agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v53 7/7] Reserve replication slots specifically for REPACK
534+ messages / 2 participants
[nested] [flat]

* [PATCH v53 7/7] Reserve replication slots specifically for REPACK
@ 2026-04-01 17:54  Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Álvaro Herrera @ 2026-04-01 17:54 UTC (permalink / raw)

This allows REPACK to not interfere with other operations that use
replication slots.  This eases configurability.
---
 doc/src/sgml/config.sgml                      | 16 ++++
 doc/src/sgml/ref/repack.sgml                  |  6 +-
 src/backend/commands/repack.c                 |  2 +-
 src/backend/commands/repack_worker.c          |  7 +-
 src/backend/replication/logical/launcher.c    |  2 +-
 src/backend/replication/logical/logical.c     |  8 +-
 .../replication/logical/logicalfuncs.c        |  2 +-
 src/backend/replication/logical/slotsync.c    |  5 +-
 src/backend/replication/slot.c                | 86 ++++++++++++-------
 src/backend/replication/slotfuncs.c           | 19 ++--
 src/backend/replication/walsender.c           |  9 +-
 src/backend/utils/misc/guc_parameters.dat     |  8 ++
 src/backend/utils/misc/postgresql.conf.sample |  2 +
 src/include/replication/logical.h             |  3 +-
 src/include/replication/slot.h                |  5 +-
 15 files changed, 117 insertions(+), 63 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index d3fea738ca3..a90d163e416 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4638,6 +4638,22 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"'  # Windows
        </listitem>
       </varlistentry>
 
+      <varlistentry id="guc-max-repack-replication-slots" xreflabel="max_repack_replication_slots">
+       <term><varname>max_repack_replication_slots</varname> (<type>integer</type>)
+       <indexterm>
+        <primary><varname>max_repack_replication_slots</varname> configuration parameter</primary>
+       </indexterm>
+       </term>
+       <listitem>
+        <para>
+         Specifies the maximum number of replication slots for use of
+         the <command>REPACK</command> command.  The default is 5.
+         This parameter can only be set at server start.
+        </para>
+       </listitem>
+      </varlistentry>
+
+
       <varlistentry id="guc-max-replication-slots" xreflabel="max_replication_slots">
        <term><varname>max_replication_slots</varname> (<type>integer</type>)
        <indexterm>
diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml
index e993dfb3108..c532a39ee07 100644
--- a/doc/src/sgml/ref/repack.sgml
+++ b/doc/src/sgml/ref/repack.sgml
@@ -293,9 +293,9 @@ REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] USING
 
        <listitem>
         <para>
-         The <link linkend="guc-max-replication-slots"><varname>max_replication_slots</varname></link>
-         configuration parameter does not allow for creation of an additional
-         replication slot.
+         The <link linkend="guc-max-repack-replication-slots"><varname>max_repack_replication_slots</varname></link>
+         configuration parameter does not allow for the creation of an
+         additional replication slot.
         </para>
        </listitem>
       </itemizedlist>
diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 92759f33969..6ba86384312 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -3381,7 +3381,7 @@ start_repack_decoding_worker(Oid relid)
 		ereport(ERROR,
 				errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				errmsg("out of background worker slots"),
-				errhint("You might need to increase \"%s\".", "max_worker_processes"));
+				errhint("You might need to increase \"%s\".", "max_repack_replication_slots"));
 
 	decoding_worker->seg = seg;
 	decoding_worker->error_mqh = mqh;
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..39cbb0252f4 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -223,7 +223,7 @@ repack_setup_logical_decoding(Oid relid)
 	 * Make sure we can use logical decoding.
 	 */
 	CheckSlotPermissions();
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(true);
 
 	/*
 	 * A single backend should not execute multiple REPACK commands at a time,
@@ -232,8 +232,8 @@ repack_setup_logical_decoding(Oid relid)
 	 * RS_TEMPORARY so that the slot gets cleaned up on ERROR.
 	 */
 	snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid);
-	ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false,
-						  false);
+	ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, true,
+						  false, false);
 
 	EnsureLogicalDecodingEnabled();
 
@@ -244,6 +244,7 @@ repack_setup_logical_decoding(Oid relid)
 	ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME,
 									NIL,
 									true,
+									true,
 									InvalidXLogRecPtr,
 									XL_ROUTINE(.page_read = read_local_xlog_page,
 											   .segment_open = wal_segment_open,
diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c
index 09964198550..d83125afd0d 100644
--- a/src/backend/replication/logical/launcher.c
+++ b/src/backend/replication/logical/launcher.c
@@ -1575,7 +1575,7 @@ CreateConflictDetectionSlot(void)
 			errmsg("creating replication conflict detection slot"));
 
 	ReplicationSlotCreate(CONFLICT_DETECTION_SLOT, false, RS_PERSISTENT, false,
-						  false, false);
+						  false, false, false);
 
 	init_conflict_slot_xmin();
 }
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index dc46a372ead..06efcaa60b2 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi
  * decoding.
  */
 void
-CheckLogicalDecodingRequirements(void)
+CheckLogicalDecodingRequirements(bool repack)
 {
-	CheckSlotRequirements();
+	CheckSlotRequirements(repack);
 
 	/*
 	 * NB: Adding a new requirement likely means that RestoreSlotFromDisk()
@@ -308,6 +308,7 @@ StartupDecodingContext(List *output_plugin_options,
  * output_plugin_options -- contains options passed to the output plugin
  * need_full_snapshot -- if true, must obtain a snapshot able to read all
  *		tables; if false, one that can read only catalogs is acceptable.
+ * for_repack -- if true, we're going to be decoding for REPACK.
  * restart_lsn -- if given as invalid, it's this routine's responsibility to
  *		mark WAL as reserved by setting a convenient restart_lsn for the slot.
  *		Otherwise, we set for decoding to start from the given LSN without
@@ -328,6 +329,7 @@ LogicalDecodingContext *
 CreateInitDecodingContext(const char *plugin,
 						  List *output_plugin_options,
 						  bool need_full_snapshot,
+						  bool for_repack,
 						  XLogRecPtr restart_lsn,
 						  XLogReaderRoutine *xl_routine,
 						  LogicalOutputPluginWriterPrepareWrite prepare_write,
@@ -344,7 +346,7 @@ CreateInitDecodingContext(const char *plugin,
 	 * On a standby, this check is also required while creating the slot.
 	 * Check the comments in the function.
 	 */
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(for_repack);
 
 	/* shorter lines... */
 	slot = MyReplicationSlot;
diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c
index 9760818941d..512013b0ef0 100644
--- a/src/backend/replication/logical/logicalfuncs.c
+++ b/src/backend/replication/logical/logicalfuncs.c
@@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin
 
 	CheckSlotPermissions();
 
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	if (PG_ARGISNULL(0))
 		ereport(ERROR,
diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c
index e75db69e3f6..28c89c5e10d 100644
--- a/src/backend/replication/logical/slotsync.c
+++ b/src/backend/replication/logical/slotsync.c
@@ -425,7 +425,7 @@ get_local_synced_slots(void)
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
-	for (int i = 0; i < max_replication_slots; i++)
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
@@ -814,6 +814,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid,
 		 */
 		ReplicationSlotCreate(remote_slot->name, true, RS_TEMPORARY,
 							  remote_slot->two_phase,
+							  false,
 							  remote_slot->failover,
 							  true);
 
@@ -1691,7 +1692,7 @@ update_synced_slots_inactive_since(void)
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
-	for (int i = 0; i < max_replication_slots; i++)
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 9533515a63b..47679161b67 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -151,6 +151,8 @@ ReplicationSlot *MyReplicationSlot = NULL;
 /* GUC variables */
 int			max_replication_slots = 10; /* the maximum number of replication
 										 * slots */
+int			max_repack_replication_slots = 5;	/* the maximum number of slots
+												 * for REPACK */
 
 /*
  * Invalidate replication slots that have remained idle longer than this
@@ -188,14 +190,15 @@ static void SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel);
 Size
 ReplicationSlotsShmemSize(void)
 {
+	int			totalslots = max_replication_slots + max_repack_replication_slots;
 	Size		size = 0;
 
-	if (max_replication_slots == 0)
+	if (totalslots == 0)
 		return size;
 
 	size = offsetof(ReplicationSlotCtlData, replication_slots);
 	size = add_size(size,
-					mul_size(max_replication_slots, sizeof(ReplicationSlot)));
+					mul_size(totalslots, sizeof(ReplicationSlot)));
 
 	return size;
 }
@@ -208,7 +211,7 @@ ReplicationSlotsShmemInit(void)
 {
 	bool		found;
 
-	if (max_replication_slots == 0)
+	if (max_replication_slots + max_repack_replication_slots == 0)
 		return;
 
 	ReplicationSlotCtl = (ReplicationSlotCtlData *)
@@ -222,7 +225,7 @@ ReplicationSlotsShmemInit(void)
 		/* First time through, so initialize */
 		MemSet(ReplicationSlotCtl, 0, ReplicationSlotsShmemSize());
 
-		for (i = 0; i < max_replication_slots; i++)
+		for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 		{
 			ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[i];
 
@@ -372,6 +375,7 @@ IsSlotForConflictCheck(const char *name)
  * db_specific: logical decoding is db specific; if the slot is going to
  *	   be used for that pass true, otherwise false.
  * two_phase: If enabled, allows decoding of prepared transactions.
+ * repack: If true, use a slot from the pool for REPACK.
  * failover: If enabled, allows the slot to be synced to standbys so
  *     that logical replication can be resumed after failover.
  * synced: True if the slot is synchronized from the primary server.
@@ -379,10 +383,11 @@ IsSlotForConflictCheck(const char *name)
 void
 ReplicationSlotCreate(const char *name, bool db_specific,
 					  ReplicationSlotPersistency persistency,
-					  bool two_phase, bool failover, bool synced)
+					  bool two_phase, bool repack, bool failover, bool synced)
 {
 	ReplicationSlot *slot = NULL;
-	int			i;
+	int			startpoint,
+				endpoint;
 
 	Assert(MyReplicationSlot == NULL);
 
@@ -431,12 +436,16 @@ ReplicationSlotCreate(const char *name, bool db_specific,
 	LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE);
 
 	/*
-	 * Check for name collision, and identify an allocatable slot.  We need to
-	 * hold ReplicationSlotControlLock in shared mode for this, so that nobody
-	 * else can change the in_use flags while we're looking at them.
+	 * Check for name collision (across the whole array), and identify an
+	 * allocatable slot (in the array slice specific to our current use case:
+	 * either general, or REPACK only).  We need to hold
+	 * ReplicationSlotControlLock in shared mode for this, so that nobody else
+	 * can change the in_use flags while we're looking at them.
 	 */
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (i = 0; i < max_replication_slots; i++)
+	startpoint = !repack ? 0 : max_replication_slots;
+	endpoint = max_replication_slots + (repack ? max_repack_replication_slots : 0);
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
@@ -444,7 +453,9 @@ ReplicationSlotCreate(const char *name, bool db_specific,
 			ereport(ERROR,
 					(errcode(ERRCODE_DUPLICATE_OBJECT),
 					 errmsg("replication slot \"%s\" already exists", name)));
-		if (!s->in_use && slot == NULL)
+
+		if (i >= startpoint && i < endpoint &&
+			!s->in_use && slot == NULL)
 			slot = s;
 	}
 	LWLockRelease(ReplicationSlotControlLock);
@@ -454,7 +465,8 @@ ReplicationSlotCreate(const char *name, bool db_specific,
 		ereport(ERROR,
 				(errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED),
 				 errmsg("all replication slots are in use"),
-				 errhint("Free one or increase \"max_replication_slots\".")));
+				 errhint("Free one or increase \"%s\".",
+						 repack ? "max_repack_replication_slots" : "max_replication_slots")));
 
 	/*
 	 * Since this slot is not in use, nobody should be looking at any part of
@@ -547,7 +559,7 @@ SearchNamedReplicationSlot(const char *name, bool need_lock)
 	if (need_lock)
 		LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
@@ -575,7 +587,8 @@ int
 ReplicationSlotIndex(ReplicationSlot *slot)
 {
 	Assert(slot >= ReplicationSlotCtl->replication_slots &&
-		   slot < ReplicationSlotCtl->replication_slots + max_replication_slots);
+		   slot < ReplicationSlotCtl->replication_slots +
+		   (max_replication_slots + max_repack_replication_slots));
 
 	return slot - ReplicationSlotCtl->replication_slots;
 }
@@ -869,7 +882,7 @@ ReplicationSlotCleanup(bool synced_only)
 restart:
 	found_valid_logicalslot = false;
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
@@ -1251,7 +1264,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked)
 	if (!already_locked)
 		LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 		TransactionId effective_xmin;
@@ -1306,7 +1319,7 @@ ReplicationSlotsComputeRequiredLSN(void)
 	Assert(ReplicationSlotCtl != NULL);
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 		XLogRecPtr	restart_lsn;
@@ -1373,12 +1386,12 @@ ReplicationSlotsComputeLogicalRestartLSN(void)
 	XLogRecPtr	result = InvalidXLogRecPtr;
 	int			i;
 
-	if (max_replication_slots <= 0)
+	if (max_replication_slots + max_repack_replication_slots <= 0)
 		return InvalidXLogRecPtr;
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s;
 		XLogRecPtr	restart_lsn;
@@ -1453,11 +1466,11 @@ ReplicationSlotsCountDBSlots(Oid dboid, int *nslots, int *nactive)
 
 	*nslots = *nactive = 0;
 
-	if (max_replication_slots <= 0)
+	if (max_replication_slots + max_repack_replication_slots <= 0)
 		return false;
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s;
 
@@ -1514,13 +1527,13 @@ ReplicationSlotsDropDBSlots(Oid dboid)
 	bool		found_valid_logicalslot;
 	bool		dropped = false;
 
-	if (max_replication_slots <= 0)
+	if (max_replication_slots + max_repack_replication_slots <= 0)
 		return;
 
 restart:
 	found_valid_logicalslot = false;
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s;
 		char	   *slotname;
@@ -1617,11 +1630,11 @@ CheckLogicalSlotExists(void)
 {
 	bool		found = false;
 
-	if (max_replication_slots <= 0)
+	if (max_replication_slots + max_repack_replication_slots <= 0)
 		return false;
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (int i = 0; i < max_replication_slots; i++)
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s;
 		bool		invalidated;
@@ -1655,17 +1668,24 @@ CheckLogicalSlotExists(void)
  * slots.
  */
 void
-CheckSlotRequirements(void)
+CheckSlotRequirements(bool repack)
 {
 	/*
 	 * NB: Adding a new requirement likely means that RestoreSlotFromDisk()
 	 * needs the same check.
 	 */
 
-	if (max_replication_slots == 0)
+	if (!repack && max_replication_slots == 0)
 		ereport(ERROR,
-				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
-				 errmsg("replication slots can only be used if \"max_replication_slots\" > 0")));
+				errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				errmsg("replication slots can only be used if \"%s\" > 0",
+					   "max_replication_slots"));
+
+	if (repack && max_repack_replication_slots == 0)
+		ereport(ERROR,
+				errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				errmsg("REPACK can only be used if \"%s\" > 0",
+					   "max_repack_replication_slots"));
 
 	if (wal_level < WAL_LEVEL_REPLICA)
 		ereport(ERROR,
@@ -2216,7 +2236,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes,
 	Assert(!(possible_causes & RS_INVAL_WAL_REMOVED) || oldestSegno > 0);
 	Assert(possible_causes != RS_INVAL_NONE);
 
-	if (max_replication_slots == 0)
+	if (max_replication_slots == 0 && max_repack_replication_slots == 0)
 		return invalidated;
 
 	XLogSegNoOffsetToRecPtr(oldestSegno, 0, wal_segment_size, oldestLSN);
@@ -2224,7 +2244,7 @@ InvalidateObsoleteReplicationSlots(uint32 possible_causes,
 restart:
 	found_valid_logicalslot = false;
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (int i = 0; i < max_replication_slots; i++)
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 		bool		released_lock = false;
@@ -2329,7 +2349,7 @@ CheckPointReplicationSlots(bool is_shutdown)
 	 */
 	LWLockAcquire(ReplicationSlotAllocationLock, LW_SHARED);
 
-	for (i = 0; i < max_replication_slots; i++)
+	for (i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 		char		path[MAXPGPATH];
@@ -2430,7 +2450,7 @@ StartupReplicationSlots(void)
 	FreeDir(replication_dir);
 
 	/* currently no slots exist, we're done. */
-	if (max_replication_slots <= 0)
+	if (max_replication_slots + max_repack_replication_slots <= 0)
 		return;
 
 	/* Now that we have recovered all the data, compute replication xmin */
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index 9f5e4f998fe..16fbd383735 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -53,7 +53,7 @@ create_physical_replication_slot(char *name, bool immediately_reserve,
 	/* acquire replication slot, this will check for conflicting names */
 	ReplicationSlotCreate(name, false,
 						  temporary ? RS_TEMPORARY : RS_PERSISTENT, false,
-						  false, false);
+						  false, false, false);
 
 	if (immediately_reserve)
 	{
@@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckSlotRequirements();
+	CheckSlotRequirements(false);
 
 	create_physical_replication_slot(NameStr(*name),
 									 immediately_reserve,
@@ -146,7 +146,7 @@ create_logical_replication_slot(char *name, char *plugin,
 	 */
 	ReplicationSlotCreate(name, true,
 						  temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase,
-						  failover, false);
+						  false, failover, false);
 
 	/*
 	 * Ensure the logical decoding is enabled before initializing the logical
@@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin,
 	 */
 	ctx = CreateInitDecodingContext(plugin, NIL,
 									false,	/* just catalogs is OK */
+									false,	/* not repack */
 									restart_lsn,
 									XL_ROUTINE(.page_read = read_local_xlog_page,
 											   .segment_open = wal_segment_open,
@@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	create_logical_replication_slot(NameStr(*name),
 									NameStr(*plugin),
@@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckSlotRequirements();
+	CheckSlotRequirements(false);
 
 	ReplicationSlotDrop(NameStr(*name), true);
 
@@ -270,7 +271,7 @@ pg_get_replication_slots(PG_FUNCTION_ARGS)
 	currlsn = GetXLogWriteRecPtr();
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
-	for (slotno = 0; slotno < max_replication_slots; slotno++)
+	for (slotno = 0; slotno < max_replication_slots + max_repack_replication_slots; slotno++)
 	{
 		ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno];
 		ReplicationSlot slot_contents;
@@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
 	CheckSlotPermissions();
 
 	if (logical_slot)
-		CheckLogicalDecodingRequirements();
+		CheckLogicalDecodingRequirements(false);
 	else
-		CheckSlotRequirements();
+		CheckSlotRequirements(false);
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
@@ -665,7 +666,7 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
 	 * managed to create the new slot, we advance the new slot's restart_lsn
 	 * to the source slot's updated restart_lsn the second time we lock it.
 	 */
-	for (int i = 0; i < max_replication_slots; i++)
+	for (int i = 0; i < max_replication_slots + max_repack_replication_slots; i++)
 	{
 		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];
 
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2bb3f34dc6d..9d7d675fa96 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1220,7 +1220,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 	{
 		ReplicationSlotCreate(cmd->slotname, false,
 							  cmd->temporary ? RS_TEMPORARY : RS_PERSISTENT,
-							  false, false, false);
+							  false, false, false, false);
 
 		if (reserve_wal)
 		{
@@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 
 		Assert(cmd->kind == REPLICATION_KIND_LOGICAL);
 
-		CheckLogicalDecodingRequirements();
+		CheckLogicalDecodingRequirements(false);
 
 		/*
 		 * Initially create persistent slot as ephemeral - that allows us to
@@ -1251,7 +1251,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 		 */
 		ReplicationSlotCreate(cmd->slotname, true,
 							  cmd->temporary ? RS_TEMPORARY : RS_EPHEMERAL,
-							  two_phase, failover, false);
+							  two_phase, false, failover, false);
 
 		/*
 		 * Do options check early so that we can bail before calling the
@@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 		Assert(IsLogicalDecodingEnabled());
 
 		ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot,
+										false,
 										InvalidXLogRecPtr,
 										XL_ROUTINE(.page_read = logical_read_xlog_page,
 												   .segment_open = WalSndSegmentOpen,
@@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd)
 	QueryCompletion qc;
 
 	/* make sure that our requirements are still fulfilled */
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	Assert(!MyReplicationSlot);
 
diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat
index a315c4ab8ab..bf82b8f6048 100644
--- a/src/backend/utils/misc/guc_parameters.dat
+++ b/src/backend/utils/misc/guc_parameters.dat
@@ -2071,6 +2071,14 @@
   max => 'MAX_BACKENDS',
 },
 
+{ name => 'max_repack_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING',
+  short_desc => 'Sets the maximum number of replication slots for use by REPACK.',
+  variable => 'max_repack_replication_slots',
+  boot_val => '5',
+  min => '0',
+  max => 'MAX_BACKENDS',
+},
+
 /* see max_wal_senders */
 { name => 'max_replication_slots', type => 'int', context => 'PGC_POSTMASTER', group => 'REPLICATION_SENDING',
   short_desc => 'Sets the maximum number of simultaneously defined replication slots.',
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 6d0337853e0..fb75990609e 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -348,6 +348,8 @@
                                 # (change requires restart)
 #max_replication_slots = 10     # max number of replication slots
                                 # (change requires restart)
+#max_repack_replication_slots = 5 # max number of replication slots for REPACK
+                                # (change requires restart)
 #wal_keep_size = 0              # in megabytes; 0 disables
 #max_slot_wal_keep_size = -1    # in megabytes; -1 disables
 #idle_replication_slot_timeout = 0      # in seconds; 0 disables
diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h
index bc9d4ece672..bc075b16741 100644
--- a/src/include/replication/logical.h
+++ b/src/include/replication/logical.h
@@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext
 } LogicalDecodingContext;
 
 
-extern void CheckLogicalDecodingRequirements(void);
+extern void CheckLogicalDecodingRequirements(bool repack);
 
 extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin,
 														 List *output_plugin_options,
 														 bool need_full_snapshot,
+														 bool for_repack,
 														 XLogRecPtr restart_lsn,
 														 XLogReaderRoutine *xl_routine,
 														 LogicalOutputPluginWriterPrepareWrite prepare_write,
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index 4b4709f6e2c..489af7d8d6c 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -324,6 +324,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot;
 
 /* GUCs */
 extern PGDLLIMPORT int max_replication_slots;
+extern PGDLLIMPORT int max_repack_replication_slots;
 extern PGDLLIMPORT char *synchronized_standby_slots;
 extern PGDLLIMPORT int idle_replication_slot_timeout_secs;
 
@@ -334,7 +335,7 @@ extern void ReplicationSlotsShmemInit(void);
 /* management of individual slots */
 extern void ReplicationSlotCreate(const char *name, bool db_specific,
 								  ReplicationSlotPersistency persistency,
-								  bool two_phase, bool failover,
+								  bool two_phase, bool repack, bool failover,
 								  bool synced);
 extern void ReplicationSlotPersist(void);
 extern void ReplicationSlotDrop(const char *name, bool nowait);
@@ -377,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname
 extern void StartupReplicationSlots(void);
 extern void CheckPointReplicationSlots(bool is_shutdown);
 
-extern void CheckSlotRequirements(void);
+extern void CheckSlotRequirements(bool repack);
 extern void CheckSlotPermissions(void);
 extern ReplicationSlotInvalidationCause
 			GetSlotInvalidationCause(const char *cause_name);
-- 
2.47.3


--qr3jlalmmcpkiodg--





^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 534+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This is for ChangeContext to handle insertions into two relations: besides the
new relation (whose file will eventually be used by the REPACKed relation), an
"auxiliary relation" is needed sometimes, in order to get the data sorted. The
concept is introduced and explained later in the patch series.
---
 src/backend/commands/repack.c    | 221 ++++++++++++++++---------------
 src/include/commands/repack.h    |  48 +++++++
 src/tools/pgindent/typedefs.list |   1 +
 3 files changed, 160 insertions(+), 110 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index fa98b8b9247..04d39ad8c86 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -93,40 +93,6 @@ typedef struct
 	Oid			indexOid;
 } RelToCluster;
 
-/*
- * The first file exported by the decoding worker must contain a snapshot, the
- * following ones contain the data changes.
- */
-#define WORKER_FILE_SNAPSHOT	0
-
-/*
- * Information needed to apply concurrent data changes.
- */
-typedef struct ChangeContext
-{
-	/* The relation the changes are applied to. */
-	Relation	cc_rel;
-
-	/* Needed to update indexes of cc_rel. */
-	ResultRelInfo *cc_rri;
-	EState	   *cc_estate;
-
-	/*
-	 * Existing tuples to UPDATE and DELETE are located via this index. We
-	 * keep the scankey in partially initialized state to avoid repeated work.
-	 * sk_argument is completed on the fly.
-	 */
-	Relation	cc_ident_index;
-	ScanKey		cc_ident_key;
-	int			cc_ident_key_nentries;
-
-	/* The latest column we need to deform to have the tuple identity */
-	AttrNumber	cc_last_key_attno;
-
-	/* Sequential number of the file containing the changes. */
-	int			cc_file_seq;
-} ChangeContext;
-
 /*
  * Backend-local information to control the decoding worker.
  */
@@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd,
 static bool repack_is_permitted_for_relation(RepackCommand cmd,
 											 Oid relid, Oid userid);
 
-static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt);
-static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-									ChangeContext *chgcxt);
-static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-									TupleTableSlot *ondisk_tuple,
-									ChangeContext *chgcxt);
+static void apply_concurrent_changes(ChangeContext *chgcxt);
+static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot);
+static void apply_concurrent_update(RepackDest *dest,
+									TupleTableSlot *spilled_tuple,
+									TupleTableSlot *ondisk_tuple);
 static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot);
 static void restore_tuple(BufFile *file, Relation relation,
 						  TupleTableSlot *slot);
 static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest,
 								  TupleTableSlot *src);
-static bool find_target_tuple(Relation rel, ChangeContext *chgcxt,
-							  TupleTableSlot *locator,
+static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 							  TupleTableSlot *retrieved);
-static bool identity_key_equal(ChangeContext *chgcxt,
-							   TupleTableSlot *locator,
+static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 							   TupleTableSlot *candidate);
 static void process_concurrent_changes(XLogRecPtr end_of_wal,
 									   ChangeContext *chgcxt,
@@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt,
 									  Relation relation,
 									  Oid ident_index_id);
 static void release_change_context(ChangeContext *chgcxt);
+static void initialize_change_dest(RepackDest *dest, Relation relation,
+								   Oid ident_index_id);
+static void release_change_dest(RepackDest *dest);
 static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 											   Oid identIdx,
 											   TransactionId frozenXid,
@@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd)
 }
 
 /*
- * Apply all the changes stored in 'file'.
+ * Apply all the changes provided by decoding worker.
  */
 static void
-apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
+apply_concurrent_changes(ChangeContext *chgcxt)
 {
 	ConcurrentChangeKind kind = '\0';
-	Relation	rel = chgcxt->cc_rel;
+	RepackDest *dest;
+	Relation	rel;
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
 	bool		have_old_tuple = false;
 	MemoryContext oldcxt;
+	DecodingWorkerShared *shared;
+	char		fname[MAXPGPATH];
+	BufFile    *file;
+
+	dest = &chgcxt->cc_dest;
+	rel = dest->rel;
+
+	shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg);
+
+	/* Open the file containing the changes. */
+	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
+	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
-	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate));
 
 	while (true)
 	{
@@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 
 		if (kind == CHANGE_INSERT)
 		{
-			apply_concurrent_insert(rel, spilled_tuple, chgcxt);
+			apply_concurrent_insert(dest, spilled_tuple);
 		}
 		else if (kind == CHANGE_DELETE)
 		{
 			bool		found;
 
 			/* Find the tuple to be deleted */
-			found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple);
+			found = find_target_tuple(dest, spilled_tuple, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 			apply_concurrent_delete(rel, ondisk_tuple);
@@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 				key = spilled_tuple;
 
 			/* Find the tuple to be updated or deleted. */
-			found = find_target_tuple(rel, chgcxt, key, ondisk_tuple);
+			found = find_target_tuple(dest, key, ondisk_tuple);
 			if (!found)
 				elog(ERROR, "could not find target tuple");
 
@@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 			 */
 			adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple);
 
-			apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt);
+			apply_concurrent_update(dest, spilled_tuple, ondisk_tuple);
 
 			ExecClearTuple(old_update_tuple);
 			have_old_tuple = false;
@@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ResetPerTupleExprContext(dest->estate);
 	}
 
 	/* Cleanup. */
@@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	ExecDropSingleTupleTableSlot(old_update_tuple);
 
 	MemoryContextSwitchTo(oldcxt);
+
+	BufFileClose(file);
 }
 
 /*
@@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
  * table.
  */
 static void
-apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
-						ChangeContext *chgcxt)
+apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot)
 {
 	/* Put the tuple in the table, but make sure it won't be decoded */
-	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+	table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true),
 					   TABLE_INSERT_NO_LOGICAL, NULL);
 
 	/* Update indexes with this new tuple. */
-	ExecInsertIndexTuples(chgcxt->cc_rri,
-						  chgcxt->cc_estate,
+	ExecInsertIndexTuples(dest->rri,
+						  dest->estate,
 						  0,
 						  slot,
 						  NIL, NULL);
@@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
  * table.
  */
 static void
-apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
-						TupleTableSlot *ondisk_tuple,
-						ChangeContext *chgcxt)
+apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple,
+						TupleTableSlot *ondisk_tuple)
 {
+	Relation	rel = dest->rel;
 	LockTupleMode lockmode;
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
@@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		ExecInsertIndexTuples(chgcxt->cc_rri,
-							  chgcxt->cc_estate,
+		ExecInsertIndexTuples(dest->rri,
+							  dest->estate,
 							  flags,
 							  spilled_tuple,
 							  NIL, NULL);
@@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s
  * not found, return false.
  */
 static bool
-find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
+find_target_tuple(RepackDest *dest, TupleTableSlot *locator,
 				  TupleTableSlot *retrieved)
 {
-	Form_pg_index idx = chgcxt->cc_ident_index->rd_index;
+	Relation	rel = dest->rel;
+	Form_pg_index idx = dest->ident_index->rd_index;
 	IndexScanDesc scan;
 	bool		retval = false;
 
@@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	 *
 	 * Use the incoming tuple to finalize the scan key.
 	 */
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
+		ScanKey		entry = &dest->ident_key[i];
 		AttrNumber	attno = idx->indkey.values[i];
 
 		entry->sk_argument = locator->tts_values[attno - 1];
@@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
 	}
 
 	/* XXX no instrumentation for now */
-	scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(),
-						   NULL, chgcxt->cc_ident_key_nentries, 0, 0);
-	index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0);
+	scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(),
+						   NULL, dest->ident_key_nentries, 0, 0);
+	index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0);
 	while (index_getnext_slot(scan, ForwardScanDirection, retrieved))
 	{
 		/* Be wary of temporal constraints */
-		if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved))
+		if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved))
 		{
 			CHECK_FOR_INTERRUPTS();
 			continue;
@@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator,
  * used for temporal constraints.
  */
 static bool
-identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator,
+identity_key_equal(RepackDest *dest, TupleTableSlot *locator,
 				   TupleTableSlot *candidate)
 {
-	slot_getsomeattrs(locator, chgcxt->cc_last_key_attno);
-	slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno);
+	slot_getsomeattrs(locator, dest->last_key_attno);
+	slot_getsomeattrs(candidate, dest->last_key_attno);
 
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		ScanKey		entry = &chgcxt->cc_ident_key[i];
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		ScanKey		entry = &dest->ident_key[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
 
@@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do
 	/* Open the file. */
 	DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq);
 	file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false);
-	apply_concurrent_changes(file, chgcxt);
+	apply_concurrent_changes(chgcxt);
 
 	BufFileClose(file);
 
@@ -3093,41 +3074,65 @@ static void
 initialize_change_context(ChangeContext *chgcxt,
 						  Relation relation, Oid ident_index_id)
 {
-	chgcxt->cc_rel = relation;
+	initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id);
+
+	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
+}
+
+/*
+ * Free up resources taken by a ChangeContext.
+ */
+static void
+release_change_context(ChangeContext *chgcxt)
+{
+	release_change_dest(&chgcxt->cc_dest);
+}
+
+/*
+ * Initialize the RepackDest struct for the given relation, with the given
+ * index as identity index. InvalidOid can be specified to only make the
+ * relation ready for insertions.
+ */
+static void
+initialize_change_dest(RepackDest *dest, Relation relation,
+					   Oid ident_index_id)
+{
+	dest->rel = relation;
+	dest->bistate = GetBulkInsertState();
 
 	/* Only initialize fields needed by ExecInsertIndexTuples(). */
-	chgcxt->cc_estate = CreateExecutorState();
+	dest->estate = CreateExecutorState();
 
-	chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
-	InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0);
-	ExecOpenIndices(chgcxt->cc_rri, false);
+	dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo));
+	InitResultRelInfo(dest->rri, relation, 0, 0, 0);
+	ExecOpenIndices(dest->rri, false);
 
 	/*
 	 * The table's relcache entry already has the relcache entry for the
 	 * identity index; find that.
 	 */
-	chgcxt->cc_ident_index = NULL;
-	for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++)
+	dest->ident_index = NULL;
+	for (int i = 0; i < dest->rri->ri_NumIndices; i++)
 	{
 		Relation	ind_rel;
 
-		ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i];
+		ind_rel = dest->rri->ri_IndexRelationDescs[i];
 		if (ind_rel->rd_id == ident_index_id)
 		{
-			chgcxt->cc_ident_index = ind_rel;
+			dest->ident_index = ind_rel;
 			break;
 		}
 	}
-	if (chgcxt->cc_ident_index == NULL)
+	if (dest->ident_index == NULL)
 		elog(ERROR, "could not find identity index");
 
 	/* Set up for scanning said identity index */
 	{
 		Form_pg_index indexForm;
 
-		indexForm = chgcxt->cc_ident_index->rd_index;
-		chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts;
-		chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
+		indexForm = dest->ident_index->rd_index;
+		dest->ident_key_nentries = indexForm->indnkeyatts;
+		dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts);
 		for (int i = 0; i < indexForm->indnkeyatts; i++)
 		{
 			ScanKey		entry;
@@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt,
 						opcode;
 			StrategyNumber eq_strategy;
 
-			entry = &chgcxt->cc_ident_key[i];
+			entry = &dest->ident_key[i];
 
-			opfamily = chgcxt->cc_ident_index->rd_opfamily[i];
-			opcintype = chgcxt->cc_ident_index->rd_opcintype[i];
+			opfamily = dest->ident_index->rd_opfamily[i];
+			opcintype = dest->ident_index->rd_opcintype[i];
 			eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ,
-													  chgcxt->cc_ident_index->rd_rel->relam,
+													  dest->ident_index->rd_rel->relam,
 													  opfamily, false);
 			if (eq_strategy == InvalidStrategy)
 				elog(ERROR, "could not find equality strategy for index operator family %u for type %u",
@@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt,
 						i + 1,
 						eq_strategy, opcode,
 						(Datum) 0);
-			entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i];
+			entry->sk_collation = dest->ident_index->rd_indcollation[i];
 		}
 	}
 
 	/* Determine the last column we must deform to read the identity */
-	chgcxt->cc_last_key_attno = InvalidAttrNumber;
-	for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++)
+	dest->last_key_attno = InvalidAttrNumber;
+	for (int i = 0; i < dest->ident_key_nentries; i++)
 	{
-		AttrNumber	attno = chgcxt->cc_ident_index->rd_index->indkey.values[i];
+		AttrNumber	attno = dest->ident_index->rd_index->indkey.values[i];
 
 		Assert(attno > 0);
-		chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno);
+		dest->last_key_attno = Max(dest->last_key_attno, attno);
 	}
-
-	chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1;
 }
 
-/*
- * Free up resources taken by a ChangeContext.
- */
 static void
-release_change_context(ChangeContext *chgcxt)
+release_change_dest(RepackDest *dest)
 {
-	ExecCloseIndices(chgcxt->cc_rri);
-	FreeExecutorState(chgcxt->cc_estate);
+	FreeBulkInsertState(dest->bistate);
+	ExecCloseIndices(dest->rri);
+	FreeExecutorState(dest->estate);
 	/* XXX are these pfrees necessary? */
-	pfree(chgcxt->cc_rri);
-	pfree(chgcxt->cc_ident_key);
+	pfree(dest->rri);
+	pfree(dest->ident_key);
 }
 
 /*
diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h
index 27105c10591..07f887e99f6 100644
--- a/src/include/commands/repack.h
+++ b/src/include/commands/repack.h
@@ -16,6 +16,7 @@
 #include <signal.h>
 
 #include "access/hio.h"
+#include "access/skey.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "parser/parse_node.h"
@@ -39,6 +40,53 @@ typedef struct ClusterParams
 
 extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending;
 
+/*
+ * Table to apply concurrent data changes to.
+ */
+typedef struct RepackDest
+{
+	/* The relation the changes are applied to. */
+	Relation	rel;
+
+	BulkInsertStateData *bistate;
+
+	/* Needed to update indexes of cc_rel. */
+	ResultRelInfo *rri;
+	EState	   *estate;
+
+	/*
+	 * Existing tuples to UPDATE and DELETE are located via this index. We
+	 * keep the scankey in partially initialized state to avoid repeated work.
+	 * sk_argument is completed on the fly.
+	 */
+	Relation	ident_index;
+	ScanKey		ident_key;
+
+	int			ident_key_nentries;
+
+	/* The latest column we need to deform to have the tuple identity */
+	AttrNumber	last_key_attno;
+} RepackDest;
+
+/*
+ * The first file exported by the decoding worker must contain a snapshot, the
+ * following ones contain the data changes.
+ */
+#define WORKER_FILE_SNAPSHOT	0
+
+/*
+ * Information needed to apply concurrent data changes.
+ *
+ * XXX Now that it's in *.h file, rename to RepackChangeContext?
+ */
+typedef struct ChangeContext
+{
+	/* The destination table. */
+	RepackDest	cc_dest;
+
+	/* Sequential number of the file containing the changes. */
+	int			cc_file_seq;
+} ChangeContext;
 
 extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel);
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index f9eb23e52c9..b4d5abbaca7 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey
 ReorderBufferUpdateProgressTxnCB
 ReorderTuple
 RepackCommand
+RepackDest
 RepackDecodingState
 RepackStmt
 ReparameterizeForeignPathByChild_function
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch



^ permalink  raw  reply  [nested|flat] 534+ messages in thread