Reconsider pg_stat_subscription_workers view.

It was decided (refer to the Discussion link below) that the stats
collector is not an appropriate place to store the error information of
subscription workers.

This patch changes the pg_stat_subscription_workers view (introduced by
commit 8d74fc9) so that it stores only statistics counters:
apply_error_count and sync_error_count, and has one entry for
each subscription. The removed error information such as error-XID and
the error message would be stored in another way in the future which is
more reliable and persistent.

After removing these error details, there is no longer any relation
information, so the subscription statistics are now a cluster-wide
statistics.

The patch also changes the view name to pg_stat_subscription_stats since
the word "worker" is an implementation detail that we use one worker for
one tablesync and one apply.

Author: Masahiko Sawada, based on suggestions by Andres Freund
Reviewed-by: Peter Smith, Haiying Tang, Takamichi Osumi, Amit Kapila
Discussion: https://postgr.es/m/20220125063131.4cmvsxbz2tdg6g65@alap3.anarazel.de

Author: Amit Kapila

doc/src/sgml/logical-replication.sgml

@@ -346,9 +346,7 @@
   <para>
    A conflict will produce an error and will stop the replication; it must be
    resolved manually by the user.  Details about the conflict can be found in
-   <link linkend="monitoring-pg-stat-subscription-workers">
-   <structname>pg_stat_subscription_workers</structname></link> and the
-   subscriber's server log.
+   the subscriber's server log.
   </para>
 
   <para>

doc/src/sgml/monitoring.sgml

@@ -628,11 +628,10 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </row>
 
      <row>
-      <entry><structname>pg_stat_subscription_workers</structname><indexterm><primary>pg_stat_subscription_workers</primary></indexterm></entry>
-      <entry>One row per subscription worker, showing statistics about errors
-      that occurred on that subscription worker.
-      See <link linkend="monitoring-pg-stat-subscription-workers">
-      <structname>pg_stat_subscription_workers</structname></link> for details.
+      <entry><structname>pg_stat_subscription_stats</structname><indexterm><primary>pg_stat_subscription_stats</primary></indexterm></entry>
+      <entry>One row per subscription, showing statistics about errors.
+      See <link linkend="monitoring-pg-stat-subscription-stats">
+      <structname>pg_stat_subscription_stats</structname></link> for details.
       </entry>
      </row>
 
@@ -3063,23 +3062,20 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
 
  </sect2>
 
- <sect2 id="monitoring-pg-stat-subscription-workers">
-  <title><structname>pg_stat_subscription_workers</structname></title>
+ <sect2 id="monitoring-pg-stat-subscription-stats">
+  <title><structname>pg_stat_subscription_stats</structname></title>
 
   <indexterm>
-   <primary>pg_stat_subscription_workers</primary>
+   <primary>pg_stat_subscription_stats</primary>
   </indexterm>
 
   <para>
-   The <structname>pg_stat_subscription_workers</structname> view will contain
-   one row per subscription worker on which errors have occurred, for workers
-   applying logical replication changes and workers handling the initial data
-   copy of the subscribed tables.  The statistics entry is removed when the
-   corresponding subscription is dropped.
+   The <structname>pg_stat_subscription_stats</structname> view will contain
+   one row per subscription.
   </para>
 
-  <table id="pg-stat-subscription-workers" xreflabel="pg_stat_subscription_workers">
-   <title><structname>pg_stat_subscription_workers</structname> View</title>
+  <table id="pg-stat-subscription-stats" xreflabel="pg_stat_subscription_stats">
+   <title><structname>pg_stat_subscription_stats</structname> View</title>
    <tgroup cols="1">
     <thead>
      <row>
@@ -3113,72 +3109,31 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
 
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>subrelid</structfield> <type>oid</type>
+       <structfield>apply_error_count</structfield> <type>bigint</type>
       </para>
       <para>
-       OID of the relation that the worker is synchronizing; null for the
-       main apply worker
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_relid</structfield> <type>oid</type>
-      </para>
-      <para>
-       OID of the relation that the worker was processing when the
-       error occurred
+       Number of times an error occurred while applying changes
       </para></entry>
      </row>
 
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_command</structfield> <type>text</type>
+       <structfield>sync_error_count</structfield> <type>bigint</type>
       </para>
       <para>
-       Name of command being applied when the error occurred.  This field
-       is null if the error was reported during the initial data copy.
+       Number of times an error occurred during the initial table
+       synchronization
       </para></entry>
      </row>
 
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_xid</structfield> <type>xid</type>
-      </para>
-      <para>
-       Transaction ID of the publisher node being applied when the error
-       occurred.  This field is null if the error was reported
-       during the initial data copy.
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_count</structfield> <type>uint8</type>
-      </para>
-      <para>
-       Number of consecutive times the error occurred
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_message</structfield> <type>text</type>
-      </para>
-      <para>
-       The error message
-      </para></entry>
-     </row>
-
-     <row>
-      <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>last_error_time</structfield> <type>timestamp with time zone</type>
+       <structfield>stats_reset</structfield> <type>timestamp with time zone</type>
       </para>
       <para>
-       Last time at which this error occurred
+       Time at which these statistics were last reset
       </para></entry>
      </row>
-
     </tbody>
    </tgroup>
   </table>
@@ -5320,22 +5275,16 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
-          <primary>pg_stat_reset_subscription_worker</primary>
+          <primary>pg_stat_reset_subscription_stats</primary>
         </indexterm>
-        <function>pg_stat_reset_subscription_worker</function> ( <parameter>subid</parameter> <type>oid</type> <optional>, <parameter>relid</parameter> <type>oid</type> </optional> )
+        <function>pg_stat_reset_subscription_stats</function> ( <type>oid</type> )
         <returnvalue>void</returnvalue>
        </para>
        <para>
-        Resets the statistics of subscription workers running on the
-        subscription with <parameter>subid</parameter> shown in the
-        <structname>pg_stat_subscription_workers</structname> view.  If the
-        argument <parameter>relid</parameter> is not <literal>NULL</literal>,
-        resets statistics of the subscription worker handling the initial data
-        copy of the relation with <parameter>relid</parameter>.  Otherwise,
-        resets the subscription worker statistics of the main apply worker.
-        If the argument <parameter>relid</parameter> is omitted, resets the
-        statistics of all subscription workers running on the subscription
-        with <parameter>subid</parameter>.
+        Resets statistics for a single subscription shown in the
+        <structname>pg_stat_subscription_stats</structname> view to zero. If
+        the argument is <literal>NULL</literal>, reset statistics for all
+        subscriptions.
        </para>
        <para>
         This function is restricted to superusers by default, but other users

src/backend/catalog/system_functions.sql

@@ -639,9 +639,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM publ
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
-REVOKE EXECUTE ON FUNCTION pg_stat_reset_subscription_worker(oid) FROM public;
-
-REVOKE EXECUTE ON FUNCTION pg_stat_reset_subscription_worker(oid, oid) FROM public;
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_subscription_stats(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION lo_import(text) FROM public;
 

src/backend/catalog/system_views.sql

@@ -1264,25 +1264,12 @@ GRANT SELECT (oid, subdbid, subname, subowner, subenabled, subbinary,
               substream, subtwophasestate, subslotname, subsynccommit, subpublications)
     ON pg_subscription TO public;
 
-CREATE VIEW pg_stat_subscription_workers AS
+CREATE VIEW pg_stat_subscription_stats AS
     SELECT
-        w.subid,
+        ss.subid,
         s.subname,
-        w.subrelid,
-        w.last_error_relid,
-        w.last_error_command,
-        w.last_error_xid,
-        w.last_error_count,
-        w.last_error_message,
-        w.last_error_time
-    FROM (SELECT
-              oid as subid,
-              NULL as relid
-          FROM pg_subscription
-          UNION ALL
-          SELECT
-              srsubid as subid,
-              srrelid as relid
-          FROM pg_subscription_rel) sr,
-          LATERAL pg_stat_get_subscription_worker(sr.subid, sr.relid) w
-          JOIN pg_subscription s ON (w.subid = s.oid);
+        ss.apply_error_count,
+        ss.sync_error_count,
+        ss.stats_reset
+    FROM pg_subscription as s,
+         pg_stat_get_subscription_stats(s.oid) as ss;