agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v35 2/5] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY).
496+ messages / 2 participants
[nested] [flat]

* [PATCH v35 2/5] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY).
@ 2026-02-16 19:49  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 496+ messages in thread

From: Antonin Houska @ 2026-02-16 19:49 UTC (permalink / raw)

This patch moves the code to index_create_copy() and adds a "concurrently"
parameter so it can be used by REPACK (CONCURRENTLY).

With the CONCURRENTLY option, REPACK cannot simply swap the heap file and
rebuild its indexes. Instead, it needs to build a separate set of indexes
(including system catalog entries) *before* the actual swap, to reduce the
time AccessExclusiveLock needs to be held for.
---
 src/backend/catalog/index.c      | 54 +++++++++++++++++++++++---------
 src/backend/commands/indexcmds.c |  6 ++--
 src/backend/nodes/makefuncs.c    |  9 +++---
 src/include/catalog/index.h      |  3 ++
 src/include/nodes/makefuncs.h    |  4 ++-
 5 files changed, 54 insertions(+), 22 deletions(-)

diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index 5ee6389d39c..f8e6c3d804e 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -1288,15 +1288,32 @@ index_create(Relation heapRelation,
 /*
  * index_concurrently_create_copy
  *
- * Create concurrently an index based on the definition of the one provided by
- * caller.  The index is inserted into catalogs and needs to be built later
- * on.  This is called during concurrent reindex processing.
- *
- * "tablespaceOid" is the tablespace to use for this index.
+ * Variant of index_create_copy(), called during concurrent reindex
+ * processing.
  */
 Oid
 index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							   Oid tablespaceOid, const char *newName)
+{
+	return index_create_copy(heapRelation, oldIndexId, tablespaceOid, newName,
+							 true);
+}
+
+/*
+ * index_create_copy
+ *
+ * Create an index based on the definition of the one provided by caller.  The
+ * index is inserted into catalogs. If 'concurrently' is TRUE, it needs to be
+ * built later on, otherwise it's built immediately.
+ *
+ * "tablespaceOid" is the tablespace to use for this index.
+ *
+ * The actual implementation of index_concurrently_create_copy(), reusable for
+ * other purposes.
+ */
+Oid
+index_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid,
+				  const char *newName, bool concurrently)
 {
 	Relation	indexRelation;
 	IndexInfo  *oldInfo,
@@ -1315,6 +1332,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	List	   *indexColNames = NIL;
 	List	   *indexExprs = NIL;
 	List	   *indexPreds = NIL;
+	int			flags = 0;
 
 	indexRelation = index_open(oldIndexId, RowExclusiveLock);
 
@@ -1325,7 +1343,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	 * Concurrent build of an index with exclusion constraints is not
 	 * supported.
 	 */
-	if (oldInfo->ii_ExclusionOps != NULL)
+	if (oldInfo->ii_ExclusionOps != NULL && concurrently)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("concurrent index creation for exclusion constraints is not supported")));
@@ -1381,9 +1399,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	}
 
 	/*
-	 * Build the index information for the new index.  Note that rebuild of
-	 * indexes with exclusion constraints is not supported, hence there is no
-	 * need to fill all the ii_Exclusion* fields.
+	 * Build the index information for the new index.
 	 */
 	newInfo = makeIndexInfo(oldInfo->ii_NumIndexAttrs,
 							oldInfo->ii_NumIndexKeyAttrs,
@@ -1392,10 +1408,13 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							indexPreds,
 							oldInfo->ii_Unique,
 							oldInfo->ii_NullsNotDistinct,
-							false,	/* not ready for inserts */
-							true,
+							!concurrently,	/* isready */
+							concurrently,	/* concurrent */
 							indexRelation->rd_indam->amsummarizing,
-							oldInfo->ii_WithoutOverlaps);
+							oldInfo->ii_WithoutOverlaps,
+							oldInfo->ii_ExclusionOps,
+							oldInfo->ii_ExclusionProcs,
+							oldInfo->ii_ExclusionStrats);
 
 	/*
 	 * Extract the list of column names and the column numbers for the new
@@ -1433,6 +1452,9 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 		stattargets[i].isnull = isnull;
 	}
 
+	if (concurrently)
+		flags = INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT;
+
 	/*
 	 * Now create the new index.
 	 *
@@ -1456,7 +1478,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							  indcoloptions->values,
 							  stattargets,
 							  reloptionsDatum,
-							  INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT,
+							  flags,
 							  0,
 							  true, /* allow table to be a system catalog? */
 							  false,	/* is_internal? */
@@ -2450,7 +2472,8 @@ BuildIndexInfo(Relation index)
 					   indexStruct->indisready,
 					   false,
 					   index->rd_indam->amsummarizing,
-					   indexStruct->indisexclusion && indexStruct->indisunique);
+					   indexStruct->indisexclusion && indexStruct->indisunique,
+					   NULL, NULL, NULL);
 
 	/* fill in attribute numbers */
 	for (i = 0; i < numAtts; i++)
@@ -2510,7 +2533,8 @@ BuildDummyIndexInfo(Relation index)
 					   indexStruct->indisready,
 					   false,
 					   index->rd_indam->amsummarizing,
-					   indexStruct->indisexclusion && indexStruct->indisunique);
+					   indexStruct->indisexclusion && indexStruct->indisunique,
+					   NULL, NULL, NULL);
 
 	/* fill in attribute numbers */
 	for (i = 0; i < numAtts; i++)
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index 635679cc1f2..34209bd1393 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -243,7 +243,8 @@ CheckIndexCompatible(Oid oldId,
 	 */
 	indexInfo = makeIndexInfo(numberOfAttributes, numberOfAttributes,
 							  accessMethodId, NIL, NIL, false, false,
-							  false, false, amsummarizing, isWithoutOverlaps);
+							  false, false, amsummarizing, isWithoutOverlaps,
+							  NULL, NULL, NULL);
 	typeIds = palloc_array(Oid, numberOfAttributes);
 	collationIds = palloc_array(Oid, numberOfAttributes);
 	opclassIds = palloc_array(Oid, numberOfAttributes);
@@ -930,7 +931,8 @@ DefineIndex(ParseState *pstate,
 							  !concurrent,
 							  concurrent,
 							  amissummarizing,
-							  stmt->iswithoutoverlaps);
+							  stmt->iswithoutoverlaps,
+							  NULL, NULL, NULL);
 
 	typeIds = palloc_array(Oid, numberOfAttributes);
 	collationIds = palloc_array(Oid, numberOfAttributes);
diff --git a/src/backend/nodes/makefuncs.c b/src/backend/nodes/makefuncs.c
index 2caec621d73..ca7e21e8349 100644
--- a/src/backend/nodes/makefuncs.c
+++ b/src/backend/nodes/makefuncs.c
@@ -834,7 +834,8 @@ IndexInfo *
 makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
 			  List *predicates, bool unique, bool nulls_not_distinct,
 			  bool isready, bool concurrent, bool summarizing,
-			  bool withoutoverlaps)
+			  bool withoutoverlaps, Oid *exclusion_ops, Oid *exclusion_procs,
+			  uint16 *exclusion_strats)
 {
 	IndexInfo  *n = makeNode(IndexInfo);
 
@@ -863,9 +864,9 @@ makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
 	n->ii_PredicateState = NULL;
 
 	/* exclusion constraints */
-	n->ii_ExclusionOps = NULL;
-	n->ii_ExclusionProcs = NULL;
-	n->ii_ExclusionStrats = NULL;
+	n->ii_ExclusionOps = exclusion_ops;
+	n->ii_ExclusionProcs = exclusion_procs;
+	n->ii_ExclusionStrats = exclusion_strats;
 
 	/* speculative inserts */
 	n->ii_UniqueOps = NULL;
diff --git a/src/include/catalog/index.h b/src/include/catalog/index.h
index b259c4141ed..3426087b445 100644
--- a/src/include/catalog/index.h
+++ b/src/include/catalog/index.h
@@ -99,6 +99,9 @@ extern Oid	index_concurrently_create_copy(Relation heapRelation,
 										   Oid oldIndexId,
 										   Oid tablespaceOid,
 										   const char *newName);
+extern Oid	index_create_copy(Relation heapRelation, Oid oldIndexId,
+							  Oid tablespaceOid, const char *newName,
+							  bool concurrently);
 
 extern void index_concurrently_build(Oid heapRelationId,
 									 Oid indexRelationId);
diff --git a/src/include/nodes/makefuncs.h b/src/include/nodes/makefuncs.h
index 982ec25ae14..dcea148ae1a 100644
--- a/src/include/nodes/makefuncs.h
+++ b/src/include/nodes/makefuncs.h
@@ -99,7 +99,9 @@ extern IndexInfo *makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid,
 								List *expressions, List *predicates,
 								bool unique, bool nulls_not_distinct,
 								bool isready, bool concurrent,
-								bool summarizing, bool withoutoverlaps);
+								bool summarizing, bool withoutoverlaps,
+								Oid *exclusion_ops, Oid *exclusion_procs,
+								uint16 *exclusion_strats);
 
 extern Node *makeStringConst(char *str, int location);
 extern DefElem *makeDefElem(char *name, Node *arg, int location);
-- 
2.47.3


--kmtyk4ln3767qrma
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v35-0003-Move-conversion-of-a-historic-to-MVCC-snapshot-t.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