doc: update release notes

An attempt will be made to delete an existing replication slot on the
old upstream node (this is important during e.g. a switchover operation
or when attaching a cascaded standby to a new upstream). However if the
standby is currently attached to the follow target node anyway, the
replication slot should never be deleted.

HISTORY

@@ -1,4 +1,8 @@
-4.3     2019-??
+4.3.1   2019-12-??
+        repmgr: ensure an existing replication slot is not deleted if the
+          follow target is the node's current upstream (Ian)
+
+4.3     2019-04-02
         repmgr: add "daemon (start|stop)" command; GitHub #528 (Ian)
         repmgr: add --version-number command line option (Ian)
         repmgr: add --compact option to "cluster show"; GitHub #521 (Ian)
@@ -26,6 +30,7 @@
         repmgrd: improve witness monitoring when primary node not available (Ian)
 		repmgrd: handle situation where a primary has unexpectedly appeared
 		  during failover; GitHub #420 (Ian)
+		general: fix Makefile (John)
 
 4.2     2018-10-24
         repmgr: add parameter "shutdown_check_timeout" for use by "standby switchover";

README.md

@@ -27,7 +27,7 @@ Documentation
 
 The main `repmgr` documentation is available here:
 
-> [repmgr 4 documentation](https://repmgr.org/docs/4.2/index.html)
+> [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
 The `README` file for `repmgr` 3.x is available here:
 
@@ -72,7 +72,7 @@ Please report bugs and other issues to:
 
 * https://github.com/2ndQuadrant/repmgr
 
-Further information is available at https://www.repmgr.org/
+Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
 news are always welcome. Send us an email at info@2ndQuadrant.com, or
@@ -97,6 +97,7 @@ Thanks from the repmgr core team.
 Further reading
 ---------------
 
+* [repmgr documentation](https://repmgr.org/docs/current/index.html)
 * https://blog.2ndquadrant.com/repmgr-3-2-is-here-barman-support-brand-new-high-availability-features/
 * https://blog.2ndquadrant.com/improvements-in-repmgr-3-1-4/
 * https://blog.2ndquadrant.com/managing-useful-clusters-repmgr/

configfile.c

@@ -836,15 +836,16 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		conninfo_options = PQconninfoParse(options->conninfo, &conninfo_errmsg);
 		if (conninfo_options == NULL)
 		{
-			char		error_message_buf[MAXLEN] = "";
+			PQExpBufferData error_message_buf;
+			initPQExpBuffer(&error_message_buf);
 
-			snprintf(error_message_buf,
+			appendPQExpBuffer(&error_message_buf,
-					 MAXLEN,
+							  _("\"conninfo\": %s	(provided: \"%s\")"),
-					 _("\"conninfo\": %s	(provided: \"%s\")"),
+							  conninfo_errmsg,
-					 conninfo_errmsg,
+							  options->conninfo);
-					 options->conninfo);
 
-			item_list_append(error_list, error_message_buf);
+			item_list_append(error_list, error_message_buf.data);
+			termPQExpBuffer(&error_message_buf);
 		}
 
 		PQconninfoFree(conninfo_options);

dbutils.c

@@ -1521,10 +1521,10 @@ get_ready_archive_files(PGconn *conn, const char *data_directory)
 	while ((arcdir_ent = readdir(arcdir)) != NULL)
 	{
 		struct stat statbuf;
-		char		file_path[MAXPGPATH] = "";
+		char		file_path[MAXPGPATH + sizeof(arcdir_ent->d_name)];
 		int			basenamelen = 0;
 
-		snprintf(file_path, MAXPGPATH,
+		snprintf(file_path, sizeof(file_path),
 				 "%s/%s",
 				 archive_status_dir,
 				 arcdir_ent->d_name);

dirutil.c

@@ -336,6 +336,15 @@ create_pg_dir(const char *path, bool force)
 				{
 					log_notice(_("-F/--force provided - deleting existing data directory \"%s\""), path);
 					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+
+					/* recreate the directory ourselves to ensure permissions are correct */
+					if (!create_dir(path))
+					{
+						log_error(_("unable to create directory \"%s\"..."),
+								  path);
+						return false;
+					}
+
 					return true;
 				}
 
@@ -347,6 +356,15 @@ create_pg_dir(const char *path, bool force)
 				{
 					log_notice(_("deleting existing directory \"%s\""), path);
 					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+
+					/* recreate the directory ourselves to ensure permissions are correct */
+					if (!create_dir(path))
+					{
+						log_error(_("unable to create directory \"%s\"..."),
+								  path);
+						return false;
+					}
+
 					return true;
 				}
 				return false;

doc/appendix-packages.sgml

@@ -481,28 +481,6 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
 
     <sect2 id="packages-old-versions-rhel-centos" xreflabel="old RHEL/CentOS package versions">
       <title>RHEL/CentOS</title>
-      <para>
-        Old RPM packages (<literal>3.2</literal> and later) can be retrieved from the
-        (deprecated) 2ndQuadrant repository at
-        <ulink url="http://packages.2ndquadrant.com/">http://packages.2ndquadrant.com/</ulink>
-        by installing the appropriate repository RPM:
-      </para>
-
-      <itemizedlist spacing="compact" mark="bullet">
-
-        <listitem>
-          <simpara>
-            <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>
-            <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>
         Old versions can be located with e.g.:
@@ -520,6 +498,32 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
           yum install repmgr96-4.0.6-1.rhel6</programlisting>
       </para>
 
+      <sect3 id="packages-old-versions-rhel-centos-repmgr3">
+        <title>repmgr 3 packages</title>
+        <para>
+          Old &repmgr; 3 RPM packages (<literal>3.2</literal> and later) can be retrieved from the
+          (deprecated) 2ndQuadrant repository at
+          <ulink url="http://packages.2ndquadrant.com/repmgr/yum/">http://packages.2ndquadrant.com/repmgr/yum/</ulink>
+          by installing the appropriate repository RPM:
+        </para>
+
+        <itemizedlist spacing="compact" mark="bullet">
+
+          <listitem>
+            <simpara>
+              <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>
+              <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>
+      </sect3>
+
     </sect2>
   </sect1>
 

doc/appendix-release-notes.sgml

@@ -14,13 +14,47 @@
   <para>
     See also: <xref linkend="upgrading-repmgr">
   </para>
+  <sect1 id="release-4.3.1">
+    <title>Release 4.3.1</title>
+    <para><emphasis>??? December ??, 2019</emphasis></para>
+    <para>
+      &repmgr; 4.3.1 is a minor release.
+    </para>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+         <listitem>
+            <para>
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>:
+	          ensure an existing replication slot is not deleted if the
+              follow target is the node's current upstream.
+            </para>
+	      </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
 
   <sect1 id="release-4.3">
     <title>Release 4.3</title>
-    <para><emphasis>Mar ???, 2019</emphasis></para>
+    <para><emphasis>Tue April 2, 2019</emphasis></para>
     <para>
       &repmgr; 4.3 is a major release.
     </para>
+    <para>
+      For details on how to upgrade an existing &repmgr; instrallation, see
+      documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
+    </para>
+    <para>
+      If <application>repmgrd</application> is in use, a PostgreSQL restart <emphasis>is</emphasis> required;
+      in that case we suggest combining this &repmgr; upgrade with the next PostgreSQL
+      minor release, which will require a PostgreSQL restart in any case.
+    </para>
+
 
 	<important>
 	  <para>
@@ -37,7 +71,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 	</important>
 
     <sect2>
-      <title>repmgr enhancements</title>
+      <title>repmgr client enhancements</title>
       <para>
         <itemizedlist>
 
@@ -191,7 +225,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
          <listitem>
             <para>
 			  In a failover situation, <application>repmgrd</application> will not attempt to promote a
-			  node if another standby has already appeared (e.g. by being promoted manually).
+			  node if another primary has already appeared (e.g. by being promoted manually).
 			  GitHub #420.
 			</para>
           </listitem>
@@ -205,52 +239,6 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       <para>
         <itemizedlist>
 
-          <listitem>
-            <para>
-              &repmgr;: when executing <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
-              prevent escaping issues with connection URIs when executing <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
-              on the demotion candidate. GitHub #525.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              &repmgr;: when executing <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>,
-              check the node to connected is actually the primary (i.e. not the witness server).  GitHub #528.
-            </para>
-          </listitem>
-
-         <listitem>
-            <para>
-              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>,
-              recheck primary/upstream connection(s) after the data copy operation is complete, as these may
-              have gone away.
-            </para>
-          </listitem>
-
-         <listitem>
-            <para>
-              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-              avoid a potential race condition when comparing received WAL on the standby to the primary's shutdown location,
-	      as the standby's walreceiver may not have yet flushed all received WAL to disk. GitHub #518.
-            </para>
-          </listitem>
-
-
-         <listitem>
-            <para>
-              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-	      verify the standby (promotion candidate) is currently attached to the primary (demotion candidate). GitHub #519.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <application>repmgrd</application>: on a cascaded standby, don't fail over if
-              <literal>failover=manual</literal>. GitHub #531.
-            </para>
-          </listitem>
-
           <listitem>
             <para>
               <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>:
@@ -272,6 +260,44 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             </para>
 	      </listitem>
 
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>,
+              recheck primary/upstream connection(s) after the data copy operation is complete, as these may
+              have gone away.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
+              prevent escaping issues with connection URIs when executing <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
+              on the demotion candidate. GitHub #525.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+	          verify the standby (promotion candidate) is currently attached to the primary (demotion candidate). GitHub #519.
+            </para>
+          </listitem>
+
+         <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+              avoid a potential race condition when comparing received WAL on the standby to the primary's shutdown location,
+	          as the standby's walreceiver may not have yet flushed all received WAL to disk. GitHub #518.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>,
+              check the node to connected is actually the primary (i.e. not the witness server).  GitHub #528.
+            </para>
+          </listitem>
+
           <listitem>
             <para>
               <command><link linkend="repmgr-node-check">repmgr node check</link></command>
@@ -281,6 +307,13 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 	        </para>
 	      </listitem>
 
+          <listitem>
+            <para>
+              <application>repmgrd</application>: on a cascaded standby, don't fail over if
+              <literal>failover=manual</literal>. GitHub #531.
+            </para>
+          </listitem>
+
         </itemizedlist>
       </para>
     </sect2>

doc/install-source.sgml

@@ -61,28 +61,28 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
          <itemizedlist spacing="compact" mark="bullet">
 
            <listitem>
-             <simpara><literal>llibedit-dev</literal></simpara>
+             <simpara><literal>libedit-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibkrb5-dev</literal></simpara>
+             <simpara><literal>libkrb5-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibpam0g-dev</literal></simpara>
+             <simpara><literal>libpam0g-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibreadline-dev</literal></simpara>
+             <simpara><literal>libreadline-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibselinux1-dev</literal></simpara>
+             <simpara><literal>libselinux1-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibssl-dev</literal></simpara>
+             <simpara><literal>libssl-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibxml2-dev</literal></simpara>
+             <simpara><literal>libxml2-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibxslt1-dev</literal></simpara>
+             <simpara><literal>libxslt1-dev</literal></simpara>
            </listitem>
          </itemizedlist>
        </para>

doc/quickstart.sgml

@@ -76,19 +76,25 @@
    </para>
    <programlisting>
 
-    # Enable replication connections; set this figure to at least one more
+    # Enable replication connections; set this value to at least one more
     # than the number of standbys which will connect to this server
-    # (note that repmgr will execute `pg_basebackup` in WAL streaming mode,
+    # (note that repmgr will execute "pg_basebackup" in WAL streaming mode,
-    # which requires two free WAL senders)
+    # which requires two free WAL senders).
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-WAL-SENDERS
 
     max_wal_senders = 10
 
-    # Enable replication slots; set this figure to at least one more
+    # If using replication slots, set this value to at least one more
     # than the number of standbys which will connect to this server.
     # Note that repmgr will only make use of replication slots if
-    # "use_replication_slots" is set to "true" in repmgr.conf
+    # "use_replication_slots" is set to "true" in "repmgr.conf".
+    # (If you are not intending to use replication slots, this value
+    # can be set to "0").
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-REPLICATION-SLOTS
 
-    max_replication_slots = 0
+    max_replication_slots = 10
 
     # Ensure WAL files contain enough information to enable read-only queries
     # on the standby.
@@ -103,24 +109,31 @@
 
     # Enable read-only queries on a standby
     # (Note: this will be ignored on a primary but we recommend including
-    # it anyway)
+    # it anyway, in case the primary later becomes a standby)
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-HOT-STANDBY
 
     hot_standby = on
 
     # Enable WAL file archiving
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-ARCHIVE-MODE
+
     archive_mode = on
 
-    # Set archive command to a script or application that will safely store
+    # Set archive command to a dummy command; this can later be changed without
-    # you WALs in a secure place. /bin/true is an example of a command that
+    # needing to restart the PostgreSQL instance.
-    # ignores archiving. Use something more sensible.
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-ARCHIVE-COMMAND
+
     archive_command = '/bin/true'
    </programlisting>
    <tip>
     <simpara>
       Rather than editing these settings in the default <filename>postgresql.conf</filename>
-     file, create a separate file such as <filename>postgresql.replication.conf</filename> and
+      file, create a separate file such as <filename>postgresql.replication.conf</filename> and
       include it from the end of the main configuration file with:
-     <command>include 'postgresql.replication.conf</command>.
+     <command>include 'postgresql.replication.conf'</command>.
     </simpara>
    </tip>
    <para>
@@ -129,7 +142,8 @@
      <varname>wal_log_hints</varname>; for more details see <xref linkend="repmgr-node-rejoin-pg-rewind">.
    </para>
     <para>
-      See also the <link linkend="configuration-postgresql">PostgreSQL configuration</link> section in the <link linkend="configuration">repmgr configuaration guide</link>.
+      See also the <link linkend="configuration-postgresql">PostgreSQL configuration</link> section in the
+      <link linkend="configuration">repmgr configuration guide</link>.
     </para>
  </sect1>
 

doc/repmgr-standby-switchover.sgml

@@ -22,10 +22,10 @@
       passwordless SSH connection to the current primary.
     </para>
     <para>
-      If other standbys are connected to the demotion candidate, &repmgr; can instruct
+      If other nodes are connected to the demotion candidate, &repmgr; can instruct
       these to follow the new primary if the option <literal>--siblings-follow</literal>
       is specified. This requires a passwordless SSH connection between the promotion
-      candidate (new primary) and the standbys attached to the demotion candidate
+      candidate (new primary) and the nodes attached to the demotion candidate
       (existing primary).
     </para>
     <note>
@@ -150,8 +150,18 @@
         <term><option>--siblings-follow</option></term>
         <listitem>
           <para>
-            Have standbys attached to the old primary follow the new primary.
+            Have nodes attached to the old primary follow the new primary.
           </para>
+          <para>
+            This will also ensure that a witness node, if in use, is updated
+            with the new primary's data.
+          </para>
+          <note>
+            <para>
+              In a future &repmgr; release, <option>--siblings-follow</option> will be applied
+              by default.
+            </para>
+          </note>
         </listitem>
       </varlistentry>
     </variablelist>

doc/repmgr.sgml

@@ -9,6 +9,7 @@
           %filelist;
 
           <!ENTITY repmgr "<productname>repmgr</productname>">
+          <!ENTITY repmgrd "<productname>repmgrd</productname>">
           <!ENTITY postgres "<productname>PostgreSQL</productname>">
 ]>
 
@@ -25,7 +26,13 @@
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
    use with PostgreSQL 9.3 - PostgreSQL 11.
-   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 repmgr documentation</ulink>.
    </para>
 
    <para>

doc/repmgrd-bdr.sgml

@@ -10,7 +10,7 @@
 
   <title>BDR failover with repmgrd</title>
   <para>
-    &repmgr; 4.x provides support for monitoring BDR nodes and taking action in
+    &repmgr; 4.x provides support for monitoring a pair of BDR 2.x nodes and taking action in
     case one of the nodes fails.
   </para>
   <note>
@@ -31,8 +31,21 @@
     reconfigure a proxy server/connection pooler such as <application>PgBouncer</application>.
   </para>
 
+  <note>
+    <simpara>
+      This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
+      It is <emphasis>not</emphasis> required for later BDR versions.
+    </simpara>
+  </note>
+
   <sect1 id="bdr-prerequisites" xreflabel="BDR prequisites">
     <title>Prerequisites</title>
+    <important>
+      <para>
+        This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
+        It is <emphasis>not</emphasis> required for later BDR versions.
+      </para>
+    </important>
     <para>
       &repmgr; 4 requires PostgreSQL 9.4 or 9.6 with the BDR 2 extension
       enabled and configured for a two-node BDR network. &repmgr; 4 packages

doc/repmgrd-configuration.sgml

@@ -217,7 +217,7 @@
               <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command> command.
             </para>
             <para>
-              It is also possible to provide e.g. a shell script to e.g. perform user-defined tasks
+              It is also possible to provide a shell script to e.g. perform user-defined tasks
               before promoting the current node. In this case the script <emphasis>must</emphasis>
               at some point execute <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command>
               to promote the node; if this is not done, &repmgr; metadata will not be updated and
@@ -257,7 +257,7 @@
             </para>
             <para>
               Normally <option>follow_command</option> is set as &repmgr;'s
-              <command><link linkend="repmgr-standby-follow">repmgr standby promote</link></command> command.
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command> command.
             </para>
             <para>
               The <option>follow_command</option> parameter
@@ -270,7 +270,7 @@
               the original primary.
             </para>
             <para>
-              It is also possible to provide e.g. a shell script to e.g. perform user-defined tasks
+              It is also possible to provide a shell script to e.g. perform user-defined tasks
               before promoting the current node. In this case the script <emphasis>must</emphasis>
               at some point execute <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>
               to promote the node; if this is not done, &repmgr; metadata will not be updated and

doc/switchover.sgml

@@ -72,7 +72,8 @@
      Ensure that a passwordless SSH connection is possible from the promotion candidate
      (standby) to the demotion candidate (current primary). If <literal>--siblings-follow</literal>
      will be used, ensure that passwordless SSH connections are possible from the
-     promotion candidate to all standbys attached to the demotion candidate.
+     promotion candidate to all nodes attached to the demotion candidate
+     (including the witness server, if in use).
    </para>
 
    <note>

repmgr-action-bdr.c

@@ -93,6 +93,15 @@ do_bdr_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	if (get_bdr_version_num() > 2)
+	{
+		log_error(_("\"repmgr bdr register\" is for BDR 2.x only"));
+		PQfinish(conn);
+		pfree(dbname);
+		exit(ERR_BAD_CONFIG);
+	}
+
+
 	/* check for a matching BDR node */
 	{
 		PQExpBufferData bdr_local_node_name;

repmgr-action-cluster.c

@@ -1065,7 +1065,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 		matrix_rec_list[i]->node_id = cell->node_info->node_id;
 		strncpy(matrix_rec_list[i]->node_name,
 				cell->node_info->node_name,
-				sizeof(cell->node_info->node_name));
+				sizeof(matrix_rec_list[i]->node_name));
 
 		/*
 		 * Find the maximum length of a node name
@@ -1280,7 +1280,7 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 
 		cube[h] = (t_node_status_cube *) pg_malloc(sizeof(t_node_status_cube));
 		cube[h]->node_id = cell->node_info->node_id;
-		strncpy(cube[h]->node_name, cell->node_info->node_name, sizeof(cell->node_info->node_name));
+		strncpy(cube[h]->node_name, cell->node_info->node_name, sizeof(cube[h]->node_name));
 
 		/*
 		 * Find the maximum length of a node name

repmgr-action-primary.c

@@ -96,28 +96,6 @@ do_primary_register(void)
 
 	initialize_voting_term(conn);
 
-	/* Ensure there isn't another registered node which is primary */
-	primary_conn = get_primary_connection(conn, &current_primary_id, NULL);
-
-	if (primary_conn != NULL)
-	{
-		if (current_primary_id != config_file_options.node_id)
-		{
-			/*
-			 * it's impossible to add a second primary to a streaming
-			 * replication cluster
-			 */
-			log_error(_("there is already an active registered primary (node ID: %i) in this cluster"), current_primary_id);
-			PQfinish(primary_conn);
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		/* we've probably connected to ourselves */
-		PQfinish(primary_conn);
-	}
-
-
 	begin_transaction(conn);
 
 	/*
@@ -128,12 +106,32 @@ do_primary_register(void)
 	current_primary_id = get_primary_node_id(conn);
 	if (current_primary_id != NODE_NOT_FOUND && current_primary_id != config_file_options.node_id)
 	{
-		log_error(_("another node with id %i is already registered as primary"), current_primary_id);
+		log_debug("XXX %i", current_primary_id);
-		log_detail(_("a streaming replication cluster can have only one primary node"));
+		primary_conn = establish_primary_db_connection(conn, false);
 
-		rollback_transaction(conn);
+		if (PQstatus(primary_conn) == CONNECTION_OK)
-		PQfinish(conn);
+		{
-		exit(ERR_BAD_CONFIG);
+			if (get_recovery_type(primary_conn) == RECTYPE_PRIMARY)
+			{
+				log_error(_("there is already an active registered primary (node ID: %i) in this cluster"),
+						  current_primary_id);
+				log_detail(_("a streaming replication cluster can have only one primary node"));
+
+				log_hint(_("ensure this node is shut down before registering a new primary"));
+				PQfinish(primary_conn);
+				rollback_transaction(conn);
+				PQfinish(conn);
+				exit(ERR_BAD_CONFIG);
+			}
+
+			log_warning(_("node %is is registered as primary but running as a standby"),
+						  current_primary_id);
+			PQfinish(primary_conn);
+		}
+
+		log_notice(_("setting node %i's node record to inactive"),
+						  current_primary_id);
+		update_node_record_set_active(conn, current_primary_id, false);
 	}
 
 	/*

repmgr-action-standby.c

@@ -770,56 +770,73 @@ do_standby_clone(void)
 void
 check_barman_config(void)
 {
-	char		command[MAXLEN];
+	PQExpBufferData command;
 	bool		command_ok = false;
 
 	/*
 	 * Check that there is at least one valid backup
 	 */
 
-	log_info(_("connecting to Barman server to verify backup for %s"), config_file_options.barman_server);
+	log_info(_("connecting to Barman server to verify backup for \"%s\""), config_file_options.barman_server);
 
-	maxlen_snprintf(command, "%s show-backup %s latest > /dev/null",
+	initPQExpBuffer(&command);
-					make_barman_ssh_command(barman_command_buf),
-					config_file_options.barman_server);
 
-	command_ok = local_command(command, NULL);
+	appendPQExpBuffer(&command, "%s show-backup %s latest > /dev/null",
+					  make_barman_ssh_command(barman_command_buf),
+					  config_file_options.barman_server);
+
+	command_ok = local_command(command.data, NULL);
 
 	if (command_ok == false)
 	{
-		log_error(_("no valid backup for server %s was found in the Barman catalogue"),
+		log_error(_("no valid backup for server \"%s\" was found in the Barman catalogue"),
 				  config_file_options.barman_server);
+		log_detail(_("command executed was:\n  %s"), command.data),
 		log_hint(_("refer to the Barman documentation for more information"));
 
+		termPQExpBuffer(&command);
 		exit(ERR_BARMAN);
 	}
-
+	else if (runtime_options.dry_run == true)
-
-	if (!create_pg_dir(local_data_directory, runtime_options.force))
 	{
-		log_error(_("unable to use directory %s"),
+		log_info(_("valid backup for server \"%s\" found in the Barman catalogue"),
-				  local_data_directory);
+				 config_file_options.barman_server);
-		log_hint(_("use -F/--force option to force this directory to be overwritten"));
-		exit(ERR_BAD_CONFIG);
 	}
 
+	termPQExpBuffer(&command);
 
 	/*
-	 * Create the local repmgr subdirectory
+	 * Attempt to create data directory (unless --dry-run specified,
+	 * in which case do nothing; warnings will be emitted elsewhere about
+	 * any issues with the data directory)
 	 */
-
+	if (runtime_options.dry_run == false)
-	maxlen_snprintf(local_repmgr_tmp_directory,
-					"%s/repmgr", local_data_directory);
-
-	maxlen_snprintf(datadir_list_filename,
-					"%s/data.txt", local_repmgr_tmp_directory);
-
-	if (!create_pg_dir(local_repmgr_tmp_directory, runtime_options.force))
 	{
-		log_error(_("unable to create directory \"%s\""),
+		if (!create_pg_dir(local_data_directory, runtime_options.force))
-				  local_repmgr_tmp_directory);
+		{
+			log_error(_("unable to use directory %s"),
+					  local_data_directory);
+			log_hint(_("use -F/--force option to force this directory to be overwritten"));
+			exit(ERR_BAD_CONFIG);
+		}
 
-		exit(ERR_BAD_CONFIG);
+		/*
+		 * Create the local repmgr subdirectory
+		 */
+
+		maxlen_snprintf(local_repmgr_tmp_directory,
+						"%s/repmgr", local_data_directory);
+
+		maxlen_snprintf(datadir_list_filename,
+						"%s/data.txt", local_repmgr_tmp_directory);
+
+		if (!create_pg_dir(local_repmgr_tmp_directory, runtime_options.force))
+		{
+			log_error(_("unable to create directory \"%s\""),
+					  local_repmgr_tmp_directory);
+
+			exit(ERR_BAD_CONFIG);
+		}
 	}
 
 	/*
@@ -827,20 +844,37 @@ check_barman_config(void)
 	 */
 	log_info(_("connecting to Barman server to fetch server parameters"));
 
-	maxlen_snprintf(command, "%s show-server %s > %s/show-server.txt",
+	initPQExpBuffer(&command);
-					make_barman_ssh_command(barman_command_buf),
-					config_file_options.barman_server,
-					local_repmgr_tmp_directory);
 
-	command_ok = local_command(command, NULL);
+	if (runtime_options.dry_run == true)
+	{
+		appendPQExpBuffer(&command, "%s show-server %s > /dev/null",
+						  make_barman_ssh_command(barman_command_buf),
+						  config_file_options.barman_server);
+	}
+	else
+	{
+		appendPQExpBuffer(&command, "%s show-server %s > %s/show-server.txt",
+						  make_barman_ssh_command(barman_command_buf),
+						  config_file_options.barman_server,
+						  local_repmgr_tmp_directory);
+	}
+
+	command_ok = local_command(command.data, NULL);
 
 	if (command_ok == false)
 	{
 		log_error(_("unable to fetch server parameters from Barman server"));
-
+		log_detail(_("command executed was:\n  %s"), command.data),
+		termPQExpBuffer(&command);
 		exit(ERR_BARMAN);
 	}
+	else if (runtime_options.dry_run == true)
+	{
+		log_info(_("server parameters were successfully fetched from Barman server"));
+	}
 
+	termPQExpBuffer(&command);
 }
 
 
@@ -872,7 +906,7 @@ _do_create_recovery_conf(void)
 	t_node_info upstream_node_record = T_NODE_INFO_INITIALIZER;
 
 	RecordStatus record_status = RECORD_NOT_FOUND;
-	char		recovery_file_path[MAXPGPATH] = "";
+	char		recovery_file_path[MAXPGPATH + sizeof(RECOVERY_COMMAND_FILE)] = "";
 	struct stat st;
 	bool		node_is_running = false;
 	bool		slot_creation_required = false;
@@ -1117,7 +1151,10 @@ _do_create_recovery_conf(void)
 
 	/* check if recovery.conf exists */
 
-	snprintf(recovery_file_path, MAXPGPATH, "%s/%s", local_data_directory, RECOVERY_COMMAND_FILE);
+	snprintf(recovery_file_path, sizeof(recovery_file_path),
+			 "%s/%s",
+			 local_data_directory,
+			 RECOVERY_COMMAND_FILE);
 
 	if (stat(recovery_file_path, &st) == -1)
 	{
@@ -2864,8 +2901,8 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 		free_conninfo_params(&local_node_conninfo);
 
 		/*
-		 * store the original upstream node id so we can delete the
+		 * Store the original upstream node id so we can delete the
-		 * replication slot, if exists
+		 * replication slot, if it exists.
 		 */
 		if (local_node_record.upstream_node_id != UNKNOWN_NODE_ID)
 		{
@@ -2877,9 +2914,17 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 		}
 
 
-		if (config_file_options.use_replication_slots && runtime_options.host_param_provided == false && original_upstream_node_id != UNKNOWN_NODE_ID)
+		if (config_file_options.use_replication_slots && runtime_options.host_param_provided == false)
 		{
-			remove_old_replication_slot = true;
+			/*
+			 * Only attempt to delete the old replication slot if the old upstream
+			 * node is known and is different to the follow target node.
+			 */
+			if (original_upstream_node_id != UNKNOWN_NODE_ID
+			 && original_upstream_node_id != follow_target_node_record->node_id)
+			{
+				remove_old_replication_slot = true;
+			}
 		}
 	}
 
@@ -3026,8 +3071,6 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 	 * Note that if this function is called by do_standby_switchover(), the
 	 * "repmgr node rejoin" command executed on the demotion candidate may already
 	 * have removed the slot, so there may be nothing to do.
-	 *
-	 * XXX check if former upstream is current primary?
 	 */
 
 	if (remove_old_replication_slot == true)
@@ -3561,9 +3604,26 @@ do_standby_switchover(void)
 	{
 		if (sibling_nodes.node_count > 0)
 		{
+			PQExpBufferData nodes;
+			NodeInfoListCell *cell;
+
+			initPQExpBuffer(&nodes);
+
+			for (cell = sibling_nodes.head; cell; cell = cell->next)
+			{
+				appendPQExpBuffer(&nodes,
+								  "  %s (node ID: %i)",
+								  cell->node_info->node_name,
+								  cell->node_info->node_id);
+				if (cell->next)
+					appendPQExpBufferStr(&nodes, "\n");
+			}
+
 			log_warning(_("%i sibling nodes found, but option \"--siblings-follow\" not specified"),
 						sibling_nodes.node_count);
-			log_detail(_("these nodes will remain attached to the current primary"));
+			log_detail(_("these nodes will remain attached to the current primary:\n%s"), nodes.data);
+
+			termPQExpBuffer(&nodes);
 		}
 	}
 	else
@@ -4030,16 +4090,24 @@ do_standby_switchover(void)
 
 				repmgrd_info[i]->pg_running = false;
 
-				item_list_append_format(&repmgrd_connection_errors,
+				/*
-										_("unable to connect to node \"%s\" (ID %i):\n%s"),
+				 * Only worry about unreachable nodes if they're marked as active
-										cell->node_info->node_name,
+				 * in the repmgr metadata.
-										cell->node_info->node_id,
+				 */
-										PQerrorMessage(cell->node_info->conn));
+				if (cell->node_info->active == true)
+				{
+					unreachable_node_count++;
+
+					item_list_append_format(&repmgrd_connection_errors,
+											_("unable to connect to node \"%s\" (ID %i):\n%s"),
+											cell->node_info->node_name,
+											cell->node_info->node_id,
+											PQerrorMessage(cell->node_info->conn));
+				}
 
 				PQfinish(cell->node_info->conn);
 				cell->node_info->conn = NULL;
 
-				unreachable_node_count++;
 				i++;
 				continue;
 			}
@@ -4982,19 +5050,41 @@ check_source_server()
 	}
 
 	/*
-	 * In the default pg_basebackup mode, we'll cowardly refuse to overwrite
+	 * Check the local directory to see if it appears to be a PostgreSQL
-	 * an existing data directory
+	 * data directory.
+	 *
+	 * Note: a previous call to check_dir() will have checked whether it contains
+	 * a running PostgreSQL instance.
 	 */
-	if (mode == pg_basebackup)
+	if (is_pg_dir(local_data_directory))
 	{
-		if (is_pg_dir(local_data_directory) && runtime_options.force != true)
+		const char *msg = _("target data directory appears to be a PostgreSQL data directory");
+		const char *hint = _("use -F/--force to overwrite the existing data directory");
+
+		if (runtime_options.force == false && runtime_options.dry_run == false)
 		{
-			log_error(_("target data directory appears to be a PostgreSQL data directory"));
+			log_error("%s", msg);
 			log_detail(_("target data directory is \"%s\""), local_data_directory);
-			log_hint(_("use -F/--force to overwrite the existing data directory"));
+			log_hint("%s", hint);
 			PQfinish(source_conn);
 			exit(ERR_BAD_CONFIG);
 		}
+
+		if (runtime_options.dry_run == true)
+		{
+			if (runtime_options.force == true)
+			{
+				log_warning("%s and will be overwritten", msg);
+				log_detail(_("target data directory is \"%s\""), local_data_directory);
+
+			}
+			else
+			{
+				log_warning("%s", msg);
+				log_detail(_("target data directory is \"%s\""), local_data_directory);
+				log_hint("%s", hint);
+			}
+		}
 	}
 
 	/*

repmgr-client.c

@@ -2219,7 +2219,7 @@ create_repmgr_extension(PGconn *conn)
 			log_detail(_("version %s is installed but newer version %s is available"),
 					   extversions.installed_version,
 					   extversions.default_version);
-			log_hint(_("execute \"ALTER EXTENSION repmgr UPGRADE\""));
+			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\""));
 			return false;
 
 		case REPMGR_INSTALLED:

repmgr.conf.sample

@@ -72,6 +72,7 @@
 				 # to the user defined in "conninfo".
 
 #replication_type=physical	 # Must be one of 'physical' or 'bdr'.
+				 # NOTE: "bdr" can only be used with BDR 2.x
 
 #location=default		 # arbitrary string defining the location of the node; this
 				 # is used during failover to check visibilty of the

repmgr_version.h.in

@@ -1,3 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.3"
+#define REPMGR_VERSION "4.3.1"
-#define REPMGR_VERSION_NUM 40300
+#define REPMGR_VERSION_NUM 40301

repmgrd-bdr.c

@@ -96,9 +96,21 @@ monitor_bdr(void)
 	if (!is_bdr_db(local_conn, NULL))
 	{
 		log_error(_("database is not BDR-enabled"));
+		PQfinish(local_conn);
 		exit(ERR_BAD_CONFIG);
 	}
 
+	/*
+	 * Check this is a supported BDR version (basically BDR 2.x)
+	 */
+	if (get_bdr_version_num() > 2)
+	{
+		log_error(_("\"bdr\" mode is for BDR 2.x only"));
+		log_hint(_("for BDR 3 and later, use \"replication_type=physical\""));
+		log_error(_("database is not BDR-enabled"));
+		exit(ERR_DB_CONN);
+	}
+
 	if (is_table_in_bdr_replication_set(local_conn, "nodes", "repmgr") == false)
 	{
 		log_error(_("repmgr metadata table 'repmgr.%s' is not in the 'repmgr' replication set"),

repmgrd-physical.c

@@ -3580,7 +3580,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		 * to follow it.
 		 */
 
-		if (sibling_replication_info.in_recovery == false)
+		if (sibling_replication_info.in_recovery == false && cell->node_info->type != WITNESS)
 		{
 			bool can_follow;
 
@@ -3931,10 +3931,13 @@ check_connection(t_node_info *node_info, PGconn **conn)
 		log_info(_("attempting to reconnect to node \"%s\" (ID: %i)"),
 				 node_info->node_name,
 				 node_info->node_id);
+
+		PQfinish(*conn);
 		*conn = establish_db_connection(node_info->conninfo, false);
 
 		if (PQstatus(*conn) != CONNECTION_OK)
 		{
+			PQfinish(*conn);
 			*conn = NULL;
 			log_warning(_("reconnection to node \"%s\" (ID: %i) failed"),
 						node_info->node_name,

repmgrd.c

@@ -409,8 +409,8 @@ main(int argc, char **argv)
 			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
 					   REPMGR_VERSION,
 					   extversions.installed_version);
+			log_hint(_("update the repmgr binaries to match the installed extension version"));
 
-			log_hint(_("verify the repmgr installation on this server is updated properly before continuing"));
 			close_connection(&local_conn);
 			exit(ERR_BAD_CONFIG);
 		}
@@ -421,8 +421,8 @@ main(int argc, char **argv)
 			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
 					   REPMGR_VERSION,
 					   extversions.installed_version);
+			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\""));
 
-			log_hint(_("verify the repmgr extension is updated properly before continuing"));
 			close_connection(&local_conn);
 			exit(ERR_BAD_CONFIG);
 		}