From 189f5418b260e730167268d0044b8072b6b88d51 Mon Sep 17 00:00:00 2001 From: wangw Date: Wed, 20 Jul 2022 09:47:14 +0800 Subject: [PATCH v13] Fix data replicated twice when specifying publish_via_partition_root option. If there are two publications - one of them publishing a parent table (using publish_via_partition_root = true) and the other is publishing one of the parent's child tables - then subscribing to both publications from one subscription results in the same initial child data being copied twice. It should only be copied once. To fix this, we exclude the partition table whose ancestor belongs to specified publications when getting the table list from publisher. --- src/backend/commands/subscriptioncmds.c | 45 ++++++++++++++++++---- src/test/subscription/t/013_partition.pl | 18 ++------- src/test/subscription/t/028_row_filter.pl | 13 ++++++- src/test/subscription/t/031_column_list.pl | 5 ++- 4 files changed, 56 insertions(+), 25 deletions(-) diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index ef4f9c175c..05b6b4c8a1 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -1756,25 +1756,56 @@ static List * fetch_table_list(WalReceiverConn *wrconn, List *publications) { WalRcvExecResult *res; - StringInfoData cmd; + StringInfoData cmd, + pub_names; TupleTableSlot *slot; Oid tableRow[3] = {TEXTOID, TEXTOID, NAMEARRAYOID}; List *tablelist = NIL; bool check_columnlist = (walrcv_server_version(wrconn) >= 150000); + initStringInfo(&pub_names); + get_publications_str(publications, &pub_names, true); + initStringInfo(&cmd); - appendStringInfoString(&cmd, "SELECT DISTINCT t.schemaname, t.tablename \n"); + + /* + * Get the list of tables from publisher, the partition table whose + * ancestor is also in this list will be ignored, otherwise the initial + * date in the partition table would be replicated twice. + */ + appendStringInfoString(&cmd, "WITH pub_tabs AS(\n" + " SELECT DISTINCT N.nspname, C.oid, C.relname, C.relispartition\n"); /* Get column lists for each relation if the publisher supports it */ if (check_columnlist) - appendStringInfoString(&cmd, ", t.attnames\n"); + appendStringInfoString(&cmd, ", ( SELECT array_agg(a.attname ORDER BY a.attnum)\n" + " FROM pg_attribute a\n" + " WHERE a.attrelid = GPT.relid AND a.attnum > 0 AND\n" + " NOT a.attisdropped AND\n" + " (a.attnum = ANY(GPT.attrs) OR GPT.attrs IS NULL)\n" + " ) AS attnames\n"); + + appendStringInfo(&cmd, " FROM pg_publication P,\n" + " LATERAL pg_get_publication_tables(P.pubname) GPT,\n" + " pg_class C JOIN pg_namespace N ON (N.oid = C.relnamespace)\n" + " WHERE C.oid = GPT.relid AND P.pubname IN ( %s )\n" + ")\n" + "SELECT DISTINCT pub_tabs.nspname, pub_tabs.relname\n", + pub_names.data); + + /* Get column lists for each relation if the publisher supports it */ + if (check_columnlist) + appendStringInfoString(&cmd, ", pub_tabs.attnames\n"); + + appendStringInfoString(&cmd, "FROM pub_tabs\n" + " WHERE (pub_tabs.relispartition IS FALSE\n" + " OR NOT EXISTS (SELECT 1 FROM pg_partition_ancestors(pub_tabs.oid) as PA\n" + " WHERE PA.relid IN (SELECT pub_tabs.oid FROM pub_tabs)\n" + " AND PA.relid != pub_tabs.oid))\n"); - appendStringInfoString(&cmd, "FROM pg_catalog.pg_publication_tables t\n" - " WHERE t.pubname IN ("); - get_publications_str(publications, &cmd, true); - appendStringInfoChar(&cmd, ')'); res = walrcv_exec(wrconn, cmd.data, check_columnlist ? 3 : 2, tableRow); + pfree(pub_names.data); pfree(cmd.data); if (res->status != WALRCV_OK_TUPLES) diff --git a/src/test/subscription/t/013_partition.pl b/src/test/subscription/t/013_partition.pl index 8b33e4e7ae..100e2d2fd0 100644 --- a/src/test/subscription/t/013_partition.pl +++ b/src/test/subscription/t/013_partition.pl @@ -473,12 +473,12 @@ $node_subscriber2->safe_psql('postgres', "CREATE TABLE tab3_1 (a int PRIMARY KEY, c text DEFAULT 'sub2_tab3_1', b text)" ); -# Note: We create two separate tables, not a partitioned one, so that we can -# easily identity through which relation were the changes replicated. +# Note: We only create one table (tab4) here. We specified +# publish_via_partition_root = true (see pub_all and pub_lower_level above), so +# all data will be replicated to that 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. We set the list of publications so that # the FOR ALL TABLES publication is second (the list order matters). @@ -550,11 +550,6 @@ $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', @@ -577,11 +572,6 @@ $result = 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"); diff --git a/src/test/subscription/t/028_row_filter.pl b/src/test/subscription/t/028_row_filter.pl index da52289dde..056ceb8096 100644 --- a/src/test/subscription/t/028_row_filter.pl +++ b/src/test/subscription/t/028_row_filter.pl @@ -386,6 +386,10 @@ $node_publisher->safe_psql('postgres', "INSERT INTO tab_rowfilter_child(a, b) VALUES(0,'0'),(30,'30'),(40,'40')" ); +# insert data into partitioned table. +$node_publisher->safe_psql('postgres', + "INSERT INTO tab_rowfilter_viaroot_part(a) VALUES(13), (17)"); + $node_subscriber->safe_psql('postgres', "CREATE SUBSCRIPTION tap_sub CONNECTION '$publisher_connstr application_name=$appname' PUBLICATION tap_pub_1, tap_pub_2, tap_pub_3, tap_pub_4a, tap_pub_4b, tap_pub_5a, tap_pub_5b, tap_pub_toast, tap_pub_inherits, tap_pub_viaroot_2, tap_pub_viaroot_1" ); @@ -707,13 +711,18 @@ is($result, qq(t|1), 'check replicated rows to tab_rowfilter_toast'); # the row filter for the top-level ancestor: # # tab_rowfilter_viaroot_part filter is: (a > 15) +# - INSERT (13) NO, 13 < 15 # - INSERT (14) NO, 14 < 15 # - INSERT (15) NO, 15 = 15 # - INSERT (16) YES, 16 > 15 +# - INSERT (17) YES, 17 > 15 $result = $node_subscriber->safe_psql('postgres', - "SELECT a FROM tab_rowfilter_viaroot_part"); -is($result, qq(16), 'check replicated rows to tab_rowfilter_viaroot_part'); + "SELECT a FROM tab_rowfilter_viaroot_part ORDER BY 1"); +is($result, qq(16 +17), + 'check replicated rows to tab_rowfilter_viaroot_part' +); # Check there is no data in tab_rowfilter_viaroot_part_1 because rows are # replicated via the top most parent table tab_rowfilter_viaroot_part diff --git a/src/test/subscription/t/031_column_list.pl b/src/test/subscription/t/031_column_list.pl index ae022faa78..a39f3d27ff 100644 --- a/src/test/subscription/t/031_column_list.pl +++ b/src/test/subscription/t/031_column_list.pl @@ -959,7 +959,8 @@ $node_publisher->safe_psql( CREATE TABLE test_root_1 PARTITION OF test_root FOR VALUES FROM (1) TO (10); CREATE TABLE test_root_2 PARTITION OF test_root FOR VALUES FROM (10) TO (20); - CREATE PUBLICATION pub_root_true FOR TABLE test_root (a) WITH (publish_via_partition_root = true); + CREATE PUBLICATION pub_root_true_1 FOR TABLE test_root (a) WITH (publish_via_partition_root = true); + CREATE PUBLICATION pub_root_true_2 FOR TABLE test_root_1 (a, b) WITH (publish_via_partition_root = true); -- initial data INSERT INTO test_root VALUES (1, 2, 3); @@ -968,7 +969,7 @@ $node_publisher->safe_psql( $node_subscriber->safe_psql( 'postgres', qq( - CREATE SUBSCRIPTION sub1 CONNECTION '$publisher_connstr' PUBLICATION pub_root_true; + CREATE SUBSCRIPTION sub1 CONNECTION '$publisher_connstr' PUBLICATION pub_root_true_1, pub_root_true_2; )); $node_subscriber->wait_for_subscription_sync; -- 2.23.0.windows.1