doc: add a link to the current documentation from the contents page

Per user report on mailing list.

dbutils.c

@@ -2178,8 +2178,9 @@ get_downstream_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoL
 					  "LEFT JOIN pg_catalog.pg_replication_slots rs "
 					  "       ON rs.slot_name = n.slot_name "
 					  "    WHERE n.slot_name IS NOT NULL"
-                      "      AND rs.slot_name IS NULL "
+					  "      AND rs.slot_name IS NULL "
-                      "      AND n.upstream_node_id = %i ",
+					  "      AND n.upstream_node_id = %i "
+					  "      AND n.type = 'standby'",
 					  this_node_id);
 
 	log_verbose(LOG_DEBUG, "get_all_node_records_with_missing_slot():\n%s", query.data);
@@ -2916,8 +2917,7 @@ get_datadir_configuration_files(PGconn *conn, KeyValueList *list)
 
 	for (i = 0; i < PQntuples(res); i++)
 	{
-		key_value_list_set(
+		key_value_list_set(list,
-						   list,
 						   PQgetvalue(res, i, 1),
 						   PQgetvalue(res, i, 0));
 	}
@@ -3654,7 +3654,7 @@ get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record)
 
 
 int
-get_free_replication_slots(PGconn *conn)
+get_free_replication_slot_count(PGconn *conn)
 {
 	PQExpBufferData query;
 	PGresult   *res = NULL;
@@ -3691,6 +3691,47 @@ get_free_replication_slots(PGconn *conn)
 }
 
 
+int
+get_inactive_replication_slots(PGconn *conn, KeyValueList *list)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+	int			i, inactive_slots = 0;
+
+	initPQExpBuffer(&query);
+
+	appendPQExpBuffer(&query,
+					  "   SELECT slot_name, slot_type "
+					  "     FROM pg_catalog.pg_replication_slots "
+					  "    WHERE active IS FALSE "
+					  " ORDER BY slot_name ");
+
+	res = PQexec(conn, query.data);
+	termPQExpBuffer(&query);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_error(_("unable to execute replication slot query"));
+		log_detail("%s", PQerrorMessage(conn));
+		PQclear(res);
+		return -1;
+	}
+
+	inactive_slots = PQntuples(res);
+
+	for (i = 0; i < inactive_slots; i++)
+	{
+		key_value_list_set(list,
+						   PQgetvalue(res, i, 0),
+						   PQgetvalue(res, i, 1));
+	}
+
+	PQclear(res);
+	return inactive_slots;
+}
+
+
+
 /* ==================== */
 /* tablespace functions */
 /* ==================== */

dbutils.h

@@ -455,7 +455,8 @@ void		create_slot_name(char *slot_name, int node_id);
 bool		create_replication_slot(PGconn *conn, char *slot_name, int server_version_num, PQExpBufferData *error_msg);
 bool		drop_replication_slot(PGconn *conn, char *slot_name);
 RecordStatus get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record);
-int			get_free_replication_slots(PGconn *conn);
+int			get_free_replication_slot_count(PGconn *conn);
+int			get_inactive_replication_slots(PGconn *conn, KeyValueList *list);
 
 /* tablespace functions */
 bool		get_tablespace_name_by_location(PGconn *conn, const char *location, char *name);

doc/appendix-release-notes.sgml

@@ -17,7 +17,7 @@
 
   <sect1 id="release-4.0.6">
     <title>Release 4.0.6</title>
-    <para><emphasis>June ??, 2018</emphasis></para>
+    <para><emphasis>June 14, 2018</emphasis></para>
     <para>
 	  &repmgr; 4.0.6 contains a number of bug fixes and usability enhancements.
     </para>
@@ -58,6 +58,23 @@
            </para>
           </listitem>
 
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Improve documentation of <option>--recovery-conf-only</option> mode
+			   (GitHub #438)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Don't require presence of <varname>user</varname> parameter in conninfo string
+			   (GitHub #437)
+           </para>
+          </listitem>
+
+
         </itemizedlist>
       </para>
     </sect2>
@@ -71,7 +88,7 @@
           <listitem>
             <para>
               <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>:
-              prevent registration of a witness server with the same name as an existing node.
+              prevent registration of a witness server with the same name as an existing node
            </para>
           </listitem>
 
@@ -84,23 +101,6 @@
            </para>
           </listitem>
 
-
-          <listitem>
-            <para>
-               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
-			   Don't require presence of <varname>user</varname> parameter in conninfo string
-			   (GitHub #437)
-           </para>
-          </listitem>
-
-          <listitem>
-            <para>
-               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
-			   Improve documentation of <option>--recovery-conf-only</option> mode
-			   (GitHub #438)
-           </para>
-          </listitem>
-
           <listitem>
             <para>
                <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:

doc/appendix-signatures.sgml

@@ -33,34 +33,5 @@
 
  </sect1>
 
- <sect1 id="repmgr-rpm-key" xreflabel="repmgr rpm key">
-   <title>repmgr RPM signing key</title>
-   <para>
-     The signing key ID used for <application>repmgr</application> source code bundles is:
-     <ulink url="http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr">
-       <literal>0x702D883A</literal></ulink>.
-   </para>
-
-   <para>
-     To download the <application>repmgr</application> source key to your computer:
-     <programlisting>
-       curl -s http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr | gpg --import
-       gpg --fingerprint 0x702D883A
-     </programlisting>
-     then verify that the fingerprint is the expected value:
-     <programlisting>
-       AE4E 390E A58E 0037 6148  3F29 888D 018B 702D 883A</programlisting>
-   </para>
-
-   <para>
-     To check a repository RPM, use <application>rpmkeys</application> to load the
-      packaging signing key into the RPM database then use <literal>rpm -K</literal>, e.g.:
-     <programlisting>
-       sudo rpmkeys --import http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr
-       rpm -K postgresql-bdr94-2ndquadrant-redhat-1.0-2.noarch.rpm
-     </programlisting>
-   </para>
-
- </sect1>
 
 </appendix>

doc/configuration-service-commands.sgml

@@ -25,7 +25,7 @@
 
   <note>
     <para>
-      If using <application>systemd</application>, ensure you have <varname>RemoteIPC</varname> set to <literal>off</literal>.
+      If using <application>systemd</application>, ensure you have <varname>RemoveIPC</varname> set to <literal>off</literal>.
       See the <ulink url="https://wiki.postgresql.org/wiki/Systemd">systemd</ulink>
       entry in the <ulink url="https://wiki.postgresql.org/wiki/Main_Page">PostgreSQL wiki</ulink> for details.
     </para>
@@ -47,16 +47,24 @@
     service_restart_command
     service_reload_command</programlisting>
   </para>
-
   <note>
     <para>
-      It's also possible to specify a <varname>service_promote_command</varname>;
+      It's also possible to specify a <varname>service_promote_command</varname>.
-      this overrides any value contained in the setting <varname>promote_command</varname>.
       This is intended for systems which provide a package-level promote command,
-      such as Debian's <application>pg_ctlcluster</application>.
+      such as Debian's <application>pg_ctlcluster</application>, to promote the
+      PostgreSQL from standby to primary.
+    </para>
+    <para>
+      If your packaging system does not provide such a command, it can be left empty,
+      and &repmgr; will generate the appropriate <command>pg_ctl ... promote</command> command.
+    </para>
+    <para>
+      Do not confuse this with <varname>promote_command</varname>, which is used
+      by <application>repmgrd</application> to execute <xref linkend="repmgr-standby-promote">.
     </para>
   </note>
 
+
   <para>
     To confirm which command &repmgr; will execute for each action, use
     <command>repmgr node service --list --action=...</command>, e.g.:

doc/event-notifications.sgml

@@ -217,9 +217,6 @@
    <listitem>
     <simpara><literal>repmgrd_promote_error</literal></simpara>
    </listitem>
-   <listitem>
-    <simpara><literal>repmgrd_failover_promote</literal></simpara>
-   </listitem>
    <listitem>
     <simpara><literal>bdr_failover</literal></simpara>
    </listitem>

doc/repmgr-node-check.sgml

@@ -79,9 +79,26 @@
 
     </itemizedlist>
   </para>
-  <para>
+  </refsect1>
-   Individual checks can also be output in a Nagios-compatible format by additionally
+
-   providing the option <literal>--nagios</literal>.
+  <refsect1>
-  </para>
+    <title>Output format</title>
+    <para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <literal>--csv</literal>: generate output in CSV format (not available
+            for individual checks)
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <literal>--nagios</literal>: generate output in a Nagios-compatible format
+          </simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
   </refsect1>
 </refentry>

doc/repmgr-node-status.sgml

@@ -24,7 +24,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-        $ repmgr -f /etc/repmgr.comf node status
+        $ repmgr -f /etc/repmgr.conf node status
         Node "node1":
             PostgreSQL version: 10beta1
             Total data size: 30 MB
@@ -38,6 +38,20 @@
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Output format</title>
+    <para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <literal>--csv</literal>: generate output in CSV format
+          </simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>See also</title>
     <para>

doc/repmgr-standby-promote.sgml

@@ -32,6 +32,7 @@
       check the promotion every <varname>promote_check_interval</varname> seconds (default: 1 second).
       Both values can be defined in <filename>repmgr.conf</filename>.
     </para>
+
   </refsect1>
 
   <refsect1>

doc/repmgr-standby-switchover.sgml

@@ -12,6 +12,7 @@
     <refpurpose>promote a standby to primary and demote the existing primary to a standby</refpurpose>
   </refnamediv>
 
+
   <refsect1>
     <title>Description</title>
 
@@ -39,6 +40,14 @@
       For more details on performing a switchover, including preparation and configuration,
       see section <xref linkend="performing-switchover">.
     </para>
+
+    <note>
+      <para>
+        <application>repmgrd</application> should not be active on any nodes while a switchover is being
+        executed. This restriction may be lifted in a later version.
+      </para>
+    </note>
+
   </refsect1>
 
   <refsect1>
@@ -171,10 +180,12 @@
       Execute with the <literal>--dry-run</literal> option to test the switchover as far as
       possible without actually changing the status of either node.
     </para>
-    <para>
+    <important>
-      <application>repmgrd</application> should not be active on any nodes while a switchover is being
+      <para>
-      executed. This restriction may be lifted in a later version.
+        <application>repmgrd</application> must be shut down on all nodes while a switchover is being
-    </para>
+        executed. This restriction will be removed in a future &repmgr; version.
+      </para>
+    </important>
     <para>
       External database connections, e.g. from an application, should not be permitted while
       the switchover is taking place. In particular, active transactions on the primary

doc/repmgr.sgml

@@ -25,7 +25,13 @@
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
    use with PostgreSQL 9.3 - PostgreSQL 10.
-   It describes the functionality supported by the current version of &repmgr;.
+   </para>
+   <para>
+     &repmgr; is being continually developed and we strongly recommend using the
+     latest version. Please check the
+     <ulink url="https://repmgr.org/">repmgr website</ulink> for details
+     about the current &repmgr; version as well as the
+     <ulink url="https://repmgr.org/docs/current/index.html">current documentation</ulink>.
    </para>
 
    <para>

doc/repmgrd-bdr.sgml

@@ -99,15 +99,16 @@
       replication cluster. The database must be the BDR-enabled database.
     </para>
     <para>
-      If defined, the evenr <application>event_notifications</application> parameter
+      If defined, the <varname>event_notifications</varname> parameter will restrict
-      will restrict execution of <varname>event_notification_command</varname>
+      execution of the script defined in  <varname>event_notification_command</varname>
       to the specified event(s).
     </para>
     <note>
       <simpara>
         <varname>event_notification_command</varname> is the script which does the actual "heavy lifting"
         of reconfiguring the proxy server/ connection pooler. It is fully
-        user-definable; a reference implementation is documented below.
+        user-definable; see section <xref linkend="bdr-event-notification-command"> for a reference
+        implementation.
       </simpara>
     </note>
 
@@ -169,8 +170,8 @@
     </para>
   </sect1>
 
-  <sect1 id="bdr-event-notification-command" xreflabel="BDR failover event notification command">
+  <sect1 id="bdr-event-notification-command" xreflabel="Defining the BDR failover &quot;event_notification command&quot;">
-    <title>Defining the "event_notification_command"</title>
+    <title>Defining the BDR failover "event_notification_command"</title>
     <para>
       Key to "failover" execution is the <literal>event_notification_command</literal>,
       which is a user-definable script specified in <filename>repmpgr.conf</filename>

doc/repmgrd-configuration.sgml

@@ -34,6 +34,24 @@
       the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
     </para>
 
+    <para>
+      To apply configuration file changes to a running <application>repmgrd</application>
+      daemon, execute the operating system's r<application>repmgrd</application> service reload command
+      (see <xref linkend="appendix-packages"> for examples),
+      or for instances  which were manually started, execute <command>kill -HUP</command>, e.g.
+      <command>kill -HUP `cat /tmp/repmgrd.pid`</command>.
+    </para>
+    <note>
+      <para>
+        Check the <application>repmgrd</application> log to see what changes were
+        applied, or if any issues were encountered when reloading the configuration.
+      </para>
+    </note>
+    <para>
+      Note that only a subset of configuration file parameters can be changed on a
+      running <application>repmgrd</application> daemon.
+    </para>
+
     <sect2 id="repmgrd-automatic-failover-configuration">
       <title>automatic failover configuration</title>
       <para>
@@ -162,13 +180,6 @@
         repmgrd -f /etc/repmgr.conf --pid-file /tmp/repmgrd.pid --daemonize</programlisting>
       and stopped with <command>kill `cat /tmp/repmgrd.pid`</command>. Adjust paths as appropriate.
     </para>
-    <para>
-      To apply configuration file changes to a running <application>repmgrd</application>
-      daemon, execute the operating system's service reload command (for manually started
-      instances, execute <command>kill -HUP `cat /tmp/repmgrd.pid`</command>).
-      Note that only a subset of configuration file parameters can be changed on a
-      running <application>repmgrd</application> daemon.
-    </para>
 
     <sect2 id="repmgrd-configuration-debian-ubuntu">
       <indexterm>

doc/switchover.sgml

@@ -140,10 +140,12 @@
     manually with <command>repmgr node check --archive-ready</command>.
    </para>
 
-   <para>
+   <note>
-    Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
+     <para>
-    promoting a node.
+       Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
-   </para>
+       promoting a node. This restriction will be removed in a future &repmgr; version.
+     </para>
+   </note>
 
    <para>
     Finally, consider executing <command>repmgr standby switchover</command> with the

repmgr-action-standby.c

@@ -2257,7 +2257,7 @@ do_standby_follow(void)
 
 	if (config_file_options.use_replication_slots)
 	{
-		int free_slots = get_free_replication_slots(primary_conn);
+		int free_slots = get_free_replication_slot_count(primary_conn);
 		if (free_slots < 0)
 		{
 			log_error(_("unable to determine number of free replication slots on the primary"));
@@ -3433,8 +3433,6 @@ do_standby_switchover(void)
 				}
 			}
 
-
-
 			/*
 			 * check there are sufficient free walsenders - obviously there's potential
 			 * for a later race condition if some walsenders come into use before the
@@ -3858,7 +3856,6 @@ do_standby_switchover(void)
 	 * If --siblings-follow specified, attempt to make them follow the new
 	 * primary
 	 */
-
 	if (runtime_options.siblings_follow == true && sibling_nodes.node_count > 0)
 	{
 		int			failed_follow_count = 0;
@@ -3885,8 +3882,17 @@ do_standby_switchover(void)
 			initPQExpBuffer(&remote_command_str);
 			make_remote_repmgr_path(&remote_command_str, &sibling_node_record);
 
-			appendPQExpBuffer(&remote_command_str,
+			if (sibling_node_record.type == WITNESS)
-							  "standby follow 2>/dev/null && echo \"1\" || echo \"0\"");
+			{
+				appendPQExpBuffer(&remote_command_str,
+								  "witness register -d \\'%s\\' --force 2>/dev/null && echo \"1\" || echo \"0\"",
+								  local_node_record.conninfo);
+			}
+			else
+			{
+				appendPQExpBuffer(&remote_command_str,
+								  "standby follow 2>/dev/null && echo \"1\" || echo \"0\"");
+			}
 			get_conninfo_value(cell->node_info->conninfo, "host", host);
 			log_debug("executing:\n  %s", remote_command_str.data);
 
@@ -3901,8 +3907,16 @@ do_standby_switchover(void)
 
 			if (success == false || command_output.data[0] == '0')
 			{
-				log_warning(_("STANDBY FOLLOW failed on node \"%s\""),
+				if (sibling_node_record.type == WITNESS)
-							cell->node_info->node_name);
+				{
+					log_warning(_("WITNESS REGISTER failed on node \"%s\""),
+								cell->node_info->node_name);
+				}
+				else
+				{
+					log_warning(_("STANDBY FOLLOW failed on node \"%s\""),
+								cell->node_info->node_name);
+				}
 				failed_follow_count++;
 			}
 

repmgr.conf.sample

@@ -253,11 +253,11 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# primary (or other upstream node)
 #reconnect_interval=10			# Interval between attempts  to reconnect to an unreachable
 					# primary (or other upstream node)
-#promote_command=			# command to execute when promoting a new primary; use something like:
+#promote_command=			# command repmgrd executes when promoting a new primary; use something like:
 					#
 					#     repmgr standby promote -f /etc/repmgr.conf
 					#
-#follow_command=			# command to execute when instructing a standby to follow a new primary;
+#follow_command=			# command repmgrd executes when instructing a standby to follow a new primary;
 					# use something like:
 					#
 					#     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
@@ -310,11 +310,11 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #service_stop_command = ''
 #service_restart_command = ''
 #service_reload_command = ''
-#service_promote_command = ''		# Note: this overrides any value contained in the setting
+#service_promote_command = ''		# This parameter is intended for systems which provide a
-					# "promote_command". This is intended for systems which
+					# package-level promote command, such as Debian's
-					# provide a package-level promote command, such as Debian's
+					# "pg_ctlcluster". *IMPORTANT*: it is *not* a substitute
-					# "pg_ctlcluster"
+					# for "promote_command"; do not use "repmgr standby promote"
-
+					# (or a script which executes "repmgr standby promote") here.
 
 #------------------------------------------------------------------------------
 # Status check thresholds