From 875693019053b8897ec3983e292acbb439b088c3 Mon Sep 17 00:00:00 2001
From: Amit Kapila <akapila@postgresql.org>
Date: Thu, 8 Sep 2022 06:54:13 +0530
Subject: Raise a warning if there is a possibility of data from multiple
 origins.

This commit raises a warning message for a combination of options
('copy_data = true' and 'origin = none') during CREATE/ALTER subscription
operations if the publication tables were also replicated from other
publishers.

During replication, we can skip the data from other origins as we have that
information in WAL but that is not possible during initial sync so we raise
a warning if there is such a possibility.

Author: Vignesh C
Reviewed-By: Peter Smith, Amit Kapila, Jonathan Katz, Shi yu, Wang wei
Discussion: https://www.postgresql.org/message-id/CALDaNm0gwjY_4HFxvvty01BOT01q_fJLKQ3pWP9=9orqubhjcQ@mail.gmail.com
---
 doc/src/sgml/ref/alter_subscription.sgml  |  5 +++++
 doc/src/sgml/ref/create_subscription.sgml | 35 +++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

(limited to 'doc/src')

diff --git a/doc/src/sgml/ref/alter_subscription.sgml b/doc/src/sgml/ref/alter_subscription.sgml
index 64efc21f537..1e8d72062b3 100644
--- a/doc/src/sgml/ref/alter_subscription.sgml
+++ b/doc/src/sgml/ref/alter_subscription.sgml
@@ -172,6 +172,11 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
           Previously subscribed tables are not copied, even if a table's row
           filter <literal>WHERE</literal> clause has since been modified.
          </para>
+         <para>
+          See <xref linkend="sql-createsubscription-notes"/> for details of
+          how <literal>copy_data = true</literal> can interact with the
+          <literal>origin</literal> parameter.
+         </para>
         </listitem>
        </varlistentry>
       </variablelist></para>
diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index 7390c715bc3..4e001f81119 100644
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -213,6 +213,11 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
           will affect what data is copied. Refer to the
           <xref linkend="sql-createsubscription-notes" /> for details.
          </para>
+         <para>
+          See <xref linkend="sql-createsubscription-notes"/> for details of how
+          <literal>copy_data = true</literal> can interact with the
+          <literal>origin</literal> parameter.
+         </para>
         </listitem>
        </varlistentry>
 
@@ -315,6 +320,11 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
           to <literal>any</literal> means that the publisher sends changes
           regardless of their origin. The default is <literal>any</literal>.
          </para>
+         <para>
+          See <xref linkend="sql-createsubscription-notes"/> for details of how
+          <literal>copy_data = true</literal> can interact with the
+          <literal>origin</literal> parameter.
+         </para>
         </listitem>
        </varlistentry>
       </variablelist></para>
@@ -386,6 +396,31 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
    can have non-existent publications.
   </para>
 
+  <para>
+   When using a subscription parameter combination of
+   <literal>copy_data = true</literal> and <literal>origin = NONE</literal>,
+   the initial sync table data is copied directly from the publisher, meaning
+   that knowledge of the true origin of that data is not possible. If the
+   publisher also has subscriptions then the copied table data might have
+   originated from further upstream. This scenario is detected and a WARNING is
+   logged to the user, but the warning is only an indication of a potential
+   problem; it is the user's responsibility to make the necessary checks to
+   ensure the copied data origins are really as wanted or not.
+  </para>
+
+  <para>
+   To find which tables might potentially include non-local origins (due to
+   other subscriptions created on the publisher) try this SQL query:
+<programlisting>
+# substitute &lt;pub-names&gt; below with your publication name(s) to be queried
+SELECT DISTINCT N.nspname AS schemaname, C.relname AS tablename
+FROM pg_publication P,
+     LATERAL pg_get_publication_tables(P.pubname) GPT
+     JOIN pg_subscription_rel PS ON (GPT.relid = PS.srrelid),
+     pg_class C JOIN pg_namespace N ON (N.oid = C.relnamespace)
+WHERE C.oid = GPT.relid AND P.pubname IN (&lt;pub-names&gt;);
+</programlisting></para>
+
  </refsect1>
 
  <refsect1>
-- 
cgit v1.2.3