v20240815-0005-Documentation-for-sequence-synchronization.patch

From 498e903ff6d9b75c9ddfe76f385ce7a5f947716c Mon Sep 17 00:00:00 2001
From: Vignesh C <vignesh21@gmail.com>
Date: Thu, 8 Aug 2024 20:27:26 +0530
Subject: [PATCH v20240815 5/5] Documentation for sequence synchronization
 feature.

Documentation for sequence synchronization feature.
---
 doc/src/sgml/catalogs.sgml                |  19 +-
 doc/src/sgml/config.sgml                  |  10 +-
 doc/src/sgml/logical-replication.sgml     | 223 ++++++++++++++++++++--
 doc/src/sgml/monitoring.sgml              |   5 +-
 doc/src/sgml/ref/alter_subscription.sgml  |  55 +++++-
 doc/src/sgml/ref/create_subscription.sgml |   6 +
 doc/src/sgml/system-views.sgml            |  67 +++++++
 7 files changed, 353 insertions(+), 32 deletions(-)

diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml
index b654fae1b2..28ca21a772 100644
--- a/doc/src/sgml/catalogs.sgml
+++ b/doc/src/sgml/catalogs.sgml
@@ -8102,16 +8102,19 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
   </indexterm>
 
   <para>
-   The catalog <structname>pg_subscription_rel</structname> contains the
-   state for each replicated relation in each subscription.  This is a
-   many-to-many mapping.
+   The catalog <structname>pg_subscription_rel</structname> stores the
+   state of each replicated table and sequence for each subscription.  This
+   is a many-to-many mapping.
   </para>
 
   <para>
-   This catalog only contains tables known to the subscription after running
-   either <link linkend="sql-createsubscription"><command>CREATE SUBSCRIPTION</command></link> or
-   <link linkend="sql-altersubscription"><command>ALTER SUBSCRIPTION ... REFRESH
-   PUBLICATION</command></link>.
+   This catalog only contains tables and sequences known to the subscription
+   after running
+   <link linkend="sql-createsubscription"><command>CREATE SUBSCRIPTION</command></link> or
+   <link linkend="sql-altersubscription-params-refresh-publication">
+   <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION</command></link> or
+   <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+   <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>.
   </para>
 
   <table>
@@ -8145,7 +8148,7 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
        (references <link linkend="catalog-pg-class"><structname>pg_class</structname></link>.<structfield>oid</structfield>)
       </para>
       <para>
-       Reference to relation
+       Reference to table or sequence
       </para></entry>
      </row>
 
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 2937384b00..4aad02e1ee 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -5206,8 +5206,8 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
       <listitem>
        <para>
         Specifies maximum number of logical replication workers. This includes
-        leader apply workers, parallel apply workers, and table synchronization
-        workers.
+        leader apply workers, parallel apply workers, table synchronization
+        workers and a sequence synchronization worker.
        </para>
        <para>
         Logical replication workers are taken from the pool defined by
@@ -5230,10 +5230,12 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
        <para>
         Maximum number of synchronization workers per subscription. This
         parameter controls the amount of parallelism of the initial data copy
-        during the subscription initialization or when new tables are added.
+        during the subscription initialization or when new tables or sequences
+        are added.
        </para>
        <para>
-        Currently, there can be only one synchronization worker per table.
+        Currently, there can be only one table synchronization worker per table
+        and one sequence synchronization worker to synchronize all sequences.
        </para>
        <para>
         The synchronization workers are taken from the pool defined by
diff --git a/doc/src/sgml/logical-replication.sgml b/doc/src/sgml/logical-replication.sgml
index a23a3d57e2..ed1fb93cbf 100644
--- a/doc/src/sgml/logical-replication.sgml
+++ b/doc/src/sgml/logical-replication.sgml
@@ -1570,6 +1570,201 @@ test_sub=# SELECT * FROM t1 ORDER BY id;
 
  </sect1>
 
+ <sect1 id="logical-replication-sequences">
+  <title>Replicating Sequences</title>
+
+  <para>
+   To replicate sequences from a publisher to a subscriber, first publish the
+   sequence using <link linkend="sql-createpublication-params-for-all-sequences">
+   <command>CREATE PUBLICATION ... FOR ALL SEQUENCES</command></link>.
+  </para>
+
+  <para>
+   At the subscriber side:
+   <itemizedlist>
+    <listitem>
+     <para>
+      use <link linkend="sql-createsubscription"><command>CREATE SUBSCRIPTION</command></link>
+      to initially synchronize the published sequences.
+     </para>
+    </listitem>
+    <listitem>
+     <para>
+      use <link linkend="sql-altersubscription-params-refresh-publication">
+      <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION</command></link>
+      to synchronize any newly added sequences.
+     </para>
+    </listitem>
+    <listitem>
+     <para>
+      use <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+      <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>
+      to re-synchronize all sequences.
+     </para>
+    </listitem>
+   </itemizedlist>
+  </para>
+
+  <para>
+   A new sequence synchronization worker will be started to synchronize the
+   sequences after executing any of the above subscriber commands, and will
+   will exit once the sequences are synchronized.
+  </para>
+  <para>
+   The ability to launch a sequence synchronization worker will be limited by
+   the <link linkend="guc-max-sync-workers-per-subscription">
+   <varname>max_sync_workers_per_subscription</varname></link>
+   configuration.
+  </para>
+
+  <sect2 id="sequence-definition-mismatches">
+   <title>Sequence Definition Mismatches</title>
+   <warning>
+    <para>
+     If there are differences in sequence definitions between the publisher and
+     subscriber, a WARNING is logged.
+    </para>
+   </warning>
+   <para>
+    To resolve this, use
+    <link linkend="sql-altersequence"><command>ALTER SEQUENCE</command></link>
+    to align the subscriber's sequence parameters with those of the publisher.
+    Subsequently, execute <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+    <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>.
+   </para>
+  </sect2>
+
+  <sect2 id="sequences-out-of-sync">
+   <title>Refreshing Stale Sequences</title>
+   <para>
+    Subscriber side sequence values may frequently become out of sync due to
+    updates on the publisher.
+   </para>
+   <para>
+    To verify this, compare the sequences values between the publisher and
+    subscriber and execute
+    <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+    <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>
+    if required.
+   </para>
+  </sect2>
+
+  <sect2 id="logical-replication-sequences-examples">
+   <title>Examples</title>
+
+   <para>
+    Create some test sequences on the publisher.
+<programlisting>
+test_pub=# CREATE SEQUENCE s1 START WITH 10 INCREMENT BY 1;
+CREATE SEQUENCE
+test_pub=# CREATE SEQUENCE s2 START WITH 100 INCREMENT BY 10;
+CREATE SEQUENCE
+</programlisting></para>
+
+   <para>
+    Create the same sequences on the subscriber.
+<programlisting>
+test_sub=# CREATE SEQUENCE s1 START WITH 10 INCREMENT BY 1
+CREATE SEQUENCE
+test_sub=# CREATE SEQUENCE s2 START WITH 100 INCREMENT BY 10;
+CREATE SEQUENCE
+</programlisting></para>
+
+   <para>
+    Update the sequences at the publisher side few times.
+<programlisting>
+test_pub=# SELECT nextval('s1');
+ nextval
+---------
+      10
+(1 row)
+test_pub=# SELECT NEXTVAL('s1');
+ nextval
+---------
+      11
+(1 row)
+test_pub=# SELECT nextval('s2');
+ nextval
+---------
+     100
+(1 row)
+test_pub=# SELECT nextval('s2');
+ nextval
+---------
+     110
+(1 row)
+</programlisting></para>
+
+   <para>
+    Create a publication for the sequences.
+<programlisting>
+test_pub=# CREATE PUBLICATION pub1 FOR ALL SEQUENCES;
+CREATE PUBLICATION
+</programlisting></para>
+
+   <para>
+    Subscribe to the publication.
+<programlisting>
+test_sub=# CREATE SUBSCRIPTION sub1
+test_sub-# CONNECTION 'host=localhost dbname=test_pub application_name=sub1'
+test_sub-# PUBLICATION pub1;
+CREATE SUBSCRIPTION
+</programlisting></para>
+
+   <para>
+    Observe that initial sequence values are synchronized.
+<programlisting>
+test_sub=# SELECT * FROM s1;
+ last_value | log_cnt | is_called
+------------+---------+-----------
+         11 |      31 | t
+(1 row)
+
+test_sub=# SELECT * FROM s2;
+ last_value | log_cnt | is_called
+------------+---------+-----------
+        110 |      31 | t
+(1 row)
+</programlisting></para>
+
+   <para>
+    Update the sequences at the publisher side.
+<programlisting>
+test_pub=# SELECT nextval('s1');
+ nextval
+---------
+      12
+(1 row)
+test_pub=# SELECT nextval('s2');
+ nextval
+---------
+     120
+(1 row)
+</programlisting></para>
+
+   <para>
+    Re-synchronize all the sequences at the subscriber side using
+    <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+    <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>.
+<programlisting>
+test_sub=# ALTER SUBSCRIPTION sub1 REFRESH PUBLICATION SEQUENCES;
+ALTER SUBSCRIPTION
+
+test_sub=# SELECT * FROM s1;
+ last_value | log_cnt | is_called
+------------+---------+-----------
+         12 |      30 | t
+(1 row)
+
+test_sub=# SELECT * FROM s2
+ last_value | log_cnt | is_called
+------------+---------+-----------
+        120 |      30 | t
+(1 row)
+</programlisting></para>
+  </sect2>
+ </sect1>
+
  <sect1 id="logical-replication-conflicts">
   <title>Conflicts</title>
 
@@ -1677,16 +1872,18 @@ CONTEXT:  processing remote data for replication origin "pg_16395" during "INSER
 
    <listitem>
     <para>
-     Sequence data is not replicated.  The data in serial or identity columns
-     backed by sequences will of course be replicated as part of the table,
-     but the sequence itself would still show the start value on the
-     subscriber.  If the subscriber is used as a read-only database, then this
-     should typically not be a problem.  If, however, some kind of switchover
-     or failover to the subscriber database is intended, then the sequences
-     would need to be updated to the latest values, either by copying the
-     current data from the publisher (perhaps
-     using <command>pg_dump</command>) or by determining a sufficiently high
-     value from the tables themselves.
+     Incremental sequence changes are not replicated.  The data in serial or
+     identity columns backed by sequences will of course be replicated as part
+     of the table, but the sequence itself would still show the start value on
+     the subscriber.  If the subscriber is used as a read-only database, then
+     this should typically not be a problem.  If, however, some kind of
+     switchover or failover to the subscriber database is intended, then the
+     sequences would need to be updated to the latest values, either by executing
+     <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+     <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>
+     or by copying the current data from the publisher (perhaps using
+     <command>pg_dump</command>) or by determining a sufficiently high value
+     from the tables themselves.
     </para>
    </listitem>
 
@@ -1999,8 +2196,8 @@ CONTEXT:  processing remote data for replication origin "pg_16395" during "INSER
    <para>
     <link linkend="guc-max-logical-replication-workers"><varname>max_logical_replication_workers</varname></link>
     must be set to at least the number of subscriptions (for leader apply
-    workers), plus some reserve for the table synchronization workers and
-    parallel apply workers.
+    workers), plus some reserve for the parallel apply workers, table synchronization workers, and a sequence
+    synchronization worker.
    </para>
 
    <para>
@@ -2014,7 +2211,7 @@ CONTEXT:  processing remote data for replication origin "pg_16395" during "INSER
    <para>
     <link linkend="guc-max-sync-workers-per-subscription"><varname>max_sync_workers_per_subscription</varname></link>
      controls the amount of parallelism of the initial data copy during the
-     subscription initialization or when new tables are added.
+     subscription initialization or when new tables or sequences are added.
    </para>
 
    <para>
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 55417a6fa9..5fbb0c9c45 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -2017,8 +2017,9 @@ description | Waiting for a newly initialized WAL file to reach durable storage
       </para>
       <para>
        Type of the subscription worker process.  Possible types are
-       <literal>apply</literal>, <literal>parallel apply</literal>, and
-       <literal>table synchronization</literal>.
+       <literal>apply</literal>, <literal>parallel apply</literal>,
+       <literal>table synchronization</literal>, and
+       <literal>sequence synchronization</literal>.
       </para></entry>
      </row>
 
diff --git a/doc/src/sgml/ref/alter_subscription.sgml b/doc/src/sgml/ref/alter_subscription.sgml
index fdc648d007..457a614ea6 100644
--- a/doc/src/sgml/ref/alter_subscription.sgml
+++ b/doc/src/sgml/ref/alter_subscription.sgml
@@ -26,6 +26,7 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> SET PUBLICA
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> ADD PUBLICATION <replaceable class="parameter">publication_name</replaceable> [, ...] [ WITH ( <replaceable class="parameter">publication_option</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] ) ]
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> DROP PUBLICATION <replaceable class="parameter">publication_name</replaceable> [, ...] [ WITH ( <replaceable class="parameter">publication_option</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] ) ]
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> REFRESH PUBLICATION [ WITH ( <replaceable class="parameter">refresh_option</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] ) ]
+ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> REFRESH PUBLICATION SEQUENCES
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> ENABLE
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> DISABLE
 ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> SET ( <replaceable class="parameter">subscription_parameter</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] )
@@ -67,6 +68,7 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
 
   <para>
    Commands <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION</command>,
+   <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command>,
    <command>ALTER SUBSCRIPTION ... {SET|ADD|DROP} PUBLICATION ...</command>
    with <literal>refresh</literal> option as <literal>true</literal>,
    <command>ALTER SUBSCRIPTION ... SET (failover = true|false)</command> and
@@ -158,30 +160,51 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
     <term><literal>REFRESH PUBLICATION</literal></term>
     <listitem>
      <para>
-      Fetch missing table information from publisher.  This will start
+      Fetch missing table information from the publisher.  This will start
       replication of tables that were added to the subscribed-to publications
       since <link linkend="sql-createsubscription">
       <command>CREATE SUBSCRIPTION</command></link> or
       the last invocation of <command>REFRESH PUBLICATION</command>.
      </para>
 
+     <para>
+      Also, fetch missing sequence information from the publisher.
+     </para>
+
+     <para>
+      The system catalog <link linkend="catalog-pg-subscription-rel">pg_subscription_rel</link>
+      is updated to record all tables and sequences known to the subscription,
+      that are still part of the publication.
+     </para>
+
      <para>
       <replaceable>refresh_option</replaceable> specifies additional options for the
-      refresh operation.  The supported options are:
+      refresh operation.  The only supported option is:
 
       <variablelist>
        <varlistentry>
         <term><literal>copy_data</literal> (<type>boolean</type>)</term>
         <listitem>
          <para>
-          Specifies whether to copy pre-existing data in the publications
-          that are being subscribed to when the replication starts.
-          The default is <literal>true</literal>.
+          Specifies whether to copy pre-existing data for tables and synchronize
+          sequences in the publications that are being subscribed to when the replication
+          starts. The default is <literal>true</literal>.
          </para>
          <para>
           Previously subscribed tables are not copied, even if a table's row
           filter <literal>WHERE</literal> clause has since been modified.
          </para>
+         <para>
+          Previously subscribed sequences are not re-synchronized. To do that,
+          see <link linkend="sql-altersubscription-params-refresh-publication-sequences">
+          <command>ALTER SUBSCRIPTION ... REFRESH PUBLICATION SEQUENCES</command></link>
+         </para>
+         <para>
+          See <xref linkend="sequence-definition-mismatches"/> for recommendations on how
+          to handle any warnings about differences in the sequence definition
+          between the publisher and the subscriber, which might occur when
+          <literal>copy_data = true</literal>.
+         </para>
          <para>
           See <xref linkend="sql-createsubscription-notes"/> for details of
           how <literal>copy_data = true</literal> can interact with the
@@ -200,6 +223,28 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
     </listitem>
    </varlistentry>
 
+   <varlistentry id="sql-altersubscription-params-refresh-publication-sequences">
+    <term><literal>REFRESH PUBLICATION SEQUENCES</literal></term>
+    <listitem>
+     <para>
+      Fetch missing sequence information from the publisher, then re-synchronize
+      sequence data with the publisher. Unlike <link linkend="sql-altersubscription-params-refresh-publication">
+      <literal>ALTER SUBSCRIPTION ... REFRESH PUBLICATION</literal></link> which
+      only synchronizes newly added sequences, <literal>REFRESH PUBLICATION SEQUENCES</literal>
+      will re-synchronize the sequence data for all subscribed sequences.
+     </para>
+     <para>
+      See <xref linkend="sequence-definition-mismatches"/> for
+      recommendations on how to handle any warnings about differences in the
+      sequence definition between the publisher and the subscriber.
+     </para>
+     <para>
+      See <xref linkend="sequences-out-of-sync"/> for recommendations on how
+      to identify sequences and handle out-of-sync sequences.
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry id="sql-altersubscription-params-enable">
     <term><literal>ENABLE</literal></term>
     <listitem>
diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index 740b7d9421..1b1c9994e0 100644
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -263,6 +263,12 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
           <literal>copy_data = true</literal> can interact with the
           <literal>origin</literal> parameter.
          </para>
+         <para>
+          See <xref linkend="sequence-definition-mismatches"/>
+          for recommendations on how to handle any warnings about differences in
+          the sequence definition between the publisher and the subscriber,
+          which might occur when <literal>copy_data = true</literal>.
+         </para>
         </listitem>
        </varlistentry>
 
diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml
index 634a4c0fab..4261637af7 100644
--- a/doc/src/sgml/system-views.sgml
+++ b/doc/src/sgml/system-views.sgml
@@ -126,6 +126,11 @@
       <entry>prepared transactions</entry>
      </row>
 
+     <row>
+      <entry><link linkend="view-pg-publication-sequences"><structname>pg_publication_sequences</structname></link></entry>
+      <entry>publications and information of their associated sequences</entry>
+     </row>
+
      <row>
       <entry><link linkend="view-pg-publication-tables"><structname>pg_publication_tables</structname></link></entry>
       <entry>publications and information of their associated tables</entry>
@@ -2176,6 +2181,68 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx
 
  </sect1>
 
+ <sect1 id="view-pg-publication-sequences">
+  <title><structname>pg_publication_sequences</structname></title>
+
+  <indexterm zone="view-pg-publication-sequences">
+   <primary>pg_publication_sequences</primary>
+  </indexterm>
+
+  <para>
+   The view <structname>pg_publication_sequences</structname> provides
+   information about the mapping between publications and information of
+   sequences they contain.
+  </para>
+
+  <table>
+   <title><structname>pg_publication_sequences</structname> Columns</title>
+   <tgroup cols="1">
+    <thead>
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       Column Type
+      </para>
+      <para>
+       Description
+      </para></entry>
+     </row>
+    </thead>
+
+    <tbody>
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>pubname</structfield> <type>name</type>
+       (references <link linkend="catalog-pg-publication"><structname>pg_publication</structname></link>.<structfield>pubname</structfield>)
+      </para>
+      <para>
+       Name of publication
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>schemaname</structfield> <type>name</type>
+       (references <link linkend="catalog-pg-namespace"><structname>pg_namespace</structname></link>.<structfield>nspname</structfield>)
+      </para>
+      <para>
+       Name of schema containing sequence
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>sequencename</structfield> <type>name</type>
+       (references <link linkend="catalog-pg-class"><structname>pg_class</structname></link>.<structfield>relname</structfield>)
+      </para>
+      <para>
+       Name of sequence
+      </para></entry>
+     </row>
+    </tbody>
+   </tgroup>
+  </table>
+ </sect1>
+
  <sect1 id="view-pg-publication-tables">
   <title><structname>pg_publication_tables</structname></title>
 
-- 
2.34.1