From e5ba6a5ab62ce05e2a762b4d26f0fd0c52c7b521 Mon Sep 17 00:00:00 2001 From: Amit Kapila Date: Tue, 30 Jul 2024 14:17:30 +0530 Subject: [PATCH] pg_createsubscriber: Fix an unpredictable recovery wait time. The problem is that the tool is using the LSN returned by pg_create_logical_replication_slot() as recovery_target_lsn. This LSN is ahead of the current WAL position and the recovery waits until the publisher writes a WAL record to reach the target and ends the recovery. On idle systems, this wait time is unpredictable and could lead to failure in promoting the subscriber. To avoid that, insert a harmless WAL record. Reported-by: Alexander Lakhin and Tom Lane Diagnosed-by: Hayato Kuroda Author: Euler Taveira Reviewed-by: Hayato Kuroda, Amit Kapila Backpatch-through: 17 Discussion: https://postgr.es/m/2377319.1719766794%40sss.pgh.pa.us Discussion: https://postgr.es/m/CA+TgmoYcY+Wb67NAwaHT7MvxCSeV86oSc+va9hHKaasE42ukyw@mail.gmail.com --- src/bin/pg_basebackup/pg_createsubscriber.c | 22 +++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/src/bin/pg_basebackup/pg_createsubscriber.c b/src/bin/pg_basebackup/pg_createsubscriber.c index b02318782a6..b15fb98994a 100644 --- a/src/bin/pg_basebackup/pg_createsubscriber.c +++ b/src/bin/pg_basebackup/pg_createsubscriber.c @@ -778,6 +778,28 @@ setup_publisher(struct LogicalRepInfo *dbinfo) else exit(1); + /* + * Since we are using the LSN returned by the last replication slot as + * recovery_target_lsn, this LSN is ahead of the current WAL position + * and the recovery waits until the publisher writes a WAL record to + * reach the target and ends the recovery. On idle systems, this wait + * time is unpredictable and could lead to failure in promoting the + * subscriber. To avoid that, insert a harmless WAL record. + */ + if (i == num_dbs - 1 && !dry_run) + { + PGresult *res; + + res = PQexec(conn, "SELECT pg_log_standby_snapshot()"); + if (PQresultStatus(res) != PGRES_TUPLES_OK) + { + pg_log_error("could not write an additional WAL record: %s", + PQresultErrorMessage(res)); + disconnect_database(conn, true); + } + PQclear(res); + } + disconnect_database(conn, false); } -- 2.30.2