agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v15 4/8] Row pattern recognition patch (planner).
496+ messages / 2 participants
[nested] [flat]

* [PATCH v15 4/8] Row pattern recognition patch (planner).
@ 2024-03-28 10:30 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Tatsuo Ishii @ 2024-03-28 10:30 UTC (permalink / raw)

---
 src/backend/optimizer/plan/createplan.c   | 24 +++++++++++++++-----
 src/backend/optimizer/plan/planner.c      |  3 +++
 src/backend/optimizer/plan/setrefs.c      | 27 ++++++++++++++++++++++-
 src/backend/optimizer/prep/prepjointree.c |  4 ++++
 src/include/nodes/plannodes.h             | 19 ++++++++++++++++
 5 files changed, 71 insertions(+), 6 deletions(-)

diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 5f479fc56c..fe51ad351e 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -287,9 +287,11 @@ static WindowAgg *make_windowagg(List *tlist, Index winref,
 								 int ordNumCols, AttrNumber *ordColIdx, Oid *ordOperators, Oid *ordCollations,
 								 int frameOptions, Node *startOffset, Node *endOffset,
 								 Oid startInRangeFunc, Oid endInRangeFunc,
-								 Oid inRangeColl, bool inRangeAsc, bool inRangeNullsFirst,
-								 List *runCondition, List *qual, bool topWindow,
-								 Plan *lefttree);
+								 Oid inRangeColl, bool inRangeAsc, bool inRangeNullsFirst, List *runCondition,
+								 RPSkipTo rpSkipTo, List *patternVariable, List *patternRegexp,
+								 List *defineClause,
+								 List *defineInitial,
+								 List *qual, bool topWindow, Plan *lefttree);
 static Group *make_group(List *tlist, List *qual, int numGroupCols,
 						 AttrNumber *grpColIdx, Oid *grpOperators, Oid *grpCollations,
 						 Plan *lefttree);
@@ -2699,6 +2701,11 @@ create_windowagg_plan(PlannerInfo *root, WindowAggPath *best_path)
 						  wc->inRangeAsc,
 						  wc->inRangeNullsFirst,
 						  wc->runCondition,
+						  wc->rpSkipTo,
+						  wc->patternVariable,
+						  wc->patternRegexp,
+						  wc->defineClause,
+						  wc->defineInitial,
 						  best_path->qual,
 						  best_path->topwindow,
 						  subplan);
@@ -6627,8 +6634,10 @@ make_windowagg(List *tlist, Index winref,
 			   int ordNumCols, AttrNumber *ordColIdx, Oid *ordOperators, Oid *ordCollations,
 			   int frameOptions, Node *startOffset, Node *endOffset,
 			   Oid startInRangeFunc, Oid endInRangeFunc,
-			   Oid inRangeColl, bool inRangeAsc, bool inRangeNullsFirst,
-			   List *runCondition, List *qual, bool topWindow, Plan *lefttree)
+			   Oid inRangeColl, bool inRangeAsc, bool inRangeNullsFirst, List *runCondition,
+			   RPSkipTo rpSkipTo, List *patternVariable, List *patternRegexp, List *defineClause,
+			   List *defineInitial,
+			   List *qual, bool topWindow, Plan *lefttree)
 {
 	WindowAgg  *node = makeNode(WindowAgg);
 	Plan	   *plan = &node->plan;
@@ -6654,6 +6663,11 @@ make_windowagg(List *tlist, Index winref,
 	node->inRangeAsc = inRangeAsc;
 	node->inRangeNullsFirst = inRangeNullsFirst;
 	node->topWindow = topWindow;
+	node->rpSkipTo = rpSkipTo,
+		node->patternVariable = patternVariable;
+	node->patternRegexp = patternRegexp;
+	node->defineClause = defineClause;
+	node->defineInitial = defineInitial;
 
 	plan->targetlist = tlist;
 	plan->lefttree = lefttree;
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index 38d070fa00..82c370c4b4 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -869,6 +869,9 @@ subquery_planner(PlannerGlobal *glob, Query *parse,
 		wc->runCondition = (List *) preprocess_expression(root,
 														  (Node *) wc->runCondition,
 														  EXPRKIND_TARGET);
+		wc->defineClause = (List *) preprocess_expression(root,
+														  (Node *) wc->defineClause,
+														  EXPRKIND_TARGET);
 	}
 
 	parse->limitOffset = preprocess_expression(root, parse->limitOffset,
diff --git a/src/backend/optimizer/plan/setrefs.c b/src/backend/optimizer/plan/setrefs.c
index 42603dbc7c..f7abb2be96 100644
--- a/src/backend/optimizer/plan/setrefs.c
+++ b/src/backend/optimizer/plan/setrefs.c
@@ -210,7 +210,6 @@ static List *set_windowagg_runcondition_references(PlannerInfo *root,
 												   List *runcondition,
 												   Plan *plan);
 
-
 /*****************************************************************************
  *
  *		SUBPLAN REFERENCES
@@ -2455,6 +2454,32 @@ set_upper_references(PlannerInfo *root, Plan *plan, int rtoffset)
 					   NRM_EQUAL,
 					   NUM_EXEC_QUAL(plan));
 
+	/*
+	 * Modifies an expression tree in each DEFINE clause so that all Var
+	 * nodes's varno refers to OUTER_VAR.
+	 */
+	if (IsA(plan, WindowAgg))
+	{
+		WindowAgg  *wplan = (WindowAgg *) plan;
+
+		if (wplan->defineClause != NIL)
+		{
+			foreach(l, wplan->defineClause)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(l);
+
+				tle->expr = (Expr *)
+					fix_upper_expr(root,
+								   (Node *) tle->expr,
+								   subplan_itlist,
+								   OUTER_VAR,
+								   rtoffset,
+								   NRM_EQUAL,
+								   NUM_EXEC_QUAL(plan));
+			}
+		}
+	}
+
 	pfree(subplan_itlist);
 }
 
diff --git a/src/backend/optimizer/prep/prepjointree.c b/src/backend/optimizer/prep/prepjointree.c
index 300691cc4d..3220072a51 100644
--- a/src/backend/optimizer/prep/prepjointree.c
+++ b/src/backend/optimizer/prep/prepjointree.c
@@ -2147,6 +2147,10 @@ perform_pullup_replace_vars(PlannerInfo *root,
 		if (wc->runCondition != NIL)
 			wc->runCondition = (List *)
 				pullup_replace_vars((Node *) wc->runCondition, rvcontext);
+
+		if (wc->defineClause != NIL)
+			wc->defineClause = (List *)
+				pullup_replace_vars((Node *) wc->defineClause, rvcontext);
 	}
 	if (parse->onConflict)
 	{
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index 7f3db5105d..b0e50ae886 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -20,6 +20,7 @@
 #include "lib/stringinfo.h"
 #include "nodes/bitmapset.h"
 #include "nodes/lockoptions.h"
+#include "nodes/parsenodes.h"
 #include "nodes/primnodes.h"
 
 
@@ -1096,6 +1097,24 @@ typedef struct WindowAgg
 	/* nulls sort first for in_range tests? */
 	bool		inRangeNullsFirst;
 
+	/* Row Pattern Recognition AFTER MACH SKIP clause */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+
+	/* Row Pattern PATTERN variable name (list of String) */
+	List	   *patternVariable;
+
+	/*
+	 * Row Pattern RPATTERN regular expression quantifier ('+' or ''. list of
+	 * String)
+	 */
+	List	   *patternRegexp;
+
+	/* Row Pattern DEFINE clause (list of TargetEntry) */
+	List	   *defineClause;
+
+	/* Row Pattern DEFINE variable initial names (list of String) */
+	List	   *defineInitial;
+
 	/*
 	 * false for all apart from the WindowAgg that's closest to the root of
 	 * the plan
-- 
2.25.1


----Next_Part(Thu_Mar_28_19_59_25_2024_076)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v15-0005-Row-pattern-recognition-patch-executor.patch"



^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--





^ permalink  raw  reply  [nested|flat] 496+ messages in thread

* [PATCH] Restructure repack worker teardown
@ 2026-05-18 17:13 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw)

The original code would leave a shared memory segment unreleased if we
fail partway through initialization.  Change the shutdown order so that
we already free it.

Author: Álvaro Herrera <[email protected]>
Discussion: https://postgr.es/m/[email protected]
---
 src/backend/commands/repack.c | 67 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 36 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index bfc62c8f752..c9064d8fd13 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid)
 	shm_mq_handle *mqh;
 	BackgroundWorker bgw;
 
+	decoding_worker = palloc0_object(DecodingWorker);
+
 	/* Setup shared memory. */
 	size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) +
 		BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE);
 	seg = dsm_create(size, 0);
+	decoding_worker->seg = seg;
+
 	shared = (DecodingWorkerShared *) dsm_segment_address(seg);
 	shared->initialized = false;
 	shared->lsn_upto = InvalidXLogRecPtr;
@@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid)
 	bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg));
 	bgw.bgw_notify_pid = MyProcPid;
 
-	decoding_worker = palloc0_object(DecodingWorker);
 	if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle))
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
 				errhint("You might need to increase \"%s\".", "max_worker_processes"));
 
-	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
 
 	/*
@@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid)
 	ConditionVariableCancelSleep();
 }
 
-/*
- * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker.
- * This ensures the worker is terminated on both ERROR and FATAL exits,
- * unlike PG_FINALLY which only handles ERROR.
- */
-static void
-repack_decoding_worker_cleanup_cb(int code, Datum arg)
-{
-	stop_repack_decoding_worker();
-}
-
 /*
  * Stop the decoding worker and cleanup the related resources.
  *
@@ -3508,39 +3499,43 @@ static void
 stop_repack_decoding_worker(void)
 {
 	BgwHandleStatus status;
+	dsm_segment	   *dsmseg;
 
-	/* Haven't reached the worker startup? */
+	/* Nothing to do if no worker was set up. */
 	if (decoding_worker == NULL)
 		return;
 
-	/* Could not register the worker? */
-	if (decoding_worker->handle == NULL)
-		return;
+	/* Terminate the worker process, if one is running. */
+	if (decoding_worker->handle != NULL)
+	{
+		TerminateBackgroundWorker(decoding_worker->handle);
+		/* The worker should really exit before the REPACK command does. */
+		HOLD_INTERRUPTS();
+		status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
+		RESUME_INTERRUPTS();
 
-	TerminateBackgroundWorker(decoding_worker->handle);
-	/* The worker should really exit before the REPACK command does. */
-	HOLD_INTERRUPTS();
-	status = WaitForBackgroundWorkerShutdown(decoding_worker->handle);
-	RESUME_INTERRUPTS();
-
-	if (status == BGWH_POSTMASTER_DIED)
-		ereport(FATAL,
-				errcode(ERRCODE_ADMIN_SHUTDOWN),
-				errmsg("postmaster exited during REPACK command"));
-
-	shm_mq_detach(decoding_worker->error_mqh);
+		if (status == BGWH_POSTMASTER_DIED)
+			ereport(FATAL,
+					errcode(ERRCODE_ADMIN_SHUTDOWN),
+					errmsg("postmaster exited during REPACK command"));
+	}
 
 	/*
-	 * If we could not cancel the current sleep due to ERROR, do that before
-	 * we detach from the shared memory the condition variable is located in.
-	 * If we did not, the bgworker ERROR handling code would try and fail
-	 * badly.
+	 * Now detach from our shared memory segment.  In error cases there might
+	 * still be messages from the worker in the queue, which ProcessInterrupts
+	 * would try to read; this is pointless (and causes an assertion failure),
+	 * so set the global pointer to NULL to have ProcessRepackMessages ignore
+	 * them.
 	 */
-	ConditionVariableCancelSleep();
-
-	dsm_detach(decoding_worker->seg);
+	dsmseg = decoding_worker->seg;
 	pfree(decoding_worker);
 	decoding_worker = NULL;
+
+	/* We must also cancel the current sleep, if one is still set up */
+	ConditionVariableCancelSleep();
+
+	if (dsmseg != NULL)
+		dsm_detach(dsmseg);
 }
 
 /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */
-- 
2.47.3


--b42ct6adeyjj4cbm--






^ permalink  raw  reply  [nested|flat] 496+ messages in thread