From 5d8b4781e6e9bcb00564f45c25e575a8abab6ae8 Mon Sep 17 00:00:00 2001 From: Euler Taveira Date: Tue, 21 May 2024 23:04:57 -0300 Subject: [PATCH 1/4] Only the recovery_timeout controls the end of recovery process It used to check if the target server is connected to the primary server (send required WAL) to rapidly react when the process won't succeed. This code is not enough to guarantee that the recovery process will complete. There is a window between the walreceiver shutdown and the pg_is_in_recovery() returns false that can reach NUM_CONN_ATTEMPTS attempts and fails. Instead, rely only on recovery_timeout option to give up the process after the specified number of seconds. --- doc/src/sgml/ref/pg_createsubscriber.sgml | 7 ----- src/bin/pg_basebackup/pg_createsubscriber.c | 29 ++----------------- .../t/040_pg_createsubscriber.pl | 2 ++ 3 files changed, 5 insertions(+), 33 deletions(-) diff --git a/doc/src/sgml/ref/pg_createsubscriber.sgml b/doc/src/sgml/ref/pg_createsubscriber.sgml index 142bffff02..a700697f88 100644 --- a/doc/src/sgml/ref/pg_createsubscriber.sgml +++ b/doc/src/sgml/ref/pg_createsubscriber.sgml @@ -325,13 +325,6 @@ PostgreSQL documentation connections to the target server should fail. - - During the recovery process, if the target server disconnects from the - source server, pg_createsubscriber will check a - few times if the connection has been reestablished to stream the required - WAL. After a few attempts, it terminates with an error. - - Since DDL commands are not replicated by logical replication, avoid executing DDL commands that change the database schema while running diff --git a/src/bin/pg_basebackup/pg_createsubscriber.c b/src/bin/pg_basebackup/pg_createsubscriber.c index 90cc580811..f62f34b1a7 100644 --- a/src/bin/pg_basebackup/pg_createsubscriber.c +++ b/src/bin/pg_basebackup/pg_createsubscriber.c @@ -1360,6 +1360,9 @@ stop_standby_server(const char *datadir) * * If recovery_timeout option is set, terminate abnormally without finishing * the recovery process. By default, it waits forever. + * + * XXX Is the recovery process still in progress? When recovery process has a + * better progress reporting mechanism, it should be added here. */ static void wait_for_end_recovery(const char *conninfo, const struct CreateSubscriberOptions *opt) @@ -1367,9 +1370,6 @@ wait_for_end_recovery(const char *conninfo, const struct CreateSubscriberOptions PGconn *conn; int status = POSTMASTER_STILL_STARTING; int timer = 0; - int count = 0; /* number of consecutive connection attempts */ - -#define NUM_CONN_ATTEMPTS 10 pg_log_info("waiting for the target server to reach the consistent state"); @@ -1377,7 +1377,6 @@ wait_for_end_recovery(const char *conninfo, const struct CreateSubscriberOptions for (;;) { - PGresult *res; bool in_recovery = server_is_in_recovery(conn); /* @@ -1391,28 +1390,6 @@ wait_for_end_recovery(const char *conninfo, const struct CreateSubscriberOptions break; } - /* - * If it is still in recovery, make sure the target server is - * connected to the primary so it can receive the required WAL to - * finish the recovery process. If it is disconnected try - * NUM_CONN_ATTEMPTS in a row and bail out if not succeed. - */ - res = PQexec(conn, - "SELECT 1 FROM pg_catalog.pg_stat_wal_receiver"); - if (PQntuples(res) == 0) - { - if (++count > NUM_CONN_ATTEMPTS) - { - stop_standby_server(subscriber_dir); - pg_log_error("standby server disconnected from the primary"); - break; - } - } - else - count = 0; /* reset counter if it connects again */ - - PQclear(res); - /* Bail out after recovery_timeout seconds if this option is set */ if (opt->recovery_timeout > 0 && timer >= opt->recovery_timeout) { diff --git a/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl b/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl index 2b883e6910..a677fefa94 100644 --- a/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl +++ b/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl @@ -264,6 +264,7 @@ $node_p->restart; command_ok( [ 'pg_createsubscriber', '--verbose', + '--recovery-timeout', "$PostgreSQL::Test::Utils::timeout_default", '--dry-run', '--pgdata', $node_s->data_dir, '--publisher-server', $node_p->connstr('pg1'), '--socket-directory', @@ -301,6 +302,7 @@ command_ok( command_ok( [ 'pg_createsubscriber', '--verbose', + '--recovery-timeout', "$PostgreSQL::Test::Utils::timeout_default", '--verbose', '--pgdata', $node_s->data_dir, '--publisher-server', $node_p->connstr('pg1'), '--socket-directory', -- 2.30.2