agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v1] Avoid orphaned objects dependencies
338+ messages / 2 participants
[nested] [flat]

* [PATCH v1] Avoid orphaned objects dependencies
@ 2024-03-29 15:43  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 338+ messages in thread

From: Bertrand Drouvot @ 2024-03-29 15:43 UTC (permalink / raw)

It's currently possible to create orphaned objects dependencies, for example:

Scenario 1:

session 1: begin; drop schema schem;
session 2: create a function in the schema schem
session 1: commit;

With the above, the function created in session 2 would be linked to a non
existing schema.

Scenario 2:

session 1: begin; create a function in the schema schem
session 2: drop schema schem;
session 1: commit;

With the above, the function created in session 1 would be linked to a non
existing schema.

To avoid those scenarios, a new lock (that conflicts with a lock taken by DROP)
has been put in place when the dependencies are being recorded. With this in
place, the drop schema in scenario 2 would be locked.

Also, after locking the object, the patch checks that the object still exists:
with this in place session 2 in scenario 1 would be locked and would report an
error once session 1 committs (that would not be the case should session 1 abort
the transaction).

The patch adds a few tests for some dependency cases (that would currently produce
orphaned objects):

- schema and function (as the above scenarios)
- function and type
- table and type
---
 src/backend/catalog/dependency.c              | 42 ++++++++++++++
 src/backend/catalog/objectaddress.c           | 57 +++++++++++++++++++
 src/backend/catalog/pg_depend.c               |  6 ++
 src/include/catalog/dependency.h              |  1 +
 src/include/catalog/objectaddress.h           |  1 +
 src/test/modules/Makefile                     |  1 +
 src/test/modules/meson.build                  |  1 +
 .../test_dependencies_locks/.gitignore        |  3 +
 .../modules/test_dependencies_locks/Makefile  | 14 +++++
 .../expected/test_dependencies_locks.out      | 49 ++++++++++++++++
 .../test_dependencies_locks/meson.build       | 12 ++++
 .../specs/test_dependencies_locks.spec        | 39 +++++++++++++
 12 files changed, 226 insertions(+)
  34.6% src/backend/catalog/
  32.7% src/test/modules/test_dependencies_locks/expected/
  20.7% src/test/modules/test_dependencies_locks/specs/
   9.2% src/test/modules/test_dependencies_locks/

diff --git a/src/backend/catalog/dependency.c b/src/backend/catalog/dependency.c
index d4b5b2ade1..2251145e3b 100644
--- a/src/backend/catalog/dependency.c
+++ b/src/backend/catalog/dependency.c
@@ -1517,6 +1517,48 @@ AcquireDeletionLock(const ObjectAddress *object, int flags)
 	}
 }
 
+/*
+ * depLockAndCheckObject
+ *
+ * Lock the object that we are about to record a dependency on.
+ * After it's locked, verify that it hasn't been dropped while we
+ * weren't looking.  If the object has been dropped, this function
+ * does not return!
+ */
+void
+depLockAndCheckObject(const ObjectAddress *object)
+{
+	char	   *object_description;
+
+	/*
+	 * Those don't rely on LockDatabaseObject() when being dropped (see
+	 * AcquireDeletionLock()). Also it looks like they can not produce
+	 * orphaned dependent objects when being dropped.
+	 */
+	if (object->classId == RelationRelationId || object->classId == AuthMemRelationId)
+		return;
+
+	object_description = getObjectDescription(object, true);
+
+	/*
+	 * If we don't get a description then there is no need to worry about this
+	 * object as it is certainly not in the progress of being dropped.
+	 */
+	if (!object_description)
+		return;
+
+	/* assume we should lock the whole object not a sub-object */
+	LockDatabaseObject(object->classId, object->objectId, 0, AccessShareLock);
+
+	/* check if object still exists */
+	if (!ObjectByIdExist(object))
+		ereport(ERROR, errmsg("%s does not exist", object_description));
+
+	pfree(object_description);
+
+	return;
+}
+
 /*
  * ReleaseDeletionLock - release an object deletion lock
  *
diff --git a/src/backend/catalog/objectaddress.c b/src/backend/catalog/objectaddress.c
index 7b536ac6fd..8cb1adae89 100644
--- a/src/backend/catalog/objectaddress.c
+++ b/src/backend/catalog/objectaddress.c
@@ -2590,6 +2590,63 @@ get_object_namespace(const ObjectAddress *address)
 	return oid;
 }
 
+/*
+ * ObjectByIdExist
+ *
+ * Return whether the given object exists.
+ *
+ * Works for most catalogs, if no special processing is needed.
+ */
+bool
+ObjectByIdExist(const ObjectAddress *address)
+{
+	int			cache;
+	HeapTuple	tuple;
+	const ObjectPropertyType *property;
+
+	property = get_object_property_data(address->classId);
+
+	cache = property->oid_catcache_id;
+
+	if (cache >= 0)
+	{
+		/* Fetch tuple from syscache. */
+		tuple = SearchSysCache1(cache, ObjectIdGetDatum(address->objectId));
+
+		if (!HeapTupleIsValid(tuple))
+		{
+			return false;
+		}
+
+		ReleaseSysCache(tuple);
+
+		return true;
+	}
+	else
+	{
+		Relation	rel;
+		ScanKeyData skey[1];
+		SysScanDesc scan;
+
+		rel = table_open(address->classId, AccessShareLock);
+
+		ScanKeyInit(&skey[0],
+					get_object_attnum_oid(address->classId),
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(address->objectId));
+
+		scan = systable_beginscan(rel, get_object_oid_index(address->classId), true,
+								  NULL, 1, skey);
+
+		/* we expect exactly one match */
+		tuple = systable_getnext(scan);
+		systable_endscan(scan);
+		table_close(rel, AccessShareLock);
+
+		return (HeapTupleIsValid(tuple));
+	}
+}
+
 /*
  * Return ObjectType for the given object type as given by
  * getObjectTypeDescription; if no valid ObjectType code exists, but it's a
diff --git a/src/backend/catalog/pg_depend.c b/src/backend/catalog/pg_depend.c
index f85a898de8..f7b0ad3a42 100644
--- a/src/backend/catalog/pg_depend.c
+++ b/src/backend/catalog/pg_depend.c
@@ -106,6 +106,12 @@ recordMultipleDependencies(const ObjectAddress *depender,
 		if (isObjectPinned(referenced))
 			continue;
 
+		/*
+		 * Acquire a lock and check object still exists while recording the
+		 * dependency.
+		 */
+		depLockAndCheckObject(referenced);
+
 		if (slot_init_count < max_slots)
 		{
 			slot[slot_stored_count] = MakeSingleTupleTableSlot(RelationGetDescr(dependDesc),
diff --git a/src/include/catalog/dependency.h b/src/include/catalog/dependency.h
index ec654010d4..8915548711 100644
--- a/src/include/catalog/dependency.h
+++ b/src/include/catalog/dependency.h
@@ -94,6 +94,7 @@ typedef struct ObjectAddresses ObjectAddresses;
 /* in dependency.c */
 
 extern void AcquireDeletionLock(const ObjectAddress *object, int flags);
+extern void depLockAndCheckObject(const ObjectAddress *object);
 
 extern void ReleaseDeletionLock(const ObjectAddress *object);
 
diff --git a/src/include/catalog/objectaddress.h b/src/include/catalog/objectaddress.h
index 3a70d80e32..56f746264b 100644
--- a/src/include/catalog/objectaddress.h
+++ b/src/include/catalog/objectaddress.h
@@ -53,6 +53,7 @@ extern void check_object_ownership(Oid roleid,
 								   Node *object, Relation relation);
 
 extern Oid	get_object_namespace(const ObjectAddress *address);
+extern bool ObjectByIdExist(const ObjectAddress *address);
 
 extern bool is_objectclass_supported(Oid class_id);
 extern const char *get_object_class_descr(Oid class_id);
diff --git a/src/test/modules/Makefile b/src/test/modules/Makefile
index 256799f520..75f357100f 100644
--- a/src/test/modules/Makefile
+++ b/src/test/modules/Makefile
@@ -17,6 +17,7 @@ SUBDIRS = \
 		  test_copy_callbacks \
 		  test_custom_rmgrs \
 		  test_ddl_deparse \
+		  test_dependencies_locks \
 		  test_dsa \
 		  test_dsm_registry \
 		  test_extensions \
diff --git a/src/test/modules/meson.build b/src/test/modules/meson.build
index d8fe059d23..60305dcccd 100644
--- a/src/test/modules/meson.build
+++ b/src/test/modules/meson.build
@@ -16,6 +16,7 @@ subdir('test_bloomfilter')
 subdir('test_copy_callbacks')
 subdir('test_custom_rmgrs')
 subdir('test_ddl_deparse')
+subdir('test_dependencies_locks')
 subdir('test_dsa')
 subdir('test_dsm_registry')
 subdir('test_extensions')
diff --git a/src/test/modules/test_dependencies_locks/.gitignore b/src/test/modules/test_dependencies_locks/.gitignore
new file mode 100644
index 0000000000..bf000faac4
--- /dev/null
+++ b/src/test/modules/test_dependencies_locks/.gitignore
@@ -0,0 +1,3 @@
+# Generated subdirectories
+/log/
+/output_iso
diff --git a/src/test/modules/test_dependencies_locks/Makefile b/src/test/modules/test_dependencies_locks/Makefile
new file mode 100644
index 0000000000..7491048380
--- /dev/null
+++ b/src/test/modules/test_dependencies_locks/Makefile
@@ -0,0 +1,14 @@
+# src/test/modules/test_dependencies_locks/Makefile
+
+ISOLATION = test_dependencies_locks
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = src/test/modules/test_dependencies_locks
+top_builddir = ../../../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/src/test/modules/test_dependencies_locks/expected/test_dependencies_locks.out b/src/test/modules/test_dependencies_locks/expected/test_dependencies_locks.out
new file mode 100644
index 0000000000..d0980f77d5
--- /dev/null
+++ b/src/test/modules/test_dependencies_locks/expected/test_dependencies_locks.out
@@ -0,0 +1,49 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_begin s1_create_function_in_schema s2_drop_schema s1_commit
+step s1_begin: BEGIN;
+step s1_create_function_in_schema: CREATE FUNCTION testschema.foo() RETURNS int AS 'select 1' LANGUAGE sql;
+step s2_drop_schema: DROP SCHEMA testschema; <waiting ...>
+step s1_commit: COMMIT;
+step s2_drop_schema: <... completed>
+ERROR:  cannot drop schema testschema because other objects depend on it
+
+starting permutation: s2_begin s2_drop_schema s1_create_function_in_schema s2_commit
+step s2_begin: BEGIN;
+step s2_drop_schema: DROP SCHEMA testschema;
+step s1_create_function_in_schema: CREATE FUNCTION testschema.foo() RETURNS int AS 'select 1' LANGUAGE sql; <waiting ...>
+step s2_commit: COMMIT;
+step s1_create_function_in_schema: <... completed>
+ERROR:  schema testschema does not exist
+
+starting permutation: s1_begin s1_create_function_with_type s2_drop_foo_type s1_commit
+step s1_begin: BEGIN;
+step s1_create_function_with_type: CREATE FUNCTION footype(num foo) RETURNS int AS 'select 1' LANGUAGE sql;
+step s2_drop_foo_type: DROP TYPE public.foo; <waiting ...>
+step s1_commit: COMMIT;
+step s2_drop_foo_type: <... completed>
+ERROR:  cannot drop type foo because other objects depend on it
+
+starting permutation: s2_begin s2_drop_foo_type s1_create_function_with_type s2_commit
+step s2_begin: BEGIN;
+step s2_drop_foo_type: DROP TYPE public.foo;
+step s1_create_function_with_type: CREATE FUNCTION footype(num foo) RETURNS int AS 'select 1' LANGUAGE sql; <waiting ...>
+step s2_commit: COMMIT;
+step s1_create_function_with_type: <... completed>
+ERROR:  type foo does not exist
+
+starting permutation: s1_begin s1_create_table_with_type s2_drop_footab_type s1_commit
+step s1_begin: BEGIN;
+step s1_create_table_with_type: CREATE TABLE tabtype(a footab);
+step s2_drop_footab_type: DROP TYPE public.footab; <waiting ...>
+step s1_commit: COMMIT;
+step s2_drop_footab_type: <... completed>
+ERROR:  cannot drop type footab because other objects depend on it
+
+starting permutation: s2_begin s2_drop_footab_type s1_create_table_with_type s2_commit
+step s2_begin: BEGIN;
+step s2_drop_footab_type: DROP TYPE public.footab;
+step s1_create_table_with_type: CREATE TABLE tabtype(a footab); <waiting ...>
+step s2_commit: COMMIT;
+step s1_create_table_with_type: <... completed>
+ERROR:  type footab does not exist
diff --git a/src/test/modules/test_dependencies_locks/meson.build b/src/test/modules/test_dependencies_locks/meson.build
new file mode 100644
index 0000000000..92a978ab93
--- /dev/null
+++ b/src/test/modules/test_dependencies_locks/meson.build
@@ -0,0 +1,12 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+tests += {
+  'name': 'test_dependencies_locks',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'test_dependencies_locks',
+    ],
+  },
+}
diff --git a/src/test/modules/test_dependencies_locks/specs/test_dependencies_locks.spec b/src/test/modules/test_dependencies_locks/specs/test_dependencies_locks.spec
new file mode 100644
index 0000000000..fd15bd2a78
--- /dev/null
+++ b/src/test/modules/test_dependencies_locks/specs/test_dependencies_locks.spec
@@ -0,0 +1,39 @@
+setup
+{
+  CREATE SCHEMA testschema;
+  CREATE TYPE public.foo as enum ('one', 'two');
+  CREATE TYPE public.footab as enum ('three', 'four');
+}
+
+teardown
+{
+  DROP FUNCTION IF EXISTS testschema.foo();
+  DROP FUNCTION IF EXISTS footype(num foo);
+  DROP TABLE IF EXISTS tabtype;
+  DROP SCHEMA IF EXISTS testschema;
+  DROP TYPE IF EXISTS public.foo;
+  DROP TYPE IF EXISTS public.footab;
+}
+
+session "s1"
+
+step "s1_begin" { BEGIN; }
+step "s1_create_function_in_schema" { CREATE FUNCTION testschema.foo() RETURNS int AS 'select 1' LANGUAGE sql; }
+step "s1_create_function_with_type" { CREATE FUNCTION footype(num foo) RETURNS int AS 'select 1' LANGUAGE sql; }
+step "s1_create_table_with_type" { CREATE TABLE tabtype(a footab); }
+step "s1_commit" { COMMIT; }
+
+session "s2"
+
+step "s2_begin" { BEGIN; }
+step "s2_drop_schema" { DROP SCHEMA testschema; }
+step "s2_drop_foo_type" { DROP TYPE public.foo; }
+step "s2_drop_footab_type" { DROP TYPE public.footab; }
+step "s2_commit" { COMMIT; }
+
+permutation "s1_begin" "s1_create_function_in_schema" "s2_drop_schema" "s1_commit"
+permutation "s2_begin" "s2_drop_schema" "s1_create_function_in_schema" "s2_commit"
+permutation "s1_begin" "s1_create_function_with_type" "s2_drop_foo_type" "s1_commit"
+permutation "s2_begin" "s2_drop_foo_type" "s1_create_function_with_type" "s2_commit"
+permutation "s1_begin" "s1_create_table_with_type" "s2_drop_footab_type" "s1_commit"
+permutation "s2_begin" "s2_drop_footab_type" "s1_create_table_with_type" "s2_commit"
-- 
2.34.1


--QMyFpY0GvHGGaeD+--





^ permalink  raw  reply  [nested|flat] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread

* [PATCH 3/8] Introduce RepackDest structure.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 338+ 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] 338+ messages in thread