Fix a WARNING for data origin discrepancies.

Previously, a WARNING was issued at the time of defining a subscription
with origin=NONE only when the publisher subscribed to the same table from
other publishers, indicating potential data origination from different
origins. However, the publisher can subscribe to the partition ancestors
or partition children of the table from other publishers, which could also
result in mixed-origin data inclusion. So, give a WARNING in those cases
as well.

Reported-by: Sergey Tatarintsev <s.tatarintsev@postgrespro.ru>
Author: Hou Zhijie <houzj.fnst@fujitsu.com>
Author: Shlok Kyal <shlok.kyal.oss@gmail.com>
Reviewed-by: Vignesh C <vignesh21@gmail.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Backpatch-through: 16, where it was introduced
Discussion: https://postgr.es/m/5eda6a9c-63cf-404d-8a49-8dcb116a29f3@postgrespro.ru

diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index 740b7d94210418d89f27dd64fbae276bf07d50f8..c9c8dd440dc7ef9dc1bf38b595d19193c02b0a90 100644 (file)
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -526,12 +526,14 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
 <programlisting>
 # substitute &lt;pub-names&gt; below with your publication name(s) to be queried
 SELECT DISTINCT PT.schemaname, PT.tablename
-FROM pg_publication_tables PT,
+FROM pg_publication_tables PT
+     JOIN pg_class C ON (C.relname = PT.tablename)
+     JOIN pg_namespace N ON (N.nspname = PT.schemaname),
      pg_subscription_rel PS
-     JOIN pg_class C ON (C.oid = PS.srrelid)
-     JOIN pg_namespace N ON (N.oid = C.relnamespace)
-WHERE N.nspname = PT.schemaname AND
-      C.relname = PT.tablename AND
+WHERE C.relnamespace = N.oid AND
+      (PS.srrelid = C.oid OR
+      C.oid IN (SELECT relid FROM pg_partition_ancestors(PS.srrelid) UNION
+                SELECT relid FROM pg_partition_tree(PS.srrelid))) AND
       PT.pubname IN (&lt;pub-names&gt;);
 </programlisting></para>
 

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index 8ecb6e0bb87ada44111459b132525f7df1759992..9467f58a23df3cd25cb46f8765e96c9e13abded1 100644 (file)
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -2012,11 +2012,12 @@ AlterSubscriptionOwner_oid(Oid subid, Oid newOwnerId)
 }
 
 /*
- * Check and log a warning if the publisher has subscribed to the same table
- * from some other publisher. This check is required only if "copy_data = true"
- * and "origin = none" for CREATE SUBSCRIPTION and
- * ALTER SUBSCRIPTION ... REFRESH statements to notify the user that data
- * having origin might have been copied.
+ * Check and log a warning if the publisher has subscribed to the same table,
+ * its partition ancestors (if it's a partition), or its partition children (if
+ * it's a partitioned table), from some other publishers. This check is
+ * required only if "copy_data = true" and "origin = none" for CREATE
+ * SUBSCRIPTION and ALTER SUBSCRIPTION ... REFRESH statements to notify the
+ * user that data having origin might have been copied.
  *
  * This check need not be performed on the tables that are already added
  * because incremental sync for those tables will happen through WAL and the
@@ -2046,7 +2047,9 @@ check_publications_origin(WalReceiverConn *wrconn, List *publications,
                           "SELECT DISTINCT P.pubname AS pubname\n"
                           "FROM pg_publication P,\n"
                           "     LATERAL pg_get_publication_tables(P.pubname) GPT\n"
-                          "     JOIN pg_subscription_rel PS ON (GPT.relid = PS.srrelid),\n"
+                          "     JOIN pg_subscription_rel PS ON (GPT.relid = PS.srrelid OR"
+                          "     GPT.relid IN (SELECT relid FROM pg_partition_ancestors(PS.srrelid) UNION"
+                          "                   SELECT relid FROM pg_partition_tree(PS.srrelid))),\n"
                           "     pg_class C JOIN pg_namespace N ON (N.oid = C.relnamespace)\n"
                           "WHERE C.oid = GPT.relid AND P.pubname IN (");
    get_publications_str(publications, &cmd, true);

diff --git a/src/test/subscription/t/030_origin.pl b/src/test/subscription/t/030_origin.pl
index 056561f00841ca4fa1e6f12c25c148e060db06e1..c0c627ee83a99d27bf37de7601013ab7be3b84c6 100644 (file)
--- a/src/test/subscription/t/030_origin.pl
+++ b/src/test/subscription/t/030_origin.pl
@@ -204,9 +204,123 @@ $node_A->poll_query_until('postgres', $synced_query)
 $node_B->wait_for_catchup($subname_AB2);
 
 # clear the operations done by this test
-$node_A->safe_psql('postgres', "DROP TABLE tab_new");
-$node_B->safe_psql('postgres', "DROP TABLE tab_new");
-$node_A->safe_psql('postgres', "DROP SUBSCRIPTION $subname_AB2");
+$node_A->safe_psql(
+   'postgres', qq(
+DROP TABLE tab_new;
+DROP SUBSCRIPTION $subname_AB2;
+DROP SUBSCRIPTION $subname_AB;
+DROP PUBLICATION tap_pub_A;
+));
+$node_B->safe_psql(
+   'postgres', qq(
+DROP TABLE tab_new;
+DROP SUBSCRIPTION $subname_BA;
+DROP PUBLICATION tap_pub_B;
+));
+
+###############################################################################
+# Specifying origin = NONE and copy_data = on must raise WARNING if we subscribe
+# to a partitioned table and this table contains any remotely originated data.
+#
+#           node_B
+#  __________________________
+# |       tab_main           | --------------> node_C (tab_main)
+# |__________________________|
+# | tab_part1  | tab_part2   | <-------------- node_A (tab_part2)
+# |____________|_____________|
+#              | tab_part2_1 |
+#              |_____________|
+#
+#           node_B
+#  __________________________
+# |       tab_main           |
+# |__________________________|
+# | tab_part1  | tab_part2   | <-------------- node_A (tab_part2)
+# |____________|_____________|
+#              | tab_part2_1 | --------------> node_C (tab_part2_1)
+#              |_____________|
+###############################################################################
+
+# create a table on node A which will act as a source for a partition on node B
+$node_A->safe_psql(
+   'postgres', qq(
+CREATE TABLE tab_part2(a int);
+CREATE PUBLICATION tap_pub_A FOR TABLE tab_part2;
+));
+
+# create a partition table on node B
+$node_B->safe_psql(
+   'postgres', qq(
+CREATE TABLE tab_main(a int) PARTITION BY RANGE(a);
+CREATE TABLE tab_part1 PARTITION OF tab_main FOR VALUES FROM (0) TO (5);
+CREATE TABLE tab_part2(a int) PARTITION BY RANGE(a);
+CREATE TABLE tab_part2_1 PARTITION OF tab_part2 FOR VALUES FROM (5) TO (10);
+ALTER TABLE tab_main ATTACH PARTITION tab_part2 FOR VALUES FROM (5) to (10);
+CREATE SUBSCRIPTION tap_sub_A_B CONNECTION '$node_A_connstr' PUBLICATION tap_pub_A;
+));
+
+# create a table on node C
+$node_C->safe_psql(
+   'postgres', qq(
+CREATE TABLE tab_main(a int);
+CREATE TABLE tab_part2_1(a int);
+));
+
+# create a logical replication setup between node B and node C with
+# subscription on node C having origin = NONE and copy_data = on
+$node_B->safe_psql(
+   'postgres', qq(
+CREATE PUBLICATION tap_pub_B FOR TABLE tab_main WITH (publish_via_partition_root);
+CREATE PUBLICATION tap_pub_B_2 FOR TABLE tab_part2_1;
+));
+
+($result, $stdout, $stderr) = $node_C->psql(
+   'postgres', "
+   CREATE SUBSCRIPTION tap_sub_B_C CONNECTION '$node_B_connstr' PUBLICATION tap_pub_B WITH (origin = none, copy_data = on);
+");
+
+# A warning must be logged as a partition 'tab_part2' in node B is subscribed to
+# node A so partition 'tab_part2' can have remotely originated data
+like(
+   $stderr,
+   qr/WARNING: ( [A-Z0-9]+:)? subscription "tap_sub_b_c" requested copy_data with origin = NONE but might copy data that had a different origin/,
+   "Create subscription with origin = none and copy_data when the publisher's partition is subscribing from different origin"
+);
+$node_C->safe_psql('postgres', "DROP SUBSCRIPTION tap_sub_B_C");
+
+($result, $stdout, $stderr) = $node_C->psql(
+   'postgres', "
+   CREATE SUBSCRIPTION tap_sub_B_C CONNECTION '$node_B_connstr' PUBLICATION tap_pub_B_2 WITH (origin = none, copy_data = on);
+");
+
+# A warning must be logged as ancestor of table 'tab_part2_1' in node B is
+# subscribed to node A so table 'tab_part2_1' can have remotely originated
+# data
+like(
+   $stderr,
+   qr/WARNING: ( [A-Z0-9]+:)? subscription "tap_sub_b_c" requested copy_data with origin = NONE but might copy data that had a different origin/,
+   "Create subscription with origin = none and copy_data when the publisher's ancestor is subscribing from different origin"
+);
+
+# clear the operations done by this test
+$node_C->safe_psql(
+   'postgres', qq(
+DROP SUBSCRIPTION tap_sub_B_C;
+DROP TABLE tab_main;
+DROP TABLE tab_part2_1;
+));
+$node_B->safe_psql(
+   'postgres', qq(
+DROP SUBSCRIPTION tap_sub_A_B;
+DROP PUBLICATION tap_pub_B;
+DROP PUBLICATION tap_pub_B_2;
+DROP TABLE tab_main;
+));
+$node_A->safe_psql(
+   'postgres', qq(
+DROP PUBLICATION tap_pub_A;
+DROP TABLE tab_part2;
+));
 
 # shutdown
 $node_B->stop('fast');