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

Per user report on mailing list.

HISTORY

@@ -1,3 +1,22 @@
+4.0.6   2018-06-14
+        repmgr: (witness register) prevent registration of a witness server with the
+ 		  same name as an existing node (Ian)
+		repmgr: (standby follow) check node has actually connected to new primary
+		  before reporting success; GitHub #444 (Ian)
+		repmgr: (standby clone) improve handling of external configuration file copying,
+		  including consideration in --dry-run check; GitHub #443 (Ian)
+		repmgr: (standby clone) don't require presence of "user" parameter in
+		  conninfo string; GitHub #437 (Ian)
+		repmgr: (standby clone) improve documentation of --recovery-conf-only
+		  mode; GitHub #438 (Ian)
+		repmgr: (node rejoin) fix bug when parsing --config-files parameter;
+		  GitHub #442 (Ian)
+		repmgr: when using --dry-run, force log level to INFO to ensure output
+		  will always be displayed; GitHub #441 (Ian)
+        repmgr: (cluster matrix/crosscheck) return non-zero exit code if node
+           connection issues detected; GitHub #447 (Ian)
+		repmgrd: ensure local node is counted as quorum member; GitHub #439 (Ian)
+
 4.0.5   2018-05-02
         repmgr: poll demoted primary after restart as a standby during a
           switchover operation; GitHub #408 (Ian)

configfile.c

@@ -319,13 +319,20 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->use_primary_conninfo_password = false;
 	memset(options->passfile, 0, sizeof(options->passfile));
 
-	/*-----------------------
+	/*-------------------------
 	 * standby promote settings
-	 *------------------------
+	 *-------------------------
 	 */
 	options->promote_check_timeout = DEFAULT_PROMOTE_CHECK_TIMEOUT;
 	options->promote_check_interval = DEFAULT_PROMOTE_CHECK_INTERVAL;
 
+	/*------------------------
+	 * standby follow settings
+	 *------------------------
+	 */
+	options->primary_follow_timeout = DEFAULT_PRIMARY_FOLLOW_TIMEOUT;
+	options->standby_follow_timeout = DEFAULT_STANDBY_FOLLOW_TIMEOUT;
+
 	/*-----------------
 	 * repmgrd settings
 	 *-----------------
@@ -345,7 +352,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->degraded_monitoring_timeout = -1;
 	options->async_query_timeout = DEFAULT_ASYNC_QUERY_TIMEOUT;
 	options->primary_notification_timeout = DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT;
-	options->primary_follow_timeout = DEFAULT_PRIMARY_FOLLOW_TIMEOUT;
 	options->standby_reconnect_timeout = DEFAULT_STANDBY_RECONNECT_TIMEOUT;
 
 	/*-------------
@@ -527,6 +533,12 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		else if (strcmp(name, "promote_check_interval") == 0)
 			options->promote_check_interval = repmgr_atoi(value, name, error_list, 1);
 
+		/* standby follow settings */
+		else if (strcmp(name, "primary_follow_timeout") == 0)
+			options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "standby_follow_timeout") == 0)
+			options->standby_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+
 		/* node check settings */
 		else if (strcmp(name, "archive_ready_warning") == 0)
 			options->archive_ready_warning = repmgr_atoi(value, name, error_list, 1);
@@ -576,8 +588,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			options->async_query_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "primary_notification_timeout") == 0)
 			options->primary_notification_timeout = repmgr_atoi(value, name, error_list, 0);
-		else if (strcmp(name, "primary_follow_timeout") == 0)
-			options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "standby_reconnect_timeout") == 0)
 			options->standby_reconnect_timeout = repmgr_atoi(value, name, error_list, 0);
 

configfile.h

@@ -98,6 +98,10 @@ typedef struct
 	int			promote_check_timeout;
 	int			promote_check_interval;
 
+	/* standby follow settings */
+	int			primary_follow_timeout;
+	int			standby_follow_timeout;
+
 	/* node check settings */
 	int			archive_ready_warning;
 	int			archive_ready_critical;
@@ -120,7 +124,6 @@ typedef struct
 	int			degraded_monitoring_timeout;
 	int			async_query_timeout;
 	int			primary_notification_timeout;
-	int			primary_follow_timeout;
 	int			standby_reconnect_timeout;
 
 	/* BDR settings */
@@ -167,6 +170,9 @@ typedef struct
 		false, "", "", { NULL, NULL }, "", false, "", false, "", \
 		/* standby promote settings */ \
 		DEFAULT_PROMOTE_CHECK_TIMEOUT, DEFAULT_PROMOTE_CHECK_INTERVAL, \
+		/* standby follow settings */ \
+		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
+		DEFAULT_STANDBY_FOLLOW_TIMEOUT,	\
 		/* node check settings */ \
 		DEFAULT_ARCHIVE_READY_WARNING, DEFAULT_ARCHIVE_READY_CRITICAL, \
 		DEFAULT_REPLICATION_LAG_WARNING, DEFAULT_REPLICATION_LAG_CRITICAL, \
@@ -180,7 +186,6 @@ typedef struct
         false, -1, \
 		DEFAULT_ASYNC_QUERY_TIMEOUT, \
 		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT,	\
-		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
 		DEFAULT_STANDBY_RECONNECT_TIMEOUT,	\
 		/* BDR settings */ \
 		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \

configure.in

@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.0.5], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
+AC_INIT([repmgr], [4.0.6], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
 
 AC_COPYRIGHT([Copyright (c) 2010-2018, 2ndQuadrant Ltd.])
 

dbutils.c

@@ -23,6 +23,7 @@
 #include <sys/time.h>
 #include <sys/stat.h>
 #include <dirent.h>
+#include <arpa/inet.h>
 
 #include "repmgr.h"
 #include "dbutils.h"
@@ -370,6 +371,37 @@ get_conninfo_value(const char *conninfo, const char *keyword, char *output)
 }
 
 
+/*
+ * Get a default conninfo value for the provided parameter, and copy
+ * it to the 'output' buffer.
+ *
+ * Returns true on success, or false on failure (provided keyword not found).
+ *
+ */
+bool
+get_conninfo_default_value(const char *param, char *output, int maxlen)
+{
+	PQconninfoOption *defs = NULL;
+	PQconninfoOption *def = NULL;
+	bool found = false;
+
+	defs = PQconndefaults();
+
+	for (def = defs; def->keyword; def++)
+	{
+		if (strncmp(def->keyword, param, maxlen) == 0)
+		{
+			strncpy(output, def->val, maxlen);
+			found = true;
+		}
+	}
+
+	PQconninfoFree(defs);
+
+	return found;
+}
+
+
 void
 initialize_conninfo_params(t_conninfo_param_list *param_list, bool set_defaults)
 {
@@ -1733,7 +1765,7 @@ _populate_node_record(PGresult *res, t_node_info *node_info, int row)
 	strncpy(node_info->location, PQgetvalue(res, row, 7), MAXLEN);
 	node_info->priority = atoi(PQgetvalue(res, row, 8));
 	node_info->active = atobool(PQgetvalue(res, row, 9));
-	strncpy(node_info->config_file, PQgetvalue(res, row, 10), MAXLEN);
+	strncpy(node_info->config_file, PQgetvalue(res, row, 10), MAXPGPATH);
 
 	/* This won't normally be set */
 	strncpy(node_info->upstream_node_name, PQgetvalue(res, row, 11), MAXLEN);
@@ -2146,8 +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 n.upstream_node_id = %i ",
+					  "      AND rs.slot_name IS NULL "
+					  "      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);
@@ -2884,8 +2917,7 @@ get_datadir_configuration_files(PGconn *conn, KeyValueList *list)
 
 	for (i = 0; i < PQntuples(res); i++)
 	{
-		key_value_list_set(
-						   list,
+		key_value_list_set(list,
 						   PQgetvalue(res, i, 1),
 						   PQgetvalue(res, i, 0));
 	}
@@ -3110,6 +3142,8 @@ _create_event(PGconn *conn, t_configuration_options *options, int node_id, char
 	char		event_timestamp[MAXLEN] = "";
 	bool		success = true;
 
+	log_verbose(LOG_DEBUG, "_create_event(): event is \"%s\" for node %i", event, node_id);
+
 	/*
 	 * Only attempt to write a record if a connection handle was provided.
 	 * Also check that the repmgr schema has been properly initialised - if
@@ -3620,7 +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;
@@ -3657,6 +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

@@ -357,7 +357,7 @@ void		close_connection(PGconn **conn);
 
 /* conninfo manipulation functions */
 bool		get_conninfo_value(const char *conninfo, const char *keyword, char *output);
-
+bool		get_conninfo_default_value(const char *param, char *output, int maxlen);
 void		initialize_conninfo_params(t_conninfo_param_list *param_list, bool set_defaults);
 void		free_conninfo_params(t_conninfo_param_list *param_list);
 void		copy_conninfo_params(t_conninfo_param_list *dest_list, t_conninfo_param_list *source_list);
@@ -369,6 +369,7 @@ bool		parse_conninfo_string(const char *conninfo_str, t_conninfo_param_list *par
 char	   *param_list_to_string(t_conninfo_param_list *param_list);
 bool		has_passfile(void);
 
+
 /* transaction functions */
 bool		begin_transaction(PGconn *conn);
 bool		commit_transaction(PGconn *conn);
@@ -454,7 +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-packages.sgml

@@ -41,18 +41,19 @@
       <title>CentOS repositories</title>
 
       <para>
-        &repmgr; packages are available from the 2ndQuadrant repository, and also the PostgreSQL
-        community repository. The 2ndQuadrant repository is updated immediately after each
+        &repmgr; packages are available from the public 2ndQuadrant repository, and also the
+        PostgreSQL community repository. The 2ndQuadrant repository is updated immediately
+        after each
         &repmgr; release.
       </para>
 
       <table id="centos-2ndquadrant-repository">
-        <title>2ndQuadrant repository</title>
+        <title>2ndQuadrant public repository</title>
         <tgroup cols="2">
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="http://packages.2ndquadrant.com/repmgr/">http://packages.2ndquadrant.com/repmgr/</ulink></entry>
+              <entry><ulink url="https://rpm.2ndquadrant.com/">https://rpm.2ndquadrant.com/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>

doc/appendix-release-notes.sgml

@@ -15,6 +15,113 @@
     See also: <xref linkend="upgrading-repmgr">
   </para>
 
+  <sect1 id="release-4.0.6">
+    <title>Release 4.0.6</title>
+    <para><emphasis>June 14, 2018</emphasis></para>
+    <para>
+	  &repmgr; 4.0.6 contains a number of bug fixes and usability enhancements.
+    </para>
+	<para>
+	  We recommend upgrading to this version as soon as possible.
+	  This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.5;
+      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      for more details.
+	</para>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command> and
+              <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command>:
+              return non-zero exit code if node connection issues detected (GitHub #447)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Improve handling of external configuration file copying,  including consideration in
+			   <option>--dry-run</option> check
+			   (GitHub #443)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              When using <option>--dry-run</option>, force log level to <literal>INFO</literal>
+			  to ensure output will always be displayed
+			  (GitHub #441)
+           </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>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+        <itemizedlist>
+
+          <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
+           </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>:
+			   check node has actually connected to new primary before reporting success
+			   (GitHub #444)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
+			   Fix bug when parsing <option>--config-files</option> parameter
+			   (GitHub #442)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: ensure local node is counted as quorum member
+			  (GitHub #439)
+           </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
   <sect1 id="release-4.0.5">
     <title>Release 4.0.5</title>
     <para><emphasis>Wed May 2, 2018</emphasis></para>
@@ -24,6 +131,7 @@
       generation and (in <application>repmgrd</application>) handling of various
       corner-case situations, as well as a number of bug fixes.
     </para>
+
     <sect2>
       <title>Usability enhancements</title>
 

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>;
-      this overrides any value contained in the setting <varname>promote_command</varname>.
+      It's also possible to specify a <varname>service_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/install-packages.sgml

@@ -5,26 +5,27 @@
   system.
  </para>
 
- <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, Fedora and CentOS">
+ <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, CentOS and Fedora">
 
   <indexterm>
    <primary>installation</primary>
    <secondary>on Red Hat/CentOS/Fedora etc.</secondary>
   </indexterm>
 
-  <title>RedHat/Fedora/CentOS</title>
+  <title>RedHat/CentOS/Fedora</title>
   <para>
-   RPM packages for &repmgr; are available via Yum through
+	&repmgr; RPM packages for RedHat/CentOS variants and Fedora are available from the
+	<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+	<ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink>; see following
+	section for details.
+  </para>
+  <para>
+   RPM packages for &repmgr; are also available via Yum through
    the PostgreSQL Global Development Group RPM repository
    (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</ulink>).
    Follow the instructions for your distribution (RedHat, CentOS,
-   Fedora, etc.) and architecture as detailed there.
-  </para>
-  <para>
-   <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink> also provides its
-   own RPM packages which are made available
-   at the same time as each &repmgr; release, as it can take some days for
-   them to become available via the main PGDG repository. See following section for details:
+   Fedora, etc.) and architecture as detailed there. Note that it can take some days
+   for new &repmgr; packages to become available via the this repository.
   </para>
   <note>
     <para>
@@ -43,59 +44,68 @@
 
 
   <sect3 id="installation-packages-redhat-2ndq">
-    <title>2ndQuadrant repmgr yum repository</title>
+    <title>2ndQuadrant public RPM yum repository</title>
+
+	<note>
+	  <para>
+		<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink> previously provided a dedicated
+        &repmgr; repository at
+        <ulink url="http://packages.2ndquadrant.com/repmgr/">http://packages.2ndquadrant.com/repmgr/</ulink>.
+		This repository will be deprecated in a future release as it is now replaced by
+		the <ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink>
+		documented below.
+	  </para>
+	</note>
+
     <para>
-      Beginning with <ulink url="http://repmgr.org/release-notes-3.1.3.html">repmgr 3.1.3</ulink>,
+      Beginning with <ulink url="https://repmgr.org/docs/4.0/release-4.0.5.html">repmgr 4.0.5</ulink>,
       <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a dedicated <literal>yum</literal>
-      repository for &repmgr; releases. This repository complements the main
-      <ulink url="https://yum.postgresql.org/repopackages.php">PGDG community repository</ulink>,
-      but enables repmgr users to access the latest &repmgr; packages before they are
-      available via the PGDG repository, which can take several days to be updated following
-      a fresh  &repmgr; release.
-    </para>
+	  <ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink> for 2ndQuadrant software,
+	  including &repmgr;. We recommend using this for all future &repmgr; releases.
+	</para>
+	<para>
+	  General instructions for using this repository can be found on its
+	  <ulink url="https://rpm.2ndquadrant.com/">homepage</ulink>. Specific instructions
+	  for installing &repmgr; follow below.
+	</para>
     <para>
       <emphasis>Installation</emphasis>
 
       <itemizedlist>
-        <listitem>
-          <para>
-            Import the repository public key (optional but recommended):
-            <programlisting>
-              rpm --import http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr</programlisting>
-          </para>
-        </listitem>
+		<listitem>
+		  <para>
+			Locate the repository RPM for your PostgreSQL version from the list at:
+			<ulink url="https://rpm.2ndquadrant.com/">https://rpm.2ndquadrant.com/</ulink>
+		  </para>
+		</listitem>
 
         <listitem>
           <para>
-            Install the repository RPM for your distribution (this enables the 2ndQuadrant
-            repository as a source of repmgr packages):
-            <itemizedlist>
-              <listitem>
-                <simpara>
-                  <emphasis>Fedora:</emphasis>
-                  <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm</ulink>
-                </simpara>
-              </listitem>
-              <listitem>
-                <simpara>
-                  <emphasis>RHEL, CentOS etc:</emphasis>
-                  <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm</ulink>
-                </simpara>
-              </listitem>
-            </itemizedlist>
-          </para>
-          <para>
-            e.g.:
-            <programlisting>
-              $ yum install http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm</programlisting>
-          </para>
-        </listitem>
+            Install the repository RPM for your distribution and PostgreSQL version
+			(this enables the 2ndQuadrant repository as a source of &repmgr; packages).
+		  </para>
+		  <para>
+			For example, for PostgreSQL 10 on CentOS, execute:
+			<programlisting>
+sudo yum install https://rpm.2ndquadrant.com/site/content/2ndquadrant-repo-10-1-1.el7.noarch.rpm
+			</programlisting>
+		  </para>
+		  <para>
+			Verify that the repository is installed with:
+			<programlisting>
+sudo yum repolist</programlisting>
+			The output should contain two entries like this:
+			<programlisting>
+2ndquadrant-repo-10/7/x86_64         2ndQuadrant packages for PG10 for rhel 7 - x86_64           1
+2ndquadrant-repo-10-debug/7/x86_64   2ndQuadrant packages for PG10 for rhel 7 - x86_64 - Debug   1</programlisting>
+		  </para>
+		</listitem>
 
         <listitem>
           <para>
-            Install the repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr96</literal>), e.g.:
+            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
-              $ yum install repmgr96</programlisting>
+$ yum install repmgr10</programlisting>
           </para>
         </listitem>
       </itemizedlist>
@@ -105,13 +115,13 @@
       <emphasis>Compatibility with PGDG Repositories</emphasis>
     </para>
     <para>
-        The 2ndQuadrant &repmgr; yum repository uses exactly the same package definitions as the
-        main PGDG repository and is effectively a selective mirror for &repmgr; packages only.
+      The 2ndQuadrant &repmgr; yum repository packages use the same definitions and file system layout as the
+      main PGDG repository.
     </para>
     <para>
-        Normally yum should prioritize the repository with the most recent &repmgr; version.
-        Once the PGDG repository has been updated, it doesn't matter which repository
-        the packages are installed from.
+      Normally <application>yum</application> will prioritize the repository with the most recent &repmgr; version.
+      Once the PGDG repository has been updated, it doesn't matter which repository
+      the packages are installed from.
     </para>
     <para>
       To ensure the 2ndQuadrant repository is always prioritised, install <literal>yum-plugin-priorities</literal>
@@ -125,30 +135,23 @@
       To install a specific package version, execute <command>yum --showduplicates list</command>
       for the package in question:
       <programlisting>
-        [root@localhost ~]# yum --showduplicates list repmgr96
+        [root@localhost ~]# yum --showduplicates list repmgr10
         Loaded plugins: fastestmirror
         Loading mirror speeds from cached hostfile
          * base: ftp.iij.ad.jp
          * extras: ftp.iij.ad.jp
          * updates: ftp.iij.ad.jp
         Available Packages
-        repmgr96.x86_64               3.2-1.el6                    2ndquadrant-repmgr
-        repmgr96.x86_64               3.2.1-1.el6                  2ndquadrant-repmgr
-        repmgr96.x86_64               3.3-1.el6                    2ndquadrant-repmgr
-        repmgr96.x86_64               3.3.1-1.el6                  2ndquadrant-repmgr
-        repmgr96.x86_64               3.3.2-1.el6                  2ndquadrant-repmgr
-        repmgr96.x86_64               3.3.2-1.rhel6                pgdg96
-        repmgr96.x86_64               4.0.0-1.el6                  2ndquadrant-repmgr
-        repmgr96.x86_64               4.0.0-1.rhel6                pgdg96</programlisting>
+		repmgr10.x86_64                       4.0.3-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.4-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.5-1.el7                          2ndquadrant-repo-10</programlisting>
       then append the appropriate version number to the package name with a hyphen, e.g.:
       <programlisting>
-        [root@localhost ~]# yum install repmgr96-3.3.2-1.el6</programlisting>
+        [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
     </para>
   </sect3>
  </sect2>
 
-
-
  <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
 
   <indexterm>
@@ -168,6 +171,79 @@
     see the appendix section <xref linkend="packages-debian-ubuntu">.
   </para>
 
+  <sect3 id="installation-packages-debian-ubuntu-2ndq">
+    <title>2ndQuadrant public apt repository for Debian/Ubuntu</title>
+
+    <para>
+      Beginning with <ulink url="https://repmgr.org/docs/4.0/release-4.0.5.html">repmgr 4.0.5</ulink>,
+      <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a
+	  <ulink url="https://apt.2ndquadrant.com/">public apt repository</ulink> for 2ndQuadrant software,
+	  including &repmgr;.
+	</para>
+	<para>
+	  General instructions for using this repository can be found on its
+	  <ulink url="https://apt.2ndquadrant.com/">homepage</ulink>. Specific instructions
+	  for installing &repmgr; follow below.
+	</para>
+
+    <para>
+      <emphasis>Installation</emphasis>
+
+      <itemizedlist>
+
+		<listitem>
+		  <para>
+			If not already present, install the  <application>apt-transport-https</application> package:
+			<programlisting>
+sudo apt-get install apt-transport-https</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Create <filename>/etc/apt/sources.list.d/2ndquadrant.list</filename> as follows:
+			<programlisting>
+sudo sh -c 'echo "deb https://apt.2ndquadrant.com/ $(lsb_release -cs)-2ndquadrant main" > /etc/apt/sources.list.d/2ndquadrant.list'</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Install the 2ndQuadrant <ulink url="https://apt.2ndquadrant.com/site/keys/9904CD4BD6BAF0C3.asc">repository key</ulink>:
+			<programlisting>
+sudo apt-get install curl ca-certificates
+curl https://apt.2ndquadrant.com/site/keys/9904CD4BD6BAF0C3.asc | sudo apt-key add -</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Update the package list
+			<programlisting>
+ sudo apt-get update</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            <programlisting>
+$ apt-get install postgresql-10-repmgr</programlisting>
+		  </para>
+          <note>
+            <para>
+            For packages for PostgreSQL 9.6 and earlier, the package name includes
+            a period between major and minor version numbers, e.g.
+            <literal>postgresql-9.6-repmgr</literal>.
+            </para>
+          </note>
+		</listitem>
+
+	  </itemizedlist>
+
+	</para>
+
+  </sect3>
  </sect2>
 
 </sect1>

doc/install-source.sgml

@@ -80,7 +80,7 @@
    </para>
 
    <para>
-    There are also tags for each &repmgr; release, e.g. <filename>REL4_0_STABLE</filename>.
+    There are also tags for each &repmgr; release, e.g. <filename>4.0.5</filename>.
    </para>
 
    <para>

doc/repmgr-cluster-crosscheck.sgml

@@ -38,5 +38,34 @@
       and therefore determine the state of outbound connections from that node.
     </para>
   </refsect1>
+
+  <refsect1>
+    <title>Exit codes</title>
+    <para>
+      Following exit codes can be emitted by <command>repmgr cluster crosscheck</command>:
+    </para>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>SUCCESS (0)</option></term>
+        <listitem>
+          <para>
+            The check completed successfully and all nodes are reachable.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_CLUSTER_CHECK (25)</option></term>
+        <listitem>
+          <para>
+            One or more nodes could not be reached.
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
 </refentry>
 

doc/repmgr-cluster-matrix.sgml

@@ -97,5 +97,35 @@
     useful result.
   </para>
   </refsect1>
+
+
+  <refsect1>
+    <title>Exit codes</title>
+    <para>
+      Following exit codes can be emitted by <command>repmgr cluster matrix</command>:
+    </para>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>SUCCESS (0)</option></term>
+        <listitem>
+          <para>
+            The check completed successfully and all nodes are reachable.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_CLUSTER_CHECK (25)</option></term>
+        <listitem>
+          <para>
+            One or more nodes could not be reached.
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
 </refentry>
 

doc/repmgr-node-check.sgml

@@ -79,9 +79,26 @@
 
     </itemizedlist>
   </para>
-  <para>
-   Individual checks can also be output in a Nagios-compatible format by additionally
-   providing the option <literal>--nagios</literal>.
-  </para>
+  </refsect1>
+
+  <refsect1>
+    <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-clone.sgml

@@ -124,7 +124,7 @@
      <para>
        We recommend using <ulink url="https://www.pgbarman.org/">Barman</ulink> to manage
        WAL file archiving. For more details on combining &repmgr; and <application>Barman</application>,
-       in particular using <varname>restore_command</varname> to configure Barman as a backu source of
+       in particular using <varname>restore_command</varname> to configure Barman as a backup source of
        WAL files, see <xref linkend="cloning-from-barman">.
      </para>
    </note>
@@ -177,12 +177,13 @@
    <title>Using a standby cloned by another method</title>
    <para>
      &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
-     <command>barman recover</command> command).
+     <command><ulink url="http://docs.pgbarman.org/release/2.4/#recover">barman recover</ulink></command> command).
    </para>
    <para>
      To integrate the standby as a &repmgr; node, ensure the <filename>repmgr.conf</filename>
-     file is created for the node, then execute the command
-     <command>repmgr standby clone --recovery-conf-only</command>.
+     file is created for the node, and that it has been registered using
+     <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>.
+     Then execute the command <command>repmgr standby clone --recovery-conf-only</command>.
      This will create the <filename>recovery.conf</filename> file needed to attach
      the node to its upstream, and will also create a replication slot on the
      upstream node if required.

doc/repmgr-standby-follow.sgml

@@ -26,10 +26,18 @@
       running. It can only be used to attach an active standby to the current primary node
    (and not to another standby).
     </para>
-    <para>
-      To re-add an inactive node to the replication cluster, see
-      <xref linkend="repmgr-node-rejoin">
-    </para>
+	<tip>
+      <para>
+		To re-add an inactive node to the replication cluster, use
+		<xref linkend="repmgr-node-rejoin">.
+      </para>
+	</tip>
+
+	<para>
+	  <command>repmgr standby follow</command> will wait up to
+	  <varname>standby_follow_timeout</varname> seconds (default: <literal>30</literal>)
+	  to verify the standby has actually connected to the new primary.
+	</para>
 
   </refsect1>
 
@@ -92,7 +100,7 @@
       A <literal>standby_follow</literal> <link linkend="event-notifications">event notification</link> will be generated.
     </para>
     <para>
-      If provided, &repmgr; will subsitute the placeholders <literal>%p</literal> with the node ID of the primary
+      If provided, &repmgr; will substitute the placeholders <literal>%p</literal> with the node ID of the primary
       being followed, <literal>%c</literal> with its <literal>conninfo</literal> string, and
       <literal>%a</literal> with its node name.
     </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-register.sgml

@@ -173,7 +173,7 @@
     </para>
 
     <para>
-      If provided, &repmgr; will subsitute the placeholders <literal>%p</literal> with the node ID of the
+      If provided, &repmgr; will substitute the placeholders <literal>%p</literal> with the node ID of the
       primary node, <literal>%c</literal> with its <literal>conninfo</literal> string, and
       <literal>%a</literal> with its node name.
     </para>

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>
-      <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>
+    <important>
+      <para>
+        <application>repmgrd</application> must be shut down on all nodes while a switchover is being
+        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
@@ -199,7 +210,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      Following exit codes can be emitted by <literal>repmgr standby switchover</literal>:
+      Following exit codes can be emitted by <command>repmgr standby switchover</command>:
     </para>
     <variablelist>
 
@@ -227,7 +238,7 @@
           <para>
             The switchover was executed but a problem was encountered.
             Typically this means the former primary could not be reattached
-            as a standby.
+            as a standby. Check preceding log messages for more information.
           </para>
         </listitem>
       </varlistentry>

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
-      will restrict execution of <varname>event_notification_command</varname>
+      If defined, the <varname>event_notifications</varname> parameter will restrict
+      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">
-    <title>Defining the "event_notification_command"</title>
+  <sect1 id="bdr-event-notification-command" xreflabel="Defining the BDR failover &quot;event_notification command&quot;">
+    <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>
-    Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
-    promoting a node.
-   </para>
+   <note>
+     <para>
+       Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
+       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

doc/version.sgml

@@ -1 +1 @@
-<!ENTITY repmgrversion "4.0.5">
+<!ENTITY repmgrversion "4.0.6">

errcode.h

@@ -46,5 +46,6 @@
 #define ERR_SWITCHOVER_INCOMPLETE 22
 #define ERR_FOLLOW_FAIL 23
 #define ERR_REJOIN_FAIL 24
+#define ERR_CLUSTER_CHECK 25
 
 #endif							/* _ERRCODE_H_ */

log.c

@@ -329,6 +329,13 @@ logger_set_terse(void)
 }
 
 
+void
+logger_set_min_level(int min_log_level)
+{
+	if (min_log_level > log_level)
+		log_level = min_log_level;
+}
+
 int
 detect_log_level(const char *level)
 {

log.h

@@ -128,6 +128,7 @@ bool		logger_shutdown(void);
 
 void		logger_set_verbose(void);
 void		logger_set_terse(void);
+void		logger_set_min_level(int min_log_level);
 
 void
 log_detail(const char *fmt,...)

repmgr-action-cluster.c

@@ -569,6 +569,8 @@ do_cluster_crosscheck(void)
 
 	t_node_status_cube **cube;
 
+	bool		error_found = false;
+
 	n = build_cluster_crosscheck(&cube, &name_length);
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -648,9 +650,11 @@ do_cluster_crosscheck(void)
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -689,6 +693,11 @@ do_cluster_crosscheck(void)
 
 		free(cube);
 	}
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 
@@ -704,6 +713,8 @@ do_cluster_matrix()
 
 	t_node_matrix_rec **matrix_rec_list;
 
+	bool		error_found = false;
+
 	n = build_cluster_matrix(&matrix_rec_list, &name_length);
 
 	if (runtime_options.output_mode == OM_CSV)
@@ -742,9 +753,11 @@ do_cluster_matrix()
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -770,6 +783,11 @@ do_cluster_matrix()
 	}
 
 	free(matrix_rec_list);
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 

repmgr-action-standby.c

@@ -87,7 +87,7 @@ static void initialise_direct_clone(t_node_info *node_record);
 static int	run_basebackup(t_node_info *node_record);
 static int	run_file_backup(t_node_info *node_record);
 
-static void copy_configuration_files(void);
+static void copy_configuration_files(bool delete_after_copy);
 
 static void drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);
 
@@ -498,7 +498,33 @@ do_standby_clone(void)
 
 			termPQExpBuffer(&msg);
 
-			/* TODO: check all files are readable */
+			/*
+			 * Here we'll attempt an initial test copy of the detected external
+			 * files, to detect any issues before we run the base backup.
+			 *
+			 * Note this will exit with an error, unless -F/--force supplied.
+			 *
+			 * TODO: put the files in a temporary directory and move to their final
+			 * destination once the database has been cloned.
+			 */
+
+			if (runtime_options.copy_external_config_files_destination == CONFIG_FILE_SAMEPATH)
+			{
+				/*
+				 * Files will be placed in the same path as on the source server;
+				 * don't delete after copying.
+				 */
+				copy_configuration_files(false);
+
+			}
+			else
+			{
+				/*
+				 * Files will be placed in the data directory - delete after copying.
+				 * They'll be copied again later; see TODO above.
+				 */
+				copy_configuration_files(true);
+			}
 		}
 
 
@@ -597,7 +623,12 @@ do_standby_clone(void)
 	 */
 	if (runtime_options.copy_external_config_files == true && config_files.entries > 0)
 	{
-		copy_configuration_files();
+		/*
+		 * If "--copy-external-config-files=samepath" was used, the files will already
+		 * have been copied.
+		 */
+		if (runtime_options.copy_external_config_files_destination == CONFIG_FILE_PGDATA)
+			copy_configuration_files(false);
 	}
 
 	/* Write the recovery.conf file */
@@ -938,7 +969,6 @@ _do_create_recovery_conf(void)
 			log_detail("%s", PQerrorMessage(source_conn));
 		}
 
-
 		exit(ERR_BAD_CONFIG);
 	}
 
@@ -955,7 +985,10 @@ _do_create_recovery_conf(void)
 		{
 			log_detail("%s", PQerrorMessage(source_conn));
 		}
-
+		else
+		{
+			log_hint(_("standby must be registered before a new recovery.conf file can be created"));
+		}
 
 		exit(ERR_BAD_CONFIG);
 	}
@@ -2126,7 +2159,13 @@ do_standby_follow(void)
 
 	log_verbose(LOG_DEBUG, "do_standby_follow()");
 
-	local_conn = establish_db_connection(config_file_options.conninfo, true);
+	local_conn = establish_db_connection(config_file_options.conninfo, false);
+
+	if (PQstatus(local_conn) != CONNECTION_OK)
+	{
+		log_hint(_("use \"repmgr node rejoin\" to re-add an inactive node to the replication cluster"));
+		exit(ERR_DB_CONN);
+	}
 
 	log_verbose(LOG_INFO, _("connected to local node"));
 
@@ -2218,7 +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"));
@@ -2313,6 +2352,74 @@ do_standby_follow(void)
 										 &follow_output,
 										 &follow_error_code);
 
+	/* unable to restart the standby */
+	if (success == false)
+	{
+		create_event_notification_extended(
+			primary_conn,
+			&config_file_options,
+			config_file_options.node_id,
+			"standby_follow",
+			success,
+			follow_output.data,
+			&event_info);
+
+		PQfinish(primary_conn);
+
+		log_notice(_("STANDBY FOLLOW failed"));
+		if (strlen( follow_output.data ))
+			log_detail("%s", follow_output.data);
+
+		termPQExpBuffer(&follow_output);
+		exit(follow_error_code);
+	}
+
+	termPQExpBuffer(&follow_output);
+
+	initPQExpBuffer(&follow_output);
+
+	/*
+	 * Wait up to "standby_follow_timeout" seconds for standby to connect to
+	 * upstream.
+	 * For 9.6 and later, we could check pg_stat_wal_receiver on the local node.
+	 */
+
+	/* assume success, necessary if standby_follow_timeout is zero */
+	success = true;
+
+	for (timer = 0; timer < config_file_options.standby_follow_timeout; timer++)
+	{
+		success = is_downstream_node_attached(primary_conn, config_file_options.node_name);
+		if (success == true)
+			break;
+
+		log_verbose(LOG_DEBUG, "sleeping %i of max %i seconds waiting for standby to attach to primary",
+					timer + 1,
+					config_file_options.standby_follow_timeout);
+		sleep(1);
+	}
+
+	if (success == true)
+	{
+		log_notice(_("STANDBY FOLLOW successful"));
+		appendPQExpBuffer(&follow_output,
+						  "standby attached to upstream node \"%s\" (node ID: %i)",
+						  primary_node_record.node_name,
+						  primary_node_id);
+	}
+	else
+	{
+		log_error(_("STANDBY FOLLOW failed"));
+		appendPQExpBuffer(&follow_output,
+						  "standby did not attach to upstream node \"%s\" (node ID: %i) after %i seconds",
+						  primary_node_record.node_name,
+						  primary_node_id,
+						  config_file_options.standby_follow_timeout);
+
+	}
+
+	log_detail("%s", follow_output.data);
+
 	create_event_notification_extended(
 		primary_conn,
 		&config_file_options,
@@ -2324,20 +2431,11 @@ do_standby_follow(void)
 
 	PQfinish(primary_conn);
 
-	if (success == false)
-	{
-		log_notice(_("STANDBY FOLLOW failed"));
-		log_detail("%s", follow_output.data);
-
-		termPQExpBuffer(&follow_output);
-		exit(follow_error_code);
-	}
-
-	log_notice(_("STANDBY FOLLOW successful"));
-	log_detail("%s", follow_output.data);
-
 	termPQExpBuffer(&follow_output);
 
+	if (success == false)
+		exit(ERR_FOLLOW_FAIL);
+
 	return;
 }
 
@@ -3335,8 +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
@@ -3760,7 +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;
@@ -3787,8 +3882,17 @@ do_standby_switchover(void)
 			initPQExpBuffer(&remote_command_str);
 			make_remote_repmgr_path(&remote_command_str, &sibling_node_record);
 
-			appendPQExpBuffer(&remote_command_str,
-							  "standby follow 2>/dev/null && echo \"1\" || echo \"0\"");
+			if (sibling_node_record.type == WITNESS)
+			{
+				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);
 
@@ -3803,8 +3907,16 @@ do_standby_switchover(void)
 
 			if (success == false || command_output.data[0] == '0')
 			{
-				log_warning(_("STANDBY FOLLOW failed on node \"%s\""),
-							cell->node_info->node_name);
+				if (sibling_node_record.type == WITNESS)
+				{
+					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++;
 			}
 
@@ -3909,6 +4021,8 @@ check_source_server()
 	PGconn	   *privileged_conn = NULL;
 
 	char		cluster_size[MAXLEN];
+	char	   *connstr = NULL;
+
 	t_node_info node_record = T_NODE_INFO_INITIALIZER;
 	RecordStatus record_status = RECORD_NOT_FOUND;
 	ExtensionStatus extension_status = REPMGR_UNKNOWN;
@@ -3917,8 +4031,11 @@ check_source_server()
 	log_verbose(LOG_DEBUG, "check_source_server()");
 	log_info(_("connecting to source node"));
 
-	source_conn = establish_db_connection_by_params(&source_conninfo, false);
+	connstr = param_list_to_string(&source_conninfo);
+	log_detail(_("connection string is: %s"), connstr);
+	pfree(connstr);
 
+	source_conn = establish_db_connection_by_params(&source_conninfo, false);
 	/*
 	 * Unless in barman mode, exit with an error;
 	 * establish_db_connection_by_params() will have already logged an error
@@ -4073,13 +4190,25 @@ check_source_server()
 		if (record_status == RECORD_FOUND)
 		{
 			t_conninfo_param_list upstream_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
+			char	   *upstream_conninfo_user;
 
 			initialize_conninfo_params(&upstream_conninfo, false);
 			parse_conninfo_string(node_record.conninfo, &upstream_conninfo, NULL, false);
 
 			strncpy(recovery_conninfo_str, node_record.conninfo, MAXLEN);
 			strncpy(upstream_repluser, node_record.repluser, NAMEDATALEN);
-			strncpy(upstream_user, param_get(&upstream_conninfo, "user"), NAMEDATALEN);
+
+			upstream_conninfo_user = param_get(&upstream_conninfo, "user");
+			if (upstream_conninfo_user != NULL)
+			{
+				strncpy(upstream_user, upstream_conninfo_user, NAMEDATALEN);
+			}
+			else
+			{
+				get_conninfo_default_value("user", upstream_user, NAMEDATALEN);
+			}
+
+			log_verbose(LOG_DEBUG, "upstream_user is \"%s\"", upstream_user);
 
 			upstream_conninfo_found = true;
 		}
@@ -4632,7 +4761,7 @@ initialise_direct_clone(t_node_info *node_record)
 		}
 		else
 		{
-			TablespaceListCell *cell = false;
+			TablespaceListCell *cell;
 			KeyValueList not_found = {NULL, NULL};
 			int			total = 0,
 						matched = 0;
@@ -5690,7 +5819,7 @@ get_barman_property(char *dst, char *name, char *local_repmgr_directory)
 
 
 static void
-copy_configuration_files(void)
+copy_configuration_files(bool delete_after_copy)
 {
 	int			i,
 				r;
@@ -5735,13 +5864,35 @@ copy_configuration_files(void)
 		r = copy_remote_files(runtime_options.host, runtime_options.remote_user,
 							  file->filepath, dest_path.data, false, source_server_version_num);
 
-		termPQExpBuffer(&dest_path);
+		/*
+		 * TODO: collate errors into list
+		 */
 
 		if (WEXITSTATUS(r))
 		{
 			log_error(_("standby clone: unable to copy config file \"%s\""),
 					  file->filename);
+			log_hint(_("see preceding messages for details"));
+
+			if (runtime_options.force == false)
+				exit(ERR_BAD_RSYNC);
 		}
+
+		/*
+		 * This is to check we can actually copy the files before running the
+		 * main clone operation
+		 */
+		if (delete_after_copy == true)
+		{
+			/* this is very unlikely to happen, but log in case it does */
+			if (unlink(dest_path.data) < 0 && errno != ENOENT)
+			{
+				log_warning(_("unable to delete %s"), dest_path.data);
+				log_detail("%s", strerror(errno));
+			}
+		}
+
+		termPQExpBuffer(&dest_path);
 	}
 
 	return;

repmgr-action-witness.c

@@ -137,7 +137,7 @@ do_witness_register(void)
 	}
 
 	/*
-	 * TODO:sanity check witness node is not part of main cluster; we could
+	 * TODO: sanity check witness node is not part of main cluster; we could
 	 * add a random application_name to the respective connections,
 	 * and do a simple check of pg_stat_activity
 	 */
@@ -193,8 +193,26 @@ do_witness_register(void)
 		}
 	}
 
+	/*
+	 * Check that an active node with the same node_name doesn't exist already
+	 */
 
-	// XXX check other node with same name does not exist
+	record_status = get_node_record_by_name(primary_conn,
+											config_file_options.node_name,
+											&node_record);
+
+
+	if (record_status == RECORD_FOUND)
+	{
+		if (node_record.active == true && node_record.node_id != config_file_options.node_id)
+		{
+			log_error(_("node %i exists already with node_name \"%s\""),
+					  node_record.node_id,
+					  config_file_options.node_name);
+			PQfinish(primary_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+	}
 
 	/*
 	 * if repmgr.nodes contains entries, delete if -F/--force provided,
@@ -225,6 +243,7 @@ do_witness_register(void)
 		PQfinish(witness_conn);
 		exit(SUCCESS);
 	}
+
 	/* create record on primary */
 
 	/*

repmgr-client.c

@@ -634,7 +634,7 @@ main(int argc, char **argv)
 	 * If -d/--dbname appears to be a conninfo string, validate by attempting
 	 * to parse it (and if successful, store the parsed parameters)
 	 */
-	if (runtime_options.dbname)
+	if (runtime_options.dbname[0])
 	{
 		if (strncmp(runtime_options.dbname, "postgresql://", 13) == 0 ||
 			strncmp(runtime_options.dbname, "postgres://", 11) == 0 ||
@@ -1010,7 +1010,6 @@ main(int argc, char **argv)
 		runtime_options.output_mode = OM_OPTFORMAT;
 	}
 
-
 	/*
 	 * Check for configuration file items which can be overriden by runtime
 	 * options
@@ -1068,6 +1067,17 @@ main(int argc, char **argv)
 	if (runtime_options.terse)
 		logger_set_terse();
 
+	/*
+	 * If --dry-run specified, ensure log_level is at least LOG_INFO, regardless
+	 * of what's in the configuration file or -L/--log-level paremeter, otherwise
+	 * some or output might not be displayed.
+	 */
+	if (runtime_options.dry_run == true)
+	{
+		logger_set_min_level(LOG_INFO);
+	}
+
+
 	/*
 	 * Node configuration information is not needed for all actions, with
 	 * STANDBY CLONE being the main exception.

repmgr.conf.sample

@@ -98,7 +98,7 @@
 #log_facility=STDERR		 # Logging facility: possible values are STDERR, or for
 				 # syslog integration, one of LOCAL0, LOCAL1, ..., LOCAL7, USER
 
-#log_file=''			 # stderr can be redirected to an arbitrary file:
+#log_file=''			 # stderr can be redirected to an arbitrary file
 #log_status_interval=300	 # interval (in seconds) for repmgrd to log a status message
 
 
@@ -213,8 +213,10 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # These settings apply when instructing a standby to follow the new primary
 # ("repmgr standby follow").
 
-#primary_follow_timeout=60		# The length of time (in seconds) to wait
+#primary_follow_timeout=60		# The max length of time (in seconds) to wait
 					# for the new primary to become available
+#standby_follow_timeout=15		# The max length of time (in seconds) to wait
+					# for the standby to connect to the primary
 
 
 #------------------------------------------------------------------------------
@@ -251,11 +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
@@ -308,11 +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
-					# "promote_command". This is intended for systems which
-					# provide a package-level promote command, such as Debian's
-					# "pg_ctlcluster"
-
+#service_promote_command = ''		# This parameter is intended for systems which provide a
+					# package-level promote command, such as Debian's
+					# "pg_ctlcluster". *IMPORTANT*: it is *not* a substitute
+					# for "promote_command"; do not use "repmgr standby promote"
+					# (or a script which executes "repmgr standby promote") here.
 
 #------------------------------------------------------------------------------
 # Status check thresholds

repmgr.h

@@ -70,6 +70,7 @@
 #define DEFAULT_ASYNC_QUERY_TIMEOUT          60  /* seconds */
 #define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
 #define DEFAULT_PRIMARY_FOLLOW_TIMEOUT       60  /* seconds */
+#define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
 #define DEFAULT_BDR_RECOVERY_TIMEOUT         30  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */

repmgr_version.h.in

@@ -1,3 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.0.5"
+#define REPMGR_VERSION "4.0.6"
 

repmgrd-physical.c

@@ -58,7 +58,7 @@ static FailoverState failover_state = FAILOVER_STATE_UNKNOWN;
 
 static int	primary_node_id = UNKNOWN_NODE_ID;
 static t_node_info upstream_node_info = T_NODE_INFO_INITIALIZER;
-static NodeInfoList standby_nodes = T_NODE_INFO_LIST_INITIALIZER;
+static NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 
 
 static ElectionResult do_election(void);
@@ -816,6 +816,29 @@ monitor_streaming_standby(void)
 		{
 			int			degraded_monitoring_elapsed = calculate_elapsed(degraded_monitoring_start);
 
+			if (config_file_options.degraded_monitoring_timeout > 0
+				&& degraded_monitoring_elapsed > config_file_options.degraded_monitoring_timeout)
+			{
+				initPQExpBuffer(&event_details);
+
+				appendPQExpBuffer(&event_details,
+								  _("degraded monitoring timeout (%i seconds) exceeded, terminating"),
+								  degraded_monitoring_elapsed);
+
+				log_notice("%s", event_details.data);
+
+				create_event_notification(NULL,
+										  &config_file_options,
+										  config_file_options.node_id,
+										  "repmgrd_shutdown",
+										  true,
+										  event_details.data);
+
+				termPQExpBuffer(&event_details);
+				terminate(ERR_MONITORING_TIMEOUT);
+			}
+
+
 			log_debug("monitoring node %i in degraded state for %i seconds",
 					  upstream_node_info.node_id,
 					  degraded_monitoring_elapsed);
@@ -918,8 +941,8 @@ monitor_streaming_standby(void)
 						get_active_sibling_node_records(local_conn,
 														local_node_info.node_id,
 														former_upstream_node_id,
-														&standby_nodes);
-						notify_followers(&standby_nodes, local_node_info.node_id);
+														&sibling_nodes);
+						notify_followers(&sibling_nodes, local_node_info.node_id);
 
 						/* this will restart monitoring in primary mode */
 						monitoring_state = MS_NORMAL;
@@ -958,12 +981,12 @@ monitor_streaming_standby(void)
 					get_active_sibling_node_records(local_conn,
 													local_node_info.node_id,
 													local_node_info.upstream_node_id,
-													&standby_nodes);
+													&sibling_nodes);
 
-					if (standby_nodes.node_count > 0)
+					if (sibling_nodes.node_count > 0)
 					{
-						log_debug("scanning %i node records to detect new primary...", standby_nodes.node_count);
-						for (cell = standby_nodes.head; cell; cell = cell->next)
+						log_debug("scanning %i node records to detect new primary...", sibling_nodes.node_count);
+						for (cell = sibling_nodes.head; cell; cell = cell->next)
 						{
 							/* skip local node check, we did that above */
 							if (cell->node_info->node_id == local_node_info.node_id)
@@ -993,7 +1016,7 @@ monitor_streaming_standby(void)
 							follow_new_primary(follow_node_id);
 						}
 					}
-					clear_node_info_list(&standby_nodes);
+					clear_node_info_list(&sibling_nodes);
 				}
 			}
 		}
@@ -1395,12 +1418,12 @@ monitor_streaming_witness(void)
 				get_active_sibling_node_records(local_conn,
 												local_node_info.node_id,
 												local_node_info.upstream_node_id,
-												&standby_nodes);
+												&sibling_nodes);
 
-				if (standby_nodes.node_count > 0)
+				if (sibling_nodes.node_count > 0)
 				{
-					log_debug("scanning %i node records to detect new primary...", standby_nodes.node_count);
-					for (cell = standby_nodes.head; cell; cell = cell->next)
+					log_debug("scanning %i node records to detect new primary...", sibling_nodes.node_count);
+					for (cell = sibling_nodes.head; cell; cell = cell->next)
 					{
 						/* skip local node check, we did that above */
 						if (cell->node_info->node_id == local_node_info.node_id)
@@ -1430,7 +1453,7 @@ monitor_streaming_witness(void)
 						witness_follow_new_primary(follow_node_id);
 					}
 				}
-				clear_node_info_list(&standby_nodes);
+				clear_node_info_list(&sibling_nodes);
 			}
 		}
 loop:
@@ -1531,7 +1554,7 @@ do_primary_failover(void)
 	}
 	else if (election_result == ELECTION_WON)
 	{
-		if (standby_nodes.node_count > 0)
+		if (sibling_nodes.node_count > 0)
 		{
 			log_notice("this node is the winner, will now promote itself and inform other nodes");
 		}
@@ -1576,7 +1599,7 @@ do_primary_failover(void)
 				get_active_sibling_node_records(local_conn,
 												local_node_info.node_id,
 												upstream_node_info.node_id,
-												&standby_nodes);
+												&sibling_nodes);
 
 			}
 			else if (config_file_options.failover == FAILOVER_MANUAL)
@@ -1638,10 +1661,10 @@ do_primary_failover(void)
 	{
 		case FAILOVER_STATE_PROMOTED:
 			/* notify former siblings that they should now follow this node */
-			notify_followers(&standby_nodes, local_node_info.node_id);
+			notify_followers(&sibling_nodes, local_node_info.node_id);
 
 			/* we no longer care about our former siblings */
-			clear_node_info_list(&standby_nodes);
+			clear_node_info_list(&sibling_nodes);
 
 			/* pass control back down to start_monitoring() */
 			log_info(_("switching to primary monitoring mode"));
@@ -1655,10 +1678,10 @@ do_primary_failover(void)
 			 * notify siblings that they should resume following the original
 			 * primary
 			 */
-			notify_followers(&standby_nodes, upstream_node_info.node_id);
+			notify_followers(&sibling_nodes, upstream_node_info.node_id);
 
 			/* we no longer care about our former siblings */
-			clear_node_info_list(&standby_nodes);
+			clear_node_info_list(&sibling_nodes);
 
 			/* pass control back down to start_monitoring() */
 			log_info(_("resuming standby monitoring mode"));
@@ -2543,6 +2566,7 @@ do_election(void)
 
 	/* we're visible */
 	int			visible_nodes = 1;
+	int			total_nodes = 0;
 
 	NodeInfoListCell *cell = NULL;
 
@@ -2593,14 +2617,16 @@ do_election(void)
 	get_active_sibling_node_records(local_conn,
 									local_node_info.node_id,
 									upstream_node_info.node_id,
-									&standby_nodes);
+									&sibling_nodes);
+
+	total_nodes = sibling_nodes.node_count + 1;
 
 	log_debug("do_election(): primary location is %s", upstream_node_info.location);
 
 	local_node_info.last_wal_receive_lsn = InvalidXLogRecPtr;
 
 	/* fast path if no other standbys (or witness) exists - normally win by default */
-	if (standby_nodes.node_count == 0)
+	if (sibling_nodes.node_count == 0)
 	{
 		if (strncmp(upstream_node_info.location, local_node_info.location, MAXLEN) == 0)
 		{
@@ -2628,7 +2654,7 @@ do_election(void)
 	}
 	else
 	{
-		/* standby nodes found - check if we're in the primary location befor checking theirs */
+		/* standby nodes found - check if we're in the primary location before checking theirs */
 		if (strncmp(upstream_node_info.location, local_node_info.location, MAXLEN) == 0)
 		{
 			primary_location_seen = true;
@@ -2643,7 +2669,7 @@ do_election(void)
 	/* pointer to "winning" node, initially self */
 	candidate_node = &local_node_info;
 
-	for (cell = standby_nodes.head; cell; cell = cell->next)
+	for (cell = sibling_nodes.head; cell; cell = cell->next)
 	{
 		/* assume the worst case */
 		cell->node_info->node_status = NODE_STATUS_UNKNOWN;
@@ -2698,7 +2724,7 @@ do_election(void)
 			candidate_node = cell->node_info;
 		}
 		/* LSN is same - tiebreak on priority, then node_id */
-		else if(cell->node_info->last_wal_receive_lsn == candidate_node->last_wal_receive_lsn)
+		else if (cell->node_info->last_wal_receive_lsn == candidate_node->last_wal_receive_lsn)
 		{
 			log_verbose(LOG_DEBUG, "node %i has same LSN as current candidate %i",
 						cell->node_info->node_id,
@@ -2750,9 +2776,9 @@ do_election(void)
 
 	log_debug("visible nodes: %i; total nodes: %i",
 			  visible_nodes,
-			  standby_nodes.node_count);
+			  total_nodes);
 
-	if (visible_nodes <= (standby_nodes.node_count / 2.0))
+	if (visible_nodes <= (total_nodes / 2.0))
 	{
 		log_notice(_("unable to reach a qualified majority of nodes"));
 		log_detail(_("node will enter degraded monitoring state waiting for reconnect"));