/*
* Start remote transaction or subtransaction, if needed.
*
* Note that we always use at least REPEATABLE READ in the remote session.
* This is so that, if a query initiates multiple scans of the same or
* different foreign tables, we will get snapshot-consistent results from
* those scans. A disadvantage is that we can't provide sane emulation of
* READ COMMITTED behavior --- it would be nice if we had some other way to
* control which remote queries share a snapshot.
*/
static void
begin_remote_xact(ConnCacheEntry *entry)
{
int curlevel = GetCurrentTransactionNestLevel();
/* Start main transaction if we haven't yet */
if (entry->xact_depth <= 0)
{
const char *sql;
elog(DEBUG3, "starting remote transaction on connection %p",
entry->conn);
if (IsolationIsSerializable())
sql = "START TRANSACTION ISOLATION LEVEL SERIALIZABLE";
else
sql = "START TRANSACTION ISOLATION LEVEL REPEATABLE READ";
do_sql_command(entry->conn, sql);
entry->xact_depth = 1;
}
/*
* If we're in a subtransaction, stack up savepoints to match our level.
* This ensures we can rollback just the desired effects when a
* subtransaction aborts.
*/
while (entry->xact_depth < curlevel)
{
char sql[64];
snprintf(sql, sizeof(sql), "SAVEPOINT s%d", entry->xact_depth + 1);
do_sql_command(entry->conn, sql);
entry->xact_depth++;
}
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(RegisteredSnapshots == 0);
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* register it internally here and unregister it at end of xact.
*/
if (IsolationUsesXactSnapshot())
{
if (IsolationIsSerializable())
CurrentSnapshot = RegisterSerializableTransaction(&CurrentSnapshotData);
else
{
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
CurrentSnapshot = RegisterSnapshotOnOwner(CurrentSnapshot,
TopTransactionResourceOwner);
}
registered_xact_snapshot = true;
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* ImportSnapshot
* Import a previously exported snapshot. The argument should be a
* filename in SNAPSHOT_EXPORT_DIR. Load the snapshot from that file.
* This is called by "SET TRANSACTION SNAPSHOT 'foo'".
*/
void
ImportSnapshot(const char *idstr)
{
char path[MAXPGPATH];
FILE *f;
struct stat stat_buf;
char *filebuf;
int xcnt;
int i;
TransactionId src_xid;
Oid src_dbid;
int src_isolevel;
bool src_readonly;
SnapshotData snapshot;
/*
* Must be at top level of a fresh transaction. Note in particular that
* we check we haven't acquired an XID --- if we have, it's conceivable
* that the snapshot would show it as not running, making for very
* screwy behavior.
*/
if (FirstSnapshotSet ||
GetTopTransactionIdIfAny() != InvalidTransactionId ||
IsSubTransaction())
ereport(ERROR,
(errcode(ERRCODE_ACTIVE_SQL_TRANSACTION),
errmsg("SET TRANSACTION SNAPSHOT must be called before any query")));
/*
* If we are in read committed mode then the next query would execute
* with a new snapshot thus making this function call quite useless.
*/
if (!IsolationUsesXactSnapshot())
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a snapshot-importing transaction must have isolation level SERIALIZABLE or REPEATABLE READ")));
/*
* Verify the identifier: only 0-9, A-F and hyphens are allowed. We do
* this mainly to prevent reading arbitrary files.
*/
if (strspn(idstr, "0123456789ABCDEF-") != strlen(idstr))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid snapshot identifier \"%s\"", idstr)));
/* OK, read the file */
snprintf(path, MAXPGPATH, SNAPSHOT_EXPORT_DIR "/%s", idstr);
f = AllocateFile(path, PG_BINARY_R);
if (!f)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid snapshot identifier \"%s\"", idstr)));
/* get the size of the file so that we know how much memory we need */
if (fstat(fileno(f), &stat_buf))
elog(ERROR, "could not stat file \"%s\": %m", path);
/* and read the file into a palloc'd string */
filebuf = (char *) palloc(stat_buf.st_size + 1);
if (fread(filebuf, stat_buf.st_size, 1, f) != 1)
elog(ERROR, "could not read file \"%s\": %m", path);
filebuf[stat_buf.st_size] = '\0';
FreeFile(f);
/*
* Construct a snapshot struct by parsing the file content.
*/
memset(&snapshot, 0, sizeof(snapshot));
src_xid = parseXidFromText("xid:", &filebuf, path);
/* we abuse parseXidFromText a bit here ... */
src_dbid = parseXidFromText("dbid:", &filebuf, path);
src_isolevel = parseIntFromText("iso:", &filebuf, path);
src_readonly = parseIntFromText("ro:", &filebuf, path);
snapshot.xmin = parseXidFromText("xmin:", &filebuf, path);
snapshot.xmax = parseXidFromText("xmax:", &filebuf, path);
snapshot.xcnt = xcnt = parseIntFromText("xcnt:", &filebuf, path);
/* sanity-check the xid count before palloc */
if (xcnt < 0 || xcnt > GetMaxSnapshotXidCount())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
snapshot.xip = (TransactionId *) palloc(xcnt * sizeof(TransactionId));
for (i = 0; i < xcnt; i++)
snapshot.xip[i] = parseXidFromText("xip:", &filebuf, path);
snapshot.suboverflowed = parseIntFromText("sof:", &filebuf, path);
if (!snapshot.suboverflowed)
{
snapshot.subxcnt = xcnt = parseIntFromText("sxcnt:", &filebuf, path);
/* sanity-check the xid count before palloc */
if (xcnt < 0 || xcnt > GetMaxSnapshotSubxidCount())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
snapshot.subxip = (TransactionId *) palloc(xcnt * sizeof(TransactionId));
for (i = 0; i < xcnt; i++)
snapshot.subxip[i] = parseXidFromText("sxp:", &filebuf, path);
}
else
{
snapshot.subxcnt = 0;
snapshot.subxip = NULL;
}
snapshot.takenDuringRecovery = parseIntFromText("rec:", &filebuf, path);
/*
* Do some additional sanity checking, just to protect ourselves. We
* don't trouble to check the array elements, just the most critical
* fields.
*/
if (!TransactionIdIsNormal(src_xid) ||
!OidIsValid(src_dbid) ||
!TransactionIdIsNormal(snapshot.xmin) ||
!TransactionIdIsNormal(snapshot.xmax))
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
/*
* If we're serializable, the source transaction must be too, otherwise
* predicate.c has problems (SxactGlobalXmin could go backwards). Also,
* a non-read-only transaction can't adopt a snapshot from a read-only
* transaction, as predicate.c handles the cases very differently.
*/
if (IsolationIsSerializable())
{
if (src_isolevel != XACT_SERIALIZABLE)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a serializable transaction cannot import a snapshot from a non-serializable transaction")));
if (src_readonly && !XactReadOnly)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a non-read-only serializable transaction cannot import a snapshot from a read-only transaction")));
}
/*
* We cannot import a snapshot that was taken in a different database,
* because vacuum calculates OldestXmin on a per-database basis; so the
* source transaction's xmin doesn't protect us from data loss. This
* restriction could be removed if the source transaction were to mark
* its xmin as being globally applicable. But that would require some
* additional syntax, since that has to be known when the snapshot is
* initially taken. (See pgsql-hackers discussion of 2011-10-21.)
*/
if (src_dbid != MyDatabaseId)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot import a snapshot from a different database")));
/* OK, install the snapshot */
SetTransactionSnapshot(&snapshot, src_xid);
}
/*
* SetTransactionSnapshot
* Set the transaction's snapshot from an imported MVCC snapshot.
*
* Note that this is very closely tied to GetTransactionSnapshot --- it
* must take care of all the same considerations as the first-snapshot case
* in GetTransactionSnapshot.
*/
static void
SetTransactionSnapshot(Snapshot sourcesnap, TransactionId sourcexid)
{
/* Caller should have checked this already */
Assert(!FirstSnapshotSet);
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* Even though we are not going to use the snapshot it computes, we must
* call GetSnapshotData, for two reasons: (1) to be sure that
* CurrentSnapshotData's XID arrays have been allocated, and (2) to update
* RecentXmin and RecentGlobalXmin. (We could alternatively include those
* two variables in exported snapshot files, but it seems better to have
* snapshot importers compute reasonably up-to-date values for them.)
*/
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/*
* Now copy appropriate fields from the source snapshot.
*/
CurrentSnapshot->xmin = sourcesnap->xmin;
CurrentSnapshot->xmax = sourcesnap->xmax;
CurrentSnapshot->xcnt = sourcesnap->xcnt;
Assert(sourcesnap->xcnt <= GetMaxSnapshotXidCount());
memcpy(CurrentSnapshot->xip, sourcesnap->xip,
sourcesnap->xcnt * sizeof(TransactionId));
CurrentSnapshot->subxcnt = sourcesnap->subxcnt;
Assert(sourcesnap->subxcnt <= GetMaxSnapshotSubxidCount());
memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
sourcesnap->subxcnt * sizeof(TransactionId));
CurrentSnapshot->suboverflowed = sourcesnap->suboverflowed;
CurrentSnapshot->takenDuringRecovery = sourcesnap->takenDuringRecovery;
/* NB: curcid should NOT be copied, it's a local matter */
/*
* Now we have to fix what GetSnapshotData did with MyProc->xmin and
* TransactionXmin. There is a race condition: to make sure we are not
* causing the global xmin to go backwards, we have to test that the
* source transaction is still running, and that has to be done atomically.
* So let procarray.c do it.
*
* Note: in serializable mode, predicate.c will do this a second time.
* It doesn't seem worth contorting the logic here to avoid two calls,
* especially since it's not clear that predicate.c *must* do this.
*/
if (!ProcArrayInstallImportedXmin(CurrentSnapshot->xmin, sourcexid))
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("could not import the requested snapshot"),
errdetail("The source transaction %u is not running anymore.",
sourcexid)));
/*
* In transaction-snapshot mode, the first snapshot must live until end of
* xact, so we must make a copy of it. Furthermore, if we're running in
* serializable mode, predicate.c needs to do its own processing.
*/
if (IsolationUsesXactSnapshot())
{
if (IsolationIsSerializable())
SetSerializableTransactionSnapshot(CurrentSnapshot, sourcexid);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
FirstSnapshotSet = true;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/*
* Return historic snapshot if doing logical decoding. We'll never need a
* non-historic transaction snapshot in this (sub-)transaction, so there's
* no need to be careful to set one up for later calls to
* GetTransactionSnapshot().
*/
if (HistoricSnapshotActive())
{
Assert(!FirstSnapshotSet);
return HistoricSnapshot;
}
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(pairingheap_is_empty(&RegisteredSnapshots));
Assert(FirstXactSnapshot == NULL);
if (IsInParallelMode())
elog(ERROR,
"cannot take query snapshot during a parallel operation");
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
pairingheap_add(&RegisteredSnapshots, &FirstXactSnapshot->ph_node);
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
{
#ifdef PGXC
/*
* Consider this test case taken from portals.sql
*
* CREATE TABLE cursor (a int, b int) distribute by replication;
* INSERT INTO cursor VALUES (10);
* BEGIN;
* SET TRANSACTION ISOLATION LEVEL SERIALIZABLE;
* DECLARE c1 NO SCROLL CURSOR FOR SELECT * FROM cursor FOR UPDATE;
* INSERT INTO cursor VALUES (2);
* FETCH ALL FROM c1;
* would result in
* ERROR: attempted to lock invisible tuple
* because FETCH would be sent as a select to the remote nodes
* with command id 0, whereas the command id would be 2
* in the current snapshot.
* (1 sent by Coordinator due to declare cursor &
* 2 because of the insert inside the transaction)
* The command id should therefore be updated in the
* current snapshot.
*/
if (IsConnFromCoord())
SnapshotSetCommandId(GetCurrentCommandId(false));
#endif
return CurrentSnapshot;
}
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/* ----------------
* index_getnext - get the next heap tuple from a scan
*
* The result is the next heap tuple satisfying the scan keys and the
* snapshot, or NULL if no more matching tuples exist. On success,
* the buffer containing the heap tuple is pinned (the pin will be dropped
* at the next index_getnext or index_endscan).
*
* Note: caller must check scan->xs_recheck, and perform rechecking of the
* scan keys if required. We do not do that here because we don't have
* enough information to do it efficiently in the general case.
* ----------------
*/
HeapTuple
index_getnext(IndexScanDesc scan, ScanDirection direction)
{
HeapTuple heapTuple = &scan->xs_ctup;
ItemPointer tid = &heapTuple->t_self;
FmgrInfo *procedure;
SCAN_CHECKS;
GET_SCAN_PROCEDURE(amgettuple);
Assert(TransactionIdIsValid(RecentGlobalXmin));
/*
* We always reset xs_hot_dead; if we are here then either we are just
* starting the scan, or we previously returned a visible tuple, and in
* either case it's inappropriate to kill the prior index entry.
*/
scan->xs_hot_dead = false;
for (;;)
{
OffsetNumber offnum;
bool at_chain_start;
Page dp;
if (scan->xs_next_hot != InvalidOffsetNumber)
{
/*
* We are resuming scan of a HOT chain after having returned an
* earlier member. Must still hold pin on current heap page.
*/
Assert(BufferIsValid(scan->xs_cbuf));
Assert(ItemPointerGetBlockNumber(tid) ==
BufferGetBlockNumber(scan->xs_cbuf));
Assert(TransactionIdIsValid(scan->xs_prev_xmax));
offnum = scan->xs_next_hot;
at_chain_start = false;
scan->xs_next_hot = InvalidOffsetNumber;
}
else
{
bool found;
Buffer prev_buf;
/*
* If we scanned a whole HOT chain and found only dead tuples,
* tell index AM to kill its entry for that TID. We do not do this
* when in recovery because it may violate MVCC to do so. see
* comments in RelationGetIndexScan().
*/
if (!scan->xactStartedInRecovery)
scan->kill_prior_tuple = scan->xs_hot_dead;
/*
* The AM's gettuple proc finds the next index entry matching the
* scan keys, and puts the TID in xs_ctup.t_self (ie, *tid). It
* should also set scan->xs_recheck, though we pay no attention to
* that here.
*/
found = DatumGetBool(FunctionCall2(procedure,
PointerGetDatum(scan),
Int32GetDatum(direction)));
/* Reset kill flag immediately for safety */
scan->kill_prior_tuple = false;
/* If we're out of index entries, break out of outer loop */
if (!found)
break;
pgstat_count_index_tuples(scan->indexRelation, 1);
/* Switch to correct buffer if we don't have it already */
prev_buf = scan->xs_cbuf;
scan->xs_cbuf = ReleaseAndReadBuffer(scan->xs_cbuf,
scan->heapRelation,
ItemPointerGetBlockNumber(tid));
/*
* Prune page, but only if we weren't already on this page
*/
if (prev_buf != scan->xs_cbuf)
heap_page_prune_opt(scan->heapRelation, scan->xs_cbuf,
RecentGlobalXmin);
/* Prepare to scan HOT chain starting at index-referenced offnum */
offnum = ItemPointerGetOffsetNumber(tid);
at_chain_start = true;
/* We don't know what the first tuple's xmin should be */
scan->xs_prev_xmax = InvalidTransactionId;
/* Initialize flag to detect if all entries are dead */
scan->xs_hot_dead = true;
}
/* Obtain share-lock on the buffer so we can examine visibility */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
dp = (Page) BufferGetPage(scan->xs_cbuf);
/* Scan through possible multiple members of HOT-chain */
for (;;)
{
ItemId lp;
ItemPointer ctid;
bool valid;
/* 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;
}
/*
* We must initialize all of *heapTuple (ie, scan->xs_ctup) since
* it is returned to the executor on success.
*/
heapTuple->t_data = (HeapTupleHeader) PageGetItem(dp, lp);
heapTuple->t_len = ItemIdGetLength(lp);
ItemPointerSetOffsetNumber(tid, offnum);
heapTuple->t_tableOid = RelationGetRelid(scan->heapRelation);
ctid = &heapTuple->t_data->t_ctid;
/*
* Shouldn't see a HEAP_ONLY tuple at chain start. (This test
* should be unnecessary, since the chain root can't be removed
* while we have pin on the index entry, but let's make it
* anyway.)
*/
if (at_chain_start && HeapTupleIsHeapOnly(heapTuple))
break;
/*
* The xmin should match the previous xmax value, else chain is
* broken. (Note: this test is not optional because it protects
* us against the case where the prior chain member's xmax aborted
* since we looked at it.)
*/
if (TransactionIdIsValid(scan->xs_prev_xmax) &&
!TransactionIdEquals(scan->xs_prev_xmax,
HeapTupleHeaderGetXmin(heapTuple->t_data)))
break;
/* If it's visible per the snapshot, we must return it */
valid = HeapTupleSatisfiesVisibility(heapTuple, scan->xs_snapshot,
scan->xs_cbuf);
CheckForSerializableConflictOut(valid, scan->heapRelation,
heapTuple, scan->xs_cbuf);
if (valid)
{
/*
* If the snapshot is MVCC, we know that it could accept at
* most one member of the HOT chain, so we can skip examining
* any more members. Otherwise, check for continuation of the
* HOT-chain, and set state for next time.
*/
if (IsMVCCSnapshot(scan->xs_snapshot)
&& !IsolationIsSerializable())
scan->xs_next_hot = InvalidOffsetNumber;
else if (HeapTupleIsHotUpdated(heapTuple))
{
Assert(ItemPointerGetBlockNumber(ctid) ==
ItemPointerGetBlockNumber(tid));
scan->xs_next_hot = ItemPointerGetOffsetNumber(ctid);
scan->xs_prev_xmax = HeapTupleHeaderGetXmax(heapTuple->t_data);
}
else
scan->xs_next_hot = InvalidOffsetNumber;
PredicateLockTuple(scan->heapRelation, heapTuple);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
pgstat_count_heap_fetch(scan->indexRelation);
return heapTuple;
}
/*
* If we can't see it, maybe no one else can either. Check to see
* if the tuple is dead to all transactions. If we find that all
* the tuples in the HOT chain are dead, we'll signal the index AM
* to not return that TID on future indexscans.
*/
if (scan->xs_hot_dead &&
HeapTupleSatisfiesVacuum(heapTuple->t_data, RecentGlobalXmin,
scan->xs_cbuf) != HEAPTUPLE_DEAD)
scan->xs_hot_dead = false;
/*
* Check to see if HOT chain continues past this tuple; if so
* fetch the next offnum (we don't bother storing it into
* xs_next_hot, but must store xs_prev_xmax), and loop around.
*/
if (HeapTupleIsHotUpdated(heapTuple))
{
Assert(ItemPointerGetBlockNumber(ctid) ==
ItemPointerGetBlockNumber(tid));
offnum = ItemPointerGetOffsetNumber(ctid);
at_chain_start = false;
scan->xs_prev_xmax = HeapTupleHeaderGetXmax(heapTuple->t_data);
}
else
break; /* end of chain */
} /* loop over a single HOT chain */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
/* Loop around to ask index AM for another TID */
scan->xs_next_hot = InvalidOffsetNumber;
}
/* Release any held pin on a heap page */
if (BufferIsValid(scan->xs_cbuf))
{
ReleaseBuffer(scan->xs_cbuf);
scan->xs_cbuf = InvalidBuffer;
}
return NULL; /* failure exit */
}