/*
* PushActiveSnapshot
* Set the given snapshot as the current active snapshot
*
* If the passed snapshot is a statically-allocated one, or it is possibly
* subject to a future command counter update, create a new long-lived copy
* with active refcount=1. Otherwise, only increment the refcount.
*/
void
PushActiveSnapshot(Snapshot snap)
{
ActiveSnapshotElt *newactive;
Assert(snap != InvalidSnapshot);
newactive = MemoryContextAlloc(TopTransactionContext, sizeof(ActiveSnapshotElt));
/*
* Checking SecondarySnapshot is probably useless here, but it seems
* better to be sure.
*/
if (snap == CurrentSnapshot || snap == SecondarySnapshot || !snap->copied)
newactive->as_snap = CopySnapshot(snap);
else
newactive->as_snap = snap;
newactive->as_next = ActiveSnapshot;
newactive->as_level = GetCurrentTransactionNestLevel();
newactive->as_snap->active_count++;
ActiveSnapshot = newactive;
}
/*
* PushUpdatedSnapshot
* As above, except we set the snapshot's CID to the current CID.
*/
void
PushUpdatedSnapshot(Snapshot snapshot)
{
Snapshot newsnap;
/*
* We cannot risk modifying a snapshot that's possibly already used
* elsewhere, so make a new copy to scribble on.
*/
newsnap = CopySnapshot(snapshot);
newsnap->curcid = GetCurrentCommandId(false);
PushActiveSnapshot(newsnap);
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* RegisterSnapshotOnOwner
* As above, but use the specified resource owner
*/
Snapshot
RegisterSnapshotOnOwner(Snapshot snapshot, ResourceOwner owner)
{
Snapshot snap;
if (snapshot == InvalidSnapshot)
return InvalidSnapshot;
/* Static snapshot? Create a persistent copy */
snap = snapshot->copied ? snapshot : CopySnapshot(snapshot);
/* and tell resowner.c about it */
ResourceOwnerEnlargeSnapshots(owner);
snap->regd_count++;
ResourceOwnerRememberSnapshot(owner, snap);
RegisteredSnapshots++;
return snap;
}
/*
* inv_open -- access an existing large object.
*
* Returns:
* Large object descriptor, appropriately filled in. The descriptor
* and subsidiary data are allocated in the specified memory context,
* which must be suitably long-lived for the caller's purposes.
*/
LargeObjectDesc *
inv_open(Oid lobjId, int flags, MemoryContext mcxt)
{
LargeObjectDesc *retval;
retval = (LargeObjectDesc *) MemoryContextAlloc(mcxt,
sizeof(LargeObjectDesc));
retval->id = lobjId;
retval->subid = GetCurrentSubTransactionId();
retval->offset = 0;
if (flags & INV_WRITE)
{
retval->snapshot = SnapshotNow;
retval->flags = IFS_WRLOCK | IFS_RDLOCK;
}
else if (flags & INV_READ)
{
/* be sure to copy snap into mcxt */
MemoryContext oldContext = MemoryContextSwitchTo(mcxt);
retval->snapshot = CopySnapshot(ActiveSnapshot);
retval->flags = IFS_RDLOCK;
MemoryContextSwitchTo(oldContext);
}
else
elog(ERROR, "invalid flags: %d", flags);
/* Can't use LargeObjectExists here because it always uses SnapshotNow */
if (!myLargeObjectExists(lobjId, retval->snapshot))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("large object %u does not exist", lobjId)));
return retval;
}
/*
* ExportSnapshot
* Export the snapshot to a file so that other backends can import it.
* Returns the token (the file name) that can be used to import this
* snapshot.
*/
static char *
ExportSnapshot(Snapshot snapshot)
{
TransactionId topXid;
TransactionId *children;
int nchildren;
int addTopXid;
StringInfoData buf;
FILE *f;
int i;
MemoryContext oldcxt;
char path[MAXPGPATH];
char pathtmp[MAXPGPATH];
/*
* It's tempting to call RequireTransactionChain here, since it's not
* very useful to export a snapshot that will disappear immediately
* afterwards. However, we haven't got enough information to do that,
* since we don't know if we're at top level or not. For example, we
* could be inside a plpgsql function that is going to fire off other
* transactions via dblink. Rather than disallow perfectly legitimate
* usages, don't make a check.
*
* Also note that we don't make any restriction on the transaction's
* isolation level; however, importers must check the level if they
* are serializable.
*/
/*
* This will assign a transaction ID if we do not yet have one.
*/
topXid = GetTopTransactionId();
/*
* We cannot export a snapshot from a subtransaction because there's no
* easy way for importers to verify that the same subtransaction is still
* running.
*/
if (IsSubTransaction())
ereport(ERROR,
(errcode(ERRCODE_ACTIVE_SQL_TRANSACTION),
errmsg("cannot export a snapshot from a subtransaction")));
/*
* We do however allow previous committed subtransactions to exist.
* Importers of the snapshot must see them as still running, so get their
* XIDs to add them to the snapshot.
*/
nchildren = xactGetCommittedChildren(&children);
/*
* Copy the snapshot into TopTransactionContext, add it to the
* exportedSnapshots list, and mark it pseudo-registered. We do this to
* ensure that the snapshot's xmin is honored for the rest of the
* transaction. (Right now, because SnapshotResetXmin is so stupid, this
* is overkill; but later we might make that routine smarter.)
*/
snapshot = CopySnapshot(snapshot);
oldcxt = MemoryContextSwitchTo(TopTransactionContext);
exportedSnapshots = lappend(exportedSnapshots, snapshot);
MemoryContextSwitchTo(oldcxt);
snapshot->regd_count++;
RegisteredSnapshots++;
/*
* Fill buf with a text serialization of the snapshot, plus identification
* data about this transaction. The format expected by ImportSnapshot
* is pretty rigid: each line must be fieldname:value.
*/
initStringInfo(&buf);
appendStringInfo(&buf, "xid:%u\n", topXid);
appendStringInfo(&buf, "dbid:%u\n", MyDatabaseId);
appendStringInfo(&buf, "iso:%d\n", XactIsoLevel);
appendStringInfo(&buf, "ro:%d\n", XactReadOnly);
appendStringInfo(&buf, "xmin:%u\n", snapshot->xmin);
appendStringInfo(&buf, "xmax:%u\n", snapshot->xmax);
/*
* We must include our own top transaction ID in the top-xid data, since
* by definition we will still be running when the importing transaction
* adopts the snapshot, but GetSnapshotData never includes our own XID in
* the snapshot. (There must, therefore, be enough room to add it.)
*
* However, it could be that our topXid is after the xmax, in which case
* we shouldn't include it because xip[] members are expected to be before
* xmax. (We need not make the same check for subxip[] members, see
* snapshot.h.)
*/
addTopXid = TransactionIdPrecedes(topXid, snapshot->xmax) ? 1 : 0;
appendStringInfo(&buf, "xcnt:%d\n", snapshot->xcnt + addTopXid);
for (i = 0; i < snapshot->xcnt; i++)
appendStringInfo(&buf, "xip:%u\n", snapshot->xip[i]);
if (addTopXid)
appendStringInfo(&buf, "xip:%u\n", topXid);
/*
* Similarly, we add our subcommitted child XIDs to the subxid data.
* Here, we have to cope with possible overflow.
*/
if (snapshot->suboverflowed ||
snapshot->subxcnt + nchildren > GetMaxSnapshotSubxidCount())
appendStringInfoString(&buf, "sof:1\n");
else
{
appendStringInfoString(&buf, "sof:0\n");
appendStringInfo(&buf, "sxcnt:%d\n", snapshot->subxcnt + nchildren);
for (i = 0; i < snapshot->subxcnt; i++)
appendStringInfo(&buf, "sxp:%u\n", snapshot->subxip[i]);
for (i = 0; i < nchildren; i++)
appendStringInfo(&buf, "sxp:%u\n", children[i]);
}
appendStringInfo(&buf, "rec:%u\n", snapshot->takenDuringRecovery);
/*
* Now write the text representation into a file. We first write to a
* ".tmp" filename, and rename to final filename if no error. This
* ensures that no other backend can read an incomplete file
* (ImportSnapshot won't allow it because of its valid-characters check).
*/
XactExportFilePath(pathtmp, topXid, list_length(exportedSnapshots), ".tmp");
if (!(f = AllocateFile(pathtmp, PG_BINARY_W)))
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not create file \"%s\": %m", pathtmp)));
if (fwrite(buf.data, buf.len, 1, f) != 1)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not write to file \"%s\": %m", pathtmp)));
/* no fsync() since file need not survive a system crash */
if (FreeFile(f))
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not write to file \"%s\": %m", pathtmp)));
/*
* Now that we have written everything into a .tmp file, rename the file
* to remove the .tmp suffix.
*/
XactExportFilePath(path, topXid, list_length(exportedSnapshots), "");
if (rename(pathtmp, path) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not rename file \"%s\" to \"%s\": %m",
pathtmp, path)));
/*
* The basename of the file is what we return from pg_export_snapshot().
* It's already in path in a textual format and we know that the path
* starts with SNAPSHOT_EXPORT_DIR. Skip over the prefix and the slash
* and pstrdup it so as not to return the address of a local variable.
*/
return pstrdup(path + strlen(SNAPSHOT_EXPORT_DIR) + 1);
}
/*
* PushCopiedSnapshot
* As above, except forcibly copy the presented snapshot.
*
* This should be used when the ActiveSnapshot has to be modifiable, for
* example if the caller intends to call UpdateActiveSnapshotCommandId.
* The new snapshot will be released when popped from the stack.
*/
void
PushCopiedSnapshot(Snapshot snapshot)
{
PushActiveSnapshot(CopySnapshot(snapshot));
}
/*
* SetTransactionSnapshot
* Set the transaction's snapshot from an imported MVCC snapshot.
*
* Note that this is very closely tied to GetTransactionSnapshot --- it
* must take care of all the same considerations as the first-snapshot case
* in GetTransactionSnapshot.
*/
static void
SetTransactionSnapshot(Snapshot sourcesnap, TransactionId sourcexid)
{
/* Caller should have checked this already */
Assert(!FirstSnapshotSet);
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* Even though we are not going to use the snapshot it computes, we must
* call GetSnapshotData, for two reasons: (1) to be sure that
* CurrentSnapshotData's XID arrays have been allocated, and (2) to update
* RecentXmin and RecentGlobalXmin. (We could alternatively include those
* two variables in exported snapshot files, but it seems better to have
* snapshot importers compute reasonably up-to-date values for them.)
*/
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/*
* Now copy appropriate fields from the source snapshot.
*/
CurrentSnapshot->xmin = sourcesnap->xmin;
CurrentSnapshot->xmax = sourcesnap->xmax;
CurrentSnapshot->xcnt = sourcesnap->xcnt;
Assert(sourcesnap->xcnt <= GetMaxSnapshotXidCount());
memcpy(CurrentSnapshot->xip, sourcesnap->xip,
sourcesnap->xcnt * sizeof(TransactionId));
CurrentSnapshot->subxcnt = sourcesnap->subxcnt;
Assert(sourcesnap->subxcnt <= GetMaxSnapshotSubxidCount());
memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
sourcesnap->subxcnt * sizeof(TransactionId));
CurrentSnapshot->suboverflowed = sourcesnap->suboverflowed;
CurrentSnapshot->takenDuringRecovery = sourcesnap->takenDuringRecovery;
/* NB: curcid should NOT be copied, it's a local matter */
/*
* Now we have to fix what GetSnapshotData did with MyProc->xmin and
* TransactionXmin. There is a race condition: to make sure we are not
* causing the global xmin to go backwards, we have to test that the
* source transaction is still running, and that has to be done atomically.
* So let procarray.c do it.
*
* Note: in serializable mode, predicate.c will do this a second time.
* It doesn't seem worth contorting the logic here to avoid two calls,
* especially since it's not clear that predicate.c *must* do this.
*/
if (!ProcArrayInstallImportedXmin(CurrentSnapshot->xmin, sourcexid))
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("could not import the requested snapshot"),
errdetail("The source transaction %u is not running anymore.",
sourcexid)));
/*
* In transaction-snapshot mode, the first snapshot must live until end of
* xact, so we must make a copy of it. Furthermore, if we're running in
* serializable mode, predicate.c needs to do its own processing.
*/
if (IsolationUsesXactSnapshot())
{
if (IsolationIsSerializable())
SetSerializableTransactionSnapshot(CurrentSnapshot, sourcexid);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
FirstSnapshotSet = true;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/*
* Return historic snapshot if doing logical decoding. We'll never need a
* non-historic transaction snapshot in this (sub-)transaction, so there's
* no need to be careful to set one up for later calls to
* GetTransactionSnapshot().
*/
if (HistoricSnapshotActive())
{
Assert(!FirstSnapshotSet);
return HistoricSnapshot;
}
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(pairingheap_is_empty(&RegisteredSnapshots));
Assert(FirstXactSnapshot == NULL);
if (IsInParallelMode())
elog(ERROR,
"cannot take query snapshot during a parallel operation");
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
pairingheap_add(&RegisteredSnapshots, &FirstXactSnapshot->ph_node);
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
{
#ifdef PGXC
/*
* Consider this test case taken from portals.sql
*
* CREATE TABLE cursor (a int, b int) distribute by replication;
* INSERT INTO cursor VALUES (10);
* BEGIN;
* SET TRANSACTION ISOLATION LEVEL SERIALIZABLE;
* DECLARE c1 NO SCROLL CURSOR FOR SELECT * FROM cursor FOR UPDATE;
* INSERT INTO cursor VALUES (2);
* FETCH ALL FROM c1;
* would result in
* ERROR: attempted to lock invisible tuple
* because FETCH would be sent as a select to the remote nodes
* with command id 0, whereas the command id would be 2
* in the current snapshot.
* (1 sent by Coordinator due to declare cursor &
* 2 because of the insert inside the transaction)
* The command id should therefore be updated in the
* current snapshot.
*/
if (IsConnFromCoord())
SnapshotSetCommandId(GetCurrentCommandId(false));
#endif
return CurrentSnapshot;
}
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}
/*
* ProcessQuery
* Execute a single plannable query within a PORTAL_MULTI_QUERY
* or PORTAL_ONE_RETURNING portal
*
* parsetree: the query tree
* plan: the plan tree for the query
* params: any parameters needed
* dest: where to send results
* completionTag: points to a buffer of size COMPLETION_TAG_BUFSIZE
* in which to store a command completion status string.
*
* completionTag may be NULL if caller doesn't want a status string.
*
* Must be called in a memory context that will be reset or deleted on
* error; otherwise the executor's memory usage will be leaked.
*/
static void
ProcessQuery(Query *parsetree,
Plan *plan,
ParamListInfo params,
DestReceiver *dest,
char *completionTag)
{
int operation = parsetree->commandType;
QueryDesc *queryDesc;
ereport(DEBUG3,
(errmsg_internal("ProcessQuery")));
/*
* Must always set snapshot for plannable queries. Note we assume that
* caller will take care of restoring ActiveSnapshot on exit/error.
*/
ActiveSnapshot = CopySnapshot(GetTransactionSnapshot());
/*
* Create the QueryDesc object
*/
queryDesc = CreateQueryDesc(parsetree, plan,
ActiveSnapshot, InvalidSnapshot,
dest, params, false);
/*
* Set up to collect AFTER triggers
*/
AfterTriggerBeginQuery();
/*
* Call ExecutorStart to prepare the plan for execution
*/
ExecutorStart(queryDesc, 0);
/*
* Run the plan to completion.
*/
ExecutorRun(queryDesc, ForwardScanDirection, 0L);
/*
* Build command completion status string, if caller wants one.
*/
if (completionTag)
{
Oid lastOid;
switch (operation)
{
case CMD_SELECT:
strcpy(completionTag, "SELECT");
break;
case CMD_INSERT:
if (queryDesc->estate->es_processed == 1)
lastOid = queryDesc->estate->es_lastoid;
else
lastOid = InvalidOid;
snprintf(completionTag, COMPLETION_TAG_BUFSIZE,
"INSERT %u %u", lastOid, queryDesc->estate->es_processed);
break;
case CMD_UPDATE:
snprintf(completionTag, COMPLETION_TAG_BUFSIZE,
"UPDATE %u", queryDesc->estate->es_processed);
break;
case CMD_DELETE:
snprintf(completionTag, COMPLETION_TAG_BUFSIZE,
"DELETE %u", queryDesc->estate->es_processed);
break;
default:
strcpy(completionTag, "???");
break;
}
}
/* Now take care of any queued AFTER triggers */
AfterTriggerEndQuery(queryDesc->estate);
/*
* Now, we close down all the scans and free allocated resources.
*/
ExecutorEnd(queryDesc);
FreeQueryDesc(queryDesc);
FreeSnapshot(ActiveSnapshot);
ActiveSnapshot = NULL;
}
