specified by a RangeVar
* heap_close - (now just a macro for relation_close)
* heap_beginscan - begin relation scan
* heap_rescan - restart a relation scan
* heap_endscan - end relation scan
* heap_getnext - retrieve next tuple in scan
* heap_fetch - retrieve tuple with given tid
* heap_insert - insert tuple into a relation
* heap_multi_insert - insert multiple tuples into a relation
* heap_delete - delete a tuple from a relation
* heap_update - replace a tuple in a relation with another tuple
* heap_sync - sync heap, for when no WAL has been written
*
* NOTES
* This file contains the heap_ routines which implement
* the POSTGRES heap access method used for all POSTGRES
* relations.
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/bufmask.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/hio.h"
#include "access/multixact.h"
#include "access/parallel.h"
#include "access/relscan.h"
#include "access/sysattr.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/valid.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/catalog.h"
#include "catalog/namespace.h"
#include "catalog/index.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "port/atomics.h"
#include "storage/bufmgr.h"
#include "storage/freespace.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "storage/procarray.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "storage/standby.h"
#include "utils/datum.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/relcache.h"
#include "utils/snapmgr.h"
#include "utils/syscache.h"
#include "utils/tqual.h"
#include "utils/memutils.h"
#include "nodes/execnodes.h"
#include "executor/executor.h"
/* GUC variable */
bool synchronize_seqscans = true;
static HeapScanDesc heap_beginscan_internal(Relation relation,
Snapshot snapshot,
int nkeys, ScanKey key,
ParallelHeapScanDesc parallel_scan,
bool allow_strat,
bool allow_sync,
bool allow_pagemode,
bool is_bitmapscan,
bool is_samplescan,
bool temp_snap);
static void heap_parallelscan_startblock_init(HeapScanDesc scan);
static BlockNumber heap_parallelscan_nextpage(HeapScanDesc scan);
static HeapTuple heap_prepare_insert(Relation relation, HeapTuple tup,
TransactionId xid, CommandId cid, int options);
static XLogRecPtr log_heap_update(Relation reln, Buffer oldbuf,
Buffer newbuf, HeapTuple oldtup,
HeapTuple newtup, HeapTuple old_key_tup,
bool all_visible_cleared, bool new_all_visible_cleared);
static Bitmapset *HeapDetermineModifiedColumns(Relation relation,
Bitmapset *interesting_cols,
HeapTuple oldtup, HeapTuple newtup);
static bool heap_acquire_tuplock(Relation relation, ItemPointer tid,
LockTupleMode mode, LockWaitPolicy wait_policy,
bool *have_tuple_lock);
static void compute_new_xmax_infomask(TransactionId xmax, uint16 old_infomask,
uint16 old_infomask2, TransactionId add_to_xmax,
LockTupleMode mode, bool is_update,
TransactionId *result_xmax, uint16 *result_infomask,
uint16 *result_infomask2);
static HTSU_Result heap_lock_updated_tuple(Relation rel, HeapTuple tuple,
ItemPointer ctid, TransactionId xid,
LockTupleMode mode);
static void GetMultiXactIdHintBits(MultiXactId multi, uint16 *new_infomask,
uint16 *new_infomask2);
static TransactionId MultiXactIdGetUpdateXid(TransactionId xmax,
uint16 t_infomask);
static bool DoesMultiXactIdConflict(MultiXactId multi, uint16 infomask,
LockTupleMode lockmode);
static void MultiXactIdWait(MultiXactId multi, MultiXactStatus status, uint16 infomask,
Relation rel, ItemPointer ctid, XLTW_Oper oper,
int *remaining);
static bool ConditionalMultiXactIdWait(MultiXactId multi, MultiXactStatus status,
uint16 infomask, Relation rel, int *remaining);
static XLogRecPtr log_heap_new_cid(Relation relation, HeapTuple tup);
static HeapTuple ExtractReplicaIdentity(Relation rel, HeapTuple tup, bool key_modified,
bool *copy);
static bool ProjIndexIsUnchanged(Relation relation, HeapTuple oldtup, HeapTuple newtup);
/*
* Each tuple lock mode has a corresponding heavyweight lock, and one or two
* corresponding MultiXactStatuses (one to merely lock tuples, another one to
* update them). This table (and the macros below) helps us determine the
* heavyweight lock mode and MultiXactStatus values to use for any particular
* tuple lock strength.
*
* Don't look at lockstatus/updstatus directly! Use get_mxact_status_for_lock
* instead.
*/
static const struct
{
LOCKMODE hwlock;
int lockstatus;
int updstatus;
}
tupleLockExtraInfo[MaxLockTupleMode + 1] =
{
{ /* LockTupleKeyShare */
AccessShareLock,
MultiXactStatusForKeyShare,
-1 /* KeyShare does not allow updating tuples */
},
{ /* LockTupleShare */
RowShareLock,
MultiXactStatusForShare,
-1 /* Share does not allow updating tuples */
},
{ /* LockTupleNoKeyExclusive */
ExclusiveLock,
MultiXactStatusForNoKeyUpdate,
MultiXactStatusNoKeyUpdate
},
{ /* LockTupleExclusive */
AccessExclusiveLock,
MultiXactStatusForUpdate,
MultiXactStatusUpdate
}
};
/* Get the LOCKMODE for a given MultiXactStatus */
#define LOCKMODE_from_mxstatus(status) \
(tupleLockExtraInfo[TUPLOCK_from_mxstatus((status))].hwlock)
/*
* Acquire heavyweight locks on tuples, using a LockTupleMode strength value.
* This is more readable than having every caller translate it to lock.h's
* LOCKMODE.
*/
#define LockTupleTuplock(rel, tup, mode) \
LockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
#define UnlockTupleTuplock(rel, tup, mode) \
UnlockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
#define ConditionalLockTupleTuplock(rel, tup, mode) \
ConditionalLockTuple((rel), (tup), tupleLockExtraInfo[mode].hwlock)
/*
* This table maps tuple lock strength values for each particular
* MultiXactStatus value.
*/
static const int MultiXactStatusLock[MaxMultiXactStatus + 1] =
{
LockTupleKeyShare, /* ForKeyShare */
LockTupleShare, /* ForShare */
LockTupleNoKeyExclusive, /* ForNoKeyUpdate */
LockTupleExclusive, /* ForUpdate */
LockTupleNoKeyExclusive, /* NoKeyUpdate */
LockTupleExclusive /* Update */
};
/* Get the LockTupleMode for a given MultiXactStatus */
#define TUPLOCK_from_mxstatus(status) \
(MultiXactStatusLock[(status)])
/* ----------------------------------------------------------------
* heap support routines
* ----------------------------------------------------------------
*/
/* ----------------
* initscan - scan code common to heap_beginscan and heap_rescan
* ----------------
*/
static void
initscan(HeapScanDesc scan, ScanKey key, bool keep_startblock)
{
bool allow_strat;
bool allow_sync;
/*
* Determine the number of blocks we have to scan.
*
* It is sufficient to do this once at scan start, since any tuples added
* while the scan is in progress will be invisible to my snapshot anyway.
* (That is not true when using a non-MVCC snapshot. However, we couldn't
* guarantee to return tuples added after scan start anyway, since they
* might go into pages we already scanned. To guarantee consistent
* results for a non-MVCC snapshot, the caller must hold some higher-level
* lock that ensures the interesting tuple(s) won't change.)
*/
if (scan->rs_parallel != NULL)
scan->rs_nblocks = scan->rs_parallel->phs_nblocks;
else
scan->rs_nblocks = RelationGetNumberOfBlocks(scan->rs_rd);
/*
* If the table is large relative to NBuffers, use a bulk-read access
* strategy and enable synchronized scanning (see syncscan.c). Although
* the thresholds for these features could be different, we make them the
* same so that there are only two behaviors to tune rather than four.
* (However, some callers need to be able to disable one or both of these
* behaviors, independently of the size of the table; also there is a GUC
* variable that can disable synchronized scanning.)
*
* Note that heap_parallelscan_initialize has a very similar test; if you
* change this, consider changing that one, too.
*/
if (!RelationUsesLocalBuffers(scan->rs_rd) &&
scan->rs_nblocks > NBuffers / 4)
{
allow_strat = scan->rs_allow_strat;
allow_sync = scan->rs_allow_sync;
}
else
allow_strat = allow_sync = false;
if (allow_strat)
{
/* During a rescan, keep the previous strategy object. */
if (scan->rs_strategy == NULL)
scan->rs_strategy = GetAccessStrategy(BAS_BULKREAD);
}
else
{
if (scan->rs_strategy != NULL)
FreeAccessStrategy(scan->rs_strategy);
scan->rs_strategy = NULL;
}
if (scan->rs_parallel != NULL)
{
/* For parallel scan, believe whatever ParallelHeapScanDesc says. */
scan->rs_syncscan = scan->rs_parallel->phs_syncscan;
}
else if (keep_startblock)
{
/*
* When rescanning, we want to keep the previous startblock setting,
* so that rewinding a cursor doesn't generate surprising results.
* Reset the active syncscan setting, though.
*/
scan->rs_syncscan = (allow_sync && synchronize_seqscans);
}
else if (allow_sync && synchronize_seqscans)
{
scan->rs_syncscan = true;
scan->rs_startblock = ss_get_location(scan->rs_rd, scan->rs_nblocks);
}
else
{
scan->rs_syncscan = false;
scan->rs_startblock = 0;
}
scan->rs_numblocks = InvalidBlockNumber;
scan->rs_inited = false;
scan->rs_ctup.t_data = NULL;
ItemPointerSetInvalid(&scan->rs_ctup.t_self);
scan->rs_cbuf = InvalidBuffer;
scan->rs_cblock = InvalidBlockNumber;
/* page-at-a-time fields are always invalid when not rs_inited */
/*
* copy the scan key, if appropriate
*/
if (key != NULL)
memcpy(scan->rs_key, key, scan->rs_nkeys * sizeof(ScanKeyData));
/*
* Currently, we don't have a stats counter for bitmap heap scans (but the
* underlying bitmap index scans will be counted) or sample scans (we only
* update stats for tuple fetches there)
*/
if (!scan->rs_bitmapscan && !scan->rs_samplescan)
pgstat_count_heap_scan(scan->rs_rd);
}
/*
* heap_setscanlimits - restrict range of a heapscan
*
* startBlk is the page to start at
* numBlks is number of pages to scan (InvalidBlockNumber means "all")
*/
void
heap_setscanlimits(HeapScanDesc scan, BlockNumber startBlk, BlockNumber numBlks)
{
Assert(!scan->rs_inited); /* else too late to change */
Assert(!scan->rs_syncscan); /* else rs_startblock is significant */
/* Check startBlk is valid (but allow case of zero blocks...) */
Assert(startBlk == 0 || startBlk < scan->rs_nblocks);
scan->rs_startblock = startBlk;
scan->rs_numblocks = numBlks;
}
/*
* heapgetpage - subroutine for heapgettup()
*
* This routine reads and pins the specified page of the relation.
* In page-at-a-time mode it performs additional work, namely determining
* which tuples on the page are visible.
*/
void
heapgetpage(HeapScanDesc scan, BlockNumber page)
{
Buffer buffer;
Snapshot snapshot;
Page dp;
int lines;
int ntup;
OffsetNumber lineoff;
ItemId lpp;
bool all_visible;
Assert(page < scan->rs_nblocks);
/* release previous scan buffer, if any */
if (BufferIsValid(scan->rs_cbuf))
{
ReleaseBuffer(scan->rs_cbuf);
scan->rs_cbuf = InvalidBuffer;
}
/*
* Be sure to check for interrupts at least once per page. Checks at
* higher code levels won't be able to stop a seqscan that encounters many
* pages' worth of consecutive dead tuples.
*/
CHECK_FOR_INTERRUPTS();
/* read page using selected strategy */
scan->rs_cbuf = ReadBufferExtended(scan->rs_rd, MAIN_FORKNUM, page,
RBM_NORMAL, scan->rs_strategy);
scan->rs_cblock = page;
if (!scan->rs_pageatatime)
return;
buffer = scan->rs_cbuf;
snapshot = scan->rs_snapshot;
/*
* Prune and repair fragmentation for the whole page, if possible.
*/
heap_page_prune_opt(scan->rs_rd, buffer);
/*
* We must hold share lock on the buffer content while examining tuple
* visibility. Afterwards, however, the tuples we have found to be
* visible are guaranteed good as long as we hold the buffer pin.
*/
LockBuffer(buffer, BUFFER_LOCK_SHARE);
dp = BufferGetPage(buffer);
TestForOldSnapshot(snapshot, scan->rs_rd, dp);
lines = PageGetMaxOffsetNumber(dp);
ntup = 0;
/*
* If the all-visible flag indicates that all tuples on the page are
* visible to everyone, we can skip the per-tuple visibility tests.
*
* Note: In hot standby, a tuple that's already visible to all
* transactions in the master might still be invisible to a read-only
* transaction in the standby. We partly handle this problem by tracking
* the minimum xmin of visible tuples as the cut-off XID while marking a
* page all-visible on master and WAL log that along with the visibility
* map SET operation. In hot standby, we wait for (or abort) all
* transactions that can potentially may not see one or more tuples on the
* page. That's how index-only scans work fine in hot standby. A crucial
* difference between index-only scans and heap scans is that the
* index-only scan completely relies on the visibility map where as heap
* scan looks at the page-level PD_ALL_VISIBLE flag. We are not sure if
* the page-level flag can be trusted in the same way, because it might
* get propagated somehow without being explicitly WAL-logged, e.g. via a
* full page write. Until we can prove that beyond doubt, let's check each
* tuple for visibility the hard way.
*/
all_visible = PageIsAllVisible(dp) && !snapshot->takenDuringRecovery;
for (lineoff = FirstOffsetNumber, lpp = PageGetItemId(dp, lineoff);
lineoff <= lines;
lineoff++, lpp++)
{
if (ItemIdIsNormal(lpp))
{
HeapTupleData loctup;
bool valid;
loctup.t_tableOid = RelationGetRelid(scan->rs_rd);
loctup.t_data = (HeapTupleHeader) PageGetItem((Page) dp, lpp);
loctup.t_len = ItemIdGetLength(lpp);
ItemPointerSet(&(loctup.t_self), page, lineoff);
if (all_visible)
valid = true;
else
valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
CheckForSerializableConflictOut(valid, scan->rs_rd, &loctup,
buffer, snapshot);
if (valid)
scan->rs_vistuples[ntup++] = lineoff;
}
}
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
Assert(ntup <= MaxHeapTuplesPerPage);
scan->rs_ntuples = ntup;
}
/* ----------------
* heapgettup - fetch next heap tuple
*
* Initialize the scan if not already done; then advance to the next
* tuple as indicated by "dir"; return the next tuple in scan->rs_ctup,
* or set scan->rs_ctup.t_data = NULL if no more tuples.
*
* dir == NoMovementScanDirection means "re-fetch the tuple indicated
* by scan->rs_ctup".
*
* Note: the reason nkeys/key are passed separately, even though they are
* kept in the scan descriptor, is that the caller may not want us to check
* the scankeys.
*
* Note: when we fall off the end of the scan in either direction, we
* reset rs_inited. This means that a further request with the same
* scan direction will restart the scan, which is a bit odd, but a
* request with the opposite scan direction will start a fresh scan
* in the proper direction. The latter is required behavior for cursors,
* while the former case is generally undefined behavior in Postgres
* so we don't care too much.
* ----------------
*/
static void
heapgettup(HeapScanDesc scan,
ScanDirection dir,
int nkeys,
ScanKey key)
{
HeapTuple tuple = &(scan->rs_ctup);
Snapshot snapshot = scan->rs_snapshot;
bool backward = ScanDirectionIsBackward(dir);
BlockNumber page;
bool finished;
Page dp;
int lines;
OffsetNumber lineoff;
int linesleft;
ItemId lpp;
/*
* calculate next starting lineoff, given scan direction
*/
if (ScanDirectionIsForward(dir))
{
if (!scan->rs_inited)
{
/*
* return null immediately if relation is empty
*/
if (scan->rs_nblocks == 0 || scan->rs_numblocks == 0)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
if (scan->rs_parallel != NULL)
{
heap_parallelscan_startblock_init(scan);
page = heap_parallelscan_nextpage(scan);
/* Other processes might have already finished the scan. */
if (page == InvalidBlockNumber)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
}
else
page = scan->rs_startblock; /* first page */
heapgetpage(scan, page);
lineoff = FirstOffsetNumber; /* first offnum */
scan->rs_inited = true;
}
else
{
/* continue from previously returned page/tuple */
page = scan->rs_cblock; /* current page */
lineoff = /* next offnum */
OffsetNumberNext(ItemPointerGetOffsetNumber(&(tuple->t_self)));
}
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(snapshot, scan->rs_rd, dp);
lines = PageGetMaxOffsetNumber(dp);
/* page and lineoff now reference the physically next tid */
linesleft = lines - lineoff + 1;
}
else if (backward)
{
/* backward parallel scan not supported */
Assert(scan->rs_parallel == NULL);
if (!scan->rs_inited)
{
/*
* return null immediately if relation is empty
*/
if (scan->rs_nblocks == 0 || scan->rs_numblocks == 0)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
/*
* Disable reporting to syncscan logic in a backwards scan; it's
* not very likely anyone else is doing the same thing at the same
* time, and much more likely that we'll just bollix things for
* forward scanners.
*/
scan->rs_syncscan = false;
/* start from last page of the scan */
if (scan->rs_startblock > 0)
page = scan->rs_startblock - 1;
else
page = scan->rs_nblocks - 1;
heapgetpage(scan, page);
}
else
{
/* continue from previously returned page/tuple */
page = scan->rs_cblock; /* current page */
}
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(snapshot, scan->rs_rd, dp);
lines = PageGetMaxOffsetNumber(dp);
if (!scan->rs_inited)
{
lineoff = lines; /* final offnum */
scan->rs_inited = true;
}
else
{
lineoff = /* previous offnum */
OffsetNumberPrev(ItemPointerGetOffsetNumber(&(tuple->t_self)));
}
/* page and lineoff now reference the physically previous tid */
linesleft = lineoff;
}
else
{
/*
* ``no movement'' scan direction: refetch prior tuple
*/
if (!scan->rs_inited)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
page = ItemPointerGetBlockNumber(&(tuple->t_self));
if (page != scan->rs_cblock)
heapgetpage(scan, page);
/* Since the tuple was previously fetched, needn't lock page here */
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(snapshot, scan->rs_rd, dp);
lineoff = ItemPointerGetOffsetNumber(&(tuple->t_self));
lpp = PageGetItemId(dp, lineoff);
Assert(ItemIdIsNormal(lpp));
tuple->t_data = (HeapTupleHeader) PageGetItem((Page) dp, lpp);
tuple->t_len = ItemIdGetLength(lpp);
return;
}
/*
* advance the scan until we find a qualifying tuple or run out of stuff
* to scan
*/
lpp = PageGetItemId(dp, lineoff);
for (;;)
{
while (linesleft > 0)
{
if (ItemIdIsNormal(lpp))
{
bool valid;
tuple->t_data = (HeapTupleHeader) PageGetItem((Page) dp, lpp);
tuple->t_len = ItemIdGetLength(lpp);
ItemPointerSet(&(tuple->t_self), page, lineoff);
/*
* if current tuple qualifies, return it.
*/
valid = HeapTupleSatisfiesVisibility(tuple,
snapshot,
scan->rs_cbuf);
CheckForSerializableConflictOut(valid, scan->rs_rd, tuple,
scan->rs_cbuf, snapshot);
if (valid && key != NULL)
HeapKeyTest(tuple, RelationGetDescr(scan->rs_rd),
nkeys, key, valid);
if (valid)
{
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
return;
}
}
/*
* otherwise move to the next item on the page
*/
--linesleft;
if (backward)
{
--lpp; /* move back in this page's ItemId array */
--lineoff;
}
else
{
++lpp; /* move forward in this page's ItemId array */
++lineoff;
}
}
/*
* if we get here, it means we've exhausted the items on this page and
* it's time to move to the next.
*/
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
/*
* advance to next/prior page and detect end of scan
*/
if (backward)
{
finished = (page == scan->rs_startblock) ||
(scan->rs_numblocks != InvalidBlockNumber ? --scan->rs_numblocks == 0 : false);
if (page == 0)
page = scan->rs_nblocks;
page--;
}
else if (scan->rs_parallel != NULL)
{
page = heap_parallelscan_nextpage(scan);
finished = (page == InvalidBlockNumber);
}
else
{
page++;
if (page >= scan->rs_nblocks)
page = 0;
finished = (page == scan->rs_startblock) ||
(scan->rs_numblocks != InvalidBlockNumber ? --scan->rs_numblocks == 0 : false);
/*
* Report our new scan position for synchronization purposes. We
* don't do that when moving backwards, however. That would just
* mess up any other forward-moving scanners.
*
* Note: we do this before checking for end of scan so that the
* final state of the position hint is back at the start of the
* rel. That's not strictly necessary, but otherwise when you run
* the same query multiple times the starting position would shift
* a little bit backwards on every invocation, which is confusing.
* We don't guarantee any specific ordering in general, though.
*/
if (scan->rs_syncscan)
ss_report_location(scan->rs_rd, page);
}
/*
* return NULL if we've exhausted all the pages
*/
if (finished)
{
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
scan->rs_cbuf = InvalidBuffer;
scan->rs_cblock = InvalidBlockNumber;
tuple->t_data = NULL;
scan->rs_inited = false;
return;
}
heapgetpage(scan, page);
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(snapshot, scan->rs_rd, dp);
lines = PageGetMaxOffsetNumber((Page) dp);
linesleft = lines;
if (backward)
{
lineoff = lines;
lpp = PageGetItemId(dp, lines);
}
else
{
lineoff = FirstOffsetNumber;
lpp = PageGetItemId(dp, FirstOffsetNumber);
}
}
}
/* ----------------
* heapgettup_pagemode - fetch next heap tuple in page-at-a-time mode
*
* Same API as heapgettup, but used in page-at-a-time mode
*
* The internal logic is much the same as heapgettup's too, but there are some
* differences: we do not take the buffer content lock (that only needs to
* happen inside heapgetpage), and we iterate through just the tuples listed
* in rs_vistuples[] rather than all tuples on the page. Notice that
* lineindex is 0-based, where the corresponding loop variable lineoff in
* heapgettup is 1-based.
* ----------------
*/
static void
heapgettup_pagemode(HeapScanDesc scan,
ScanDirection dir,
int nkeys,
ScanKey key)
{
HeapTuple tuple = &(scan->rs_ctup);
bool backward = ScanDirectionIsBackward(dir);
BlockNumber page;
bool finished;
Page dp;
int lines;
int lineindex;
OffsetNumber lineoff;
int linesleft;
ItemId lpp;
/*
* calculate next starting lineindex, given scan direction
*/
if (ScanDirectionIsForward(dir))
{
if (!scan->rs_inited)
{
/*
* return null immediately if relation is empty
*/
if (scan->rs_nblocks == 0 || scan->rs_numblocks == 0)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
if (scan->rs_parallel != NULL)
{
heap_parallelscan_startblock_init(scan);
page = heap_parallelscan_nextpage(scan);
/* Other processes might have already finished the scan. */
if (page == InvalidBlockNumber)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
}
else
page = scan->rs_startblock; /* first page */
heapgetpage(scan, page);
lineindex = 0;
scan->rs_inited = true;
}
else
{
/* continue from previously returned page/tuple */
page = scan->rs_cblock; /* current page */
lineindex = scan->rs_cindex + 1;
}
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(scan->rs_snapshot, scan->rs_rd, dp);
lines = scan->rs_ntuples;
/* page and lineindex now reference the next visible tid */
linesleft = lines - lineindex;
}
else if (backward)
{
/* backward parallel scan not supported */
Assert(scan->rs_parallel == NULL);
if (!scan->rs_inited)
{
/*
* return null immediately if relation is empty
*/
if (scan->rs_nblocks == 0 || scan->rs_numblocks == 0)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
/*
* Disable reporting to syncscan logic in a backwards scan; it's
* not very likely anyone else is doing the same thing at the same
* time, and much more likely that we'll just bollix things for
* forward scanners.
*/
scan->rs_syncscan = false;
/* start from last page of the scan */
if (scan->rs_startblock > 0)
page = scan->rs_startblock - 1;
else
page = scan->rs_nblocks - 1;
heapgetpage(scan, page);
}
else
{
/* continue from previously returned page/tuple */
page = scan->rs_cblock; /* current page */
}
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(scan->rs_snapshot, scan->rs_rd, dp);
lines = scan->rs_ntuples;
if (!scan->rs_inited)
{
lineindex = lines - 1;
scan->rs_inited = true;
}
else
{
lineindex = scan->rs_cindex - 1;
}
/* page and lineindex now reference the previous visible tid */
linesleft = lineindex + 1;
}
else
{
/*
* ``no movement'' scan direction: refetch prior tuple
*/
if (!scan->rs_inited)
{
Assert(!BufferIsValid(scan->rs_cbuf));
tuple->t_data = NULL;
return;
}
page = ItemPointerGetBlockNumber(&(tuple->t_self));
if (page != scan->rs_cblock)
heapgetpage(scan, page);
/* Since the tuple was previously fetched, needn't lock page here */
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(scan->rs_snapshot, scan->rs_rd, dp);
lineoff = ItemPointerGetOffsetNumber(&(tuple->t_self));
lpp = PageGetItemId(dp, lineoff);
Assert(ItemIdIsNormal(lpp));
tuple->t_data = (HeapTupleHeader) PageGetItem((Page) dp, lpp);
tuple->t_len = ItemIdGetLength(lpp);
/* check that rs_cindex is in sync */
Assert(scan->rs_cindex < scan->rs_ntuples);
Assert(lineoff == scan->rs_vistuples[scan->rs_cindex]);
return;
}
/*
* advance the scan until we find a qualifying tuple or run out of stuff
* to scan
*/
for (;;)
{
while (linesleft > 0)
{
lineoff = scan->rs_vistuples[lineindex];
lpp = PageGetItemId(dp, lineoff);
Assert(ItemIdIsNormal(lpp));
tuple->t_data = (HeapTupleHeader) PageGetItem((Page) dp, lpp);
tuple->t_len = ItemIdGetLength(lpp);
ItemPointerSet(&(tuple->t_self), page, lineoff);
/*
* if current tuple qualifies, return it.
*/
if (key != NULL)
{
bool valid;
HeapKeyTest(tuple, RelationGetDescr(scan->rs_rd),
nkeys, key, valid);
if (valid)
{
scan->rs_cindex = lineindex;
return;
}
}
else
{
scan->rs_cindex = lineindex;
return;
}
/*
* otherwise move to the next item on the page
*/
--linesleft;
if (backward)
--lineindex;
else
++lineindex;
}
/*
* if we get here, it means we've exhausted the items on this page and
* it's time to move to the next.
*/
if (backward)
{
finished = (page == scan->rs_startblock) ||
(scan->rs_numblocks != InvalidBlockNumber ? --scan->rs_numblocks == 0 : false);
if (page == 0)
page = scan->rs_nblocks;
page--;
}
else if (scan->rs_parallel != NULL)
{
page = heap_parallelscan_nextpage(scan);
finished = (page == InvalidBlockNumber);
}
else
{
page++;
if (page >= scan->rs_nblocks)
page = 0;
finished = (page == scan->rs_startblock) ||
(scan->rs_numblocks != InvalidBlockNumber ? --scan->rs_numblocks == 0 : false);
/*
* Report our new scan position for synchronization purposes. We
* don't do that when moving backwards, however. That would just
* mess up any other forward-moving scanners.
*
* Note: we do this before checking for end of scan so that the
* final state of the position hint is back at the start of the
* rel. That's not strictly necessary, but otherwise when you run
* the same query multiple times the starting position would shift
* a little bit backwards on every invocation, which is confusing.
* We don't guarantee any specific ordering in general, though.
*/
if (scan->rs_syncscan)
ss_report_location(scan->rs_rd, page);
}
/*
* return NULL if we've exhausted all the pages
*/
if (finished)
{
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
scan->rs_cbuf = InvalidBuffer;
scan->rs_cblock = InvalidBlockNumber;
tuple->t_data = NULL;
scan->rs_inited = false;
return;
}
heapgetpage(scan, page);
dp = BufferGetPage(scan->rs_cbuf);
TestForOldSnapshot(scan->rs_snapshot, scan->rs_rd, dp);
lines = scan->rs_ntuples;
linesleft = lines;
if (backward)
lineindex = lines - 1;
else
lineindex = 0;
}
}
#if defined(DISABLE_COMPLEX_MACRO)
/*
* This is formatted so oddly so that the correspondence to the macro
* definition in access/htup_details.h is maintained.
*/
Datum
fastgetattr(HeapTuple tup, int attnum, TupleDesc tupleDesc,
bool *isnull)
{
return (
(attnum) > 0 ?
(
(*(isnull) = false),
HeapTupleNoNulls(tup) ?
(
TupleDescAttr((tupleDesc), (attnum) - 1)->attcacheoff >= 0 ?
(
fetchatt(TupleDescAttr((tupleDesc), (attnum) - 1),
(char *) (tup)->t_data + (tup)->t_data->t_hoff +
TupleDescAttr((tupleDesc), (attnum) - 1)->attcacheoff)
)
:
nocachegetattr((tup), (attnum), (tupleDesc))
)
:
(
att_isnull((attnum) - 1, (tup)->t_data->t_bits) ?
(
(*(isnull) = true),
(Datum) NULL
)
:
(
nocachegetattr((tup), (attnum), (tupleDesc))
)
)
)
:
(
(Datum) NULL
)
);
}
#endif /* defined(DISABLE_COMPLEX_MACRO) */
/* ----------------------------------------------------------------
* heap access method interface
* ----------------------------------------------------------------
*/
/* ----------------
* relation_open - open any relation by relation OID
*
* If lockmode is not "NoLock", the specified kind of lock is
* obtained on the relation. (Generally, NoLock should only be
* used if the caller knows it has some appropriate lock on the
* relation already.)
*
* An error is raised if the relation does not exist.
*
* NB: a "relation" is anything with a pg_class entry. The caller is
* expected to check whether the relkind is something it can handle.
* ----------------
*/
Relation
relation_open(Oid relationId, LOCKMODE lockmode)
{
Relation r;
Assert(lockmode >= NoLock && lockmode < MAX_LOCKMODES);
/* Get the lock before trying to open the relcache entry */
if (lockmode != NoLock)
LockRelationOid(relationId, lockmode);
/* The relcache does all the real work... */
r = RelationIdGetRelation(relationId);
if (!RelationIsValid(r))
elog(ERROR, "could not open relation with OID %u", relationId);
/*
* If we didn't get the lock ourselves, assert that caller holds one,
* except in bootstrap mode where no locks are used.
*/
Assert(lockmode != NoLock ||
IsBootstrapProcessingMode() ||
CheckRelationLockedByMe(r, AccessShareLock, true));
/* Make note that we've accessed a temporary relation */
if (RelationUsesLocalBuffers(r))
MyXactFlags |= XACT_FLAGS_ACCESSEDTEMPREL;
pgstat_initstats(r);
return r;
}
/* ----------------
* try_relation_open - open any relation by relation OID
*
* Same as relation_open, except return NULL instead of failing
* if the relation does not exist.
* ----------------
*/
Relation
try_relation_open(Oid relationId, LOCKMODE lockmode)
{
Relation r;
Assert(lockmode >= NoLock && lockmode < MAX_LOCKMODES);
/* Get the lock first */
if (lockmode != NoLock)
LockRelationOid(relationId, lockmode);
/*
* Now that we have the lock, probe to see if the relation really exists
* or not.
*/
if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(relationId)))
{
/* Release useless lock */
if (lockmode != NoLock)
UnlockRelationOid(relationId, lockmode);
return NULL;
}
/* Should be safe to do a relcache load */
r = RelationIdGetRelation(relationId);
if (!RelationIsValid(r))
elog(ERROR, "could not open relation with OID %u", relationId);
/* If we didn't get the lock ourselves, assert that caller holds one */
Assert(lockmode != NoLock ||
CheckRelationLockedByMe(r, AccessShareLock, true));
/* Make note that we've accessed a temporary relation */
if (RelationUsesLocalBuffers(r))
MyXactFlags |= XACT_FLAGS_ACCESSEDTEMPREL;
pgstat_initstats(r);
return r;
}
/* ----------------
* relation_openrv - open any relation specified by a RangeVar
*
* Same as relation_open, but the relation is specified by a RangeVar.
* ----------------
*/
Relation
relation_openrv(const RangeVar *relation, LOCKMODE lockmode)
{
Oid relOid;
/*
* Check for shared-cache-inval messages before trying to open the
* relation. This is needed even if we already hold a lock on the
* relation, because GRANT/REVOKE are executed without taking any lock on
* the target relation, and we want to be sure we see current ACL
* information. We can skip this if asked for NoLock, on the assumption
* that such a call is not the first one in the current command, and so we
* should be reasonably up-to-date already. (XXX this all could stand to
* be redesigned, but for the moment we'll keep doing this like it's been
* done historically.)
*/
if (lockmode != NoLock)
AcceptInvalidationMessages();
/* Look up and lock the appropriate relation using namespace search */
relOid = RangeVarGetRelid(relation, lockmode, false);
/* Let relation_open do the rest */
return relation_open(relOid, NoLock);
}
/* ----------------
* relation_openrv_extended - open any relation specified by a RangeVar
*
* Same as relation_openrv, but with an additional missing_ok argument
* allowing a NULL return rather than an error if the relation is not
* found. (Note that some other causes, such as permissions problems,
* will still result in an ereport.)
* ----------------
*/
Relation
relation_openrv_extended(const RangeVar *relation, LOCKMODE lockmode,
bool missing_ok)
{
Oid relOid;
/*
* Check for shared-cache-inval messages before trying to open the
* relation. See comments in relation_openrv().
*/
if (lockmode != NoLock)
AcceptInvalidationMessages();
/* Look up and lock the appropriate relation using namespace search */
relOid = RangeVarGetRelid(relation, lockmode, missing_ok);
/* Return NULL on not-found */
if (!OidIsValid(relOid))
return NULL;
/* Let relation_open do the rest */
return relation_open(relOid, NoLock);
}
/* ----------------
* relation_close - close any relation
*
* If lockmode is not "NoLock", we then release the specified lock.
*
* Note that it is often sensible to hold a lock beyond relation_close;
* in that case, the lock is released automatically at xact end.
* ----------------
*/
void
relation_close(Relation relation, LOCKMODE lockmode)
{
LockRelId relid = relation->rd_lockInfo.lockRelId;
Assert(lockmode >= NoLock && lockmode < MAX_LOCKMODES);
/* The relcache does the real work... */
RelationClose(relation);
if (lockmode != NoLock)
UnlockRelationId(&relid, lockmode);
}
/* ----------------
* heap_open - open a heap relation by relation OID
*
* This is essentially relation_open plus check that the relation
* is not an index nor a composite type. (The caller should also
* check that it's not a view or foreign table before assuming it has
* storage.)
* ----------------
*/
Relation
heap_open(Oid relationId, LOCKMODE lockmode)
{
Relation r;
r = relation_open(relationId, lockmode);
if (r->rd_rel->relkind == RELKIND_INDEX ||
r->rd_rel->relkind == RELKIND_PARTITIONED_INDEX)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is an index",
RelationGetRelationName(r))));
else if (r->rd_rel->relkind == RELKIND_COMPOSITE_TYPE)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is a composite type",
RelationGetRelationName(r))));
return r;
}
/* ----------------
* heap_openrv - open a heap relation specified
* by a RangeVar node
*
* As above, but relation is specified by a RangeVar.
* ----------------
*/
Relation
heap_openrv(const RangeVar *relation, LOCKMODE lockmode)
{
Relation r;
r = relation_openrv(relation, lockmode);
if (r->rd_rel->relkind == RELKIND_INDEX ||
r->rd_rel->relkind == RELKIND_PARTITIONED_INDEX)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is an index",
RelationGetRelationName(r))));
else if (r->rd_rel->relkind == RELKIND_COMPOSITE_TYPE)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is a composite type",
RelationGetRelationName(r))));
return r;
}
/* ----------------
* heap_openrv_extended - open a heap relation specified
* by a RangeVar node
*
* As above, but optionally return NULL instead of failing for
* relation-not-found.
* ----------------
*/
Relation
heap_openrv_extended(const RangeVar *relation, LOCKMODE lockmode,
bool missing_ok)
{
Relation r;
r = relation_openrv_extended(relation, lockmode, missing_ok);
if (r)
{
if (r->rd_rel->relkind == RELKIND_INDEX ||
r->rd_rel->relkind == RELKIND_PARTITIONED_INDEX)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is an index",
RelationGetRelationName(r))));
else if (r->rd_rel->relkind == RELKIND_COMPOSITE_TYPE)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is a composite type",
RelationGetRelationName(r))));
}
return r;
}
/* ----------------
* heap_beginscan - begin relation scan
*
* heap_beginscan is the "standard" case.
*
* heap_beginscan_catalog differs in setting up its own temporary snapshot.
*
* heap_beginscan_strat offers an extended API that lets the caller control
* whether a nondefault buffer access strategy can be used, and whether
* syncscan can be chosen (possibly resulting in the scan not starting from
* block zero). Both of these default to true with plain heap_beginscan.
*
* heap_beginscan_bm is an alternative entry point for setting up a
* HeapScanDesc for a bitmap heap scan. Although that scan technology is
* really quite unlike a standard seqscan, there is just enough commonality
* to make it worth using the same data structure.
*
* heap_beginscan_sampling is an alternative entry point for setting up a
* HeapScanDesc for a TABLESAMPLE scan. As with bitmap scans, it's worth
* using the same data structure although the behavior is rather different.
* In addition to the options offered by heap_beginscan_strat, this call
* also allows control of whether page-mode visibility checking is used.
* ----------------
*/
HeapScanDesc
heap_beginscan(Relation relation, Snapshot snapshot,
int nkeys, ScanKey key)
{
return heap_beginscan_internal(relation, snapshot, nkeys, key, NULL,
true, true, true, false, false, false);
}
HeapScanDesc
heap_beginscan_catalog(Relation relation, int nkeys, ScanKey key)
{
Oid relid = RelationGetRelid(relation);
Snapshot snapshot = RegisterSnapshot(GetCatalogSnapshot(relid));
return heap_beginscan_internal(relation, snapshot, nkeys, key, NULL,
true, true, true, false, false, true);
}
HeapScanDesc
heap_beginscan_strat(Relation relation, Snapshot snapshot,
int nkeys, ScanKey key,
bool allow_strat, bool allow_sync)
{
return heap_beginscan_internal(relation, snapshot, nkeys, key, NULL,
allow_strat, allow_sync, true,
false, false, false);
}
HeapScanDesc
heap_beginscan_bm(Relation relation, Snapshot snapshot,
int nkeys, ScanKey key)
{
return heap_beginscan_internal(relation, snapshot, nkeys, key, NULL,
false, false, true, true, false, false);
}
HeapScanDesc
heap_beginscan_sampling(Relation relation, Snapshot snapshot,
int nkeys, ScanKey key,
bool allow_strat, bool allow_sync, bool allow_pagemode)
{
return heap_beginscan_internal(relation, snapshot, nkeys, key, NULL,
allow_strat, allow_sync, allow_pagemode,
false, true, false);
}
static HeapScanDesc
heap_beginscan_internal(Relation relation, Snapshot snapshot,
int nkeys, ScanKey key,
ParallelHeapScanDesc parallel_scan,
bool allow_strat,
bool allow_sync,
bool allow_pagemode,
bool is_bitmapscan,
bool is_samplescan,
bool temp_snap)
{
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_rd = relation;
scan->rs_snapshot = snapshot;
scan->rs_nkeys = nkeys;
scan->rs_bitmapscan = is_bitmapscan;
scan->rs_samplescan = is_samplescan;
scan->rs_strategy = NULL; /* set in initscan */
scan->rs_allow_strat = allow_strat;
scan->rs_allow_sync = allow_sync;
scan->rs_temp_snap = temp_snap;
scan->rs_parallel = parallel_scan;
/*
* we can use page-at-a-time mode if it's an MVCC-safe snapshot
*/
scan->rs_pageatatime = allow_pagemode && IsMVCCSnapshot(snapshot);
/*
* For a seqscan 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.
*/
if (!is_bitmapscan)
PredicateLockRelation(relation, snapshot);
/* we only need to set this up once */
scan->rs_ctup.t_tableOid = RelationGetRelid(relation);
/*
* 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_key = (ScanKey) palloc(sizeof(ScanKeyData) * nkeys);
else
scan->rs_key = NULL;
initscan(scan, key, false);
return scan;
}
/* ----------------
* heap_rescan - restart a relation scan
* ----------------
*/
void
heap_rescan(HeapScanDesc scan,
ScanKey key)
{
/*
* unpin scan buffers
*/
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
/*
* reinitialize scan descriptor
*/
initscan(scan, key, true);
}
/* ----------------
* heap_rescan_set_params - restart a relation scan after changing params
*
* This call allows changing the buffer strategy, syncscan, and pagemode
* options before starting a fresh scan. Note that although the actual use
* of syncscan might change (effectively, enabling or disabling reporting),
* the previously selected startblock will be kept.
* ----------------
*/
void
heap_rescan_set_params(HeapScanDesc scan, ScanKey key,
bool allow_strat, bool allow_sync, bool allow_pagemode)
{
/* adjust parameters */
scan->rs_allow_strat = allow_strat;
scan->rs_allow_sync = allow_sync;
scan->rs_pageatatime = allow_pagemode && IsMVCCSnapshot(scan->rs_snapshot);
/* ... and rescan */
heap_rescan(scan, key);
}
/* ----------------
* heap_endscan - end relation scan
*
* See how to integrate with index scans.
* Check handling if reldesc caching.
* ----------------
*/
void
heap_endscan(HeapScanDesc scan)
{
/* Note: no locking manipulations needed */
/*
* unpin scan buffers
*/
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
/*
* decrement relation reference count and free scan descriptor storage
*/
RelationDecrementReferenceCount(scan->rs_rd);
if (scan->rs_key)
pfree(scan->rs_key);
if (scan->rs_strategy != NULL)
FreeAccessStrategy(scan->rs_strategy);
if (scan->rs_temp_snap)
UnregisterSnapshot(scan->rs_snapshot);
pfree(scan);
}
/* ----------------
* heap_parallelscan_estimate - estimate storage for ParallelHeapScanDesc
*
* Sadly, this doesn't reduce to a constant, because the size required
* to serialize the snapshot can vary.
* ----------------
*/
Size
heap_parallelscan_estimate(Snapshot snapshot)
{
return add_size(offsetof(ParallelHeapScanDescData, phs_snapshot_data),
EstimateSnapshotSpace(snapshot));
}
/* ----------------
* heap_parallelscan_initialize - initialize ParallelHeapScanDesc
*
* Must allow as many bytes of shared memory as returned by
* heap_parallelscan_estimate. Call this just once in the leader
* process; then, individual workers attach via heap_beginscan_parallel.
* ----------------
*/
void
heap_parallelscan_initialize(ParallelHeapScanDesc target, Relation relation,
Snapshot snapshot)
{
target->phs_relid = RelationGetRelid(relation);
target->phs_nblocks = RelationGetNumberOfBlocks(relation);
/* compare phs_syncscan initialization to similar logic in initscan */
target->phs_syncscan = synchronize_seqscans &&
!RelationUsesLocalBuffers(relation) &&
target->phs_nblocks > NBuffers / 4;
SpinLockInit(&target->phs_mutex);
target->phs_startblock = InvalidBlockNumber;
pg_atomic_init_u64(&target->phs_nallocated, 0);
if (IsMVCCSnapshot(snapshot))
{
SerializeSnapshot(snapshot, target->phs_snapshot_data);
target->phs_snapshot_any = false;
}
else
{
Assert(snapshot == SnapshotAny);
target->phs_snapshot_any = true;
}
}
/* ----------------
* heap_parallelscan_reinitialize - reset a parallel scan
*
* Call this in the leader process. Caller is responsible for
* making sure that all workers have finished the scan beforehand.
* ----------------
*/
void
heap_parallelscan_reinitialize(ParallelHeapScanDesc parallel_scan)
{
pg_atomic_write_u64(&parallel_scan->phs_nallocated, 0);
}
/* ----------------
* heap_beginscan_parallel - join a parallel scan
*
* Caller must hold a suitable lock on the correct relation.
* ----------------
*/
HeapScanDesc
heap_beginscan_parallel(Relation relation, ParallelHeapScanDesc parallel_scan)
{
Snapshot snapshot;
Assert(RelationGetRelid(relation) == parallel_scan->phs_relid);
if (!parallel_scan->phs_snapshot_any)
{
/* Snapshot was serialized -- restore it */
snapshot = RestoreSnapshot(parallel_scan->phs_snapshot_data);
RegisterSnapshot(snapshot);
}
else
{
/* SnapshotAny passed by caller (not serialized) */
snapshot = SnapshotAny;
}
return heap_beginscan_internal(relation, snapshot, 0, NULL, parallel_scan,
true, true, true, false, false,
!parallel_scan->phs_snapshot_any);
}
/* ----------------
* heap_parallelscan_startblock_init - find and set the scan's startblock
*
* Determine where the parallel seq scan should start. This function may
* be called many times, once by each parallel worker. We must be careful
* only to set the startblock once.
* ----------------
*/
static void
heap_parallelscan_startblock_init(HeapScanDesc scan)
{
BlockNumber sync_startpage = InvalidBlockNumber;
ParallelHeapScanDesc parallel_scan;
Assert(scan->rs_parallel);
parallel_scan = scan->rs_parallel;
retry:
/* Grab the spinlock. */
SpinLockAcquire(&parallel_scan->phs_mutex);
/*
* If the scan's startblock has not yet been initialized, we must do so
* now. If this is not a synchronized scan, we just start at block 0, but
* if it is a synchronized scan, we must get the starting position from
* the synchronized scan machinery. We can't hold the spinlock while
* doing that, though, so release the spinlock, get the information we
* need, and retry. If nobody else has initialized the scan in the
* meantime, we'll fill in the value we fetched on the second time
* through.
*/
if (parallel_scan->phs_startblock == InvalidBlockNumber)
{
if (!parallel_scan->phs_syncscan)
parallel_scan->phs_startblock = 0;
else if (sync_startpage != InvalidBlockNumber)
parallel_scan->phs_startblock = sync_startpage;
else
{
SpinLockRelease(&parallel_scan->phs_mutex);
sync_startpage = ss_get_location(scan->rs_rd, scan->rs_nblocks);
goto retry;
}
}
SpinLockRelease(&parallel_scan->phs_mutex);
}
/* ----------------
* heap_parallelscan_nextpage - get the next page to scan
*
* Get the next page to scan. Even if there are no pages left to scan,
* another backend could have grabbed a page to scan and not yet finished
* looking at it, so it doesn't follow that the scan is done when the
* first backend gets an InvalidBlockNumber return.
* ----------------
*/
static BlockNumber
heap_parallelscan_nextpage(HeapScanDesc scan)
{
BlockNumber page;
ParallelHeapScanDesc parallel_scan;
uint64 nallocated;
Assert(scan->rs_parallel);
parallel_scan = scan->rs_parallel;
/*
* phs_nallocated tracks how many pages have been allocated to workers
* already. When phs_nallocated >= rs_nblocks, all blocks have been
* allocated.
*
* Because we use an atomic fetch-and-add to fetch the current value, the
* phs_nallocated counter will exceed rs_nblocks, because workers will
* still increment the value, when they try to allocate the next block but
* all blocks have been allocated already. The counter must be 64 bits
* wide because of that, to avoid wrapping around when rs_nblocks is close
* to 2^32.
*
* The actual page to return is calculated by adding the counter to the
* starting block number, modulo nblocks.
*/
nallocated = pg_atomic_fetch_add_u64(&parallel_scan->phs_nallocated, 1);
if (nallocated >= scan->rs_nblocks)
page = InvalidBlockNumber; /* all blocks have been allocated */
else
page = (nallocated + parallel_scan->phs_startblock) % scan->rs_nblocks;
/*
* Report scan location. Normally, we report the current page number.
* When we reach the end of the scan, though, we report the starting page,
* not the ending page, just so the starting positions for later scans
* doesn't slew backwards. We only report the position at the end of the
* scan once, though: subsequent callers will report nothing.
*/
if (scan->rs_syncscan)
{
if (page != InvalidBlockNumber)
ss_report_location(scan->rs_rd, page);
else if (nallocated == scan->rs_nblocks)
ss_report_location(scan->rs_rd, parallel_scan->phs_startblock);
}
return page;
}
/* ----------------
* heap_update_snapshot
*
* Update snapshot info in heap scan descriptor.
* ----------------
*/
void
heap_update_snapshot(HeapScanDesc scan, Snapshot snapshot)
{
Assert(IsMVCCSnapshot(snapshot));
RegisterSnapshot(snapshot);
scan->rs_snapshot = snapshot;
scan->rs_temp_snap = true;
}
/* ----------------
* heap_getnext - retrieve next tuple in scan
*
* Fix to work with index relations.
* We don't return the buffer anymore, but you can get it from the
* returned HeapTuple.
* ----------------
*/
#ifdef HEAPDEBUGALL
#define HEAPDEBUG_1 \
elog(DEBUG2, "heap_getnext([%s,nkeys=%d],dir=%d) called", \
RelationGetRelationName(scan->rs_rd), scan->rs_nkeys, (int) direction)
#define HEAPDEBUG_2 \
elog(DEBUG2, "heap_getnext returning EOS")
#define HEAPDEBUG_3 \
elog(DEBUG2, "heap_getnext returning tuple")
#else
#define HEAPDEBUG_1
#define HEAPDEBUG_2
#define HEAPDEBUG_3
#endif /* !defined(HEAPDEBUGALL) */
HeapTuple
heap_getnext(HeapScanDesc scan, ScanDirection direction)
{
/* Note: no locking manipulations needed */
HEAPDEBUG_1; /* heap_getnext( info ) */
if (scan->rs_pageatatime)
heapgettup_pagemode(scan, direction,
scan->rs_nkeys, scan->rs_key);
else
heapgettup(scan, direction, scan->rs_nkeys, scan->rs_key);
if (scan->rs_ctup.t_data == NULL)
{
HEAPDEBUG_2; /* heap_getnext returning EOS */
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.
*/
HEAPDEBUG_3; /* heap_getnext returning tuple */
pgstat_count_heap_getnext(scan->rs_rd);
return &(scan->rs_ctup);
}
/*
* heap_fetch - retrieve tuple with given tid
*
* On entry, tuple->t_self is the TID to fetch. We pin the buffer holding
* the tuple, fill in the remaining fields of *tuple, and check the tuple
* against the specified snapshot.
*
* If successful (tuple found and passes snapshot time qual), then *userbuf
* is set to the buffer holding the tuple and true is returned. The caller
* must unpin the buffer when done with the tuple.
*
* If the tuple is not found (ie, item number references a deleted slot),
* then tuple->t_data is set to NULL and false is returned.
*
* If the tuple is found but fails the time qual check, then false is returned
* but tuple->t_data is left pointing to the tuple.
*
* keep_buf determines what is done with the buffer in the false-result cases.
* When the caller specifies keep_buf = true, we retain the pin on the buffer
* and return it in *userbuf (so the caller must eventually unpin it); when
* keep_buf = false, the pin is released and *userbuf is set to InvalidBuffer.
*
* stats_relation is the relation to charge the heap_fetch operation against
* for statistical purposes. (This could be the heap rel itself, an
* associated index, or NULL to not count the fetch at all.)
*
* heap_fetch does not follow HOT chains: only the exact TID requested will
* be fetched.
*
* It is somewhat inconsistent that we ereport() on invalid block number but
* return false on invalid item number. There are a couple of reasons though.
* One is that the caller can relatively easily check the block number for
* validity, but cannot check the item number without reading the page
* himself. Another is that when we are following a t_ctid link, we can be
* reasonably confident that the page number is valid (since VACUUM shouldn't
* truncate off the destination page without having killed the referencing
* tuple first), but the item number might well not be good.
*/
bool
heap_fetch(Relation relation,
Snapshot snapshot,
HeapTuple tuple,
Buffer *userbuf,
bool keep_buf,
Relation stats_relation)
{
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);
TestForOldSnapshot(snapshot, relation, page);
/*
* 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);
if (keep_buf)
*userbuf = buffer;
else
{
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);
if (keep_buf)
*userbuf = buffer;
else
{
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 time qualification of tuple, then release lock
*/
valid = HeapTupleSatisfiesVisibility(tuple, snapshot, buffer);
if (valid)
PredicateLockTuple(relation, tuple, snapshot);
CheckForSerializableConflictOut(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;
/* Count the successful fetch against appropriate rel, if any */
if (stats_relation != NULL)
pgstat_count_heap_fetch(stats_relation);
return true;
}
/* Tuple failed time qual, but maybe caller wants to see it anyway. */
if (keep_buf)
*userbuf = buffer;
else
{
ReleaseBuffer(buffer);
*userbuf = InvalidBuffer;
}
return false;
}
/*
* heap_hot_search_buffer - search HOT chain for tuple satisfying snapshot
*
* On entry, *tid is the TID of a tuple (either a simple tuple, or the root
* of a HOT chain), and buffer is the buffer holding this tuple. We search
* for the first chain member satisfying the given snapshot. If one is
* found, we update *tid to reference that tuple's offset number, and
* return true. If no match, return false without modifying *tid.
*
* heapTuple is a caller-supplied buffer. When a match is found, we return
* the tuple here, in addition to updating *tid. If no match is found, the
* contents of this buffer on return are undefined.
*
* If all_dead is not NULL, we check non-visible tuples to see if they are
* globally dead; *all_dead is set true if all members of the HOT chain
* are vacuumable, false if not.
*
* Unlike heap_fetch, the caller must already have pin and (at least) share
* lock on the buffer; it is still pinned/locked at exit. Also unlike
* heap_fetch, we do not report any pgstats count; caller may do so if wanted.
*/
bool
heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
Snapshot snapshot, HeapTuple heapTuple,
bool *all_dead, bool first_call)
{
Page dp = (Page) BufferGetPage(buffer);
TransactionId prev_xmax = InvalidTransactionId;
OffsetNumber offnum;
bool at_chain_start;
bool valid;
bool skip;
/* If this is not the first call, previous call returned a (live!) tuple */
if (all_dead)
*all_dead = first_call;
Assert(TransactionIdIsValid(RecentGlobalXmin));
Assert(ItemPointerGetBlockNumber(tid) == BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(tid);
at_chain_start = first_call;
skip = !first_call;
heapTuple->t_self = *tid;
/* Scan through possible multiple members of HOT-chain */
for (;;)
{
ItemId lp;
/* check for bogus TID */
if (offnum < FirstOffsetNumber || offnum > PageGetMaxOffsetNumber(dp))
break;
lp = PageGetItemId(dp, 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;
}
heapTuple->t_data = (HeapTupleHeader) PageGetItem(dp, lp);
heapTuple->t_len = ItemIdGetLength(lp);
heapTuple->t_tableOid = RelationGetRelid(relation);
ItemPointerSetOffsetNumber(&heapTuple->t_self, 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)
{
/*
* For the benefit of logical decoding, have t_self point at the
* element of the HOT chain we're currently investigating instead
* of the root tuple of the HOT chain. This is important because
* the *Satisfies routine for historical mvcc snapshots needs the
* correct tid to decide about the visibility in some cases.
*/
ItemPointerSet(&(heapTuple->t_self), BufferGetBlockNumber(buffer), offnum);
/* If it's visible per the snapshot, we must return it */
valid = HeapTupleSatisfiesVisibility(heapTuple, snapshot, buffer);
CheckForSerializableConflictOut(valid, relation, heapTuple,
buffer, snapshot);
/* reset to original, non-redirected, tid */
heapTuple->t_self = *tid;
if (valid)
{
ItemPointerSetOffsetNumber(tid, offnum);
PredicateLockTuple(relation, heapTuple, snapshot);
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 &&
!HeapTupleIsSurelyDead(heapTuple, RecentGlobalXmin))
*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) ==
ItemPointerGetBlockNumber(tid));
offnum = ItemPointerGetOffsetNumber(&heapTuple->t_data->t_ctid);
at_chain_start = false;
prev_xmax = HeapTupleHeaderGetUpdateXid(heapTuple->t_data);
}
else
break; /* end of chain */
}
return false;
}
/*
* heap_hot_search - search HOT chain for tuple satisfying snapshot
*
* This has the same API as heap_hot_search_buffer, except that the caller
* does not provide the buffer containing the page, rather we access it
* locally.
*/
bool
heap_hot_search(ItemPointer tid, Relation relation, Snapshot snapshot,
bool *all_dead)
{
bool result;
Buffer buffer;
HeapTupleData heapTuple;
buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
LockBuffer(buffer, BUFFER_LOCK_SHARE);
result = heap_hot_search_buffer(tid, relation, buffer, snapshot,
&heapTuple, all_dead, true);
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
return result;
}
/*
* heap_get_latest_tid - get the latest tid of a specified tuple
*
* Actually, this gets the latest version that is visible according to
* the passed snapshot. You can pass SnapshotDirty to get the very latest,
* possibly uncommitted version.
*
* *tid is both an input and an output parameter: it is updated to
* show the latest version of the row. Note that it will not be changed
* if no version of the row passes the snapshot test.
*/
void
heap_get_latest_tid(Relation relation,
Snapshot snapshot,
ItemPointer tid)
{
BlockNumber blk;
ItemPointerData ctid;
TransactionId priorXmax;
/* this is to avoid Assert failures on bad input */
if (!ItemPointerIsValid(tid))
return;
/*
* Since this can be called with user-supplied TID, don't trust the input
* too much. (RelationGetNumberOfBlocks is an expensive check, so we
* don't check t_ctid links again this way. Note that it would not do to
* call it just once and save the result, either.)
*/
blk = ItemPointerGetBlockNumber(tid);
if (blk >= RelationGetNumberOfBlocks(relation))
elog(ERROR, "block number %u is out of range for relation \"%s\"",
blk, RelationGetRelationName(relation));
/*
* 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);
TestForOldSnapshot(snapshot, relation, page);
/*
* 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 time qualification of tuple; if visible, set it as the new
* result candidate.
*/
valid = HeapTupleSatisfiesVisibility(&tp, snapshot, buffer);
CheckForSerializableConflictOut(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 */
}
/*
* UpdateXmaxHintBits - update tuple hint bits after xmax transaction ends
*
* This is called after we have waited for the XMAX transaction to terminate.
* If the transaction aborted, we guarantee the XMAX_INVALID hint bit will
* be set on exit. If the transaction committed, we set the XMAX_COMMITTED
* hint bit if possible --- but beware that that may not yet be possible,
* if the transaction committed asynchronously.
*
* Note that if the transaction was a locker only, we set HEAP_XMAX_INVALID
* even if it commits.
*
* Hence callers should look only at XMAX_INVALID.
*
* Note this is not allowed for tuples whose xmax is a multixact.
*/
static void
UpdateXmaxHintBits(HeapTupleHeader tuple, Buffer buffer, TransactionId xid)
{
Assert(TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple), xid));
Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
if (!(tuple->t_infomask & (HEAP_XMAX_COMMITTED | HEAP_XMAX_INVALID)))
{
if (!HEAP_XMAX_IS_LOCKED_ONLY(tuple->t_infomask) &&
TransactionIdDidCommit(xid))
HeapTupleSetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
xid);
else
HeapTupleSetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
}
}
/*
* GetBulkInsertState - prepare status object for a bulk insert
*/
BulkInsertState
GetBulkInsertState(void)
{
BulkInsertState bistate;
bistate = (BulkInsertState) palloc(sizeof(BulkInsertStateData));
bistate->strategy = GetAccessStrategy(BAS_BULKWRITE);
bistate->current_buf = InvalidBuffer;
return bistate;
}
/*
* FreeBulkInsertState - clean up after finishing a bulk insert
*/
void
FreeBulkInsertState(BulkInsertState bistate)
{
if (bistate->current_buf != InvalidBuffer)
ReleaseBuffer(bistate->current_buf);
FreeAccessStrategy(bistate->strategy);
pfree(bistate);
}
/*
* ReleaseBulkInsertStatePin - release a buffer currently held in bistate
*/
void
ReleaseBulkInsertStatePin(BulkInsertState bistate)
{
if (bistate->current_buf != InvalidBuffer)
ReleaseBuffer(bistate->current_buf);
bistate->current_buf = InvalidBuffer;
}
/*
* heap_insert - insert tuple into a heap
*
* The new tuple is stamped with current transaction ID and the specified
* command ID.
*
* If the HEAP_INSERT_SKIP_WAL option is specified, the new tuple is not
* logged in WAL, even for a non-temp relation. Safe usage of this behavior
* requires that we arrange that all new tuples go into new pages not
* containing any tuples from other transactions, and that the relation gets
* fsync'd before commit. (See also heap_sync() comments)
*
* The HEAP_INSERT_SKIP_FSM option is passed directly to
* RelationGetBufferForTuple, which see for more info.
*
* HEAP_INSERT_FROZEN should only be specified for inserts into
* relfilenodes created during the current subtransaction and when
* there are no prior snapshots or pre-existing portals open.
* This causes rows to be frozen, which is an MVCC violation and
* requires explicit options chosen by user.
*
* HEAP_INSERT_SPECULATIVE is used on so-called "speculative insertions",
* which can be backed out afterwards without aborting the whole transaction.
* Other sessions can wait for the speculative insertion to be confirmed,
* turning it into a regular tuple, or aborted, as if it never existed.
* Speculatively inserted tuples behave as "value locks" of short duration,
* used to implement INSERT .. ON CONFLICT.
*
* HEAP_INSERT_NO_LOGICAL force-disables the emitting of logical decoding
* information for the tuple. This should solely be used during table rewrites
* where RelationIsLogicallyLogged(relation) is not yet accurate for the new
* relation.
*
* Note that most of these options will be applied when inserting into the
* heap's TOAST table, too, if the tuple requires any out-of-line data. Only
* HEAP_INSERT_SPECULATIVE is explicitly ignored, as the toast data does not
* partake in speculative insertion.
*
* The BulkInsertState object (if any; bistate can be NULL for default
* behavior) is also just passed through to RelationGetBufferForTuple.
*
* The return value is the OID assigned to the tuple (either here or by the
* caller), or InvalidOid if no OID. The header fields of *tup are updated
* to match the stored tuple; in particular tup->t_self receives the actual
* TID where the tuple was stored. But note that any toasting of fields
* within the tuple data is NOT reflected into *tup.
*/
void
heap_insert(Relation relation, HeapTuple tup, CommandId cid,
int options, BulkInsertState bistate)
{
TransactionId xid = GetCurrentTransactionId();
HeapTuple heaptup;
Buffer buffer;
Buffer vmbuffer = InvalidBuffer;
bool all_visible_cleared = false;
/*
* Fill in tuple header fields, assign an OID, 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);
/*
* 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, InvalidBuffer);
/* 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 (!(options & HEAP_INSERT_SKIP_WAL) && 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 combocids 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;
}
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);
}
}
/*
* Subroutine for heap_insert(). Prepares a tuple for insertion. This sets the
* tuple header fields, assigns an OID, and toasts the tuple if necessary.
* Returns a toasted version of the tuple if it was toasted, or the original
* tuple if not. Note that in any case, the header fields are also set in
* the original tuple.
*/
static HeapTuple
heap_prepare_insert(Relation relation, HeapTuple tup, TransactionId xid,
CommandId cid, int options)
{
/*
* Parallel operations are required to be strictly read-only in a parallel
* worker. Parallel inserts are not safe even in the leader in the
* general case, because group locking means that heavyweight locks for
* relation extension or GIN page locks will not conflict between members
* of a lock group, but we don't prohibit that case here because there are
* useful special cases that we can safely allow, such as CREATE TABLE AS.
*/
if (IsParallelWorker())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot insert tuples in a parallel worker")));
tup->t_data->t_infomask &= ~(HEAP_XACT_MASK);
tup->t_data->t_infomask2 &= ~(HEAP2_XACT_MASK);
tup->t_data->t_infomask |= HEAP_XMAX_INVALID;
HeapTupleHeaderSetXmin(tup->t_data, xid);
if (options & HEAP_INSERT_FROZEN)
HeapTupleHeaderSetXminFrozen(tup->t_data);
HeapTupleHeaderSetCmin(tup->t_data, cid);
HeapTupleHeaderSetXmax(tup->t_data, 0); /* for cleanliness */
tup->t_tableOid = RelationGetRelid(relation);
/*
* If the new tuple is too big for storage or contains already toasted
* out-of-line attributes from some other relation, invoke the toaster.
*/
if (relation->rd_rel->relkind != RELKIND_RELATION &&
relation->rd_rel->relkind != RELKIND_MATVIEW)
{
/* toast table entries should never be recursively toasted */
Assert(!HeapTupleHasExternal(tup));
return tup;
}
else if (HeapTupleHasExternal(tup) || tup->t_len > TOAST_TUPLE_THRESHOLD)
return toast_insert_or_update(relation, tup, NULL, options);
else
return tup;
}
/*
* heap_multi_insert - insert multiple tuple into a heap
*
* This is like heap_insert(), but inserts multiple tuples in one operation.
* That's faster than calling heap_insert() in a loop, because when multiple
* tuples can be inserted on a single page, we can write just a single WAL
* record covering all of them, and only need to lock/unlock the page once.
*
* Note: this leaks memory into the current memory context. You can create a
* temporary context before calling this, if that's a problem.
*/
void
heap_multi_insert(Relation relation, HeapTuple *tuples, int ntuples,
CommandId cid, int options, BulkInsertState bistate)
{
TransactionId xid = GetCurrentTransactionId();
HeapTuple *heaptuples;
int i;
int ndone;
PGAlignedBlock scratch;
Page page;
bool needwal;
Size saveFreeSpace;
bool need_tuple_data = RelationIsLogicallyLogged(relation);
bool need_cids = RelationIsAccessibleInLogicalDecoding(relation);
/* currently not needed (thus unsupported) for heap_multi_insert() */
AssertArg(!(options & HEAP_INSERT_NO_LOGICAL));
needwal = !(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation);
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
/* Toast and set header data in all the tuples */
heaptuples = palloc(ntuples * sizeof(HeapTuple));
for (i = 0; i < ntuples; i++)
heaptuples[i] = heap_prepare_insert(relation, tuples[i],
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 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, InvalidBuffer);
ndone = 0;
while (ndone < ntuples)
{
Buffer buffer;
Buffer vmbuffer = InvalidBuffer;
bool all_visible_cleared = false;
int nthispage;
CHECK_FOR_INTERRUPTS();
/*
* 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.
*/
buffer = RelationGetBufferForTuple(relation, heaptuples[ndone]->t_len,
InvalidBuffer, options, bistate,
&vmbuffer, NULL);
page = BufferGetPage(buffer);
/* 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 (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);
/*
* We don't use heap_multi_insert for catalog tuples yet, but
* better be prepared...
*/
if (needwal && need_cids)
log_heap_new_cid(relation, heaptup);
}
if (PageIsAllVisible(page))
{
all_visible_cleared = true;
PageClearAllVisible(page);
visibilitymap_clear(relation,
BufferGetBlockNumber(buffer),
vmbuffer, VISIBILITYMAP_VALID_BITS);
}
/*
* 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 = (ItemPointerGetOffsetNumber(&(heaptuples[ndone]->t_self)) == FirstOffsetNumber &&
PageGetMaxOffsetNumber(page) == FirstOffsetNumber + nthispage - 1);
/* 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;
xlrec->flags = all_visible_cleared ? XLH_INSERT_ALL_VISIBLE_CLEARED : 0;
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();
UnlockReleaseBuffer(buffer);
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
ndone += nthispage;
}
/*
* 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, InvalidBuffer);
/*
* 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 original tuples. This does
* nothing for untoasted tuples (tuples[i] == heaptuples[i)], but it's
* probably faster to always copy than check.
*/
for (i = 0; i < ntuples; i++)
tuples[i]->t_self = heaptuples[i]->t_self;
pgstat_count_heap_insert(relation, ntuples);
}
/*
* simple_heap_insert - insert a tuple
*
* Currently, this routine differs from heap_insert only in supplying
* a default command ID and not allowing access to the speedup options.
*
* This should be used rather than using heap_insert directly in most places
* where we are modifying system catalogs.
*/
void
simple_heap_insert(Relation relation, HeapTuple tup)
{
heap_insert(relation, tup, GetCurrentCommandId(true), 0, NULL);
}
/*
* Given infomask/infomask2, compute the bits that must be saved in the
* "infobits" field of xl_heap_delete, xl_heap_update, xl_heap_lock,
* xl_heap_lock_updated WAL records.
*
* See fix_infomask_from_infobits.
*/
static uint8
compute_infobits(uint16 infomask, uint16 infomask2)
{
return
((infomask & HEAP_XMAX_IS_MULTI) != 0 ? XLHL_XMAX_IS_MULTI : 0) |
((infomask & HEAP_XMAX_LOCK_ONLY) != 0 ? XLHL_XMAX_LOCK_ONLY : 0) |
((infomask & HEAP_XMAX_EXCL_LOCK) != 0 ? XLHL_XMAX_EXCL_LOCK : 0) |
/* note we ignore HEAP_XMAX_SHR_LOCK here */
((infomask & HEAP_XMAX_KEYSHR_LOCK) != 0 ? XLHL_XMAX_KEYSHR_LOCK : 0) |
((infomask2 & HEAP_KEYS_UPDATED) != 0 ?
XLHL_KEYS_UPDATED : 0);
}
/*
* Given two versions of the same t_infomask for a tuple, compare them and
* return whether the relevant status for a tuple Xmax has changed. This is
* used after a buffer lock has been released and reacquired: we want to ensure
* that the tuple state continues to be the same it was when we previously
* examined it.
*
* Note the Xmax field itself must be compared separately.
*/
static inline bool
xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask)
{
const uint16 interesting =
HEAP_XMAX_IS_MULTI | HEAP_XMAX_LOCK_ONLY | HEAP_LOCK_MASK;
if ((new_infomask & interesting) != (old_infomask & interesting))
return true;
return false;
}
/*
* heap_delete - delete a tuple
*
* NB: do not call this directly unless you are prepared to deal with
* concurrent-update conditions. Use simple_heap_delete instead.
*
* relation - table to be modified (caller must hold suitable lock)
* tid - TID of tuple to be deleted
* cid - delete command ID (used for visibility test, and stored into
* cmax if successful)
* crosscheck - if not InvalidSnapshot, also check tuple against this
* wait - true if should wait for any conflicting update to commit/abort
* hufd - output parameter, filled in failure cases (see below)
* changingPart - true iff the tuple is being moved to another partition
* table due to an update of the partition key. Otherwise, false.
*
* Normal, successful return value is HeapTupleMayBeUpdated, which
* actually means we did delete it. Failure return codes are
* HeapTupleSelfUpdated, HeapTupleUpdated, or HeapTupleBeingUpdated
* (the last only possible if wait == false).
*
* In the failure cases, the routine fills *hufd with the tuple's t_ctid,
* t_xmax (resolving a possible MultiXact, if necessary), and t_cmax
* (the last only for HeapTupleSelfUpdated, since we
* cannot obtain cmax from a combocid generated by another transaction).
* See comments for struct HeapUpdateFailureData for additional info.
*/
HTSU_Result
heap_delete(Relation relation, ItemPointer tid,
CommandId cid, Snapshot crosscheck, bool wait,
HeapUpdateFailureData *hufd, bool changingPart)
{
HTSU_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 combocid.
* Other workers might need that combocid 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);
/*
* 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);
}
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:
result = HeapTupleSatisfiesUpdate(&tp, cid, buffer);
if (result == HeapTupleInvisible)
{
UnlockReleaseBuffer(buffer);
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("attempted to delete invisible tuple")));
}
else if (result == HeapTupleBeingUpdated && 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)
{
/* wait for multixact */
if (DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
LockTupleExclusive))
{
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
/* acquire tuple lock, if necessary */
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.
*/
if (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.
*/
if (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 = HeapTupleMayBeUpdated;
else
result = HeapTupleUpdated;
}
if (crosscheck != InvalidSnapshot && result == HeapTupleMayBeUpdated)
{
/* Perform additional check for transaction-snapshot mode RI updates */
if (!HeapTupleSatisfiesVisibility(&tp, crosscheck, buffer))
result = HeapTupleUpdated;
}
if (result != HeapTupleMayBeUpdated)
{
Assert(result == HeapTupleSelfUpdated ||
result == HeapTupleUpdated ||
result == HeapTupleBeingUpdated);
Assert(!(tp.t_data->t_infomask & HEAP_XMAX_INVALID));
hufd->ctid = tp.t_data->t_ctid;
hufd->xmax = HeapTupleHeaderGetUpdateXid(tp.t_data);
if (result == HeapTupleSelfUpdated)
hufd->cmax = HeapTupleHeaderGetCmax(tp.t_data);
else
hufd->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, &tp, 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;
XLogRecPtr recptr;
/* For logical decode we need combocids 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)
{
xl_heap_header xlhdr;
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))
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 HeapTupleMayBeUpdated;
}
/*
* simple_heap_delete - delete a tuple
*
* This routine may be used to delete a tuple when concurrent updates of
* the target tuple are not expected (for example, because we have a lock
* on the relation associated with the tuple). Any failure is reported
* via ereport().
*/
void
simple_heap_delete(Relation relation, ItemPointer tid)
{
HTSU_Result result;
HeapUpdateFailureData hufd;
result = heap_delete(relation, tid,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
&hufd, false /* changingPart */ );
switch (result)
{
case HeapTupleSelfUpdated:
/* Tuple was already updated in current command? */
elog(ERROR, "tuple already updated by self");
break;
case HeapTupleMayBeUpdated:
/* done successfully */
break;
case HeapTupleUpdated:
elog(ERROR, "tuple concurrently updated");
break;
default:
elog(ERROR, "unrecognized heap_delete status: %u", result);
break;
}
}
/*
* heap_update - replace a tuple
*
* NB: do not call this directly unless you are prepared to deal with
* concurrent-update conditions. Use simple_heap_update instead.
*
* relation - table to be modified (caller must hold suitable lock)
* otid - TID of old tuple to be replaced
* newtup - newly constructed tuple data to store
* cid - update command ID (used for visibility test, and stored into
* cmax/cmin if successful)
* crosscheck - if not InvalidSnapshot, also check old tuple against this
* wait - true if should wait for any conflicting update to commit/abort
* hufd - output parameter, filled in failure cases (see below)
* lockmode - output parameter, filled with lock mode acquired on tuple
*
* Normal, successful return value is HeapTupleMayBeUpdated, which
* actually means we *did* update it. Failure return codes are
* HeapTupleSelfUpdated, HeapTupleUpdated, or HeapTupleBeingUpdated
* (the last only possible if wait == false).
*
* On success, the header fields of *newtup are updated to match the new
* stored tuple; in particular, newtup->t_self is set to the TID where the
* new tuple was inserted, and its HEAP_ONLY_TUPLE flag is set iff a HOT
* update was done. However, any TOAST changes in the new tuple's
* data are not reflected into *newtup.
*
* In the failure cases, the routine fills *hufd with the tuple's t_ctid,
* t_xmax (resolving a possible MultiXact, if necessary), and t_cmax
* (the last only for HeapTupleSelfUpdated, since we
* cannot obtain cmax from a combocid generated by another transaction).
* See comments for struct HeapUpdateFailureData for additional info.
*/
HTSU_Result
heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
HeapUpdateFailureData *hufd, LockTupleMode *lockmode)
{
HTSU_Result result;
TransactionId xid = GetCurrentTransactionId();
Bitmapset *hot_attrs;
Bitmapset *proj_idx_attrs;
Bitmapset *key_attrs;
Bitmapset *id_attrs;
Bitmapset *interesting_attrs;
Bitmapset *modified_attrs;
ItemId lp;
HeapTupleData oldtup;
HeapTuple heaptup;
HeapTuple old_key_tuple = NULL;
bool old_key_copied = false;
Page page;
BlockNumber block;
MultiXactStatus mxact_status;
Buffer buffer,
newbuf,
vmbuffer = InvalidBuffer,
vmbuffer_new = InvalidBuffer;
bool need_toast;
Size newtupsize,
pagefree;
bool have_tuple_lock = false;
bool iscombo;
bool use_hot_update = false;
bool hot_attrs_checked = false;
bool key_intact;
bool all_visible_cleared = false;
bool all_visible_cleared_new = false;
bool checked_lockers;
bool locker_remains;
TransactionId xmax_new_tuple,
xmax_old_tuple;
uint16 infomask_old_tuple,
infomask2_old_tuple,
infomask_new_tuple,
infomask2_new_tuple;
Assert(ItemPointerIsValid(otid));
/*
* Forbid this during a parallel operation, lest it allocate a combocid.
* Other workers might need that combocid for visibility checks, and we
* have no provision for broadcasting it to them.
*/
if (IsInParallelMode())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot update tuples during a parallel operation")));
/*
* Fetch the list of attributes to be checked for various operations.
*
* For HOT considerations, this is wasted effort if we fail to update or
* have to put the new tuple on a different page. But we must compute the
* list before obtaining buffer lock --- in the worst case, if we are
* doing an update on one of the relevant system catalogs, we could
* deadlock if we try to fetch the list later. In any case, the relcache
* caches the data so this is usually pretty cheap.
*
* We also need columns used by the replica identity and columns that are
* considered the "key" of rows in the table.
*
* Note that we get copies of each bitmap, so we need not worry about
* relcache flush happening midway through.
*/
hot_attrs = RelationGetIndexAttrBitmap(relation, INDEX_ATTR_BITMAP_HOT);
proj_idx_attrs = RelationGetIndexAttrBitmap(relation, INDEX_ATTR_BITMAP_PROJ);
key_attrs = RelationGetIndexAttrBitmap(relation, INDEX_ATTR_BITMAP_KEY);
id_attrs = RelationGetIndexAttrBitmap(relation,
INDEX_ATTR_BITMAP_IDENTITY_KEY);
block = ItemPointerGetBlockNumber(otid);
buffer = ReadBuffer(relation, block);
page = BufferGetPage(buffer);
interesting_attrs = NULL;
/*
* If the page is already full, there is hardly any chance of doing a HOT
* update on this page. It might be wasteful effort to look for index
* column updates only to later reject HOT updates for lack of space in
* the same page. So we be conservative and only fetch hot_attrs if the
* page is not already full. Since we are already holding a pin on the
* buffer, there is no chance that the buffer can get cleaned up
* concurrently and even if that was possible, in the worst case we lose a
* chance to do a HOT update.
*/
if (!PageIsFull(page))
{
interesting_attrs = bms_add_members(interesting_attrs, hot_attrs);
interesting_attrs = bms_add_members(interesting_attrs, proj_idx_attrs);
hot_attrs_checked = true;
}
interesting_attrs = bms_add_members(interesting_attrs, key_attrs);
interesting_attrs = bms_add_members(interesting_attrs, id_attrs);
/*
* Before locking the buffer, pin the visibility map page if it appears to
* be necessary. Since we haven't got the lock yet, someone else might be
* in the middle of changing this, so we'll need to recheck after we have
* the lock.
*/
if (PageIsAllVisible(page))
visibilitymap_pin(relation, block, &vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
lp = PageGetItemId(page, ItemPointerGetOffsetNumber(otid));
Assert(ItemIdIsNormal(lp));
/*
* Fill in enough data in oldtup for HeapDetermineModifiedColumns to work
* properly.
*/
oldtup.t_tableOid = RelationGetRelid(relation);
oldtup.t_data = (HeapTupleHeader) PageGetItem(page, lp);
oldtup.t_len = ItemIdGetLength(lp);
oldtup.t_self = *otid;
/* the new tuple is ready, except for this: */
newtup->t_tableOid = RelationGetRelid(relation);
/* Determine columns modified by the update. */
modified_attrs = HeapDetermineModifiedColumns(relation, interesting_attrs,
&oldtup, newtup);
/*
* If we're not updating any "key" column, we can grab a weaker lock type.
* This allows for more concurrency when we are running simultaneously
* with foreign key checks.
*
* Note that if a column gets detoasted while executing the update, but
* the value ends up being the same, this test will fail and we will use
* the stronger lock. This is acceptable; the important case to optimize
* is updates that don't manipulate key columns, not those that
* serendipitiously arrive at the same key values.
*/
if (!bms_overlap(modified_attrs, key_attrs))
{
*lockmode = LockTupleNoKeyExclusive;
mxact_status = MultiXactStatusNoKeyUpdate;
key_intact = true;
/*
* If this is the first possibly-multixact-able operation in the
* current transaction, set my per-backend OldestMemberMXactId
* setting. We can be certain that the transaction will never become a
* member of any older MultiXactIds than that. (We have to do this
* even if we end up just using our own TransactionId below, since
* some other backend could incorporate our XID into a MultiXact
* immediately afterwards.)
*/
MultiXactIdSetOldestMember();
}
else
{
*lockmode = LockTupleExclusive;
mxact_status = Multi