We currently never set the HEAP_XMAX_COMMITTED when the HEAP_XMAX_IS_MULTI bit
is set.
+Locking to write inplace-updated tables
+---------------------------------------
+
+If IsInplaceUpdateRelation() returns true for a table, the table is a system
+catalog that receives systable_inplace_update_begin() calls. Preparing a
+heap_update() of these tables follows additional locking rules, to ensure we
+don't lose the effects of an inplace update. In particular, consider a moment
+when a backend has fetched the old tuple to modify, not yet having called
+heap_update(). Another backend's inplace update starting then can't conclude
+until the heap_update() places its new tuple in a buffer. We enforce that
+using locktags as follows. While DDL code is the main audience, the executor
+follows these rules to make e.g. "MERGE INTO pg_class" safer. Locking rules
+are per-catalog:
+
+ pg_class systable_inplace_update_begin() callers: before the call, acquire a
+ lock on the relation in mode ShareUpdateExclusiveLock or stricter. If the
+ update targets a row of RELKIND_INDEX (but not RELKIND_PARTITIONED_INDEX),
+ that lock must be on the table. Locking the index rel is not necessary.
+ (This allows VACUUM to overwrite per-index pg_class while holding a lock on
+ the table alone.) systable_inplace_update_begin() acquires and releases
+ LOCKTAG_TUPLE in InplaceUpdateTupleLock, an alias for ExclusiveLock, on each
+ tuple it overwrites.
+
+ pg_class heap_update() callers: before copying the tuple to modify, take a
+ lock on the tuple, a ShareUpdateExclusiveLock on the relation, or a
+ ShareRowExclusiveLock or stricter on the relation.
+
+ SearchSysCacheLocked1() is one convenient way to acquire the tuple lock.
+ Most heap_update() callers already hold a suitable lock on the relation for
+ other reasons and can skip the tuple lock. If you do acquire the tuple
+ lock, release it immediately after the update.
+
+
+ pg_database: before copying the tuple to modify, all updaters of pg_database
+ rows acquire LOCKTAG_TUPLE. (Few updaters acquire LOCKTAG_OBJECT on the
+ database OID, so it wasn't worth extending that as a second option.)
+
+Ideally, DDL might want to perform permissions checks before LockTuple(), as
+we do with RangeVarGetRelidExtended() callbacks. We typically don't bother.
+LOCKTAG_TUPLE acquirers release it after each row, so the potential
+inconvenience is lower.
+
Reading inplace-updated columns
-------------------------------
#include "access/valid.h"
#include "access/visibilitymap.h"
#include "access/xloginsert.h"
+#include "catalog/pg_database.h"
+#include "catalog/pg_database_d.h"
#include "commands/vacuum.h"
#include "pgstat.h"
#include "port/pg_bitutils.h"
Buffer newbuf, HeapTuple oldtup,
HeapTuple newtup, HeapTuple old_key_tuple,
bool all_visible_cleared, bool new_all_visible_cleared);
+#ifdef USE_ASSERT_CHECKING
+static void check_lock_if_inplace_updateable_rel(Relation relation,
+ ItemPointer otid,
+ HeapTuple newtup);
+static void check_inplace_rel_lock(HeapTuple oldtup);
+#endif
static Bitmapset *HeapDetermineColumnsInfo(Relation relation,
Bitmapset *interesting_cols,
Bitmapset *external_cols,
* heavyweight lock mode and MultiXactStatus values to use for any particular
* tuple lock strength.
*
+ * These interact with InplaceUpdateTupleLock, an alias for ExclusiveLock.
+ *
* Don't look at lockstatus/updstatus directly! Use get_mxact_status_for_lock
* instead.
*/
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot update tuples during a parallel operation")));
+#ifdef USE_ASSERT_CHECKING
+ check_lock_if_inplace_updateable_rel(relation, otid, newtup);
+#endif
+
/*
* Fetch the list of attributes to be checked for various operations.
*
return TM_Ok;
}
+#ifdef USE_ASSERT_CHECKING
+/*
+ * Confirm adequate lock held during heap_update(), per rules from
+ * README.tuplock section "Locking to write inplace-updated tables".
+ */
+static void
+check_lock_if_inplace_updateable_rel(Relation relation,
+ ItemPointer otid,
+ HeapTuple newtup)
+{
+ /* LOCKTAG_TUPLE acceptable for any catalog */
+ switch (RelationGetRelid(relation))
+ {
+ case RelationRelationId:
+ case DatabaseRelationId:
+ {
+ LOCKTAG tuptag;
+
+ SET_LOCKTAG_TUPLE(tuptag,
+ relation->rd_lockInfo.lockRelId.dbId,
+ relation->rd_lockInfo.lockRelId.relId,
+ ItemPointerGetBlockNumber(otid),
+ ItemPointerGetOffsetNumber(otid));
+ if (LockHeldByMe(&tuptag, InplaceUpdateTupleLock, false))
+ return;
+ }
+ break;
+ default:
+ Assert(!IsInplaceUpdateRelation(relation));
+ return;
+ }
+
+ switch (RelationGetRelid(relation))
+ {
+ case RelationRelationId:
+ {
+ /* LOCKTAG_TUPLE or LOCKTAG_RELATION ok */
+ Form_pg_class classForm = (Form_pg_class) GETSTRUCT(newtup);
+ Oid relid = classForm->oid;
+ Oid dbid;
+ LOCKTAG tag;
+
+ if (IsSharedRelation(relid))
+ dbid = InvalidOid;
+ else
+ dbid = MyDatabaseId;
+
+ if (classForm->relkind == RELKIND_INDEX)
+ {
+ Relation irel = index_open(relid, AccessShareLock);
+
+ SET_LOCKTAG_RELATION(tag, dbid, irel->rd_index->indrelid);
+ index_close(irel, AccessShareLock);
+ }
+ else
+ SET_LOCKTAG_RELATION(tag, dbid, relid);
+
+ if (!LockHeldByMe(&tag, ShareUpdateExclusiveLock, false) &&
+ !LockHeldByMe(&tag, ShareRowExclusiveLock, true))
+ elog(WARNING,
+ "missing lock for relation \"%s\" (OID %u, relkind %c) @ TID (%u,%u)",
+ NameStr(classForm->relname),
+ relid,
+ classForm->relkind,
+ ItemPointerGetBlockNumber(otid),
+ ItemPointerGetOffsetNumber(otid));
+ }
+ break;
+ case DatabaseRelationId:
+ {
+ /* LOCKTAG_TUPLE required */
+ Form_pg_database dbForm = (Form_pg_database) GETSTRUCT(newtup);
+
+ elog(WARNING,
+ "missing lock on database \"%s\" (OID %u) @ TID (%u,%u)",
+ NameStr(dbForm->datname),
+ dbForm->oid,
+ ItemPointerGetBlockNumber(otid),
+ ItemPointerGetOffsetNumber(otid));
+ }
+ break;
+ }
+}
+
+/*
+ * Confirm adequate relation lock held, per rules from README.tuplock section
+ * "Locking to write inplace-updated tables".
+ */
+static void
+check_inplace_rel_lock(HeapTuple oldtup)
+{
+ Form_pg_class classForm = (Form_pg_class) GETSTRUCT(oldtup);
+ Oid relid = classForm->oid;
+ Oid dbid;
+ LOCKTAG tag;
+
+ if (IsSharedRelation(relid))
+ dbid = InvalidOid;
+ else
+ dbid = MyDatabaseId;
+
+ if (classForm->relkind == RELKIND_INDEX)
+ {
+ Relation irel = index_open(relid, AccessShareLock);
+
+ SET_LOCKTAG_RELATION(tag, dbid, irel->rd_index->indrelid);
+ index_close(irel, AccessShareLock);
+ }
+ else
+ SET_LOCKTAG_RELATION(tag, dbid, relid);
+
+ if (!LockHeldByMe(&tag, ShareUpdateExclusiveLock, true))
+ elog(WARNING,
+ "missing lock for relation \"%s\" (OID %u, relkind %c) @ TID (%u,%u)",
+ NameStr(classForm->relname),
+ relid,
+ classForm->relkind,
+ ItemPointerGetBlockNumber(&oldtup->t_self),
+ ItemPointerGetOffsetNumber(&oldtup->t_self));
+}
+#endif
+
/*
* Check if the specified attribute's values are the same. Subroutine for
* HeapDetermineColumnsInfo.
TM_Result result;
bool ret;
+#ifdef USE_ASSERT_CHECKING
+ if (RelationGetRelid(relation) == RelationRelationId)
+ check_inplace_rel_lock(oldtup_ptr);
+#endif
+
Assert(BufferIsValid(buffer));
+ LockTuple(relation, &oldtup.t_self, InplaceUpdateTupleLock);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/*----------
* Interpret HeapTupleSatisfiesUpdate() like heap_update() does, except:
*
* - wait unconditionally
- * - no tuple locks
+ * - already locked tuple above, since inplace needs that unconditionally
* - don't recheck header after wait: simpler to defer to next iteration
* - don't try to continue even if the updater aborts: likewise
* - no crosscheck
* don't bother optimizing that.
*/
if (!ret)
+ {
+ UnlockTuple(relation, &oldtup.t_self, InplaceUpdateTupleLock);
InvalidateCatalogSnapshot();
+ }
return ret;
}
*
* The tuple cannot change size, and therefore its header fields and null
* bitmap (if any) don't change either.
+ *
+ * Since we hold LOCKTAG_TUPLE, no updater has a local copy of this tuple.
*/
void
heap_inplace_update_and_unlock(Relation relation,
HeapTuple oldtup, Buffer buffer)
{
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+ UnlockTuple(relation, &oldtup->t_self, InplaceUpdateTupleLock);
}
#define FRM_NOOP 0x0001
*
* Overwriting violates both MVCC and transactional safety, so the uses of
* this function in Postgres are extremely limited. Nonetheless we find some
- * places to use it. Standard flow:
+ * places to use it. See README.tuplock section "Locking to write
+ * inplace-updated tables" and later sections for expectations of readers and
+ * writers of a table that gets inplace updates. Standard flow:
*
* ... [any slow preparation not requiring oldtup] ...
* systable_inplace_update_begin([...], &tup, &inplace_state);
#include "nodes/makefuncs.h"
#include "parser/parse_func.h"
#include "parser/parse_type.h"
+#include "storage/lmgr.h"
#include "utils/acl.h"
#include "utils/aclchk_internal.h"
#include "utils/builtins.h"
HeapTuple tuple;
ListCell *cell_colprivs;
- tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(relOid));
+ tuple = SearchSysCacheLocked1(RELOID, ObjectIdGetDatum(relOid));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for relation %u", relOid);
pg_class_tuple = (Form_pg_class) GETSTRUCT(tuple);
values, nulls, replaces);
CatalogTupleUpdate(relation, &newtuple->t_self, newtuple);
+ UnlockTuple(relation, &tuple->t_self, InplaceUpdateTupleLock);
/* Update initial privileges for extensions */
recordExtensionInitPriv(relOid, RelationRelationId, 0, new_acl);
pfree(new_acl);
}
+ else
+ UnlockTuple(relation, &tuple->t_self, InplaceUpdateTupleLock);
/*
* Handle column-level privileges, if any were specified or implied.
Oid *oldmembers;
Oid *newmembers;
- tuple = SearchSysCache1(cacheid, ObjectIdGetDatum(objectid));
+ tuple = SearchSysCacheLocked1(cacheid, ObjectIdGetDatum(objectid));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for %s %u", get_object_class_descr(classid), objectid);
nulls, replaces);
CatalogTupleUpdate(relation, &newtuple->t_self, newtuple);
+ UnlockTuple(relation, &tuple->t_self, InplaceUpdateTupleLock);
/* Update initial privileges for extensions */
recordExtensionInitPriv(objectid, classid, 0, new_acl);
/*
* IsInplaceUpdateRelation
* True iff core code performs inplace updates on the relation.
+ *
+ * This is used for assertions and for making the executor follow the
+ * locking protocol described at README.tuplock section "Locking to write
+ * inplace-updated tables". Extensions may inplace-update other heap
+ * tables, but concurrent SQL UPDATE on the same table may overwrite
+ * those modifications.
+ *
+ * The executor can assume these are not partitions or partitioned and
+ * have no triggers.
*/
bool
IsInplaceUpdateRelation(Relation relation)
{
Oid db_id;
HeapTuple newtup;
+ ItemPointerData otid;
Relation rel;
int notherbackends;
int npreparedxacts;
errdetail_busy_db(notherbackends, npreparedxacts)));
/* rename */
- newtup = SearchSysCacheCopy1(DATABASEOID, ObjectIdGetDatum(db_id));
+ newtup = SearchSysCacheLockedCopy1(DATABASEOID, ObjectIdGetDatum(db_id));
if (!HeapTupleIsValid(newtup))
elog(ERROR, "cache lookup failed for database %u", db_id);
+ otid = newtup->t_self;
namestrcpy(&(((Form_pg_database) GETSTRUCT(newtup))->datname), newname);
- CatalogTupleUpdate(rel, &newtup->t_self, newtup);
+ CatalogTupleUpdate(rel, &otid, newtup);
+ UnlockTuple(rel, &otid, InplaceUpdateTupleLock);
InvokeObjectPostAlterHook(DatabaseRelationId, db_id, 0);
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database \"%s\" does not exist", dbname)));
+ LockTuple(pgdbrel, &oldtuple->t_self, InplaceUpdateTupleLock);
new_record[Anum_pg_database_dattablespace - 1] = ObjectIdGetDatum(dst_tblspcoid);
new_record_repl[Anum_pg_database_dattablespace - 1] = true;
new_record,
new_record_nulls, new_record_repl);
CatalogTupleUpdate(pgdbrel, &oldtuple->t_self, newtuple);
+ UnlockTuple(pgdbrel, &oldtuple->t_self, InplaceUpdateTupleLock);
InvokeObjectPostAlterHook(DatabaseRelationId, db_id, 0);
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database \"%s\" does not exist", stmt->dbname)));
+ LockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
datform = (Form_pg_database) GETSTRUCT(tuple);
dboid = datform->oid;
newtuple = heap_modify_tuple(tuple, RelationGetDescr(rel), new_record,
new_record_nulls, new_record_repl);
CatalogTupleUpdate(rel, &tuple->t_self, newtuple);
+ UnlockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
InvokeObjectPostAlterHook(DatabaseRelationId, dboid, 0);
if (!object_ownercheck(DatabaseRelationId, db_id, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_DATABASE,
stmt->dbname);
+ LockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
datum = heap_getattr(tuple, Anum_pg_database_datcollversion, RelationGetDescr(rel), &isnull);
oldversion = isnull ? NULL : TextDatumGetCString(datum);
bool nulls[Natts_pg_database] = {0};
bool replaces[Natts_pg_database] = {0};
Datum values[Natts_pg_database] = {0};
+ HeapTuple newtuple;
ereport(NOTICE,
(errmsg("changing version from %s to %s",
values[Anum_pg_database_datcollversion - 1] = CStringGetTextDatum(newversion);
replaces[Anum_pg_database_datcollversion - 1] = true;
- tuple = heap_modify_tuple(tuple, RelationGetDescr(rel),
- values, nulls, replaces);
- CatalogTupleUpdate(rel, &tuple->t_self, tuple);
- heap_freetuple(tuple);
+ newtuple = heap_modify_tuple(tuple, RelationGetDescr(rel),
+ values, nulls, replaces);
+ CatalogTupleUpdate(rel, &tuple->t_self, newtuple);
+ heap_freetuple(newtuple);
}
else
ereport(NOTICE,
(errmsg("version has not changed")));
+ UnlockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
InvokeObjectPostAlterHook(DatabaseRelationId, db_id, 0);
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("permission denied to change owner of database")));
+ LockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
+
repl_repl[Anum_pg_database_datdba - 1] = true;
repl_val[Anum_pg_database_datdba - 1] = ObjectIdGetDatum(newOwnerId);
newtuple = heap_modify_tuple(tuple, RelationGetDescr(rel), repl_val, repl_null, repl_repl);
CatalogTupleUpdate(rel, &newtuple->t_self, newtuple);
+ UnlockTuple(rel, &tuple->t_self, InplaceUpdateTupleLock);
heap_freetuple(newtuple);
/* Set dathasloginevt flag in pg_database */
Form_pg_database db;
Relation pg_db = table_open(DatabaseRelationId, RowExclusiveLock);
+ ItemPointerData otid;
HeapTuple tuple;
/*
*/
LockSharedObject(DatabaseRelationId, MyDatabaseId, 0, AccessExclusiveLock);
- tuple = SearchSysCacheCopy1(DATABASEOID, ObjectIdGetDatum(MyDatabaseId));
+ tuple = SearchSysCacheLockedCopy1(DATABASEOID, ObjectIdGetDatum(MyDatabaseId));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for database %u", MyDatabaseId);
+ otid = tuple->t_self;
db = (Form_pg_database) GETSTRUCT(tuple);
if (!db->dathasloginevt)
{
db->dathasloginevt = true;
- CatalogTupleUpdate(pg_db, &tuple->t_self, tuple);
+ CatalogTupleUpdate(pg_db, &otid, tuple);
CommandCounterIncrement();
}
+ UnlockTuple(pg_db, &otid, InplaceUpdateTupleLock);
table_close(pg_db, RowExclusiveLock);
heap_freetuple(tuple);
}
{
HeapTuple tup;
Relation classRel;
+ ItemPointerData otid;
classRel = table_open(RelationRelationId, RowExclusiveLock);
- tup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relationId));
+ tup = SearchSysCacheLockedCopy1(RELOID, ObjectIdGetDatum(relationId));
if (!HeapTupleIsValid(tup))
elog(ERROR, "cache lookup failed for relation %u", relationId);
+ otid = tup->t_self;
Assert(((Form_pg_class) GETSTRUCT(tup))->relispartition != newval);
((Form_pg_class) GETSTRUCT(tup))->relispartition = newval;
- CatalogTupleUpdate(classRel, &tup->t_self, tup);
+ CatalogTupleUpdate(classRel, &otid, tup);
+ UnlockTuple(classRel, &otid, InplaceUpdateTupleLock);
heap_freetuple(tup);
table_close(classRel, RowExclusiveLock);
}
{
Relation pg_class;
HeapTuple tuple;
+ ItemPointerData otid;
Form_pg_class rd_rel;
Oid reloid = RelationGetRelid(rel);
/* Get a modifiable copy of the relation's pg_class row. */
pg_class = table_open(RelationRelationId, RowExclusiveLock);
- tuple = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(reloid));
+ tuple = SearchSysCacheLockedCopy1(RELOID, ObjectIdGetDatum(reloid));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for relation %u", reloid);
+ otid = tuple->t_self;
rd_rel = (Form_pg_class) GETSTRUCT(tuple);
/* Update the pg_class row. */
InvalidOid : newTableSpaceId;
if (RelFileNumberIsValid(newRelFilenumber))
rd_rel->relfilenode = newRelFilenumber;
- CatalogTupleUpdate(pg_class, &tuple->t_self, tuple);
+ CatalogTupleUpdate(pg_class, &otid, tuple);
+ UnlockTuple(pg_class, &otid, InplaceUpdateTupleLock);
/*
* Record dependency on tablespace. This is only required for relations
{
Relation targetrelation;
Relation relrelation; /* for RELATION relation */
+ ItemPointerData otid;
HeapTuple reltup;
Form_pg_class relform;
Oid namespaceId;
*/
relrelation = table_open(RelationRelationId, RowExclusiveLock);
- reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(myrelid));
+ reltup = SearchSysCacheLockedCopy1(RELOID, ObjectIdGetDatum(myrelid));
+ otid = reltup->t_self;
if (!HeapTupleIsValid(reltup)) /* shouldn't happen */
elog(ERROR, "cache lookup failed for relation %u", myrelid);
relform = (Form_pg_class) GETSTRUCT(reltup);
*/
namestrcpy(&(relform->relname), newrelname);
- CatalogTupleUpdate(relrelation, &reltup->t_self, reltup);
+ CatalogTupleUpdate(relrelation, &otid, reltup);
+ UnlockTuple(relrelation, &otid, InplaceUpdateTupleLock);
InvokeObjectPostAlterHookArg(RelationRelationId, myrelid, 0,
InvalidOid, is_internal);
/* Fetch heap tuple */
relid = RelationGetRelid(rel);
- tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(relid));
+ tuple = SearchSysCacheLocked1(RELOID, ObjectIdGetDatum(relid));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for relation %u", relid);
repl_val, repl_null, repl_repl);
CatalogTupleUpdate(pgclass, &newtuple->t_self, newtuple);
+ UnlockTuple(pgclass, &tuple->t_self, InplaceUpdateTupleLock);
InvokeObjectPostAlterHook(RelationRelationId, RelationGetRelid(rel), 0);
ObjectAddress thisobj;
bool already_done = false;
- classTup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relOid));
+ /* no rel lock for relkind=c so use LOCKTAG_TUPLE */
+ classTup = SearchSysCacheLockedCopy1(RELOID, ObjectIdGetDatum(relOid));
if (!HeapTupleIsValid(classTup))
elog(ERROR, "cache lookup failed for relation %u", relOid);
classForm = (Form_pg_class) GETSTRUCT(classTup);
already_done = object_address_present(&thisobj, objsMoved);
if (!already_done && oldNspOid != newNspOid)
{
+ ItemPointerData otid = classTup->t_self;
+
/* check for duplicate name (more friendly than unique-index failure) */
if (get_relname_relid(NameStr(classForm->relname),
newNspOid) != InvalidOid)
/* classTup is a copy, so OK to scribble on */
classForm->relnamespace = newNspOid;
- CatalogTupleUpdate(classRel, &classTup->t_self, classTup);
+ CatalogTupleUpdate(classRel, &otid, classTup);
+ UnlockTuple(classRel, &otid, InplaceUpdateTupleLock);
+
/* Update dependency on schema if caller said so */
if (hasDependEntry &&
elog(ERROR, "could not change schema dependency for relation \"%s\"",
NameStr(classForm->relname));
}
+ else
+ UnlockTuple(classRel, &classTup->t_self, InplaceUpdateTupleLock);
if (!already_done)
{
add_exact_object_address(&thisobj, objsMoved);
Relation resultRel = resultRelInfo->ri_RelationDesc;
FdwRoutine *fdwroutine;
+ /* Expect a fully-formed ResultRelInfo from InitResultRelInfo(). */
+ Assert(resultRelInfo->ri_needLockTagTuple ==
+ IsInplaceUpdateRelation(resultRel));
+
switch (resultRel->rd_rel->relkind)
{
case RELKIND_RELATION:
resultRelInfo->ri_NumIndices = 0;
resultRelInfo->ri_IndexRelationDescs = NULL;
resultRelInfo->ri_IndexRelationInfo = NULL;
+ resultRelInfo->ri_needLockTagTuple =
+ IsInplaceUpdateRelation(resultRelationDesc);
/* make a copy so as not to depend on relcache info not changing... */
resultRelInfo->ri_TrigDesc = CopyTriggerDesc(resultRelationDesc->trigdesc);
if (resultRelInfo->ri_TrigDesc)
Relation rel = resultRelInfo->ri_RelationDesc;
ItemPointer tid = &(searchslot->tts_tid);
- /* For now we support only tables. */
+ /*
+ * We support only non-system tables, with
+ * check_publication_add_relation() accountable.
+ */
Assert(rel->rd_rel->relkind == RELKIND_RELATION);
+ Assert(!IsCatalogRelation(rel));
CheckCmdReplicaIdentity(rel, CMD_UPDATE);
}
else
{
+ ItemPointerData lockedtid;
+
/*
* If we generate a new candidate tuple after EvalPlanQual testing, we
* must loop back here to try again. (We don't need to redo triggers,
* to do them again.)
*/
redo_act:
+ lockedtid = *tupleid;
result = ExecUpdateAct(context, resultRelInfo, tupleid, oldtuple, slot,
canSetTag, &updateCxt);
ExecInitUpdateProjection(context->mtstate,
resultRelInfo);
+ if (resultRelInfo->ri_needLockTagTuple)
+ {
+ UnlockTuple(resultRelationDesc,
+ &lockedtid, InplaceUpdateTupleLock);
+ LockTuple(resultRelationDesc,
+ tupleid, InplaceUpdateTupleLock);
+ }
+
/* Fetch the most recent version of old tuple. */
oldSlot = resultRelInfo->ri_oldTupleSlot;
if (!table_tuple_fetch_row_version(resultRelationDesc,
TransactionId xmin;
bool isnull;
+ /*
+ * Parse analysis should have blocked ON CONFLICT for all system
+ * relations, which includes these. There's no fundamental obstacle to
+ * supporting this; we'd just need to handle LOCKTAG_TUPLE like the other
+ * ExecUpdate() caller.
+ */
+ Assert(!resultRelInfo->ri_needLockTagTuple);
+
/* Determine lock mode to use */
lockmode = ExecUpdateLockMode(context->estate, resultRelInfo);
{
ModifyTableState *mtstate = context->mtstate;
List **mergeActions = resultRelInfo->ri_MergeActions;
+ ItemPointerData lockedtid;
List *actionStates;
TupleTableSlot *newslot = NULL;
TupleTableSlot *rslot = NULL;
* target wholerow junk attr.
*/
Assert(tupleid != NULL || oldtuple != NULL);
+ ItemPointerSetInvalid(&lockedtid);
if (oldtuple != NULL)
+ {
+ Assert(!resultRelInfo->ri_needLockTagTuple);
ExecForceStoreHeapTuple(oldtuple, resultRelInfo->ri_oldTupleSlot,
false);
- else if (!table_tuple_fetch_row_version(resultRelInfo->ri_RelationDesc,
- tupleid,
- SnapshotAny,
- resultRelInfo->ri_oldTupleSlot))
- elog(ERROR, "failed to fetch the target tuple");
+ }
+ else
+ {
+ if (resultRelInfo->ri_needLockTagTuple)
+ {
+ /*
+ * This locks even for CMD_DELETE, for CMD_NOTHING, and for tuples
+ * that don't match mas_whenqual. MERGE on system catalogs is a
+ * minor use case, so don't bother optimizing those.
+ */
+ LockTuple(resultRelInfo->ri_RelationDesc, tupleid,
+ InplaceUpdateTupleLock);
+ lockedtid = *tupleid;
+ }
+ if (!table_tuple_fetch_row_version(resultRelInfo->ri_RelationDesc,
+ tupleid,
+ SnapshotAny,
+ resultRelInfo->ri_oldTupleSlot))
+ elog(ERROR, "failed to fetch the target tuple");
+ }
/*
* Test the join condition. If it's satisfied, perform a MATCHED action.
tupleid, NULL, newslot, &result))
{
if (result == TM_Ok)
- return NULL; /* "do nothing" */
+ goto out; /* "do nothing" */
break; /* concurrent update/delete */
}
{
if (!ExecIRUpdateTriggers(estate, resultRelInfo,
oldtuple, newslot))
- return NULL; /* "do nothing" */
+ goto out; /* "do nothing" */
}
else
{
- /* called table_tuple_fetch_row_version() above */
+ /* checked ri_needLockTagTuple above */
Assert(oldtuple == NULL);
result = ExecUpdateAct(context, resultRelInfo, tupleid,
if (updateCxt.crossPartUpdate)
{
mtstate->mt_merge_updated += 1;
- return context->cpUpdateReturningSlot;
+ rslot = context->cpUpdateReturningSlot;
+ goto out;
}
}
NULL, NULL, &result))
{
if (result == TM_Ok)
- return NULL; /* "do nothing" */
+ goto out; /* "do nothing" */
break; /* concurrent update/delete */
}
{
if (!ExecIRDeleteTriggers(estate, resultRelInfo,
oldtuple))
- return NULL; /* "do nothing" */
+ goto out; /* "do nothing" */
}
else
{
- /* called table_tuple_fetch_row_version() above */
+ /* checked ri_needLockTagTuple above */
Assert(oldtuple == NULL);
result = ExecDeleteAct(context, resultRelInfo, tupleid,
* let caller handle it under NOT MATCHED [BY TARGET] clauses.
*/
*matched = false;
- return NULL;
+ goto out;
case TM_Updated:
{
* more to do.
*/
if (TupIsNull(epqslot))
- return NULL;
+ goto out;
/*
* If we got a NULL ctid from the subplan, the
* we need to switch to the NOT MATCHED BY
* SOURCE case.
*/
+ if (resultRelInfo->ri_needLockTagTuple)
+ {
+ if (ItemPointerIsValid(&lockedtid))
+ UnlockTuple(resultRelInfo->ri_RelationDesc, &lockedtid,
+ InplaceUpdateTupleLock);
+ LockTuple(resultRelInfo->ri_RelationDesc, &context->tmfd.ctid,
+ InplaceUpdateTupleLock);
+ lockedtid = context->tmfd.ctid;
+ }
if (!table_tuple_fetch_row_version(resultRelationDesc,
&context->tmfd.ctid,
SnapshotAny,
* MATCHED [BY TARGET] actions
*/
*matched = false;
- return NULL;
+ goto out;
case TM_SelfModified:
/* This shouldn't happen */
elog(ERROR, "attempted to update or delete invisible tuple");
- return NULL;
+ goto out;
default:
/* see table_tuple_lock call in ExecDelete() */
elog(ERROR, "unexpected table_tuple_lock status: %u",
result);
- return NULL;
+ goto out;
}
}
/*
* Successfully executed an action or no qualifying action was found.
*/
+out:
+ if (ItemPointerIsValid(&lockedtid))
+ UnlockTuple(resultRelInfo->ri_RelationDesc, &lockedtid,
+ InplaceUpdateTupleLock);
return rslot;
}
HeapTupleData oldtupdata;
HeapTuple oldtuple;
ItemPointer tupleid;
+ bool tuplock;
CHECK_FOR_INTERRUPTS();
break;
case CMD_UPDATE:
+ tuplock = false;
+
/* Initialize projection info if first time for this table */
if (unlikely(!resultRelInfo->ri_projectNewInfoValid))
ExecInitUpdateProjection(node, resultRelInfo);
oldSlot = resultRelInfo->ri_oldTupleSlot;
if (oldtuple != NULL)
{
+ Assert(!resultRelInfo->ri_needLockTagTuple);
/* Use the wholerow junk attr as the old tuple. */
ExecForceStoreHeapTuple(oldtuple, oldSlot, false);
}
/* Fetch the most recent version of old tuple. */
Relation relation = resultRelInfo->ri_RelationDesc;
+ if (resultRelInfo->ri_needLockTagTuple)
+ {
+ LockTuple(relation, tupleid, InplaceUpdateTupleLock);
+ tuplock = true;
+ }
if (!table_tuple_fetch_row_version(relation, tupleid,
SnapshotAny,
oldSlot))
/* Now apply the update. */
slot = ExecUpdate(&context, resultRelInfo, tupleid, oldtuple,
slot, node->canSetTag);
+ if (tuplock)
+ UnlockTuple(resultRelInfo->ri_RelationDesc, tupleid,
+ InplaceUpdateTupleLock);
break;
case CMD_DELETE:
{
RelFileNumber newrelfilenumber;
Relation pg_class;
+ ItemPointerData otid;
HeapTuple tuple;
Form_pg_class classform;
MultiXactId minmulti = InvalidMultiXactId;
*/
pg_class = table_open(RelationRelationId, RowExclusiveLock);
- tuple = SearchSysCacheCopy1(RELOID,
- ObjectIdGetDatum(RelationGetRelid(relation)));
+ tuple = SearchSysCacheLockedCopy1(RELOID,
+ ObjectIdGetDatum(RelationGetRelid(relation)));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "could not find tuple for relation %u",
RelationGetRelid(relation));
+ otid = tuple->t_self;
classform = (Form_pg_class) GETSTRUCT(tuple);
/*
classform->relminmxid = minmulti;
classform->relpersistence = persistence;
- CatalogTupleUpdate(pg_class, &tuple->t_self, tuple);
+ CatalogTupleUpdate(pg_class, &otid, tuple);
}
+ UnlockTuple(pg_class, &otid, InplaceUpdateTupleLock);
heap_freetuple(tuple);
table_close(pg_class, RowExclusiveLock);
#include "catalog/pg_shseclabel_d.h"
#include "common/int.h"
#include "lib/qunique.h"
+#include "miscadmin.h"
+#include "storage/lmgr.h"
#include "utils/catcache.h"
+#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"
#include "utils/syscache.h"
ReleaseCatCache(tuple);
}
+/*
+ * SearchSysCacheLocked1
+ *
+ * Combine SearchSysCache1() with acquiring a LOCKTAG_TUPLE at mode
+ * InplaceUpdateTupleLock. This is a tool for complying with the
+ * README.tuplock section "Locking to write inplace-updated tables". After
+ * the caller's heap_update(), it should UnlockTuple(InplaceUpdateTupleLock)
+ * and ReleaseSysCache().
+ *
+ * The returned tuple may be the subject of an uncommitted update, so this
+ * doesn't prevent the "tuple concurrently updated" error.
+ */
+HeapTuple
+SearchSysCacheLocked1(int cacheId,
+ Datum key1)
+{
+ ItemPointerData tid;
+ LOCKTAG tag;
+ Oid dboid =
+ SysCache[cacheId]->cc_relisshared ? InvalidOid : MyDatabaseId;
+ Oid reloid = cacheinfo[cacheId].reloid;
+
+ /*----------
+ * Since inplace updates may happen just before our LockTuple(), we must
+ * return content acquired after LockTuple() of the TID we return. If we
+ * just fetched twice instead of looping, the following sequence would
+ * defeat our locking:
+ *
+ * GRANT: SearchSysCache1() = TID (1,5)
+ * GRANT: LockTuple(pg_class, (1,5))
+ * [no more inplace update of (1,5) until we release the lock]
+ * CLUSTER: SearchSysCache1() = TID (1,5)
+ * CLUSTER: heap_update() = TID (1,8)
+ * CLUSTER: COMMIT
+ * GRANT: SearchSysCache1() = TID (1,8)
+ * GRANT: return (1,8) from SearchSysCacheLocked1()
+ * VACUUM: SearchSysCache1() = TID (1,8)
+ * VACUUM: LockTuple(pg_class, (1,8)) # two TIDs now locked for one rel
+ * VACUUM: inplace update
+ * GRANT: heap_update() = (1,9) # lose inplace update
+ *
+ * In the happy case, this takes two fetches, one to determine the TID to
+ * lock and another to get the content and confirm the TID didn't change.
+ *
+ * This is valid even if the row gets updated to a new TID, the old TID
+ * becomes LP_UNUSED, and the row gets updated back to its old TID. We'd
+ * still hold the right LOCKTAG_TUPLE and a copy of the row captured after
+ * the LOCKTAG_TUPLE.
+ */
+ ItemPointerSetInvalid(&tid);
+ for (;;)
+ {
+ HeapTuple tuple;
+ LOCKMODE lockmode = InplaceUpdateTupleLock;
+
+ tuple = SearchSysCache1(cacheId, key1);
+ if (ItemPointerIsValid(&tid))
+ {
+ if (!HeapTupleIsValid(tuple))
+ {
+ LockRelease(&tag, lockmode, false);
+ return tuple;
+ }
+ if (ItemPointerEquals(&tid, &tuple->t_self))
+ return tuple;
+ LockRelease(&tag, lockmode, false);
+ }
+ else if (!HeapTupleIsValid(tuple))
+ return tuple;
+
+ tid = tuple->t_self;
+ ReleaseSysCache(tuple);
+ /* like: LockTuple(rel, &tid, lockmode) */
+ SET_LOCKTAG_TUPLE(tag, dboid, reloid,
+ ItemPointerGetBlockNumber(&tid),
+ ItemPointerGetOffsetNumber(&tid));
+ (void) LockAcquire(&tag, lockmode, false, false);
+
+ /*
+ * If an inplace update just finished, ensure we process the syscache
+ * inval. XXX this is insufficient: the inplace updater may not yet
+ * have reached AtEOXact_Inval(). See test at inplace-inval.spec.
+ *
+ * If a heap_update() call just released its LOCKTAG_TUPLE, we'll
+ * probably find the old tuple and reach "tuple concurrently updated".
+ * If that heap_update() aborts, our LOCKTAG_TUPLE blocks inplace
+ * updates while our caller works.
+ */
+ AcceptInvalidationMessages();
+ }
+}
+
/*
* SearchSysCacheCopy
*
return newtuple;
}
+/*
+ * SearchSysCacheLockedCopy1
+ *
+ * Meld SearchSysCacheLockedCopy1 with SearchSysCacheCopy(). After the
+ * caller's heap_update(), it should UnlockTuple(InplaceUpdateTupleLock) and
+ * heap_freetuple().
+ */
+HeapTuple
+SearchSysCacheLockedCopy1(int cacheId,
+ Datum key1)
+{
+ HeapTuple tuple,
+ newtuple;
+
+ tuple = SearchSysCacheLocked1(cacheId, key1);
+ if (!HeapTupleIsValid(tuple))
+ return tuple;
+ newtuple = heap_copytuple(tuple);
+ ReleaseSysCache(tuple);
+ return newtuple;
+}
+
/*
* SearchSysCacheExists
*
/* Have the projection and the slots above been initialized? */
bool ri_projectNewInfoValid;
+ /* updates do LockTuple() before oldtup read; see README.tuplock */
+ bool ri_needLockTagTuple;
+
/* triggers to be fired, if any */
TriggerDesc *ri_TrigDesc;
#define MaxLockMode 8 /* highest standard lock mode */
+/* See README.tuplock section "Locking to write inplace-updated tables" */
+#define InplaceUpdateTupleLock ExclusiveLock
/* WAL representation of an AccessExclusiveLock on a table */
typedef struct xl_standby_lock
extern void ReleaseSysCache(HeapTuple tuple);
+extern HeapTuple SearchSysCacheLocked1(int cacheId,
+ Datum key1);
+
/* convenience routines */
extern HeapTuple SearchSysCacheCopy(int cacheId,
Datum key1, Datum key2, Datum key3, Datum key4);
+extern HeapTuple SearchSysCacheLockedCopy1(int cacheId,
+ Datum key1);
extern bool SearchSysCacheExists(int cacheId,
Datum key1, Datum key2, Datum key3, Datum key4);
extern Oid GetSysCacheOid(int cacheId, AttrNumber oidcol,
step addk2: ALTER TABLE intra_grant_inplace ADD PRIMARY KEY (c);
step c2: COMMIT;
-starting permutation: b3 sfu3 b1 grant1 read2 as3 addk2 r3 c1 read2
+starting permutation: b3 sfu3 b1 grant1 read2 addk2 r3 c1 read2
step b3: BEGIN ISOLATION LEVEL READ COMMITTED;
step sfu3:
SELECT relhasindex FROM pg_class
f
(1 row)
-step as3: LOCK TABLE intra_grant_inplace IN ACCESS SHARE MODE;
step addk2: ALTER TABLE intra_grant_inplace ADD PRIMARY KEY (c);
step r3: ROLLBACK;
step grant1: <... completed>
step grant1:
GRANT SELECT ON intra_grant_inplace TO PUBLIC;
-step addk2: ALTER TABLE intra_grant_inplace ADD PRIMARY KEY (c);
-step c2: COMMIT;
+step addk2: ALTER TABLE intra_grant_inplace ADD PRIMARY KEY (c);
+step addk2: <... completed>
+ERROR: deadlock detected
step grant1: <... completed>
+step c2: COMMIT;
step c1: COMMIT;
step read2:
SELECT relhasindex FROM pg_class
f
(1 row)
-s4: WARNING: got: tuple concurrently updated
-step revoke4: <... completed>
step r3: ROLLBACK;
+step revoke4: <... completed>
starting permutation: b1 drop1 b3 sfu3 revoke4 c1 r3
step b1: BEGIN;
-----------
(0 rows)
-s4: WARNING: got: tuple concurrently deleted
+s4: WARNING: got: cache lookup failed for relation REDACTED
step revoke4: <... completed>
step r3: ROLLBACK;
update parttbl set b = 2 where c = 1 returning *;
}
-# test system class updates
+# test system class LockTuple()
step sys1 {
UPDATE pg_class SET reltuples = 123 WHERE oid = 'accounts'::regclass;
# heap_update()
session s1
+setup { SET deadlock_timeout = '100s'; }
step b1 { BEGIN; }
step grant1 {
GRANT SELECT ON intra_grant_inplace TO PUBLIC;
# inplace update
session s2
+setup { SET deadlock_timeout = '10ms'; }
step read2 {
SELECT relhasindex FROM pg_class
WHERE oid = 'intra_grant_inplace'::regclass;
SELECT relhasindex FROM pg_class
WHERE oid = 'intra_grant_inplace'::regclass FOR UPDATE;
}
-step as3 { LOCK TABLE intra_grant_inplace IN ACCESS SHARE MODE; }
step r3 { ROLLBACK; }
# Additional heap_update()
teardown { ROLLBACK; }
-# XXX extant bugs: permutation comments refer to planned future LockTuple()
-
permutation
b1
grant1
b1
grant1(r3) # acquire LockTuple(), await sfu3 xmax
read2
- as3 # XXX temporary until patch adds locking to addk2
addk2(c1) # block in LockTuple() behind grant1
r3 # unblock grant1; addk2 now awaits grant1 xmax
c1
b2
sfnku2
b1
- grant1(c2) # acquire LockTuple(), await sfnku2 xmax
- addk2 # block in LockTuple() behind grant1 = deadlock
+ grant1(addk2) # acquire LockTuple(), await sfnku2 xmax
+ addk2(*) # block in LockTuple() behind grant1 = deadlock
c2
c1
read2
grant1
b3
sfu3(c1) # acquire LockTuple(), await grant1 xmax
- revoke4(sfu3) # block in LockTuple() behind sfu3
+ revoke4(r3) # block in LockTuple() behind sfu3
c1
r3 # revoke4 unlocks old tuple and finds new
projects / postgresql.git / commitdiff