agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v24 04/15] Allow to prolong life span of transition tables until transaction end
21+ messages / 2 participants
[nested] [flat]

* [PATCH v24 04/15] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 +++++++++++++++++++++++++++++++++-
 src/include/commands/trigger.h |  2 +
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index d8890d2c74..c7a2bc3ed8 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3570,6 +3570,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3635,6 +3639,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3670,6 +3675,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 	Tuplestorestate *old_tuplestore;	/* "old" transition table, if any */
 	Tuplestorestate *new_tuplestore;	/* "new" transition table, if any */
@@ -4448,6 +4454,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4642,6 +4687,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -4802,11 +4848,29 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -4818,6 +4882,18 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 9ef7f6d768..0cfb0b3c5c 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -251,6 +251,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Fri__29_Oct_2021_18_16_28_+0900_jlYRKjywLqhZ7oyk
Content-Type: text/x-diff;
 name="v24-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v24-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v27 3/9] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 13cb516752..aa1da7b279 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3730,6 +3730,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3795,6 +3799,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3830,6 +3835,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3879,6 +3885,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState state);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4725,6 +4732,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4933,6 +4979,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5093,19 +5140,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -5117,6 +5164,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 194e8d5bc1..2e9f1ac8c7 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -261,6 +261,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_14_58_01_+0900_MN3L/o2YUVF2g4zw
Content-Type: text/x-diff;
 name="v27-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v27-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v37 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index b87b4b40d07..49fe531198a 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3819,6 +3819,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3884,6 +3888,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3932,6 +3937,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/* "old" transition table for UPDATE/DELETE, if any */
@@ -3978,6 +3984,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4873,6 +4880,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -5113,6 +5159,7 @@ AfterTriggerBeginXact(void)
 	afterTriggers.firing_depth = 0;
 	afterTriggers.batch_callbacks = NIL;
 	afterTriggers.firing_batch_callbacks = false;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5287,11 +5334,11 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5309,8 +5356,33 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	qs->tables = NIL;
 	list_free_deep(tables);
 
-	list_free_deep(qs->batch_callbacks);
-	qs->batch_callbacks = NIL;
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 1d9869973c0..e5dd915096d 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -269,6 +269,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v37-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v38 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index b87b4b40d07..49fe531198a 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3819,6 +3819,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3884,6 +3888,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3932,6 +3937,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/* "old" transition table for UPDATE/DELETE, if any */
@@ -3978,6 +3984,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4873,6 +4880,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -5113,6 +5159,7 @@ AfterTriggerBeginXact(void)
 	afterTriggers.firing_depth = 0;
 	afterTriggers.batch_callbacks = NIL;
 	afterTriggers.firing_batch_callbacks = false;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5287,11 +5334,11 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5309,8 +5356,33 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	qs->tables = NIL;
 	list_free_deep(tables);
 
-	list_free_deep(qs->batch_callbacks);
-	qs->batch_callbacks = NIL;
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 0c3d485abf4..f0f052cc759 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -269,6 +269,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v38-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v39 3/8] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 401baddbfc6..dc746bccc8e 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3844,6 +3844,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3909,6 +3913,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3957,6 +3962,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/* "old" transition table for UPDATE/DELETE, if any */
@@ -4003,6 +4009,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4898,6 +4905,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -5138,6 +5184,7 @@ AfterTriggerBeginXact(void)
 	afterTriggers.firing_depth = 0;
 	afterTriggers.batch_callbacks = NIL;
 	afterTriggers.firing_batch_callbacks = false;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5312,11 +5359,11 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5334,8 +5381,33 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	qs->tables = NIL;
 	list_free_deep(tables);
 
-	list_free_deep(qs->batch_callbacks);
-	qs->batch_callbacks = NIL;
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 0c3d485abf4..f0f052cc759 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -269,6 +269,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v39-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v27 3/9] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 13cb516752..aa1da7b279 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3730,6 +3730,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3795,6 +3799,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3830,6 +3835,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3879,6 +3885,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState state);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4725,6 +4732,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4933,6 +4979,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5093,19 +5140,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -5117,6 +5164,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 194e8d5bc1..2e9f1ac8c7 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -261,6 +261,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_11_29_39_+0900_ZOAC7UMt5e8j1Nvx
Content-Type: text/x-diff;
 name="v27-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v27-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v37 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index b87b4b40d07..49fe531198a 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3819,6 +3819,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3884,6 +3888,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3932,6 +3937,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/* "old" transition table for UPDATE/DELETE, if any */
@@ -3978,6 +3984,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4873,6 +4880,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -5113,6 +5159,7 @@ AfterTriggerBeginXact(void)
 	afterTriggers.firing_depth = 0;
 	afterTriggers.batch_callbacks = NIL;
 	afterTriggers.firing_batch_callbacks = false;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5287,11 +5334,11 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5309,8 +5356,33 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	qs->tables = NIL;
 	list_free_deep(tables);
 
-	list_free_deep(qs->batch_callbacks);
-	qs->batch_callbacks = NIL;
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 1d9869973c0..e5dd915096d 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -269,6 +269,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v37-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v38 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index b87b4b40d07..49fe531198a 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3819,6 +3819,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3884,6 +3888,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3932,6 +3937,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/* "old" transition table for UPDATE/DELETE, if any */
@@ -3978,6 +3984,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4873,6 +4880,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -5113,6 +5159,7 @@ AfterTriggerBeginXact(void)
 	afterTriggers.firing_depth = 0;
 	afterTriggers.batch_callbacks = NIL;
 	afterTriggers.firing_batch_callbacks = false;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5287,11 +5334,11 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5309,8 +5356,33 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	qs->tables = NIL;
 	list_free_deep(tables);
 
-	list_free_deep(qs->batch_callbacks);
-	qs->batch_callbacks = NIL;
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 0c3d485abf4..f0f052cc759 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -269,6 +269,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v38-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v34 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 170360edda..0e1b3faed7 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3754,6 +3754,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3819,6 +3823,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3854,6 +3859,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3903,6 +3909,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4782,6 +4789,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4992,6 +5038,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5152,19 +5199,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5181,6 +5228,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 8a5a9fe642..6718514d34 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.34.1


--Multipart=_Thu__11_Jul_2024_13_23_57_+0900_hKsU2G3a3BgS2FFs--





^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v33 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 58b7fc5bbd..bd4a2219a4 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3753,6 +3753,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3818,6 +3822,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3853,6 +3858,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3902,6 +3908,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4781,6 +4788,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4991,6 +5037,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5151,19 +5198,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5180,6 +5227,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 8a5a9fe642..6718514d34 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Tue__2_Jul_2024_17_03_11_+0900_6OrVBZxOB4o_k6A1
Content-Type: text/x-diff;
 name="v33-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v33-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v30 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index c344ff0944..364e3a53f7 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3761,6 +3761,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3826,6 +3830,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3861,6 +3866,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3910,6 +3916,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4787,6 +4794,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4997,6 +5043,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5157,19 +5204,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5186,6 +5233,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 8a5a9fe642..6718514d34 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v30-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v31 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 84494c4b81..0424ab9a29 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3729,6 +3729,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3794,6 +3798,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3829,6 +3834,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3878,6 +3884,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4755,6 +4762,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4965,6 +5011,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5125,19 +5172,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5154,6 +5201,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index cb968d03ec..768d6e1c0b 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1
Content-Type: text/x-diff;
 name="v31-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v31-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v32 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 84494c4b81..0424ab9a29 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3729,6 +3729,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3794,6 +3798,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3829,6 +3834,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3878,6 +3884,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4755,6 +4762,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4965,6 +5011,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5125,19 +5172,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5154,6 +5201,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index cb968d03ec..768d6e1c0b 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Sun__31_Mar_2024_22_59_31_+0900_msknEviJj08_wgqO
Content-Type: text/x-diff;
 name="v32-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v32-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v29 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 52177759ab..00b20f4b5b 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3742,6 +3742,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3807,6 +3811,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3842,6 +3847,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3891,6 +3897,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4768,6 +4775,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4978,6 +5024,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5138,19 +5185,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5167,6 +5214,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 430e3ca7dd..48a21c4c51 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v29-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v29 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 52177759ab..00b20f4b5b 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3742,6 +3742,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3807,6 +3811,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3842,6 +3847,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3891,6 +3897,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4768,6 +4775,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4978,6 +5024,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5138,19 +5185,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5167,6 +5214,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 430e3ca7dd..48a21c4c51 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v29-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v28 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 4b295f8da5..354ea94777 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3742,6 +3742,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3807,6 +3811,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3842,6 +3847,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3891,6 +3897,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4737,6 +4744,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4947,6 +4993,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5107,19 +5154,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5136,6 +5183,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 430e3ca7dd..48a21c4c51 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K
Content-Type: text/x-diff;
 name="v28-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v28-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v25 04/15] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 +++++++++++++++++++++++++++++++++-
 src/include/commands/trigger.h |  2 +
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 1a9c1ac290..0fcb1aa0b5 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3651,6 +3651,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3716,6 +3720,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3751,6 +3756,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 	Tuplestorestate *old_tuplestore;	/* "old" transition table, if any */
 	Tuplestorestate *new_tuplestore;	/* "new" transition table, if any */
@@ -4529,6 +4535,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4723,6 +4768,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -4883,11 +4929,29 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -4899,6 +4963,18 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index e1271420e5..697a6f6d55 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -255,6 +255,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Fri__4_Feb_2022_01_48_06_+0900_N8BNZpfOR27sWrgY
Content-Type: text/x-diff;
 name="v25-0003-Add-new-deptype-option-m-in-pg_depend-system-cat.patch"
Content-Disposition: attachment;
 filename="v25-0003-Add-new-deptype-option-m-in-pg_depend-system-cat.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v26 04/10] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 +++++++++++++++++++++++++++++++++-
 src/include/commands/trigger.h |  2 +
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index e08bd9a370..adc853a570 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3651,6 +3651,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3716,6 +3720,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3751,6 +3756,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 	Tuplestorestate *old_tuplestore;	/* "old" transition table, if any */
 	Tuplestorestate *new_tuplestore;	/* "new" transition table, if any */
@@ -4539,6 +4545,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4733,6 +4778,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -4893,11 +4939,29 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -4909,6 +4973,18 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index e1271420e5..697a6f6d55 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -255,6 +255,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Mon__14_Mar_2022_19_12_17_+0900_E9HVp8j5QFkIIek.
Content-Type: text/x-diff;
 name="v26-0003-Add-new-deptype-option-m-in-pg_depend-system-cat.patch"
Content-Disposition: attachment;
 filename="v26-0003-Add-new-deptype-option-m-in-pg_depend-system-cat.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v23 04/15] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 +++++++++++++++++++++++++++++++++-
 src/include/commands/trigger.h |  2 +
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index fc0a4b2fa7..049007a484 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3570,6 +3570,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3635,6 +3639,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3670,6 +3675,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 	Tuplestorestate *old_tuplestore;	/* "old" transition table, if any */
 	Tuplestorestate *new_tuplestore;	/* "new" transition table, if any */
@@ -4448,6 +4454,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4642,6 +4687,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -4802,11 +4848,29 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -4818,6 +4882,18 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 9ef7f6d768..0cfb0b3c5c 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -251,6 +251,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Mon__2_Aug_2021_15_28_34_+0900_wlHCjIpnD/FrGAKu
Content-Type: text/x-diff;
 name="v23-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v23-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH v24 04/15] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 80 +++++++++++++++++++++++++++++++++-
 src/include/commands/trigger.h |  2 +
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index d8890d2c74..c7a2bc3ed8 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3570,6 +3570,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3635,6 +3639,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3670,6 +3675,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 	Tuplestorestate *old_tuplestore;	/* "old" transition table, if any */
 	Tuplestorestate *new_tuplestore;	/* "new" transition table, if any */
@@ -4448,6 +4454,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4642,6 +4687,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -4802,11 +4848,29 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_tuplestore;
 		table->old_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		ts = table->new_tuplestore;
 		table->new_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+		{
+			if (table->prolonged && afterTriggers.query_depth > 0)
+			{
+				MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+				afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+				MemoryContextSwitchTo(oldcxt);
+			}
+			else
+				tuplestore_end(ts);
+		}
 		if (table->storeslot)
 			ExecDropSingleTupleTableSlot(table->storeslot);
 	}
@@ -4818,6 +4882,18 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 9ef7f6d768..0cfb0b3c5c 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -251,6 +251,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.17.1


--Multipart=_Thu__23_Sep_2021_04_57_30_+0900_b5pmgR1N8oMaMz.U
Content-Type: text/x-diff;
 name="v24-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v24-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

* [PATCH 2/8] Pass all scan keys to BRIN consistent function at once
@ 2020-09-12 13:07  Tomas Vondra <[email protected]>
  0 siblings, 0 replies; 21+ messages in thread

From: Tomas Vondra @ 2020-09-12 13:07 UTC (permalink / raw)

Passing all scan keys to the BRIN consistent function at once may allow
elimination of additional ranges, which would be impossible when only
passing individual scan keys.

This modifies the existing BRIN opclasses (minmax, inclusion) although
those don't really benefit from this change. The primary purpose of this
is to allow future opclases to benefit from seeing all keys at once.

This does break existing BRIN opclasses, because the signature of the
consistent function changed. We might support both variants (with 3 and
4 parameters), but that seems pointless - the changes to NULL handling
likely require updates too. So better to make the failure clear. Also,
we're not aware of any out-of-core opclasses - there may be some, but
probably not many.

Author: Tomas Vondra <[email protected]>
Reviewed-by: Alvaro Herrera <[email protected]>
Reviewed-by: Mark Dilger <[email protected]>
Reviewed-by: Alexander Korotkov <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 doc/src/sgml/brin.sgml                   |   8 +-
 src/backend/access/brin/brin.c           | 118 +++++++++++++------
 src/backend/access/brin/brin_inclusion.c | 140 ++++++++++++++++-------
 src/backend/access/brin/brin_minmax.c    |  92 ++++++++++++---
 src/backend/access/brin/brin_validate.c  |   4 +-
 src/include/catalog/pg_proc.dat          |   4 +-
 6 files changed, 269 insertions(+), 97 deletions(-)

diff --git a/doc/src/sgml/brin.sgml b/doc/src/sgml/brin.sgml
index 06880c0f7b..078f51bb55 100644
--- a/doc/src/sgml/brin.sgml
+++ b/doc/src/sgml/brin.sgml
@@ -464,12 +464,14 @@ typedef struct BrinOpcInfo
 
    <varlistentry>
     <term><function>bool consistent(BrinDesc *bdesc, BrinValues *column,
-       ScanKey key)</function></term>
+       ScanKey *keys, int nkeys)</function></term>
     <listitem>
      <para>
-      Returns whether the ScanKey is consistent with the given indexed
-      values for a range.
+      Returns whether all the ScanKey entries are consistent with the given
+      indexed values for a range.
       The attribute number to use is passed as part of the scan key.
+      Multiple scan keys for the same attribute may be passed at once, the
+      number of entries is determined by the <literal>nkeys</literal> parameter.
      </para>
     </listitem>
    </varlistentry>
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index 27ba596c6e..743f2a925a 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -390,6 +390,9 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 	BrinMemTuple *dtup;
 	BrinTuple  *btup = NULL;
 	Size		btupsz = 0;
+	ScanKey   **keys;
+	int		   *nkeys;
+	int			keyno;
 
 	opaque = (BrinOpaque *) scan->opaque;
 	bdesc = opaque->bo_bdesc;
@@ -411,6 +414,66 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 	 */
 	consistentFn = palloc0(sizeof(FmgrInfo) * bdesc->bd_tupdesc->natts);
 
+	/*
+	 * Make room for per-attribute lists of scan keys that we'll pass to the
+	 * consistent support procedure. We allocate space for all attributes, so
+	 * that we don't have to bother determining which attributes are used.
+	 *
+	 * XXX The widest table can have ~1600 attributes, so this may allocate a
+	 * couple kilobytes of memory). We could invent a more compact approach
+	 * (with just space for used attributes) but that would make the matching
+	 * more complicated, so it may not be a win.
+	 */
+	keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
+	nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts);
+
+	/*
+	 * Preprocess the scan keys - split them into per-attribute arrays.
+	 */
+	for (keyno = 0; keyno < scan->numberOfKeys; keyno++)
+	{
+		ScanKey		key = &scan->keyData[keyno];
+		AttrNumber	keyattno = key->sk_attno;
+
+		/*
+		 * The collation of the scan key must match the collation used in the
+		 * index column (but only if the search is not IS NULL/ IS NOT NULL).
+		 * Otherwise we shouldn't be using this index ...
+		 */
+		Assert((key->sk_flags & SK_ISNULL) ||
+			   (key->sk_collation ==
+				TupleDescAttr(bdesc->bd_tupdesc,
+							  keyattno - 1)->attcollation));
+
+		/* First time we see this index attribute, so init as needed. */
+		if (!keys[keyattno - 1])
+		{
+			FmgrInfo   *tmp;
+
+			/*
+			 * This is a bit of an overkill - we don't know how many scan keys
+			 * are there for this attribute, so we simply allocate the largest
+			 * number possible. This may waste a bit of memory, but we only
+			 * expect small number of scan keys in general, so this should be
+			 * negligible, and it's cheaper than having to repalloc
+			 * repeatedly.
+			 */
+			keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys);
+
+			/* First time this column, so look up consistent function */
+			Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid);
+
+			tmp = index_getprocinfo(idxRel, keyattno,
+									BRIN_PROCNUM_CONSISTENT);
+			fmgr_info_copy(&consistentFn[keyattno - 1], tmp,
+						   CurrentMemoryContext);
+		}
+
+		/* Add key to the per-attribute array. */
+		keys[keyattno - 1][nkeys[keyattno - 1]] = key;
+		nkeys[keyattno - 1]++;
+	}
+
 	/* allocate an initial in-memory tuple, out of the per-range memcxt */
 	dtup = brin_new_memtuple(bdesc);
 
@@ -471,7 +534,7 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 			}
 			else
 			{
-				int			keyno;
+				int			attno;
 
 				/*
 				 * Compare scan keys with summary values stored for the range.
@@ -481,51 +544,40 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 				 * no keys.
 				 */
 				addrange = true;
-				for (keyno = 0; keyno < scan->numberOfKeys; keyno++)
+				for (attno = 1; attno <= bdesc->bd_tupdesc->natts; attno++)
 				{
-					ScanKey		key = &scan->keyData[keyno];
-					AttrNumber	keyattno = key->sk_attno;
-					BrinValues *bval = &dtup->bt_columns[keyattno - 1];
+					BrinValues *bval;
 					Datum		add;
+					Oid			collation;
 
-					/*
-					 * The collation of the scan key must match the collation
-					 * used in the index column (but only if the search is not
-					 * IS NULL/ IS NOT NULL).  Otherwise we shouldn't be using
-					 * this index ...
-					 */
-					Assert((key->sk_flags & SK_ISNULL) ||
-						   (key->sk_collation ==
-							TupleDescAttr(bdesc->bd_tupdesc,
-										  keyattno - 1)->attcollation));
-
-					/* First time this column? look up consistent function */
-					if (consistentFn[keyattno - 1].fn_oid == InvalidOid)
-					{
-						FmgrInfo   *tmp;
-
-						tmp = index_getprocinfo(idxRel, keyattno,
-												BRIN_PROCNUM_CONSISTENT);
-						fmgr_info_copy(&consistentFn[keyattno - 1], tmp,
-									   CurrentMemoryContext);
-					}
+					/* skip attributes without any scan keys */
+					if (nkeys[attno - 1] == 0)
+						continue;
+
+					bval = &dtup->bt_columns[attno - 1];
+
+					Assert((nkeys[attno - 1] > 0) &&
+						   (nkeys[attno - 1] <= scan->numberOfKeys));
 
 					/*
 					 * Check whether the scan key is consistent with the page
 					 * range values; if so, have the pages in the range added
 					 * to the output bitmap.
 					 *
-					 * When there are multiple scan keys, failure to meet the
-					 * criteria for a single one of them is enough to discard
-					 * the range as a whole, so break out of the loop as soon
-					 * as a false return value is obtained.
+					 * XXX We simply use the collation from the first key (it
+					 * has to be the same for all keys for the same attribue).
 					 */
-					add = FunctionCall3Coll(&consistentFn[keyattno - 1],
-											key->sk_collation,
+					collation = keys[attno - 1][0]->sk_collation;
+
+					/* Check all keys at once */
+					add = FunctionCall4Coll(&consistentFn[attno - 1],
+											collation,
 											PointerGetDatum(bdesc),
 											PointerGetDatum(bval),
-											PointerGetDatum(key));
+											PointerGetDatum(keys[attno - 1]),
+											Int32GetDatum(nkeys[attno - 1]));
 					addrange = DatumGetBool(add);
+
 					if (!addrange)
 						break;
 				}
diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c
index 12e5bddd1f..a260074c91 100644
--- a/src/backend/access/brin/brin_inclusion.c
+++ b/src/backend/access/brin/brin_inclusion.c
@@ -85,6 +85,8 @@ static FmgrInfo *inclusion_get_procinfo(BrinDesc *bdesc, uint16 attno,
 										uint16 procnum);
 static FmgrInfo *inclusion_get_strategy_procinfo(BrinDesc *bdesc, uint16 attno,
 												 Oid subtype, uint16 strategynum);
+static bool inclusion_consistent_key(BrinDesc *bdesc, BrinValues *column,
+									 ScanKey key, Oid colloid);
 
 
 /*
@@ -251,6 +253,10 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS)
 /*
  * BRIN inclusion consistent function
  *
+ * We inspect the IS NULL scan keys first, which allows us to make a decision
+ * without looking at the contents of the page range. Only when the page range
+ * matches all those keys, we check the regular scan keys.
+ *
  * All of the strategies are optional.
  */
 Datum
@@ -258,24 +264,31 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 {
 	BrinDesc   *bdesc = (BrinDesc *) PG_GETARG_POINTER(0);
 	BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1);
-	ScanKey		key = (ScanKey) PG_GETARG_POINTER(2);
-	Oid			colloid = PG_GET_COLLATION(),
-				subtype;
-	Datum		unionval;
-	AttrNumber	attno;
-	Datum		query;
-	FmgrInfo   *finfo;
-	Datum		result;
-
-	Assert(key->sk_attno == column->bv_attno);
+	ScanKey    *keys = (ScanKey *) PG_GETARG_POINTER(2);
+	int			nkeys = PG_GETARG_INT32(3);
+	Oid			colloid = PG_GET_COLLATION();
+	int			keyno;
+	bool		has_regular_keys = false;
 
-	/* Handle IS NULL/IS NOT NULL tests. */
-	if (key->sk_flags & SK_ISNULL)
+	/* Handle IS NULL/IS NOT NULL tests */
+	for (keyno = 0; keyno < nkeys; keyno++)
 	{
+		ScanKey		key = keys[keyno];
+
+		Assert(key->sk_attno == column->bv_attno);
+
+		/* Skip regular scan keys (and remember that we have some). */
+		if ((!key->sk_flags & SK_ISNULL))
+		{
+			has_regular_keys = true;
+			continue;
+		}
+
 		if (key->sk_flags & SK_SEARCHNULL)
 		{
 			if (column->bv_allnulls || column->bv_hasnulls)
-				PG_RETURN_BOOL(true);
+				continue;		/* this key is fine, continue */
+
 			PG_RETURN_BOOL(false);
 		}
 
@@ -284,7 +297,12 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 		 * only nulls.
 		 */
 		if (key->sk_flags & SK_SEARCHNOTNULL)
-			PG_RETURN_BOOL(!column->bv_allnulls);
+		{
+			if (column->bv_allnulls)
+				PG_RETURN_BOOL(false);
+
+			continue;
+		}
 
 		/*
 		 * Neither IS NULL nor IS NOT NULL was used; assume all indexable
@@ -293,7 +311,14 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 		PG_RETURN_BOOL(false);
 	}
 
-	/* If it is all nulls, it cannot possibly be consistent. */
+	/* If there are no regular keys, the page range is considered consistent. */
+	if (!has_regular_keys)
+		PG_RETURN_BOOL(true);
+
+	/*
+	 * If is all nulls, it cannot possibly be consistent (at this point we
+	 * know there are at least some regular scan keys).
+	 */
 	if (column->bv_allnulls)
 		PG_RETURN_BOOL(false);
 
@@ -301,10 +326,45 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 	if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE]))
 		PG_RETURN_BOOL(true);
 
-	attno = key->sk_attno;
-	subtype = key->sk_subtype;
-	query = key->sk_argument;
-	unionval = column->bv_values[INCLUSION_UNION];
+	/* Check that the range is consistent with all regular scan keys. */
+	for (keyno = 0; keyno < nkeys; keyno++)
+	{
+		ScanKey		key = keys[keyno];
+
+		/* Skip IS NULL/IS NOT NULL keys (already handled above). */
+		if (key->sk_flags & SK_ISNULL)
+			continue;
+
+		/*
+		 * When there are multiple scan keys, failure to meet the criteria for
+		 * a single one of them is enough to discard the range as a whole, so
+		 * break out of the loop as soon as a false return value is obtained.
+		 */
+		if (!inclusion_consistent_key(bdesc, column, key, colloid))
+			PG_RETURN_BOOL(false);
+	}
+
+	PG_RETURN_BOOL(true);
+}
+
+/*
+ * inclusion_consistent_key
+ *		Determine if the range is consistent with a single scan key.
+ */
+static bool
+inclusion_consistent_key(BrinDesc *bdesc, BrinValues *column, ScanKey key,
+						 Oid colloid)
+{
+	FmgrInfo   *finfo;
+	AttrNumber	attno = key->sk_attno;
+	Oid			subtype = key->sk_subtype;
+	Datum		query = key->sk_argument;
+	Datum		unionval = column->bv_values[INCLUSION_UNION];
+	Datum		result;
+
+	/* This should be called only for regular keys, not for IS [NOT] NULL. */
+	Assert(!(key->sk_flags & SK_ISNULL));
+
 	switch (key->sk_strategy)
 	{
 			/*
@@ -324,49 +384,49 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTOverRightStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTOverLeftStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTRightStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTOverRightStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTLeftStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTRightStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTOverLeftStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTBelowStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTOverAboveStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTOverBelowStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTAboveStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTOverAboveStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTBelowStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		case RTAboveStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTOverBelowStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 			/*
 			 * Overlap and contains strategies
@@ -384,7 +444,7 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													key->sk_strategy);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_DATUM(result);
+			return DatumGetBool(result);
 
 			/*
 			 * Contained by strategies
@@ -404,9 +464,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 													RTOverlapStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
 			if (DatumGetBool(result))
-				PG_RETURN_BOOL(true);
+				return true;
 
-			PG_RETURN_DATUM(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
+			return DatumGetBool(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
 
 			/*
 			 * Adjacent strategy
@@ -423,12 +483,12 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 													RTOverlapStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
 			if (DatumGetBool(result))
-				PG_RETURN_BOOL(true);
+				return true;
 
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTAdjacentStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_DATUM(result);
+			return DatumGetBool(result);
 
 			/*
 			 * Basic comparison strategies
@@ -458,9 +518,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 													RTRightStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
 			if (!DatumGetBool(result))
-				PG_RETURN_BOOL(true);
+				return true;
 
-			PG_RETURN_DATUM(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
+			return DatumGetBool(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
 
 		case RTSameStrategyNumber:
 		case RTEqualStrategyNumber:
@@ -468,30 +528,30 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS)
 													RTContainsStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
 			if (DatumGetBool(result))
-				PG_RETURN_BOOL(true);
+				return true;
 
-			PG_RETURN_DATUM(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
+			return DatumGetBool(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
 
 		case RTGreaterEqualStrategyNumber:
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTLeftStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
 			if (!DatumGetBool(result))
-				PG_RETURN_BOOL(true);
+				return true;
 
-			PG_RETURN_DATUM(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
+			return DatumGetBool(column->bv_values[INCLUSION_CONTAINS_EMPTY]);
 
 		case RTGreaterStrategyNumber:
 			/* no need to check for empty elements */
 			finfo = inclusion_get_strategy_procinfo(bdesc, attno, subtype,
 													RTLeftStrategyNumber);
 			result = FunctionCall2Coll(finfo, colloid, unionval, query);
-			PG_RETURN_BOOL(!DatumGetBool(result));
+			return !DatumGetBool(result);
 
 		default:
 			/* shouldn't happen */
 			elog(ERROR, "invalid strategy number %d", key->sk_strategy);
-			PG_RETURN_BOOL(false);
+			return false;
 	}
 }
 
diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c
index 2ffbd9bf0d..e116084a02 100644
--- a/src/backend/access/brin/brin_minmax.c
+++ b/src/backend/access/brin/brin_minmax.c
@@ -30,6 +30,8 @@ typedef struct MinmaxOpaque
 
 static FmgrInfo *minmax_get_strategy_procinfo(BrinDesc *bdesc, uint16 attno,
 											  Oid subtype, uint16 strategynum);
+static bool minmax_consistent_key(BrinDesc *bdesc, BrinValues *column,
+								  ScanKey key, Oid colloid);
 
 
 Datum
@@ -140,29 +142,41 @@ brin_minmax_add_value(PG_FUNCTION_ARGS)
  * Given an index tuple corresponding to a certain page range and a scan key,
  * return whether the scan key is consistent with the index tuple's min/max
  * values.  Return true if so, false otherwise.
+ *
+ * We inspect the IS NULL scan keys first, which allows us to make a decision
+ * without looking at the contents of the page range. Only when the page range
+ * matches all those keys, we check the regular scan keys.
  */
 Datum
 brin_minmax_consistent(PG_FUNCTION_ARGS)
 {
 	BrinDesc   *bdesc = (BrinDesc *) PG_GETARG_POINTER(0);
 	BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1);
-	ScanKey		key = (ScanKey) PG_GETARG_POINTER(2);
-	Oid			colloid = PG_GET_COLLATION(),
-				subtype;
-	AttrNumber	attno;
-	Datum		value;
-	Datum		matches;
-	FmgrInfo   *finfo;
-
-	Assert(key->sk_attno == column->bv_attno);
+	ScanKey    *keys = (ScanKey *) PG_GETARG_POINTER(2);
+	int			nkeys = PG_GETARG_INT32(3);
+	Oid			colloid = PG_GET_COLLATION();
+	int			keyno;
+	bool		has_regular_keys = false;
 
 	/* handle IS NULL/IS NOT NULL tests */
-	if (key->sk_flags & SK_ISNULL)
+	for (keyno = 0; keyno < nkeys; keyno++)
 	{
+		ScanKey		key = keys[keyno];
+
+		Assert(key->sk_attno == column->bv_attno);
+
+		/* Skip regular scan keys (and remember that we have some). */
+		if ((!key->sk_flags & SK_ISNULL))
+		{
+			has_regular_keys = true;
+			continue;
+		}
+
 		if (key->sk_flags & SK_SEARCHNULL)
 		{
 			if (column->bv_allnulls || column->bv_hasnulls)
-				PG_RETURN_BOOL(true);
+				continue;		/* this key is fine, continue */
+
 			PG_RETURN_BOOL(false);
 		}
 
@@ -171,7 +185,12 @@ brin_minmax_consistent(PG_FUNCTION_ARGS)
 		 * only nulls.
 		 */
 		if (key->sk_flags & SK_SEARCHNOTNULL)
-			PG_RETURN_BOOL(!column->bv_allnulls);
+		{
+			if (column->bv_allnulls)
+				PG_RETURN_BOOL(false);
+
+			continue;
+		}
 
 		/*
 		 * Neither IS NULL nor IS NOT NULL was used; assume all indexable
@@ -180,13 +199,52 @@ brin_minmax_consistent(PG_FUNCTION_ARGS)
 		PG_RETURN_BOOL(false);
 	}
 
-	/* if the range is all empty, it cannot possibly be consistent */
+	/* If there are no regular keys, the page range is considered consistent. */
+	if (!has_regular_keys)
+		PG_RETURN_BOOL(true);
+
+	/*
+	 * If is all nulls, it cannot possibly be consistent (at this point we
+	 * know there are at least some regular scan keys).
+	 */
 	if (column->bv_allnulls)
 		PG_RETURN_BOOL(false);
 
-	attno = key->sk_attno;
-	subtype = key->sk_subtype;
-	value = key->sk_argument;
+	/* Check that the range is consistent with all scan keys. */
+	for (keyno = 0; keyno < nkeys; keyno++)
+	{
+		ScanKey		key = keys[keyno];
+
+		/* ignore IS NULL/IS NOT NULL tests handled above */
+		if (key->sk_flags & SK_ISNULL)
+			continue;
+
+		/*
+		 * When there are multiple scan keys, failure to meet the criteria for
+		 * a single one of them is enough to discard the range as a whole, so
+		 * break out of the loop as soon as a false return value is obtained.
+		 */
+		if (!minmax_consistent_key(bdesc, column, key, colloid))
+			PG_RETURN_DATUM(false);;
+	}
+
+	PG_RETURN_DATUM(true);
+}
+
+/*
+ * minmax_consistent_key
+ *		Determine if the range is consistent with a single scan key.
+ */
+static bool
+minmax_consistent_key(BrinDesc *bdesc, BrinValues *column, ScanKey key,
+					  Oid colloid)
+{
+	FmgrInfo   *finfo;
+	AttrNumber	attno = key->sk_attno;
+	Oid			subtype = key->sk_subtype;
+	Datum		value = key->sk_argument;
+	Datum		matches;
+
 	switch (key->sk_strategy)
 	{
 		case BTLessStrategyNumber:
@@ -229,7 +287,7 @@ brin_minmax_consistent(PG_FUNCTION_ARGS)
 			break;
 	}
 
-	PG_RETURN_DATUM(matches);
+	return DatumGetBool(matches);
 }
 
 /*
diff --git a/src/backend/access/brin/brin_validate.c b/src/backend/access/brin/brin_validate.c
index 6d4253c05e..2c4f9a3eff 100644
--- a/src/backend/access/brin/brin_validate.c
+++ b/src/backend/access/brin/brin_validate.c
@@ -97,8 +97,8 @@ brinvalidate(Oid opclassoid)
 				break;
 			case BRIN_PROCNUM_CONSISTENT:
 				ok = check_amproc_signature(procform->amproc, BOOLOID, true,
-											3, 3, INTERNALOID, INTERNALOID,
-											INTERNALOID);
+											4, 4, INTERNALOID, INTERNALOID,
+											INTERNALOID, INT4OID);
 				break;
 			case BRIN_PROCNUM_UNION:
 				ok = check_amproc_signature(procform->amproc, BOOLOID, true,
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index c7619f8cd3..cd1eda38ab 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -8207,7 +8207,7 @@
   prosrc => 'brin_minmax_add_value' },
 { oid => '3385', descr => 'BRIN minmax support',
   proname => 'brin_minmax_consistent', prorettype => 'bool',
-  proargtypes => 'internal internal internal',
+  proargtypes => 'internal internal internal int4',
   prosrc => 'brin_minmax_consistent' },
 { oid => '3386', descr => 'BRIN minmax support',
   proname => 'brin_minmax_union', prorettype => 'bool',
@@ -8223,7 +8223,7 @@
   prosrc => 'brin_inclusion_add_value' },
 { oid => '4107', descr => 'BRIN inclusion support',
   proname => 'brin_inclusion_consistent', prorettype => 'bool',
-  proargtypes => 'internal internal internal',
+  proargtypes => 'internal internal internal int4',
   prosrc => 'brin_inclusion_consistent' },
 { oid => '4108', descr => 'BRIN inclusion support',
   proname => 'brin_inclusion_union', prorettype => 'bool',
-- 
2.26.2


--------------D524CD37E77B36A2883A7617
Content-Type: text/x-patch; charset=UTF-8;
 name="0003-Move-IS-NOT-NULL-handling-from-BRIN-support-20210311.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="0003-Move-IS-NOT-NULL-handling-from-BRIN-support-20210311.pa";
 filename*1="tch"



^ permalink  raw  reply  [nested|flat] 21+ messages in thread

end of thread, other threads:[~2020-09-12 13:07 UTC | newest]

Thread overview: 21+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2019-12-20 01:09 [PATCH v37 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v38 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v39 3/8] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v33 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v30 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v32 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v25 04/15] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v23 04/15] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v29 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v24 04/15] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v27 3/9] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v27 3/9] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v28 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v34 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v31 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v29 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v26 04/10] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v37 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v24 04/15] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2019-12-20 01:09 [PATCH v38 03/11] Allow to prolong life span of transition tables until transaction end Yugo Nagata <[email protected]>
2020-09-12 13:07 [PATCH 2/8] Pass all scan keys to BRIN consistent function at once Tomas Vondra <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox