Track statistics for spilling of changes from ReorderBuffer.

This adds the statistics about transactions spilled to disk from
ReorderBuffer. Users can query the pg_stat_replication_slots view to check
these stats and call pg_stat_reset_replication_slot to reset the stats of
a particular slot. Users can pass NULL in pg_stat_reset_replication_slot
to reset stats of all the slots.

This commit extends the statistics collector to track this information
about slots.

Author: Sawada Masahiko and Amit Kapila
Reviewed-by: Amit Kapila and Dilip Kumar
Discussion: https://postgr.es/m/CA+fd4k5_pPAYRTDrO2PbtTOe0eHQpBvuqmCr8ic39uTNmR49Eg@mail.gmail.com

1 files changed, 112 insertions, 0 deletions

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 171ba7049c7..66566765f0c 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -315,6 +315,15 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </row>
 
      <row>
+      <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
+      <entry>One row per replication slot, showing statistics about
+       replication slot usage.
+       See <link linkend="monitoring-pg-stat-replication-slots-view">
+       <structname>pg_stat_replication_slots</structname></link> for details.
+      </entry>
+     </row>
+
+     <row>
       <entry><structname>pg_stat_wal_receiver</structname><indexterm><primary>pg_stat_wal_receiver</primary></indexterm></entry>
       <entry>Only one row, showing statistics about the WAL receiver from
        that receiver's connected server.
@@ -2552,6 +2561,88 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
 
  </sect2>
 
+ <sect2 id="monitoring-pg-stat-replication-slots-view">
+  <title><structname>pg_stat_replication_slots</structname></title>
+
+  <indexterm>
+   <primary>pg_stat_replication_slots</primary>
+  </indexterm>
+
+  <para>
+   The <structname>pg_stat_replication_slots</structname> view will contain
+   one row per logical replication slot, showing statistics about its usage.
+  </para>
+
+  <table id="pg-stat-replication-slots-view" xreflabel="pg_stat_replication_slots">
+   <title><structname>pg_stat_replication_slots</structname> View</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>name</structfield> <type>text</type>
+       </para>
+       <para>
+        A unique, cluster-wide identifier for the replication slot
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+        <structfield>spill_txns</structfield> <type>bigint</type>
+       </para>
+       <para>
+        Number of transactions spilled to disk after the memory used by
+        logical decoding exceeds <literal>logical_decoding_work_mem</literal>. The
+        counter gets incremented both for toplevel transactions and
+        subtransactions.
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+        <structfield>spill_count</structfield> <type>bigint</type>
+       </para>
+       <para>
+        Number of times transactions were spilled to disk. Transactions
+        may get spilled repeatedly, and this counter gets incremented on every
+        such invocation.
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+        <structfield>spill_bytes</structfield> <type>bigint</type>
+       </para>
+       <para>
+        Amount of decoded transaction data spilled to disk.
+      </para></entry>
+     </row>
+
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+        <structfield>stats_reset</structfield> <type>timestamp with time zone</type>
+       </para>
+       <para>
+        Time at which these statistics were last reset
+       </para></entry>
+     </row>
+    </tbody>
+   </tgroup>
+  </table>
+
+ </sect2>
+
  <sect2 id="monitoring-pg-stat-wal-receiver-view">
   <title><structname>pg_stat_wal_receiver</structname></title>
 
@@ -4802,6 +4893,27 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i
         can be granted EXECUTE to run the function.
        </para></entry>
       </row>
+
+      <row>
+        <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+          <primary>pg_stat_reset_replication_slot</primary>
+        </indexterm>
+        <function>pg_stat_reset_replication_slot</function> ( <type>text</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+         Resets statistics to zero for a single replication slot, or for all
+         replication slots in the cluster.  The argument can be either the name
+         of the slot to reset the stats or NULL.  If the argument is NULL, all
+         counters shown in the <structname>pg_stat_replication_slots</structname>
+         view for all replication slots are reset.
+       </para>
+       <para>
+         This function is restricted to superusers by default, but other users
+         can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
      </tbody>
     </tgroup>
    </table>