/*
* GetLatestSnapshot
* Get a snapshot that is up-to-date as of the current instant,
* even if we are executing in transaction-snapshot mode.
*/
Snapshot
GetLatestSnapshot(void)
{
/*
* We might be able to relax this, but nothing that could otherwise work
* needs it.
*/
if (IsInParallelMode())
elog(ERROR,
"cannot update SecondarySnapshot during a parallel operation");
/*
* So far there are no cases requiring support for GetLatestSnapshot()
* during logical decoding, but it wouldn't be hard to add if required.
*/
Assert(!HistoricSnapshotActive());
/* If first call in transaction, go ahead and set the xact snapshot */
if (!FirstSnapshotSet)
return GetTransactionSnapshot();
SecondarySnapshot = GetSnapshotData(&SecondarySnapshotData);
return SecondarySnapshot;
}
static void
PreventAdvisoryLocksInParallelMode(void)
{
if (IsInParallelMode())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot use advisory locks during a parallel operation")));
}
/*
* RelationMapUpdateMap
*
* Install a new relfilenode mapping for the specified relation.
*
* If immediate is true (or we're bootstrapping), the mapping is activated
* immediately. Otherwise it is made pending until CommandCounterIncrement.
*/
void
RelationMapUpdateMap(Oid relationId, Oid fileNode, bool shared,
bool immediate)
{
RelMapFile *map;
if (IsBootstrapProcessingMode())
{
/*
* In bootstrap mode, the mapping gets installed in permanent map.
*/
if (shared)
map = &shared_map;
else
map = &local_map;
}
else
{
/*
* We don't currently support map changes within subtransactions, or
* when in parallel mode. This could be done with more bookkeeping
* infrastructure, but it doesn't presently seem worth it.
*/
if (GetCurrentTransactionNestLevel() > 1)
elog(ERROR, "cannot change relation mapping within subtransaction");
if (IsInParallelMode())
elog(ERROR, "cannot change relation mapping in parallel mode");
if (immediate)
{
/* Make it active, but only locally */
if (shared)
map = &active_shared_updates;
else
map = &active_local_updates;
}
else
{
/* Make it pending */
if (shared)
map = &pending_shared_updates;
else
map = &pending_local_updates;
}
}
apply_map_update(map, relationId, fileNode, true);
}
/*
* UpdateActiveSnapshotCommandId
*
* Update the current CID of the active snapshot. This can only be applied
* to a snapshot that is not referenced elsewhere.
*/
void
UpdateActiveSnapshotCommandId(void)
{
CommandId save_curcid,
curcid;
Assert(ActiveSnapshot != NULL);
Assert(ActiveSnapshot->as_snap->active_count == 1);
Assert(ActiveSnapshot->as_snap->regd_count == 0);
/*
* Don't allow modification of the active snapshot during parallel
* operation. We share the snapshot to worker backends at beginning of
* parallel operation, so any change to snapshot can lead to
* inconsistencies. We have other defenses against
* CommandCounterIncrement, but there are a few places that call this
* directly, so we put an additional guard here.
*/
save_curcid = ActiveSnapshot->as_snap->curcid;
curcid = GetCurrentCommandId(false);
if (IsInParallelMode() && save_curcid != curcid)
elog(ERROR, "cannot modify commandid in active snapshot during a parallel operation");
ActiveSnapshot->as_snap->curcid = curcid;
}
/*
* 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;
}
/* ----------------------------------------------------------------
* ExecGather(node)
*
* Scans the relation via multiple workers and returns
* the next qualifying tuple.
* ----------------------------------------------------------------
*/
TupleTableSlot *
ExecGather(GatherState *node)
{
TupleTableSlot *fslot = node->funnel_slot;
int i;
TupleTableSlot *slot;
TupleTableSlot *resultSlot;
ExprDoneCond isDone;
ExprContext *econtext;
/*
* Initialize the parallel context and workers on first execution. We do
* this on first execution rather than during node initialization, as it
* needs to allocate large dynamic segement, so it is better to do if it
* is really needed.
*/
if (!node->initialized)
{
EState *estate = node->ps.state;
Gather *gather = (Gather *) node->ps.plan;
/*
* Sometimes we might have to run without parallelism; but if
* parallel mode is active then we can try to fire up some workers.
*/
if (gather->num_workers > 0 && IsInParallelMode())
{
ParallelContext *pcxt;
bool got_any_worker = false;
/* Initialize the workers required to execute Gather node. */
if (!node->pei)
node->pei = ExecInitParallelPlan(node->ps.lefttree,
estate,
gather->num_workers);
/*
* Register backend workers. We might not get as many as we
* requested, or indeed any at all.
*/
pcxt = node->pei->pcxt;
LaunchParallelWorkers(pcxt);
/* Set up tuple queue readers to read the results. */
if (pcxt->nworkers > 0)
{
node->nreaders = 0;
node->reader =
palloc(pcxt->nworkers * sizeof(TupleQueueReader *));
for (i = 0; i < pcxt->nworkers; ++i)
{
if (pcxt->worker[i].bgwhandle == NULL)
continue;
shm_mq_set_handle(node->pei->tqueue[i],
pcxt->worker[i].bgwhandle);
node->reader[node->nreaders++] =
CreateTupleQueueReader(node->pei->tqueue[i],
fslot->tts_tupleDescriptor);
got_any_worker = true;
}
}
/* No workers? Then never mind. */
if (!got_any_worker)
ExecShutdownGatherWorkers(node);
}
/* Run plan locally if no workers or not single-copy. */
node->need_to_scan_locally = (node->reader == NULL)
|| !gather->single_copy;
node->initialized = true;
}
/*
* Check to see if we're still projecting out tuples from a previous scan
* tuple (because there is a function-returning-set in the projection
* expressions). If so, try to project another one.
*/
if (node->ps.ps_TupFromTlist)
{
resultSlot = ExecProject(node->ps.ps_ProjInfo, &isDone);
if (isDone == ExprMultipleResult)
return resultSlot;
/* Done with that source tuple... */
node->ps.ps_TupFromTlist = false;
}
/*
* Reset per-tuple memory context to free any expression evaluation
* storage allocated in the previous tuple cycle. Note we can't do this
* until we're done projecting.
*/
econtext = node->ps.ps_ExprContext;
ResetExprContext(econtext);
/* Get and return the next tuple, projecting if necessary. */
for (;;)
{
/*
* Get next tuple, either from one of our workers, or by running the
* plan ourselves.
*/
slot = gather_getnext(node);
if (TupIsNull(slot))
return NULL;
/*
* form the result tuple using ExecProject(), and return it --- unless
* the projection produces an empty set, in which case we must loop
* back around for another tuple
*/
econtext->ecxt_outertuple = slot;
resultSlot = ExecProject(node->ps.ps_ProjInfo, &isDone);
if (isDone != ExprEndResult)
{
node->ps.ps_TupFromTlist = (isDone == ExprMultipleResult);
return resultSlot;
}
}
return slot;
}
/*
* We have to cut&paste copde of GetNewTransactionId from varsup because we change way of advancing ShmemVariableCache->nextXid
*/
TransactionId
DtmGetNewTransactionId(bool isSubXact)
{
TransactionId xid;
XTM_INFO("%d: GetNewTransactionId\n", getpid());
/*
* Workers synchronize transaction state at the beginning of each parallel
* operation, so we can't account for new XIDs after that point.
*/
if (IsInParallelMode())
elog(ERROR, "cannot assign TransactionIds during a parallel operation");
/*
* During bootstrap initialization, we return the special bootstrap
* transaction id.
*/
if (IsBootstrapProcessingMode())
{
Assert(!isSubXact);
MyPgXact->xid = BootstrapTransactionId;
return BootstrapTransactionId;
}
/* safety check, we should never get this far in a HS slave */
if (RecoveryInProgress())
elog(ERROR, "cannot assign TransactionIds during recovery");
LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
xid = DtmGetNextXid();
/*----------
* Check to see if it's safe to assign another XID. This protects against
* catastrophic data loss due to XID wraparound. The basic rules are:
*
* If we're past xidVacLimit, start trying to force autovacuum cycles.
* If we're past xidWarnLimit, start issuing warnings.
* If we're past xidStopLimit, refuse to execute transactions, unless
* we are running in single-user mode (which gives an escape hatch
* to the DBA who somehow got past the earlier defenses).
*
* Note that this coding also appears in GetNewMultiXactId.
*----------
*/
if (TransactionIdFollowsOrEquals(xid, ShmemVariableCache->xidVacLimit))
{
/*
* For safety's sake, we release XidGenLock while sending signals,
* warnings, etc. This is not so much because we care about
* preserving concurrency in this situation, as to avoid any
* possibility of deadlock while doing get_database_name(). First,
* copy all the shared values we'll need in this path.
*/
TransactionId xidWarnLimit = ShmemVariableCache->xidWarnLimit;
TransactionId xidStopLimit = ShmemVariableCache->xidStopLimit;
TransactionId xidWrapLimit = ShmemVariableCache->xidWrapLimit;
Oid oldest_datoid = ShmemVariableCache->oldestXidDB;
LWLockRelease(XidGenLock);
/*
* To avoid swamping the postmaster with signals, we issue the autovac
* request only once per 64K transaction starts. This still gives
* plenty of chances before we get into real trouble.
*/
if (IsUnderPostmaster && (xid % 65536) == 0)
SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_LAUNCHER);
if (IsUnderPostmaster && TransactionIdFollowsOrEquals(xid, xidStopLimit))
{
char *oldest_datname = get_database_name(oldest_datoid);
/* complain even if that DB has disappeared */
if (oldest_datname)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("database is not accepting commands to avoid wraparound data loss in database \"%s\"",
oldest_datname),
errhint("Stop the postmaster and vacuum that database in single-user mode.\n"
"You might also need to commit or roll back old prepared transactions.")));
else
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("database is not accepting commands to avoid wraparound data loss in database with OID %u",
oldest_datoid),
errhint("Stop the postmaster and vacuum that database in single-user mode.\n"
"You might also need to commit or roll back old prepared transactions.")));
}
else
if (TransactionIdFollowsOrEquals(xid, xidWarnLimit))
{
char *oldest_datname = get_database_name(oldest_datoid);
/* complain even if that DB has disappeared */
if (oldest_datname)
ereport(WARNING,
(errmsg("database \"%s\" must be vacuumed within %u transactions",
oldest_datname,
xidWrapLimit - xid),
errhint("To avoid a database shutdown, execute a database-wide VACUUM in that database.\n"
"You might also need to commit or roll back old prepared transactions.")));
else
ereport(WARNING,
(errmsg("database with OID %u must be vacuumed within %u transactions",
oldest_datoid,
xidWrapLimit - xid),
errhint("To avoid a database shutdown, execute a database-wide VACUUM in that database.\n"
"You might also need to commit or roll back old prepared transactions.")));
}
/* Re-acquire lock and start over */
LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
xid = DtmGetNextXid();
}
/*
* If we are allocating the first XID of a new page of the commit log,
* zero out that commit-log page before returning. We must do this while
* holding XidGenLock, else another xact could acquire and commit a later
* XID before we zero the page. Fortunately, a page of the commit log
* holds 32K or more transactions, so we don't have to do this very often.
*
* Extend pg_subtrans and pg_commit_ts too.
*/
if (TransactionIdFollowsOrEquals(xid, ShmemVariableCache->nextXid))
{
ExtendCLOG(xid);
ExtendCommitTs(xid);
ExtendSUBTRANS(xid);
}
/*
* Now advance the nextXid counter. This must not happen until after we
* have successfully completed ExtendCLOG() --- if that routine fails, we
* want the next incoming transaction to try it again. We cannot assign
* more XIDs until there is CLOG space for them.
*/
if (xid == ShmemVariableCache->nextXid)
TransactionIdAdvance(ShmemVariableCache->nextXid);
else
Assert(TransactionIdPrecedes(xid, ShmemVariableCache->nextXid));
/*
* We must store the new XID into the shared ProcArray before releasing
* XidGenLock. This ensures that every active XID older than
* latestCompletedXid is present in the ProcArray, which is essential for
* correct OldestXmin tracking; see src/backend/access/transam/README.
*
* XXX by storing xid into MyPgXact without acquiring ProcArrayLock, we
* are relying on fetch/store of an xid to be atomic, else other backends
* might see a partially-set xid here. But holding both locks at once
* would be a nasty concurrency hit. So for now, assume atomicity.
*
* Note that readers of PGXACT xid fields should be careful to fetch the
* value only once, rather than assume they can read a value multiple
* times and get the same answer each time.
*
* The same comments apply to the subxact xid count and overflow fields.
*
* A solution to the atomic-store problem would be to give each PGXACT its
* own spinlock used only for fetching/storing that PGXACT's xid and
* related fields.
*
* If there's no room to fit a subtransaction XID into PGPROC, set the
* cache-overflowed flag instead. This forces readers to look in
* pg_subtrans to map subtransaction XIDs up to top-level XIDs. There is a
* race-condition window, in that the new XID will not appear as running
* until its parent link has been placed into pg_subtrans. However, that
* will happen before anyone could possibly have a reason to inquire about
* the status of the XID, so it seems OK. (Snapshots taken during this
* window *will* include the parent XID, so they will deliver the correct
* answer later on when someone does have a reason to inquire.)
*/
{
/*
* Use volatile pointer to prevent code rearrangement; other backends
* could be examining my subxids info concurrently, and we don't want
* them to see an invalid intermediate state, such as incrementing
* nxids before filling the array entry. Note we are assuming that
* TransactionId and int fetch/store are atomic.
*/
volatile PGPROC *myproc = MyProc;
volatile PGXACT *mypgxact = MyPgXact;
if (!isSubXact)
mypgxact->xid = xid;
else
{
int nxids = mypgxact->nxids;
if (nxids < PGPROC_MAX_CACHED_SUBXIDS)
{
myproc->subxids.xids[nxids] = xid;
mypgxact->nxids = nxids + 1;
}
else
mypgxact->overflowed = true;
}
}
LWLockRelease(XidGenLock);
return xid;
}
/* ----------------------------------------------------------------
* ExecGatherMerge(node)
*
* Scans the relation via multiple workers and returns
* the next qualifying tuple.
* ----------------------------------------------------------------
*/
static TupleTableSlot *
ExecGatherMerge(PlanState *pstate)
{
GatherMergeState *node = castNode(GatherMergeState, pstate);
TupleTableSlot *slot;
ExprContext *econtext;
int i;
CHECK_FOR_INTERRUPTS();
/*
* As with Gather, we don't launch workers until this node is actually
* executed.
*/
if (!node->initialized)
{
EState *estate = node->ps.state;
GatherMerge *gm = (GatherMerge *) node->ps.plan;
/*
* Sometimes we might have to run without parallelism; but if parallel
* mode is active then we can try to fire up some workers.
*/
if (gm->num_workers > 0 && IsInParallelMode())
{
ParallelContext *pcxt;
/* Initialize data structures for workers. */
if (!node->pei)
node->pei = ExecInitParallelPlan(node->ps.lefttree,
estate,
gm->num_workers);
/* Try to launch workers. */
pcxt = node->pei->pcxt;
LaunchParallelWorkers(pcxt);
node->nworkers_launched = pcxt->nworkers_launched;
/* Set up tuple queue readers to read the results. */
if (pcxt->nworkers_launched > 0)
{
node->nreaders = 0;
node->reader = palloc(pcxt->nworkers_launched *
sizeof(TupleQueueReader *));
Assert(gm->numCols);
for (i = 0; i < pcxt->nworkers_launched; ++i)
{
shm_mq_set_handle(node->pei->tqueue[i],
pcxt->worker[i].bgwhandle);
node->reader[node->nreaders++] =
CreateTupleQueueReader(node->pei->tqueue[i],
node->tupDesc);
}
}
else
{
/* No workers? Then never mind. */
ExecShutdownGatherMergeWorkers(node);
}
}
/* always allow leader to participate */
node->need_to_scan_locally = true;
node->initialized = true;
}
/*
* Reset per-tuple memory context to free any expression evaluation
* storage allocated in the previous tuple cycle.
*/
econtext = node->ps.ps_ExprContext;
ResetExprContext(econtext);
/*
* Get next tuple, either from one of our workers, or by running the plan
* ourselves.
*/
slot = gather_merge_getnext(node);
if (TupIsNull(slot))
return NULL;
/*
* form the result tuple using ExecProject(), and return it --- unless the
* projection produces an empty set, in which case we must loop back
* around for another tuple
*/
econtext->ecxt_outertuple = slot;
return ExecProject(node->ps.ps_ProjInfo);
}