/*
* This function performs checks for certain system tables to validate tuple
* fetched from table has the key, using which it was fetched from index.
*/
static void
CrossCheckTuple(int cacheId,
Datum key1,
Datum key2,
Datum key3,
Datum key4,
HeapTuple tuple)
{
Form_pg_class rd_rel;
switch (cacheId)
{
case RELOID:
if (HeapTupleGetOid(tuple) != DatumGetObjectId(key1))
{
elog(ERROR, "pg_class_oid_index is broken, oid=%d is pointing to tuple with oid=%d (xmin:%u xmax:%u)",
DatumGetObjectId(key1), HeapTupleGetOid(tuple),
HeapTupleHeaderGetXmin((tuple)->t_data),
HeapTupleHeaderGetXmax((tuple)->t_data));
}
break;
case RELNAMENSP:
rd_rel = (Form_pg_class) GETSTRUCT(tuple);
if (strncmp(rd_rel->relname.data, DatumGetCString(key1), NAMEDATALEN) != 0)
{
elog(ERROR, "pg_class_relname_nsp_index is broken, intended tuple with name \"%s\" fetched \"%s\""
" (xmin:%u xmax:%u)",
DatumGetCString(key1), rd_rel->relname.data,
HeapTupleHeaderGetXmin((tuple)->t_data),
HeapTupleHeaderGetXmax((tuple)->t_data));
}
break;
case TYPEOID:
if (HeapTupleGetOid(tuple) != DatumGetObjectId(key1))
{
elog(ERROR, "pg_type_oid_index is broken, oid=%d is pointing to tuple with oid=%d (xmin:%u xmax:%u)",
DatumGetObjectId(key1), HeapTupleGetOid(tuple),
HeapTupleHeaderGetXmin((tuple)->t_data),
HeapTupleHeaderGetXmax((tuple)->t_data));
}
break;
}
}
/* ----------------
* heap_getsysattr
*
* Fetch the value of a system attribute for a tuple.
*
* This is a support routine for the heap_getattr macro. The macro
* has already determined that the attnum refers to a system attribute.
* ----------------
*/
Datum
heap_getsysattr(HeapTuple tup, int attnum, bool *isnull)
{
Datum result;
Assert(tup);
Assert(!is_heaptuple_memtuple(tup));
/* Currently, no sys attribute ever reads as NULL. */
if (isnull)
*isnull = false;
switch (attnum)
{
case SelfItemPointerAttributeNumber:
/* pass-by-reference datatype */
result = PointerGetDatum(&(tup->t_self));
break;
case ObjectIdAttributeNumber:
result = ObjectIdGetDatum(HeapTupleGetOid(tup));
break;
case MinTransactionIdAttributeNumber:
result = TransactionIdGetDatum(HeapTupleHeaderGetXmin(tup->t_data));
break;
case MaxTransactionIdAttributeNumber:
result = TransactionIdGetDatum(HeapTupleHeaderGetXmax(tup->t_data));
break;
case MinCommandIdAttributeNumber:
case MaxCommandIdAttributeNumber:
/*
* cmin and cmax are now both aliases for the same field, which
* can in fact also be a combo command id. XXX perhaps we should
* return the "real" cmin or cmax if possible, that is if we are
* inside the originating transaction?
*/
result = CommandIdGetDatum(HeapTupleHeaderGetRawCommandId(tup->t_data));
break;
case TableOidAttributeNumber:
/* CDB: Must now use a TupleTableSlot to access the 'tableoid'. */
result = ObjectIdGetDatum(InvalidOid);
elog(ERROR, "Invalid reference to \"tableoid\" system attribute");
break;
case GpSegmentIdAttributeNumber: /*CDB*/
result = Int32GetDatum(Gp_segment);
break;
default:
elog(ERROR, "invalid attnum: %d", attnum);
result = 0; /* keep compiler quiet */
break;
}
return result;
}
CommandId
HeapTupleHeaderGetCmax(HeapTupleHeader tup)
{
CommandId cid = HeapTupleHeaderGetRawCommandId(tup);
/* We do not store cmax when locking a tuple */
Assert(!(tup->t_infomask & (HEAP_MOVED | HEAP_IS_LOCKED)));
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tup)));
if (tup->t_infomask & HEAP_COMBOCID)
return GetRealCmax(cid);
else
return cid;
}
CommandId
HeapTupleHeaderGetCmax(HeapTupleHeader tup)
{
CommandId cid = HeapTupleHeaderGetRawCommandId(tup);
/* We do not store cmax when locking a tuple */
Assert(!(tup->t_infomask & (HEAP_MOVED | HEAP_IS_LOCKED)));
/*
* MPP-8317: cursors can't always *tell* that this is the current transaction.
*/
Assert(QEDtxContextInfo.cursorContext || TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tup)));
if (tup->t_infomask & HEAP_COMBOCID)
return GetRealCmax(HeapTupleHeaderGetXmin(tup), cid);
else
return cid;
}
/*
* HeapTupleSatisfiesSnapshot
* True iff heap tuple is valid for the given snapshot.
*
* Here, we consider the effects of:
* all transactions committed as of the time of the given snapshot
* previous commands of this transaction
*
* Does _not_ include:
* transactions shown as in-progress by the snapshot
* transactions started after the snapshot was taken
* changes made by the current command
*
* This is the same as HeapTupleSatisfiesNow, except that transactions that
* were in progress or as yet unstarted when the snapshot was taken will
* be treated as uncommitted, even if they have committed by now.
*
* (Notice, however, that the tuple status hint bits will be updated on the
* basis of the true state of the transaction, even if we then pretend we
* can't see it.)
*/
bool
HeapTupleSatisfiesSnapshot(HeapTupleHeader tuple, Snapshot snapshot)
{
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return false;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return false;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return false;
if (TransactionIdDidCommit(xvac))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (HeapTupleHeaderGetCmin(tuple) >= snapshot->curcid)
return false; /* inserted after scan started */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return true;
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
if (HeapTupleHeaderGetCmax(tuple) >= snapshot->curcid)
return true; /* deleted after scan started */
else
return false; /* deleted before scan started */
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
return false;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
/*
* By here, the inserting transaction has committed - have to check
* when...
*/
if (TransactionIdFollowsOrEquals(HeapTupleHeaderGetXmin(tuple),
snapshot->xmin))
{
uint32 i;
if (TransactionIdFollowsOrEquals(HeapTupleHeaderGetXmin(tuple),
snapshot->xmax))
return false;
for (i = 0; i < snapshot->xcnt; i++)
{
if (TransactionIdEquals(HeapTupleHeaderGetXmin(tuple),
snapshot->xip[i]))
return false;
}
}
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return true;
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (HeapTupleHeaderGetCmax(tuple) >= snapshot->curcid)
return true; /* deleted after scan started */
else
return false; /* deleted before scan started */
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return true;
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMAX_INVALID;
return true;
}
/* xmax transaction committed */
tuple->t_infomask |= HEAP_XMAX_COMMITTED;
}
/*
* OK, the deleting transaction committed too ... but when?
*/
if (TransactionIdFollowsOrEquals(HeapTupleHeaderGetXmax(tuple), snapshot->xmin))
{
uint32 i;
if (TransactionIdFollowsOrEquals(HeapTupleHeaderGetXmax(tuple),
snapshot->xmax))
return true;
for (i = 0; i < snapshot->xcnt; i++)
{
if (TransactionIdEquals(HeapTupleHeaderGetXmax(tuple), snapshot->xip[i]))
return true;
}
}
return false;
}
/*
* HeapTupleSatisfiesDirty
* True iff heap tuple is valid including effects of open transactions.
*
* Here, we consider the effects of:
* all committed and in-progress transactions (as of the current instant)
* previous commands of this transaction
* changes made by the current command
*
* This is essentially like HeapTupleSatisfiesSelf as far as effects of
* the current transaction and committed/aborted xacts are concerned.
* However, we also include the effects of other xacts still in progress.
*
* A special hack is that the passed-in snapshot struct is used as an
* output argument to return the xids of concurrent xacts that affected the
* tuple. snapshot->xmin is set to the tuple's xmin if that is another
* transaction that's still in progress; or to InvalidTransactionId if the
* tuple's xmin is committed good, committed dead, or my own xact. Similarly
* for snapshot->xmax and the tuple's xmax.
*/
bool
HeapTupleSatisfiesDirty(HeapTupleHeader tuple, Snapshot snapshot,
Buffer buffer)
{
snapshot->xmin = snapshot->xmax = InvalidTransactionId;
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return false;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return false;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return false;
if (TransactionIdDidCommit(xvac))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
else
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return true;
if (tuple->t_infomask & HEAP_IS_LOCKED) /* not deleter */
return true;
Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
if (!TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
/* deleting subtransaction must have aborted */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return true;
}
return false;
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
{
snapshot->xmin = HeapTupleHeaderGetXmin(tuple);
/* XXX shouldn't we fall through to look at xmax? */
return true; /* in insertion by other */
}
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
HeapTupleHeaderGetXmin(tuple));
else
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
}
/* by here, the inserting transaction has committed */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return true;
if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
{
if (tuple->t_infomask & HEAP_IS_LOCKED)
return true;
return false; /* updated by other */
}
if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
{
/* MultiXacts are currently only allowed to lock tuples */
Assert(tuple->t_infomask & HEAP_IS_LOCKED);
return true;
}
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (tuple->t_infomask & HEAP_IS_LOCKED)
return true;
return false;
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
{
snapshot->xmax = HeapTupleHeaderGetXmax(tuple);
return true;
}
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return true;
}
/* xmax transaction committed */
if (tuple->t_infomask & HEAP_IS_LOCKED)
{
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return true;
}
SetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
HeapTupleHeaderGetXmax(tuple));
return false; /* updated by other */
}
/*
* HeapTupleSatisfiesMVCC
* True iff heap tuple is valid for the given MVCC snapshot.
*
* Here, we consider the effects of:
* all transactions committed as of the time of the given snapshot
* previous commands of this transaction
*
* Does _not_ include:
* transactions shown as in-progress by the snapshot
* transactions started after the snapshot was taken
* changes made by the current command
*
* This is the same as HeapTupleSatisfiesNow, except that transactions that
* were in progress or as yet unstarted when the snapshot was taken will
* be treated as uncommitted, even if they have committed by now.
*
* (Notice, however, that the tuple status hint bits will be updated on the
* basis of the true state of the transaction, even if we then pretend we
* can't see it.)
*/
bool
HeapTupleSatisfiesMVCC(HeapTupleHeader tuple, Snapshot snapshot,
Buffer buffer)
{
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return false;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return false;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return false;
if (TransactionIdDidCommit(xvac))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
else
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (HeapTupleHeaderGetCmin(tuple) >= snapshot->curcid)
return false; /* inserted after scan started */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return true;
if (tuple->t_infomask & HEAP_IS_LOCKED) /* not deleter */
return true;
Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
if (!TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
/* deleting subtransaction must have aborted */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return true;
}
if (HeapTupleHeaderGetCmax(tuple) >= snapshot->curcid)
return true; /* deleted after scan started */
else
return false; /* deleted before scan started */
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
return false;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
HeapTupleHeaderGetXmin(tuple));
else
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return false;
}
}
/*
* By here, the inserting transaction has committed - have to check
* when...
*/
if (XidInMVCCSnapshot(HeapTupleHeaderGetXmin(tuple), snapshot))
return false; /* treat as still in progress */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return true;
if (tuple->t_infomask & HEAP_IS_LOCKED)
return true;
if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
{
/* MultiXacts are currently only allowed to lock tuples */
Assert(tuple->t_infomask & HEAP_IS_LOCKED);
return true;
}
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (HeapTupleHeaderGetCmax(tuple) >= snapshot->curcid)
return true; /* deleted after scan started */
else
return false; /* deleted before scan started */
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return true;
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return true;
}
/* xmax transaction committed */
SetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
HeapTupleHeaderGetXmax(tuple));
}
/*
* OK, the deleting transaction committed too ... but when?
*/
if (XidInMVCCSnapshot(HeapTupleHeaderGetXmax(tuple), snapshot))
return true; /* treat as still in progress */
return false;
}
/*
* HeapTupleSatisfiesVacuum
*
* Determine the status of tuples for VACUUM purposes. Here, what
* we mainly want to know is if a tuple is potentially visible to *any*
* running transaction. If so, it can't be removed yet by VACUUM.
*
* OldestXmin is a cutoff XID (obtained from GetOldestXmin()). Tuples
* deleted by XIDs >= OldestXmin are deemed "recently dead"; they might
* still be visible to some open transaction, so we can't remove them,
* even if we see that the deleting transaction has committed.
*/
HTSV_Result
HeapTupleSatisfiesVacuum(HeapTupleHeader tuple, TransactionId OldestXmin,
Buffer buffer)
{
/*
* Has inserting transaction committed?
*
* If the inserting transaction aborted, then the tuple was never visible
* to any other transaction, so we can delete it immediately.
*/
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return HEAPTUPLE_DEAD;
else if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HEAPTUPLE_DELETE_IN_PROGRESS;
if (TransactionIdIsInProgress(xvac))
return HEAPTUPLE_DELETE_IN_PROGRESS;
if (TransactionIdDidCommit(xvac))
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HEAPTUPLE_DEAD;
}
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HEAPTUPLE_INSERT_IN_PROGRESS;
if (TransactionIdIsInProgress(xvac))
return HEAPTUPLE_INSERT_IN_PROGRESS;
if (TransactionIdDidCommit(xvac))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
else
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HEAPTUPLE_DEAD;
}
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
{
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return HEAPTUPLE_INSERT_IN_PROGRESS;
if (tuple->t_infomask & HEAP_IS_LOCKED)
return HEAPTUPLE_INSERT_IN_PROGRESS;
/* inserted and then deleted by same xact */
return HEAPTUPLE_DELETE_IN_PROGRESS;
}
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
HeapTupleHeaderGetXmin(tuple));
else
{
/*
* Not in Progress, Not Committed, so either Aborted or crashed
*/
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HEAPTUPLE_DEAD;
}
/*
* At this point the xmin is known committed, but we might not have
* been able to set the hint bit yet; so we can no longer Assert that
* it's set.
*/
}
/*
* Okay, the inserter committed, so it was good at some point. Now what
* about the deleting transaction?
*/
if (tuple->t_infomask & HEAP_XMAX_INVALID)
return HEAPTUPLE_LIVE;
if (tuple->t_infomask & HEAP_IS_LOCKED)
{
/*
* "Deleting" xact really only locked it, so the tuple is live in any
* case. However, we should make sure that either XMAX_COMMITTED or
* XMAX_INVALID gets set once the xact is gone, to reduce the costs of
* examining the tuple for future xacts. Also, marking dead
* MultiXacts as invalid here provides defense against MultiXactId
* wraparound (see also comments in heap_freeze_tuple()).
*/
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
{
if (MultiXactIdIsRunning(HeapTupleHeaderGetXmax(tuple)))
return HEAPTUPLE_LIVE;
}
else
{
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HEAPTUPLE_LIVE;
}
/*
* We don't really care whether xmax did commit, abort or crash.
* We know that xmax did lock the tuple, but it did not and will
* never actually update it.
*/
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
}
return HEAPTUPLE_LIVE;
}
if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
{
/* MultiXacts are currently only allowed to lock tuples */
Assert(tuple->t_infomask & HEAP_IS_LOCKED);
return HEAPTUPLE_LIVE;
}
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HEAPTUPLE_DELETE_IN_PROGRESS;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
SetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
HeapTupleHeaderGetXmax(tuple));
else
{
/*
* Not in Progress, Not Committed, so either Aborted or crashed
*/
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return HEAPTUPLE_LIVE;
}
/*
* At this point the xmax is known committed, but we might not have
* been able to set the hint bit yet; so we can no longer Assert that
* it's set.
*/
}
/*
* Deleter committed, but check special cases.
*/
if (TransactionIdEquals(HeapTupleHeaderGetXmin(tuple),
HeapTupleHeaderGetXmax(tuple)))
{
/*
* Inserter also deleted it, so it was never visible to anyone else.
* However, we can only remove it early if it's not an updated tuple;
* else its parent tuple is linking to it via t_ctid, and this tuple
* mustn't go away before the parent does.
*/
if (!(tuple->t_infomask & HEAP_UPDATED))
return HEAPTUPLE_DEAD;
}
if (!TransactionIdPrecedes(HeapTupleHeaderGetXmax(tuple), OldestXmin))
{
/* deleting xact is too recent, tuple could still be visible */
return HEAPTUPLE_RECENTLY_DEAD;
}
/* Otherwise, it's dead and removable */
return HEAPTUPLE_DEAD;
}
/*
* HeapTupleSatisfiesUpdate
*
* Same logic as HeapTupleSatisfiesNow, but returns a more detailed result
* code, since UPDATE needs to know more than "is it visible?". Also,
* tuples of my own xact are tested against the passed CommandId not
* CurrentCommandId.
*
* The possible return codes are:
*
* HeapTupleInvisible: the tuple didn't exist at all when the scan started,
* e.g. it was created by a later CommandId.
*
* HeapTupleMayBeUpdated: The tuple is valid and visible, so it may be
* updated.
*
* HeapTupleSelfUpdated: The tuple was updated by the current transaction,
* after the current scan started.
*
* HeapTupleUpdated: The tuple was updated by a committed transaction.
*
* HeapTupleBeingUpdated: The tuple is being updated by an in-progress
* transaction other than the current transaction. (Note: this includes
* the case where the tuple is share-locked by a MultiXact, even if the
* MultiXact includes the current transaction. Callers that want to
* distinguish that case must test for it themselves.)
*/
HTSU_Result
HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
Buffer buffer)
{
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return HeapTupleInvisible;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HeapTupleInvisible;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HeapTupleInvisible;
}
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return HeapTupleInvisible;
if (TransactionIdDidCommit(xvac))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
InvalidTransactionId);
else
{
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HeapTupleInvisible;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (HeapTupleHeaderGetCmin(tuple) >= curcid)
return HeapTupleInvisible; /* inserted after scan started */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return HeapTupleMayBeUpdated;
if (tuple->t_infomask & HEAP_IS_LOCKED) /* not deleter */
return HeapTupleMayBeUpdated;
Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
if (!TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
/* deleting subtransaction must have aborted */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return HeapTupleMayBeUpdated;
}
if (HeapTupleHeaderGetCmax(tuple) >= curcid)
return HeapTupleSelfUpdated; /* updated after scan started */
else
return HeapTupleInvisible; /* updated before scan started */
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
return HeapTupleInvisible;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
SetHintBits(tuple, buffer, HEAP_XMIN_COMMITTED,
HeapTupleHeaderGetXmin(tuple));
else
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMIN_INVALID,
InvalidTransactionId);
return HeapTupleInvisible;
}
}
/* by here, the inserting transaction has committed */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return HeapTupleMayBeUpdated;
if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
{
if (tuple->t_infomask & HEAP_IS_LOCKED)
return HeapTupleMayBeUpdated;
return HeapTupleUpdated; /* updated by other */
}
if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
{
/* MultiXacts are currently only allowed to lock tuples */
Assert(tuple->t_infomask & HEAP_IS_LOCKED);
if (MultiXactIdIsRunning(HeapTupleHeaderGetXmax(tuple)))
return HeapTupleBeingUpdated;
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return HeapTupleMayBeUpdated;
}
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (tuple->t_infomask & HEAP_IS_LOCKED)
return HeapTupleMayBeUpdated;
if (HeapTupleHeaderGetCmax(tuple) >= curcid)
return HeapTupleSelfUpdated; /* updated after scan started */
else
return HeapTupleInvisible; /* updated before scan started */
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HeapTupleBeingUpdated;
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return HeapTupleMayBeUpdated;
}
/* xmax transaction committed */
if (tuple->t_infomask & HEAP_IS_LOCKED)
{
SetHintBits(tuple, buffer, HEAP_XMAX_INVALID,
InvalidTransactionId);
return HeapTupleMayBeUpdated;
}
SetHintBits(tuple, buffer, HEAP_XMAX_COMMITTED,
HeapTupleHeaderGetXmax(tuple));
return HeapTupleUpdated; /* updated by other */
}
/*
* Prune specified item pointer or a HOT chain originating at that item.
*
* If the item is an index-referenced tuple (i.e. not a heap-only tuple),
* the HOT chain is pruned by removing all DEAD tuples at the start of the HOT
* chain. We also prune any RECENTLY_DEAD tuples preceding a DEAD tuple.
* This is OK because a RECENTLY_DEAD tuple preceding a DEAD tuple is really
* DEAD, the OldestXmin test is just too coarse to detect it.
*
* The root line pointer is redirected to the tuple immediately after the
* latest DEAD tuple. If all tuples in the chain are DEAD, the root line
* pointer is marked LP_DEAD. (This includes the case of a DEAD simple
* tuple, which we treat as a chain of length 1.)
*
* OldestXmin is the cutoff XID used to identify dead tuples.
*
* We don't actually change the page here, except perhaps for hint-bit updates
* caused by HeapTupleSatisfiesVacuum. We just add entries to the arrays in
* prstate showing the changes to be made. Items to be redirected are added
* to the redirected[] array (two entries per redirection); items to be set to
* LP_DEAD state are added to nowdead[]; and items to be set to LP_UNUSED
* state are added to nowunused[].
*
* If redirect_move is true, we intend to get rid of redirecting line pointers,
* not just make redirection entries.
*
* Returns the number of tuples (to be) deleted from the page.
*/
static int
heap_prune_chain(Relation relation, Buffer buffer, OffsetNumber rootoffnum,
TransactionId OldestXmin,
PruneState *prstate,
bool redirect_move)
{
int ndeleted = 0;
Page dp = (Page) BufferGetPage(buffer);
TransactionId priorXmax = InvalidTransactionId;
ItemId rootlp;
HeapTupleHeader htup;
OffsetNumber latestdead = InvalidOffsetNumber,
redirect_target = InvalidOffsetNumber,
maxoff = PageGetMaxOffsetNumber(dp),
offnum;
OffsetNumber chainitems[MaxHeapTuplesPerPage];
int nchain = 0,
i;
rootlp = PageGetItemId(dp, rootoffnum);
/*
* If it's a heap-only tuple, then it is not the start of a HOT chain.
*/
if (ItemIdIsNormal(rootlp))
{
htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
if (HeapTupleHeaderIsHeapOnly(htup))
{
/*
* If the tuple is DEAD and doesn't chain to anything else, mark
* it unused immediately. (If it does chain, we can only remove
* it as part of pruning its chain.)
*
* We need this primarily to handle aborted HOT updates, that is,
* XMIN_INVALID heap-only tuples. Those might not be linked to by
* any chain, since the parent tuple might be re-updated before
* any pruning occurs. So we have to be able to reap them
* separately from chain-pruning. (Note that
* HeapTupleHeaderIsHotUpdated will never return true for an
* XMIN_INVALID tuple, so this code will work even when there were
* sequential updates within the aborted transaction.)
*
* Note that we might first arrive at a dead heap-only tuple
* either here or while following a chain below. Whichever path
* gets there first will mark the tuple unused.
*/
if (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer)
== HEAPTUPLE_DEAD && !HeapTupleHeaderIsHotUpdated(htup))
{
heap_prune_record_unused(prstate, rootoffnum);
ndeleted++;
}
/* Nothing more to do */
return ndeleted;
}
}
/* Start from the root tuple */
offnum = rootoffnum;
/* while not end of the chain */
for (;;)
{
ItemId lp;
bool tupdead,
recent_dead;
/* Some sanity checks */
if (offnum < FirstOffsetNumber || offnum > maxoff)
break;
/* If item is already processed, stop --- it must not be same chain */
if (prstate->marked[offnum])
break;
lp = PageGetItemId(dp, offnum);
/* Unused item obviously isn't part of the chain */
if (!ItemIdIsUsed(lp))
break;
/*
* If we are looking at the redirected root line pointer, jump to the
* first normal tuple in the chain. If we find a redirect somewhere
* else, stop --- it must not be same chain.
*/
if (ItemIdIsRedirected(lp))
{
if (nchain > 0)
break; /* not at start of chain */
chainitems[nchain++] = offnum;
offnum = ItemIdGetRedirect(rootlp);
continue;
}
/*
* Likewise, a dead item pointer can't be part of the chain. (We
* already eliminated the case of dead root tuple outside this
* function.)
*/
if (ItemIdIsDead(lp))
break;
Assert(ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(dp, lp);
/*
* Check the tuple XMIN against prior XMAX, if any
*/
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
/*
* OK, this tuple is indeed a member of the chain.
*/
chainitems[nchain++] = offnum;
/*
* Check tuple's visibility status.
*/
tupdead = recent_dead = false;
switch (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer))
{
case HEAPTUPLE_DEAD:
tupdead = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
recent_dead = true;
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* If we wanted to optimize for aborts, we might consider
* marking the page prunable when we see INSERT_IN_PROGRESS.
* But we don't. See related decisions about when to mark the
* page prunable in heapam.c.
*/
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
/*
* Remember the last DEAD tuple seen. We will advance past
* RECENTLY_DEAD tuples just in case there's a DEAD one after them;
* but we can't advance past anything else. (XXX is it really worth
* continuing to scan beyond RECENTLY_DEAD? The case where we will
* find another DEAD tuple is a fairly unusual corner case.)
*/
if (tupdead)
latestdead = offnum;
else if (!recent_dead)
break;
/*
* If the tuple is not HOT-updated, then we are at the end of this
* HOT-update chain.
*/
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/*
* Advance to next chain member.
*/
Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetXmax(htup);
}
/*
* If we found a DEAD tuple in the chain, adjust the HOT chain so that all
* the DEAD tuples at the start of the chain are removed and the root line
* pointer is appropriately redirected.
*/
if (OffsetNumberIsValid(latestdead))
{
/*
* Mark as unused each intermediate item that we are able to remove
* from the chain.
*
* When the previous item is the last dead tuple seen, we are at the
* right candidate for redirection.
*/
for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
{
heap_prune_record_unused(prstate, chainitems[i]);
ndeleted++;
}
/*
* If the root entry had been a normal tuple, we are deleting it, so
* count it in the result. But changing a redirect (even to DEAD
* state) doesn't count.
*/
if (ItemIdIsNormal(rootlp))
ndeleted++;
/*
* If the DEAD tuple is at the end of the chain, the entire chain is
* dead and the root line pointer can be marked dead. Otherwise just
* redirect the root to the correct chain member.
*/
if (i >= nchain)
heap_prune_record_dead(prstate, rootoffnum);
else
{
heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
/* If the redirection will be a move, need more processing */
if (redirect_move)
redirect_target = chainitems[i];
}
}
else if (nchain < 2 && ItemIdIsRedirected(rootlp))
{
/*
* We found a redirect item that doesn't point to a valid follow-on
* item. This can happen if the loop in heap_page_prune caused us to
* visit the dead successor of a redirect item before visiting the
* redirect item. We can clean up by setting the redirect item to
* DEAD state.
*/
heap_prune_record_dead(prstate, rootoffnum);
}
else if (redirect_move && ItemIdIsRedirected(rootlp))
{
/*
* If we desire to eliminate LP_REDIRECT items by moving tuples, make
* a redirection entry for each redirected root item; this will cause
* heap_page_prune_execute to actually do the move. (We get here only
* when there are no DEAD tuples in the chain; otherwise the
* redirection entry was made above.)
*/
heap_prune_record_redirect(prstate, rootoffnum, chainitems[1]);
redirect_target = chainitems[1];
}
/*
* If we are going to implement a redirect by moving tuples, we have to
* issue a cache invalidation against the redirection target tuple,
* because its CTID will be effectively changed by the move. Note that
* CacheInvalidateHeapTuple only queues the request, it doesn't send it;
* if we fail before reaching EndNonTransactionalInvalidation, nothing
* happens and no harm is done.
*/
if (OffsetNumberIsValid(redirect_target))
{
ItemId firstlp = PageGetItemId(dp, redirect_target);
HeapTupleData firsttup;
Assert(ItemIdIsNormal(firstlp));
/* Set up firsttup to reference the tuple at its existing CTID */
firsttup.t_data = (HeapTupleHeader) PageGetItem(dp, firstlp);
firsttup.t_len = ItemIdGetLength(firstlp);
ItemPointerSet(&firsttup.t_self,
BufferGetBlockNumber(buffer),
redirect_target);
CacheInvalidateHeapTuple(relation, &firsttup);
}
return ndeleted;
}
/*
* For all items in this page, find their respective root line pointers.
* If item k is part of a HOT-chain with root at item j, then we set
* root_offsets[k - 1] = j.
*
* The passed-in root_offsets array must have MaxHeapTuplesPerPage entries.
* We zero out all unused entries.
*
* The function must be called with at least share lock on the buffer, to
* prevent concurrent prune operations.
*
* Note: The information collected here is valid only as long as the caller
* holds a pin on the buffer. Once pin is released, a tuple might be pruned
* and reused by a completely unrelated tuple.
*/
void
heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
{
OffsetNumber offnum,
maxoff;
MemSet(root_offsets, 0, MaxHeapTuplesPerPage * sizeof(OffsetNumber));
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
{
ItemId lp = PageGetItemId(page, offnum);
HeapTupleHeader htup;
OffsetNumber nextoffnum;
TransactionId priorXmax;
/* skip unused and dead items */
if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
continue;
if (ItemIdIsNormal(lp))
{
htup = (HeapTupleHeader) PageGetItem(page, lp);
/*
* Check if this tuple is part of a HOT-chain rooted at some other
* tuple. If so, skip it for now; we'll process it when we find
* its root.
*/
if (HeapTupleHeaderIsHeapOnly(htup))
continue;
/*
* This is either a plain tuple or the root of a HOT-chain.
* Remember it in the mapping.
*/
root_offsets[offnum - 1] = offnum;
/* If it's not the start of a HOT-chain, we're done with it */
if (!HeapTupleHeaderIsHotUpdated(htup))
continue;
/* Set up to scan the HOT-chain */
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetXmax(htup);
}
else
{
/* Must be a redirect item. We do not set its root_offsets entry */
Assert(ItemIdIsRedirected(lp));
/* Set up to scan the HOT-chain */
nextoffnum = ItemIdGetRedirect(lp);
priorXmax = InvalidTransactionId;
}
/*
* Now follow the HOT-chain and collect other tuples in the chain.
*
* Note: Even though this is a nested loop, the complexity of the
* function is O(N) because a tuple in the page should be visited not
* more than twice, once in the outer loop and once in HOT-chain
* chases.
*/
for (;;)
{
lp = PageGetItemId(page, nextoffnum);
/* Check for broken chains */
if (!ItemIdIsNormal(lp))
break;
htup = (HeapTupleHeader) PageGetItem(page, lp);
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
break;
/* Remember the root line pointer for this item */
root_offsets[nextoffnum - 1] = offnum;
/* Advance to next chain member, if any */
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetXmax(htup);
}
}
}
/*
* HeapTupleSatisfiesVacuum
*
* Determine the status of tuples for VACUUM purposes. Here, what
* we mainly want to know is if a tuple is potentially visible to *any*
* running transaction. If so, it can't be removed yet by VACUUM.
*
* OldestXmin is a cutoff XID (obtained from GetOldestXmin()). Tuples
* deleted by XIDs >= OldestXmin are deemed "recently dead"; they might
* still be visible to some open transaction, so we can't remove them,
* even if we see that the deleting transaction has committed.
*/
HTSV_Result
HeapTupleSatisfiesVacuum(HeapTupleHeader tuple, TransactionId OldestXmin)
{
/*
* Has inserting transaction committed?
*
* If the inserting transaction aborted, then the tuple was never visible
* to any other transaction, so we can delete it immediately.
*/
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return HEAPTUPLE_DEAD;
else if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HEAPTUPLE_DELETE_IN_PROGRESS;
if (TransactionIdIsInProgress(xvac))
return HEAPTUPLE_DELETE_IN_PROGRESS;
if (TransactionIdDidCommit(xvac))
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HEAPTUPLE_DEAD;
}
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HEAPTUPLE_INSERT_IN_PROGRESS;
if (TransactionIdIsInProgress(xvac))
return HEAPTUPLE_INSERT_IN_PROGRESS;
if (TransactionIdDidCommit(xvac))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HEAPTUPLE_DEAD;
}
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
{
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return HEAPTUPLE_INSERT_IN_PROGRESS;
Assert(HeapTupleHeaderGetXmin(tuple) ==
HeapTupleHeaderGetXmax(tuple));
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return HEAPTUPLE_INSERT_IN_PROGRESS;
/* inserted and then deleted by same xact */
return HEAPTUPLE_DELETE_IN_PROGRESS;
}
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
/*
* Not in Progress, Not Committed, so either Aborted or
* crashed
*/
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HEAPTUPLE_DEAD;
}
/* Should only get here if we set XMIN_COMMITTED */
Assert(tuple->t_infomask & HEAP_XMIN_COMMITTED);
}
/*
* Okay, the inserter committed, so it was good at some point. Now
* what about the deleting transaction?
*/
if (tuple->t_infomask & HEAP_XMAX_INVALID)
return HEAPTUPLE_LIVE;
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
{
/*
* "Deleting" xact really only marked it for update, so the tuple
* is live in any case. However, we must make sure that either
* XMAX_COMMITTED or XMAX_INVALID gets set once the xact is gone;
* otherwise it is unsafe to recycle CLOG status after vacuuming.
*/
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HEAPTUPLE_LIVE;
/*
* We don't really care whether xmax did commit, abort or
* crash. We know that xmax did mark the tuple for update, but
* it did not and will never actually update it.
*/
tuple->t_infomask |= HEAP_XMAX_INVALID;
}
return HEAPTUPLE_LIVE;
}
if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
{
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HEAPTUPLE_DELETE_IN_PROGRESS;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
tuple->t_infomask |= HEAP_XMAX_COMMITTED;
else
{
/*
* Not in Progress, Not Committed, so either Aborted or
* crashed
*/
tuple->t_infomask |= HEAP_XMAX_INVALID;
return HEAPTUPLE_LIVE;
}
/* Should only get here if we set XMAX_COMMITTED */
Assert(tuple->t_infomask & HEAP_XMAX_COMMITTED);
}
/*
* Deleter committed, but check special cases.
*/
if (TransactionIdEquals(HeapTupleHeaderGetXmin(tuple),
HeapTupleHeaderGetXmax(tuple)))
{
/*
* Inserter also deleted it, so it was never visible to anyone
* else. However, we can only remove it early if it's not an
* updated tuple; else its parent tuple is linking to it via t_ctid,
* and this tuple mustn't go away before the parent does.
*/
if (!(tuple->t_infomask & HEAP_UPDATED))
return HEAPTUPLE_DEAD;
}
if (!TransactionIdPrecedes(HeapTupleHeaderGetXmax(tuple), OldestXmin))
{
/* deleting xact is too recent, tuple could still be visible */
return HEAPTUPLE_RECENTLY_DEAD;
}
/* Otherwise, it's dead and removable */
return HEAPTUPLE_DEAD;
}
/*
* HeapTupleSatisfiesItself
* True iff heap tuple is valid "for itself".
*
* Here, we consider the effects of:
* all committed transactions (as of the current instant)
* previous commands of this transaction
* changes made by the current command
*
* Note:
* Assumes heap tuple is valid.
*
* The satisfaction of "itself" requires the following:
*
* ((Xmin == my-transaction && the row was updated by the current transaction, and
* (Xmax is null it was not deleted
* [|| Xmax != my-transaction)]) [or it was deleted by another transaction]
* ||
*
* (Xmin is committed && the row was modified by a committed transaction, and
* (Xmax is null || the row has not been deleted, or
* (Xmax != my-transaction && the row was deleted by another transaction
* Xmax is not committed))) that has not been committed
*/
bool
HeapTupleSatisfiesItself(HeapTupleHeader tuple)
{
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return false;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return false;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return false;
if (TransactionIdDidCommit(xvac))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return true;
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
return false;
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
return false;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
/* by here, the inserting transaction has committed */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return true;
if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
return false; /* updated by other */
}
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
return false;
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return true;
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMAX_INVALID;
return true;
}
/* xmax transaction committed */
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
{
tuple->t_infomask |= HEAP_XMAX_INVALID;
return true;
}
tuple->t_infomask |= HEAP_XMAX_COMMITTED;
return false;
}
/*
* HeapTupleSatisfiesDirty
* True iff heap tuple is valid including effects of open transactions.
*
* Here, we consider the effects of:
* all committed and in-progress transactions (as of the current instant)
* previous commands of this transaction
* changes made by the current command
*
* This is essentially like HeapTupleSatisfiesItself as far as effects of
* the current transaction and committed/aborted xacts are concerned.
* However, we also include the effects of other xacts still in progress.
*
* Returns extra information in the global variable SnapshotDirty, namely
* xids of concurrent xacts that affected the tuple. Also, the tuple's
* t_ctid (forward link) is returned if it's being updated.
*/
bool
HeapTupleSatisfiesDirty(HeapTupleHeader tuple)
{
SnapshotDirty->xmin = SnapshotDirty->xmax = InvalidTransactionId;
ItemPointerSetInvalid(&(SnapshotDirty->tid));
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return false;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return false;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return false;
if (TransactionIdDidCommit(xvac))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return true;
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
return false;
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
{
SnapshotDirty->xmin = HeapTupleHeaderGetXmin(tuple);
/* XXX shouldn't we fall through to look at xmax? */
return true; /* in insertion by other */
}
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMIN_INVALID;
return false;
}
}
/* by here, the inserting transaction has committed */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return true;
if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
SnapshotDirty->tid = tuple->t_ctid;
return false; /* updated by other */
}
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return true;
return false;
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
{
SnapshotDirty->xmax = HeapTupleHeaderGetXmax(tuple);
return true;
}
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMAX_INVALID;
return true;
}
/* xmax transaction committed */
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
{
tuple->t_infomask |= HEAP_XMAX_INVALID;
return true;
}
tuple->t_infomask |= HEAP_XMAX_COMMITTED;
SnapshotDirty->tid = tuple->t_ctid;
return false; /* updated by other */
}
/*
* IndexBuildHeapScan - scan the heap relation to find tuples to be indexed
*
* This is called back from an access-method-specific index build procedure
* after the AM has done whatever setup it needs. The parent heap relation
* is scanned to find tuples that should be entered into the index. Each
* such tuple is passed to the AM's callback routine, which does the right
* things to add it to the new index. After we return, the AM's index
* build procedure does whatever cleanup is needed; in particular, it should
* close the heap and index relations.
*
* The total count of heap tuples is returned. This is for updating pg_class
* statistics. (It's annoying not to be able to do that here, but we can't
* do it until after the relation is closed.) Note that the index AM itself
* must keep track of the number of index tuples; we don't do so here because
* the AM might reject some of the tuples for its own reasons, such as being
* unable to store NULLs.
*/
double
IndexBuildHeapScan(Relation heapRelation,
Relation indexRelation,
IndexInfo *indexInfo,
IndexBuildCallback callback,
void *callback_state)
{
HeapScanDesc scan;
HeapTuple heapTuple;
TupleDesc heapDescriptor;
Datum attdata[INDEX_MAX_KEYS];
char nulls[INDEX_MAX_KEYS];
double reltuples;
List *predicate;
TupleTable tupleTable;
TupleTableSlot *slot;
EState *estate;
ExprContext *econtext;
Snapshot snapshot;
TransactionId OldestXmin;
/*
* sanity checks
*/
Assert(OidIsValid(indexRelation->rd_rel->relam));
heapDescriptor = RelationGetDescr(heapRelation);
/*
* Need an EState for evaluation of index expressions and
* partial-index predicates.
*/
estate = CreateExecutorState();
econtext = GetPerTupleExprContext(estate);
/*
* If this is a predicate (partial) index, we will need to evaluate
* the predicate using ExecQual, which requires the current tuple to
* be in a slot of a TupleTable. Likewise if there are any
* expressions.
*/
if (indexInfo->ii_Predicate != NIL || indexInfo->ii_Expressions != NIL)
{
tupleTable = ExecCreateTupleTable(1);
slot = ExecAllocTableSlot(tupleTable);
ExecSetSlotDescriptor(slot, heapDescriptor, false);
/* Arrange for econtext's scan tuple to be the tuple under test */
econtext->ecxt_scantuple = slot;
/* Set up execution state for predicate. */
predicate = (List *)
ExecPrepareExpr((Expr *) indexInfo->ii_Predicate,
estate);
}
else
{
tupleTable = NULL;
slot = NULL;
predicate = NIL;
}
/*
* Ok, begin our scan of the base relation. We use SnapshotAny
* because we must retrieve all tuples and do our own time qual
* checks.
*/
if (IsBootstrapProcessingMode())
{
snapshot = SnapshotNow;
OldestXmin = InvalidTransactionId;
}
else
{
snapshot = SnapshotAny;
OldestXmin = GetOldestXmin(heapRelation->rd_rel->relisshared);
}
scan = heap_beginscan(heapRelation, /* relation */
snapshot, /* seeself */
0, /* number of keys */
(ScanKey) NULL); /* scan key */
reltuples = 0;
/*
* Scan all tuples in the base relation.
*/
while ((heapTuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
bool tupleIsAlive;
CHECK_FOR_INTERRUPTS();
if (snapshot == SnapshotAny)
{
/* do our own time qual check */
bool indexIt;
uint16 sv_infomask;
/*
* HeapTupleSatisfiesVacuum may update tuple's hint status
* bits. We could possibly get away with not locking the
* buffer here, since caller should hold ShareLock on the
* relation, but let's be conservative about it.
*/
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
sv_infomask = heapTuple->t_data->t_infomask;
switch (HeapTupleSatisfiesVacuum(heapTuple->t_data, OldestXmin))
{
case HEAPTUPLE_DEAD:
indexIt = false;
tupleIsAlive = false;
break;
case HEAPTUPLE_LIVE:
indexIt = true;
tupleIsAlive = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must index it
* anyway to keep VACUUM from complaining.
*/
indexIt = true;
tupleIsAlive = false;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* Since caller should hold ShareLock or better, we
* should not see any tuples inserted by open
* transactions --- unless it's our own transaction.
* (Consider INSERT followed by CREATE INDEX within a
* transaction.) An exception occurs when reindexing
* a system catalog, because we often release lock on
* system catalogs before committing.
*/
if (!TransactionIdIsCurrentTransactionId(
HeapTupleHeaderGetXmin(heapTuple->t_data))
&& !IsSystemRelation(heapRelation))
elog(ERROR, "concurrent insert in progress");
indexIt = true;
tupleIsAlive = true;
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* Since caller should hold ShareLock or better, we
* should not see any tuples deleted by open
* transactions --- unless it's our own transaction.
* (Consider DELETE followed by CREATE INDEX within a
* transaction.) An exception occurs when reindexing
* a system catalog, because we often release lock on
* system catalogs before committing.
*/
if (!TransactionIdIsCurrentTransactionId(
HeapTupleHeaderGetXmax(heapTuple->t_data))
&& !IsSystemRelation(heapRelation))
elog(ERROR, "concurrent delete in progress");
indexIt = true;
tupleIsAlive = false;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
indexIt = tupleIsAlive = false; /* keep compiler quiet */
break;
}
/* check for hint-bit update by HeapTupleSatisfiesVacuum */
if (sv_infomask != heapTuple->t_data->t_infomask)
SetBufferCommitInfoNeedsSave(scan->rs_cbuf);
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
if (!indexIt)
continue;
}
else
{
/* heap_getnext did the time qual check */
tupleIsAlive = true;
}
reltuples += 1;
MemoryContextReset(econtext->ecxt_per_tuple_memory);
/* Set up for predicate or expression evaluation */
if (slot)
ExecStoreTuple(heapTuple, slot, InvalidBuffer, false);
/*
* In a partial index, discard tuples that don't satisfy the
* predicate. We can also discard recently-dead tuples, since
* VACUUM doesn't complain about tuple count mismatch for partial
* indexes.
*/
if (predicate != NIL)
{
if (!tupleIsAlive)
continue;
if (!ExecQual(predicate, econtext, false))
continue;
}
/*
* For the current heap tuple, extract all the attributes we use
* in this index, and note which are null. This also performs
* evaluation of any expressions needed.
*/
FormIndexDatum(indexInfo,
heapTuple,
heapDescriptor,
estate,
attdata,
nulls);
/*
* You'd think we should go ahead and build the index tuple here,
* but some index AMs want to do further processing on the data
* first. So pass the attdata and nulls arrays, instead.
*/
/* Call the AM's callback routine to process the tuple */
callback(indexRelation, heapTuple, attdata, nulls, tupleIsAlive,
callback_state);
}
heap_endscan(scan);
if (tupleTable)
ExecDropTupleTable(tupleTable, true);
FreeExecutorState(estate);
/* These may have been pointing to the now-gone estate */
indexInfo->ii_ExpressionsState = NIL;
indexInfo->ii_PredicateState = NIL;
return reltuples;
}
/*
* HeapTupleSatisfiesUpdate
*
* Same logic as HeapTupleSatisfiesNow, but returns a more detailed result
* code, since UPDATE needs to know more than "is it visible?". Also,
* tuples of my own xact are tested against the passed CommandId not
* CurrentCommandId.
*/
int
HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid)
{
if (!(tuple->t_infomask & HEAP_XMIN_COMMITTED))
{
if (tuple->t_infomask & HEAP_XMIN_INVALID)
return HeapTupleInvisible;
if (tuple->t_infomask & HEAP_MOVED_OFF)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (TransactionIdIsCurrentTransactionId(xvac))
return HeapTupleInvisible;
if (!TransactionIdIsInProgress(xvac))
{
if (TransactionIdDidCommit(xvac))
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HeapTupleInvisible;
}
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
}
}
else if (tuple->t_infomask & HEAP_MOVED_IN)
{
TransactionId xvac = HeapTupleHeaderGetXvac(tuple);
if (!TransactionIdIsCurrentTransactionId(xvac))
{
if (TransactionIdIsInProgress(xvac))
return HeapTupleInvisible;
if (TransactionIdDidCommit(xvac))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HeapTupleInvisible;
}
}
}
else if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmin(tuple)))
{
if (HeapTupleHeaderGetCmin(tuple) >= curcid)
return HeapTupleInvisible; /* inserted after scan
* started */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid */
return HeapTupleMayBeUpdated;
Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return HeapTupleMayBeUpdated;
if (HeapTupleHeaderGetCmax(tuple) >= curcid)
return HeapTupleSelfUpdated; /* updated after scan
* started */
else
return HeapTupleInvisible; /* updated before scan
* started */
}
else if (TransactionIdIsInProgress(HeapTupleHeaderGetXmin(tuple)))
return HeapTupleInvisible;
else if (TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
tuple->t_infomask |= HEAP_XMIN_COMMITTED;
else
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMIN_INVALID;
return HeapTupleInvisible;
}
}
/* by here, the inserting transaction has committed */
if (tuple->t_infomask & HEAP_XMAX_INVALID) /* xid invalid or aborted */
return HeapTupleMayBeUpdated;
if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return HeapTupleMayBeUpdated;
return HeapTupleUpdated; /* updated by other */
}
if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
{
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
return HeapTupleMayBeUpdated;
if (HeapTupleHeaderGetCmax(tuple) >= curcid)
return HeapTupleSelfUpdated; /* updated after scan
* started */
else
return HeapTupleInvisible; /* updated before scan started */
}
if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
return HeapTupleBeingUpdated;
if (!TransactionIdDidCommit(HeapTupleHeaderGetXmax(tuple)))
{
/* it must have aborted or crashed */
tuple->t_infomask |= HEAP_XMAX_INVALID;
return HeapTupleMayBeUpdated;
}
/* xmax transaction committed */
if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
{
tuple->t_infomask |= HEAP_XMAX_INVALID;
return HeapTupleMayBeUpdated;
}
tuple->t_infomask |= HEAP_XMAX_COMMITTED;
return HeapTupleUpdated; /* updated by other */
}
/*
* Add a tuple to the new heap.
*
* Visibility information is copied from the original tuple, except that
* we "freeze" very-old tuples. Note that since we scribble on new_tuple,
* it had better be temp storage not a pointer to the original tuple.
*
* state opaque state as returned by begin_heap_rewrite
* old_tuple original tuple in the old heap
* new_tuple new, rewritten tuple to be inserted to new heap
*/
void
rewrite_heap_tuple(RewriteState state,
HeapTuple old_tuple, HeapTuple new_tuple)
{
MemoryContext old_cxt;
ItemPointerData old_tid;
TidHashKey hashkey;
bool found;
bool free_new;
old_cxt = MemoryContextSwitchTo(state->rs_cxt);
/*
* Copy the original tuple's visibility information into new_tuple.
*
* XXX we might later need to copy some t_infomask2 bits, too? Right now,
* we intentionally clear the HOT status bits.
*/
memcpy(&new_tuple->t_data->t_choice.t_heap,
&old_tuple->t_data->t_choice.t_heap,
sizeof(HeapTupleFields));
new_tuple->t_data->t_infomask &= ~HEAP_XACT_MASK;
new_tuple->t_data->t_infomask2 &= ~HEAP2_XACT_MASK;
new_tuple->t_data->t_infomask |=
old_tuple->t_data->t_infomask & HEAP_XACT_MASK;
/*
* While we have our hands on the tuple, we may as well freeze any
* very-old xmin or xmax, so that future VACUUM effort can be saved.
*
* Note we abuse heap_freeze_tuple() a bit here, since it's expecting to
* be given a pointer to a tuple in a disk buffer. It happens though that
* we can get the right things to happen by passing InvalidBuffer for the
* buffer.
*/
heap_freeze_tuple(new_tuple->t_data, state->rs_freeze_xid, InvalidBuffer);
/*
* Invalid ctid means that ctid should point to the tuple itself. We'll
* override it later if the tuple is part of an update chain.
*/
ItemPointerSetInvalid(&new_tuple->t_data->t_ctid);
/*
* If the tuple has been updated, check the old-to-new mapping hash table.
*/
if (!(old_tuple->t_data->t_infomask & (HEAP_XMAX_INVALID |
HEAP_IS_LOCKED)) &&
!(ItemPointerEquals(&(old_tuple->t_self),
&(old_tuple->t_data->t_ctid))))
{
OldToNewMapping mapping;
memset(&hashkey, 0, sizeof(hashkey));
hashkey.xmin = HeapTupleHeaderGetXmax(old_tuple->t_data);
hashkey.tid = old_tuple->t_data->t_ctid;
mapping = (OldToNewMapping)
hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_FIND, NULL);
if (mapping != NULL)
{
/*
* We've already copied the tuple that t_ctid points to, so we can
* set the ctid of this tuple to point to the new location, and
* insert it right away.
*/
new_tuple->t_data->t_ctid = mapping->new_tid;
/* We don't need the mapping entry anymore */
hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_REMOVE, &found);
Assert(found);
}
else
{
/*
* We haven't seen the tuple t_ctid points to yet. Stash this
* tuple into unresolved_tups to be written later.
*/
UnresolvedTup unresolved;
unresolved = hash_search(state->rs_unresolved_tups, &hashkey,
HASH_ENTER, &found);
Assert(!found);
unresolved->old_tid = old_tuple->t_self;
unresolved->tuple = heap_copytuple(new_tuple);
/*
* We can't do anything more now, since we don't know where the
* tuple will be written.
*/
MemoryContextSwitchTo(old_cxt);
return;
}
}
/*
* Now we will write the tuple, and then check to see if it is the B tuple
* in any new or known pair. When we resolve a known pair, we will be
* able to write that pair's A tuple, and then we have to check if it
* resolves some other pair. Hence, we need a loop here.
*/
old_tid = old_tuple->t_self;
free_new = false;
for (;;)
{
ItemPointerData new_tid;
/* Insert the tuple and find out where it's put in new_heap */
raw_heap_insert(state, new_tuple);
new_tid = new_tuple->t_self;
/*
* If the tuple is the updated version of a row, and the prior version
* wouldn't be DEAD yet, then we need to either resolve the prior
* version (if it's waiting in rs_unresolved_tups), or make an entry
* in rs_old_new_tid_map (so we can resolve it when we do see it). The
* previous tuple's xmax would equal this one's xmin, so it's
* RECENTLY_DEAD if and only if the xmin is not before OldestXmin.
*/
if ((new_tuple->t_data->t_infomask & HEAP_UPDATED) &&
!TransactionIdPrecedes(HeapTupleHeaderGetXmin(new_tuple->t_data),
state->rs_oldest_xmin))
{
/*
* Okay, this is B in an update pair. See if we've seen A.
*/
UnresolvedTup unresolved;
memset(&hashkey, 0, sizeof(hashkey));
hashkey.xmin = HeapTupleHeaderGetXmin(new_tuple->t_data);
hashkey.tid = old_tid;
unresolved = hash_search(state->rs_unresolved_tups, &hashkey,
HASH_FIND, NULL);
if (unresolved != NULL)
{
/*
* We have seen and memorized the previous tuple already. Now
* that we know where we inserted the tuple its t_ctid points
* to, fix its t_ctid and insert it to the new heap.
*/
if (free_new)
heap_freetuple(new_tuple);
new_tuple = unresolved->tuple;
free_new = true;
old_tid = unresolved->old_tid;
new_tuple->t_data->t_ctid = new_tid;
/*
* We don't need the hash entry anymore, but don't free its
* tuple just yet.
*/
hash_search(state->rs_unresolved_tups, &hashkey,
HASH_REMOVE, &found);
Assert(found);
/* loop back to insert the previous tuple in the chain */
continue;
}
else
{
/*
* Remember the new tid of this tuple. We'll use it to set the
* ctid when we find the previous tuple in the chain.
*/
OldToNewMapping mapping;
mapping = hash_search(state->rs_old_new_tid_map, &hashkey,
HASH_ENTER, &found);
Assert(!found);
mapping->new_tid = new_tid;
}
}
/* Done with this (chain of) tuples, for now */
if (free_new)
heap_freetuple(new_tuple);
break;
}
MemoryContextSwitchTo(old_cxt);
}
Datum
pgrowlocks(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
HeapScanDesc scan;
HeapTuple tuple;
TupleDesc tupdesc;
AttInMetadata *attinmeta;
Datum result;
MyData *mydata;
Relation rel;
if (SRF_IS_FIRSTCALL())
{
text *relname;
RangeVar *relrv;
MemoryContext oldcontext;
AclResult aclresult;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
attinmeta = TupleDescGetAttInMetadata(tupdesc);
funcctx->attinmeta = attinmeta;
relname = PG_GETARG_TEXT_P(0);
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = heap_openrv(relrv, AccessShareLock);
/* check permissions: must have SELECT on table */
aclresult = pg_class_aclcheck(RelationGetRelid(rel), GetUserId(),
ACL_SELECT);
if (aclresult != ACLCHECK_OK)
aclcheck_error(aclresult, ACL_KIND_CLASS,
RelationGetRelationName(rel));
scan = heap_beginscan(rel, SnapshotNow, 0, NULL);
mydata = palloc(sizeof(*mydata));
mydata->rel = rel;
mydata->scan = scan;
mydata->ncolumns = tupdesc->natts;
funcctx->user_fctx = mydata;
MemoryContextSwitchTo(oldcontext);
}
funcctx = SRF_PERCALL_SETUP();
attinmeta = funcctx->attinmeta;
mydata = (MyData *) funcctx->user_fctx;
scan = mydata->scan;
/* scan the relation */
while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
/* must hold a buffer lock to call HeapTupleSatisfiesUpdate */
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
if (HeapTupleSatisfiesUpdate(rel, tuple->t_data,
GetCurrentCommandId(/*false*/),
scan->rs_cbuf) == HeapTupleBeingUpdated)
{
char **values;
int i;
values = (char **) palloc(mydata->ncolumns * sizeof(char *));
i = 0;
values[i++] = (char *) DirectFunctionCall1(tidout, PointerGetDatum(&tuple->t_self));
if (tuple->t_data->t_infomask & HEAP_XMAX_SHARED_LOCK)
values[i++] = pstrdup("Shared");
else
values[i++] = pstrdup("Exclusive");
values[i] = palloc(NCHARS * sizeof(char));
snprintf(values[i++], NCHARS, "%d", HeapTupleHeaderGetXmax(tuple->t_data));
if (tuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI)
{
TransactionId *xids;
int nxids;
int j;
int isValidXid = 0; /* any valid xid ever exists? */
values[i++] = pstrdup("true");
nxids = GetMultiXactIdMembers(HeapTupleHeaderGetXmax(tuple->t_data), &xids);
if (nxids == -1)
{
elog(ERROR, "GetMultiXactIdMembers returns error");
}
values[i] = palloc(NCHARS * nxids);
values[i + 1] = palloc(NCHARS * nxids);
strcpy(values[i], "{");
strcpy(values[i + 1], "{");
for (j = 0; j < nxids; j++)
{
char buf[NCHARS];
if (TransactionIdIsInProgress(xids[j]))
{
if (isValidXid)
{
strcat(values[i], ",");
strcat(values[i + 1], ",");
}
snprintf(buf, NCHARS, "%d", xids[j]);
strcat(values[i], buf);
snprintf(buf, NCHARS, "%d", BackendXidGetPid(xids[j]));
strcat(values[i + 1], buf);
isValidXid = 1;
}
}
strcat(values[i], "}");
strcat(values[i + 1], "}");
i++;
}
else
{
values[i++] = pstrdup("false");
values[i] = palloc(NCHARS * sizeof(char));
snprintf(values[i++], NCHARS, "{%d}", HeapTupleHeaderGetXmax(tuple->t_data));
values[i] = palloc(NCHARS * sizeof(char));
snprintf(values[i++], NCHARS, "{%d}", BackendXidGetPid(HeapTupleHeaderGetXmax(tuple->t_data)));
}
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
/* build a tuple */
tuple = BuildTupleFromCStrings(attinmeta, values);
/* make the tuple into a datum */
result = HeapTupleGetDatum(tuple);
/* Clean up */
for (i = 0; i < mydata->ncolumns; i++)
pfree(values[i]);
pfree(values);
SRF_RETURN_NEXT(funcctx, result);
}
else
{
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
}
}
heap_endscan(scan);
heap_close(mydata->rel, AccessShareLock);
SRF_RETURN_DONE(funcctx);
}
/* ----------------
* 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 */
}
Datum
heap_page_items(PG_FUNCTION_ARGS)
{
bytea *raw_page = PG_GETARG_BYTEA_P(0);
heap_page_items_state *inter_call_data = NULL;
FuncCallContext *fctx;
int raw_page_size;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use raw page functions"))));
raw_page_size = VARSIZE(raw_page) - VARHDRSZ;
if (SRF_IS_FIRSTCALL())
{
TupleDesc tupdesc;
MemoryContext mctx;
if (raw_page_size < SizeOfPageHeaderData)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page too small (%d bytes)", raw_page_size)));
fctx = SRF_FIRSTCALL_INIT();
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
inter_call_data = palloc(sizeof(heap_page_items_state));
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
inter_call_data->tupd = tupdesc;
inter_call_data->offset = FirstOffsetNumber;
inter_call_data->page = VARDATA(raw_page);
fctx->max_calls = PageGetMaxOffsetNumber(inter_call_data->page);
fctx->user_fctx = inter_call_data;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
inter_call_data = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
Page page = inter_call_data->page;
HeapTuple resultTuple;
Datum result;
ItemId id;
Datum values[13];
bool nulls[13];
uint16 lp_offset;
uint16 lp_flags;
uint16 lp_len;
memset(nulls, 0, sizeof(nulls));
/* Extract information from the line pointer */
id = PageGetItemId(page, inter_call_data->offset);
lp_offset = ItemIdGetOffset(id);
lp_flags = ItemIdGetFlags(id);
lp_len = ItemIdGetLength(id);
values[0] = UInt16GetDatum(inter_call_data->offset);
values[1] = UInt16GetDatum(lp_offset);
values[2] = UInt16GetDatum(lp_flags);
values[3] = UInt16GetDatum(lp_len);
/*
* We do just enough validity checking to make sure we don't reference
* data outside the page passed to us. The page could be corrupt in
* many other ways, but at least we won't crash.
*/
if (ItemIdHasStorage(id) &&
lp_len >= sizeof(HeapTupleHeader) &&
lp_offset == MAXALIGN(lp_offset) &&
lp_offset + lp_len <= raw_page_size)
{
HeapTupleHeader tuphdr;
int bits_len;
/* Extract information from the tuple header */
tuphdr = (HeapTupleHeader) PageGetItem(page, id);
values[4] = UInt32GetDatum(HeapTupleHeaderGetXmin(tuphdr));
values[5] = UInt32GetDatum(HeapTupleHeaderGetXmax(tuphdr));
values[6] = UInt32GetDatum(HeapTupleHeaderGetRawCommandId(tuphdr)); /* shared with xvac */
values[7] = PointerGetDatum(&tuphdr->t_ctid);
values[8] = UInt32GetDatum(tuphdr->t_infomask2);
values[9] = UInt32GetDatum(tuphdr->t_infomask);
values[10] = UInt8GetDatum(tuphdr->t_hoff);
/*
* We already checked that the item as is completely within the
* raw page passed to us, with the length given in the line
* pointer.. Let's check that t_hoff doesn't point over lp_len,
* before using it to access t_bits and oid.
*/
if (tuphdr->t_hoff >= sizeof(HeapTupleHeader) &&
tuphdr->t_hoff <= lp_len)
{
if (tuphdr->t_infomask & HEAP_HASNULL)
{
bits_len = tuphdr->t_hoff -
(((char *) tuphdr->t_bits) -((char *) tuphdr));
values[11] = CStringGetTextDatum(
bits_to_text(tuphdr->t_bits, bits_len * 8));
}
else
nulls[11] = true;
if (tuphdr->t_infomask & HEAP_HASOID)
values[12] = HeapTupleHeaderGetOid(tuphdr);
else
nulls[12] = true;
}
else
{
nulls[11] = true;
nulls[12] = true;
}
}
else
{
/*
* The line pointer is not used, or it's invalid. Set the rest of
* the fields to NULL
*/
int i;
for (i = 4; i <= 12; i++)
nulls[i] = true;
}
/* Build and return the result tuple. */
resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls);
result = HeapTupleGetDatum(resultTuple);
inter_call_data->offset++;
SRF_RETURN_NEXT(fctx, result);
}
else
SRF_RETURN_DONE(fctx);
}