From 6fdf89b34b4a0dfd0174cca8c8d8d39d1b2746e4 Mon Sep 17 00:00:00 2001
From: Hou Zhijie <houzj.fnst@cn.fujitsu.com>
Date: Tue, 2 Apr 2024 08:41:02 +0800
Subject: [PATCH v7 2/2] test the data loss case

---
 .../t/040_standby_failover_slots_sync.pl      | 75 ++++++++++++++++++-
 1 file changed, 72 insertions(+), 3 deletions(-)

diff --git a/src/test/recovery/t/040_standby_failover_slots_sync.pl b/src/test/recovery/t/040_standby_failover_slots_sync.pl
index 0818c3c068..3b5d73d28c 100644
--- a/src/test/recovery/t/040_standby_failover_slots_sync.pl
+++ b/src/test/recovery/t/040_standby_failover_slots_sync.pl
@@ -365,6 +365,67 @@ ok( $stderr =~
 
 $cascading_standby->stop;
 
+##################################################
+# Create a failover slot and advance the restart_lsn to a position where a
+# running transaction exists. This setup is for testing the synced slot's
+# capability to reach the consistent point from the restart_lsn after
+# promotion, guaranteeing no data loss from changes before reaching a
+# consistent point.
+##################################################
+
+$primary->safe_psql('postgres',
+	"SELECT pg_create_logical_replication_slot('snap_test_slot', 'test_decoding', false, false, true);"
+);
+
+$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();");
+
+# Two xl_running_xacts logs are generated here. When decoding the first log, it
+# only serializes the snapshot, without advancing the restart_lsn to the latest
+# position. This is because if a transaction is running, the restart_lsn can
+# only move to a position before that transaction. Hence, the second
+# xl_running_xacts log is needed, decoding the second log allows the
+# restart_lsn to advance to the last serialized snapshot's position (the first
+# log).
+$primary->safe_psql(
+	'postgres', qq(
+		BEGIN;
+		SELECT txid_current();
+		SELECT pg_log_standby_snapshot();
+		COMMIT;
+		BEGIN;
+		SELECT txid_current();
+		SELECT pg_log_standby_snapshot();
+		COMMIT;
+));
+
+$primary->wait_for_replay_catchup($standby1);
+
+# Advance the restart_lsn to the position of the first xl_running_xacts log
+# generated above. Note that there might be concurrent xl_running_xacts logs
+# written by the bgwriter, which could cause the position to be advanced to a
+# unexpected point, but this is a rare scenario and acceptable.
+$primary->safe_psql('postgres',
+	"SELECT pg_replication_slot_advance('snap_test_slot', pg_current_wal_lsn());"
+);
+
+# Log a message that will be consumed on the standby after promotion using the
+# synced slot.
+$primary->safe_psql('postgres',
+	"SELECT pg_logical_emit_message(false, 'test', 'test');"
+);
+
+# Get the confirmed_flush_lsn for the logical slot snap_test_slot on the primary
+my $confirmed_flush_lsn = $primary->safe_psql('postgres',
+	"SELECT confirmed_flush_lsn from pg_replication_slots WHERE slot_name = 'snap_test_slot';");
+
+$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();");
+
+# Confirm that confirmed_flush_lsn of snap_test_slot slot are synced to the standby
+ok( $standby1->poll_query_until(
+		'postgres',
+		"SELECT '$confirmed_flush_lsn' = confirmed_flush_lsn from pg_replication_slots WHERE slot_name = 'snap_test_slot' AND synced AND NOT temporary;"),
+	'confirmed_flush_lsn of slot snap_test_slot synced to standby');
+
 ##################################################
 # Test to confirm that the slot synchronization is protected from malicious
 # users.
@@ -739,8 +800,9 @@ $primary->reload;
 
 ##################################################
 # Promote the standby1 to primary. Confirm that:
-# a) the slot 'lsub1_slot' is retained on the new primary
+# a) the slot 'lsub1_slot' and 'snap_test_slot' are retained on the new primary
 # b) logical replication for regress_mysub1 is resumed successfully after failover
+# c) changes can be consumed from the synced slot 'snap_test_slot'
 ##################################################
 $standby1->start;
 $primary->wait_for_replay_catchup($standby1);
@@ -754,8 +816,8 @@ $subscriber1->safe_psql('postgres',
 
 # Confirm the synced slot 'lsub1_slot' is retained on the new primary
 is($standby1->safe_psql('postgres',
-	q{SELECT slot_name FROM pg_replication_slots WHERE slot_name = 'lsub1_slot' AND synced AND NOT temporary;}),
-	'lsub1_slot',
+	q{SELECT count(*) = 2 FROM pg_replication_slots WHERE slot_name IN ('lsub1_slot', 'snap_test_slot') AND synced AND NOT temporary;}),
+	't',
 	'synced slot retained on the new primary');
 
 # Insert data on the new primary
@@ -768,4 +830,11 @@ is( $subscriber1->safe_psql('postgres', q{SELECT count(*) FROM tab_int;}),
 	"20",
 	'data replicated from the new primary');
 
+# Consume the data from the snap_test_slot
+$result = $standby1->safe_psql('postgres',
+	"SELECT count(*) FROM pg_logical_slot_get_changes('snap_test_slot', NULL, NULL) WHERE data ~ 'message*';"
+);
+
+is($result, '1', "data can be consumed using snap_test_slot");
+
 done_testing();
-- 
2.30.0.windows.2