From d95019cbaaee049ee3535ef0e6ab455fb2419043 Mon Sep 17 00:00:00 2001 From: wangw Date: Thu, 28 Apr 2022 11:28:35 +0800 Subject: [PATCH v4] Fix data replicated twice when specifying PUBLISH_VIA_PARTITION_ROOT option. If there are two publications that publish the parent table and the child table separately, and both specify the option PUBLISH_VIA_PARTITION_ROOT, when subscribing to both publications using one subscription, the data is replicated twice in inital copy. What we expect is to be copied only once. To fix this, we exclude the partitioned table whose ancestor belongs to specified publications when getting the table list from publisher. --- src/backend/commands/subscriptioncmds.c | 37 +++++++++++++++++++----- src/test/subscription/t/013_partition.pl | 19 +++++------- 2 files changed, 36 insertions(+), 20 deletions(-) diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index 1719f04517..6ab6f249d0 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -1477,7 +1477,8 @@ static List * fetch_table_list(WalReceiverConn *wrconn, List *publications) { WalRcvExecResult *res; - StringInfoData cmd; + StringInfoData cmd, + pub_names; TupleTableSlot *slot; Oid tableRow[2] = {TEXTOID, TEXTOID}; ListCell *lc; @@ -1486,10 +1487,7 @@ fetch_table_list(WalReceiverConn *wrconn, List *publications) Assert(list_length(publications) > 0); - initStringInfo(&cmd); - appendStringInfoString(&cmd, "SELECT DISTINCT t.schemaname, t.tablename\n" - " FROM pg_catalog.pg_publication_tables t\n" - " WHERE t.pubname IN ("); + initStringInfo(&pub_names); first = true; foreach(lc, publications) { @@ -1498,14 +1496,37 @@ fetch_table_list(WalReceiverConn *wrconn, List *publications) if (first) first = false; else - appendStringInfoString(&cmd, ", "); + appendStringInfoString(&pub_names, ", "); - appendStringInfoString(&cmd, quote_literal_cstr(pubname)); + appendStringInfoString(&pub_names, quote_literal_cstr(pubname)); } - appendStringInfoChar(&cmd, ')'); + + /* + * Get the list of tables from publisher, the partitioned table whose + * ancestor is also in this list should be ignored, otherwise the initial + * date in the partitioned table would be replicated twice. + */ + initStringInfo(&cmd); + appendStringInfo(&cmd, "SELECT DISTINCT ns.nspname, c.relname\n" + " FROM pg_catalog.pg_publication_tables t\n" + " JOIN pg_catalog.pg_namespace ns\n" + " ON ns.nspname = t.schemaname\n" + " JOIN pg_catalog.pg_class c\n" + " ON c.relname = t.tablename AND c.relnamespace = ns.oid\n" + " WHERE t.pubname IN (%s)\n" + " AND (c.relispartition IS FALSE\n" + " OR NOT EXISTS\n" + " ( SELECT 1 FROM pg_partition_ancestors(c.oid) as pa\n" + " WHERE pa.relid IN\n" + " (SELECT DISTINCT (t.schemaname || '.' || t.tablename)::regclass::oid\n" + " FROM pg_catalog.pg_publication_tables t\n" + " WHERE t.pubname IN (%s))\n" + " AND pa.relid != c.oid))\n", + pub_names.data, pub_names.data); res = walrcv_exec(wrconn, cmd.data, 2, tableRow); pfree(cmd.data); + pfree(pub_names.data); if (res->status != WALRCV_OK_TUPLES) ereport(ERROR, diff --git a/src/test/subscription/t/013_partition.pl b/src/test/subscription/t/013_partition.pl index 39946c735b..c57a8eb7c5 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 => 67; +use Test::More tests => 65; # setup @@ -471,12 +471,15 @@ $node_subscriber2->safe_psql('postgres', $node_subscriber2->safe_psql('postgres', "CREATE TABLE tab3_1 (a int PRIMARY KEY, c text DEFAULT 'sub2_tab3_1', b text)" ); + +# Note: We only create one table for the partition table (tab4) here. +# Because we specify option PUBLISH_VIA_PARTITION_ROOT (see pub_all and +# pub_lower_level above), all data should be replicated to the partition table. +# So we do not need to create table for the partitioned table. $node_subscriber2->safe_psql('postgres', "CREATE TABLE tab4 (a int PRIMARY KEY)" ); -$node_subscriber2->safe_psql('postgres', - "CREATE TABLE tab4_1 (a int PRIMARY KEY)" -); + # Publication that sub2 points to now publishes via root, so must update # subscription target relations. $node_subscriber2->safe_psql('postgres', @@ -546,10 +549,6 @@ $result = $node_subscriber2->safe_psql('postgres', "SELECT a FROM tab4 ORDER BY 1"); is( $result, qq(0), 'inserts into tab4 replicated'); -$result = $node_subscriber2->safe_psql('postgres', - "SELECT a FROM tab4_1 ORDER BY 1"); -is( $result, qq(), 'inserts into tab4_1 replicated'); - # now switch the order of publications in the list, try again, the result # should be the same (no dependence on order of pulications) $node_subscriber2->safe_psql('postgres', @@ -574,10 +573,6 @@ $result = $node_subscriber2->safe_psql('postgres', is( $result, qq(0 1), 'inserts into tab4 replicated'); -$result = $node_subscriber2->safe_psql('postgres', - "SELECT a FROM tab4_1 ORDER BY 1"); -is( $result, qq(), 'inserts into tab4_1 replicated'); - # update (replicated as update) $node_publisher->safe_psql('postgres', "UPDATE tab1 SET a = 6 WHERE a = 5"); $node_publisher->safe_psql('postgres', "UPDATE tab2 SET a = 6 WHERE a = 5"); -- 2.23.0.windows.1