v8-pg14-0002-Fix-data-inconsistency-between-publisher-and-su_patch

From 232967797758d2ba44318a3d58182b11d4bd7592 Mon Sep 17 00:00:00 2001
From: "shiy.fnst" <shiy.fnst@fujitsu.com>
Date: Wed, 15 Jun 2022 10:48:21 +0800
Subject: [PATCH v814 2/2] Fix data inconsistency between publisher and
 subscriber.

We were not updating the partition map cache in the subscriber even when
the corresponding remote rel is changed. Due to this data was getting
incorrectly replicated after the publisher has changed the table schema.

Fix it by resetting the required entries in the partition map cache after
receiving a new relation mapping from the publisher.

Reported-by: Shi Yu
Author: Shi Yu, Hou Zhijie
Reviewed-by: Amit Langote, Amit Kapila
Backpatch-through: 13, where it was introduced
Discussion: https://postgr.es/m/OSZPR01MB6310F46CD425A967E4AEF736FDA49@OSZPR01MB6310.jpnprd01.prod.outlook.com
---
 src/backend/replication/logical/relation.c | 34 ++++++++++++++++++++++
 src/backend/replication/logical/worker.c   |  3 ++
 src/include/replication/logicalrelation.h  |  1 +
 src/test/subscription/t/013_partition.pl   | 17 ++++++++++-
 4 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/src/backend/replication/logical/relation.c b/src/backend/replication/logical/relation.c
index 5f4689f182..5c7e9d11ac 100644
--- a/src/backend/replication/logical/relation.c
+++ b/src/backend/replication/logical/relation.c
@@ -486,6 +486,40 @@ logicalrep_partmap_invalidate_cb(Datum arg, Oid reloid)
 	}
 }
 
+/*
+ * Reset the entries in the partition map that refer to remoterel.
+ *
+ * Called when new relation mapping is sent by the publisher to update our
+ * expected view of incoming data from said publisher.
+ *
+ * Note that we don't update the remoterel information in the entry here,
+ * we will update the information in logicalrep_partition_open to avoid
+ * unnecessary work.
+ */
+void
+logicalrep_partmap_reset_relmap(LogicalRepRelation *remoterel)
+{
+	HASH_SEQ_STATUS status;
+	LogicalRepPartMapEntry *part_entry;
+	LogicalRepRelMapEntry *entry;
+
+	if (LogicalRepPartMap == NULL)
+		return;
+
+	hash_seq_init(&status, LogicalRepPartMap);
+	while ((part_entry = (LogicalRepPartMapEntry *) hash_seq_search(&status)) != NULL)
+	{
+		entry = &part_entry->relmapentry;
+
+		if (entry->remoterel.remoteid != remoterel->remoteid)
+			continue;
+
+		logicalrep_relmap_free_entry(entry);
+
+		memset(entry, 0, sizeof(LogicalRepRelMapEntry));
+	}
+}
+
 /*
  * Initialize the partition map cache.
  */
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 833b2809d0..bf97fa44ba 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -1191,6 +1191,9 @@ apply_handle_relation(StringInfo s)
 
 	rel = logicalrep_read_rel(s);
 	logicalrep_relmap_update(rel);
+
+	/* Also reset all entries in the partition map that refer to remoterel. */
+	logicalrep_partmap_reset_relmap(rel);
 }
 
 /*
diff --git a/src/include/replication/logicalrelation.h b/src/include/replication/logicalrelation.h
index 3c662d3abc..10f91490b5 100644
--- a/src/include/replication/logicalrelation.h
+++ b/src/include/replication/logicalrelation.h
@@ -38,6 +38,7 @@ typedef struct LogicalRepRelMapEntry
 } LogicalRepRelMapEntry;
 
 extern void logicalrep_relmap_update(LogicalRepRelation *remoterel);
+extern void logicalrep_partmap_reset_relmap(LogicalRepRelation *remoterel);
 
 extern LogicalRepRelMapEntry *logicalrep_rel_open(LogicalRepRelId remoteid,
 												  LOCKMODE lockmode);
diff --git a/src/test/subscription/t/013_partition.pl b/src/test/subscription/t/013_partition.pl
index e53bc5b568..568e4d104e 100644
--- a/src/test/subscription/t/013_partition.pl
+++ b/src/test/subscription/t/013_partition.pl
@@ -6,7 +6,7 @@ use strict;
 use warnings;
 use PostgresNode;
 use TestLib;
-use Test::More tests => 69;
+use Test::More tests => 70;
 
 # setup
 
@@ -841,3 +841,18 @@ $node_publisher->wait_for_catchup('sub2');
 $result = $node_subscriber2->safe_psql('postgres',
 	"SELECT a, b, c FROM tab5 ORDER BY 1");
 is($result, qq(3|1|), 'updates of tab5 replicated correctly after altering table on subscriber');
+
+# Test that replication into the partitioned target table continues to
+# work correctly when the published table is altered.
+$node_publisher->safe_psql(
+	'postgres', q{
+	ALTER TABLE tab5 DROP COLUMN b, ADD COLUMN c INT;
+	ALTER TABLE tab5 ADD COLUMN b INT;});
+
+$node_publisher->safe_psql('postgres', "UPDATE tab5 SET c = 1 WHERE a = 3");
+
+$node_publisher->wait_for_catchup('sub2');
+
+$result = $node_subscriber2->safe_psql('postgres',
+	"SELECT a, b, c FROM tab5 ORDER BY 1");
+is($result, qq(3||1), 'updates of tab5 replicated correctly after altering table on publisher');
-- 
2.18.4