Fix typo: upstream_node_id → upstream_node

This checks if the active libpq version (9.6 and later) has the
"passfile" option, and returns 0 if present, 1 if not.
`

HISTORY

@@ -1,6 +1,17 @@
+4.0.1   2017-12-04
+        repmgr: ensure "repmgr node check --action=" returns appropriate return
+          code; GitHub #340 (Ian)
+        repmgr: add missing schema qualification in get_all_node_records_with_upstream()
+          query GitHub #341 (Martín)
+        repmgr: initialise "voting_term" table in application, not extension SQL;
+          GitHub #344 (Ian)
+        repmgr: delete any replication slots copied by pg_rewind; GitHub #334 (Ian)
+        repmgr: fix configuration file sanity check; GitHub #342 (Ian)
+        Improve event notification documentation (Ian)
+
 4.0.0   2017-11-21
         Complete rewrite with many changes; for details see the repmgr 4.0.0 release
-        notes at: https://repmgr.org/docs/4.0/release-4.0.html
+        notes at: https://repmgr.org/docs/4.0/release-4.0.0.html
 
 3.3.2   2017-06-01
         Add support for PostgreSQL 10 (Ian)

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.0.0.
+# Generated by GNU Autoconf 2.69 for repmgr 4.0.1.
 #
 # Report bugs to <pgsql-bugs@postgresql.org>.
 #
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.0.0'
-PACKAGE_STRING='repmgr 4.0.0'
+PACKAGE_VERSION='4.0.1'
+PACKAGE_STRING='repmgr 4.0.1'
 PACKAGE_BUGREPORT='pgsql-bugs@postgresql.org'
 PACKAGE_URL='https://2ndquadrant.com/en/resources/repmgr/'
 
@@ -1179,7 +1179,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures repmgr 4.0.0 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.0.1 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1240,7 +1240,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.0.0:";;
+     short | recursive ) echo "Configuration of repmgr 4.0.1:";;
    esac
   cat <<\_ACEOF
 
@@ -1319,7 +1319,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.0.0
+repmgr configure 4.0.1
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1338,7 +1338,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by repmgr $as_me 4.0.0, which was
+It was created by repmgr $as_me 4.0.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2379,7 +2379,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by repmgr $as_me 4.0.0, which was
+This file was extended by repmgr $as_me 4.0.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2442,7 +2442,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-repmgr config.status 4.0.0
+repmgr config.status 4.0.1
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.0.0], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
+AC_INIT([repmgr], [4.0.1], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
 
 AC_COPYRIGHT([Copyright (c) 2010-2017, 2ndQuadrant Ltd.])
 

dbutils.c

@@ -700,7 +700,7 @@ has_passfile(void)
 
 	PQconninfoFree(defs);
 
-    return has_passfile;
+	return has_passfile;
 }
 
 
@@ -2130,7 +2130,7 @@ get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list)
 					  "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
 					  "           n.slot_name, n.location, n.priority, n.active, un.node_name AS upstream_node_name "
 					  "      FROM repmgr.nodes n "
-					  " LEFT JOIN nodes un "
+					  " LEFT JOIN repmgr.nodes un "
 					  "        ON un.node_id = n.upstream_node_id"
 					  "  ORDER BY n.node_id ");
 
@@ -3735,7 +3735,7 @@ int
 get_current_term(PGconn *conn)
 {
 	PGresult   *res = NULL;
-	int term = -1;
+	int term = VOTING_TERM_NOT_SET;
 
 	res = PQexec(conn, "SELECT term FROM repmgr.voting_term");
 
@@ -3747,13 +3747,43 @@ get_current_term(PGconn *conn)
 		return -1;
 	}
 
-	term = atoi(PQgetvalue(res, 0, 0));
+	if (PQntuples(res) > 0)
+	{
+		term = atoi(PQgetvalue(res, 0, 0));
+	}
 
 	PQclear(res);
 	return term;
 }
 
 
+void
+initialize_voting_term(PGconn *conn)
+{
+	PGresult   *res = NULL;
+
+	int current_term = get_current_term(conn);
+
+	if (current_term == VOTING_TERM_NOT_SET)
+	{
+		res = PQexec(conn, "INSERT INTO repmgr.voting_term (term) VALUES (1)");
+	}
+	else
+	{
+		res = PQexec(conn, "UPDATE repmgr.voting_term SET term = 1");
+	}
+
+	if (PQresultStatus(res) != PGRES_COMMAND_OK)
+	{
+		log_error(_("unable to initialize repmgr.voting_term:\n  %s"),
+				  PQerrorMessage(conn));
+	}
+
+	PQclear(res);
+	return;
+}
+
+
 void
 increment_current_term(PGconn *conn)
 {
@@ -3765,8 +3795,6 @@ increment_current_term(PGconn *conn)
 	{
 		log_error(_("unable to increment repmgr.voting_term:\n  %s"),
 				  PQerrorMessage(conn));
-		PQclear(res);
-		return;
 	}
 
 	PQclear(res);
@@ -4050,7 +4078,7 @@ is_active_bdr_node(PGconn *conn, const char *node_name)
 	appendPQExpBuffer(&query,
 					  "    SELECT COALESCE(s.active, TRUE) AS active"
 					  "      FROM bdr.bdr_nodes n "
-					  " LEFT JOIN pg_replication_slots s "
+					  " LEFT JOIN pg_catalog.pg_replication_slots s "
 					  "        ON slot_name=bdr.bdr_format_slot_name(n.node_sysid, n.node_timeline, n.node_dboid, (SELECT oid FROM pg_database WHERE datname = current_database())) "
 					  "     WHERE node_name='%s' ",
 					  node_name);

dbutils.h

@@ -473,6 +473,7 @@ bool		delete_monitoring_records(PGconn *primary_conn, int keep_history);
 
 
 /* node voting functions */
+void		initialize_voting_term(PGconn *conn);
 int			get_current_term(PGconn *conn);
 void		increment_current_term(PGconn *conn);
 bool		announce_candidature(PGconn *conn, t_node_info *this_node, t_node_info *other_node, int electoral_term);

dirutil.c

@@ -311,6 +311,14 @@ create_pg_dir(char *path, bool force)
 	return true;
 }
 
+
+
+int
+rmdir_recursive(char *path)
+{
+	return nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+}
+
 static int
 unlink_dir_callback(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf)
 {

dirutil.h

@@ -26,5 +26,5 @@ extern int	check_dir(char *path);
 extern bool create_dir(char *path);
 extern bool is_pg_dir(char *path);
 extern bool create_pg_dir(char *path, bool force);
-
+extern int rmdir_recursive(char *path);
 #endif

doc/appendix-release-notes.sgml

@@ -1,4 +1,4 @@
-<appendix id="appendix-release-notes" xreflabel="Release notes">
+<appendix id="appendix-release-notes">
  <title>Release notes</title>
  <indexterm>
   <primary>Release notes</primary>
@@ -16,30 +16,210 @@
   See also: <xref linkend="upgrading-repmgr">
  </para>
 
- <sect1 id="release-4.0">
-  <title>Release 4.0beta1</title>
+ <sect1 id="release-4.0.1">
+  <title>Release 4.0.1</title>
 
-  <para><emphasis>Thu Oct 5, 2017</emphasis></para>
+  <para><emphasis>Mon Dec 4, 2017</emphasis></para>
 
   <para>
-    repmgr 4.0 is an entirely new version of &repmgr;, providing many
-    improvements together with some changes in the way it works.
-    In particular changes have been made to some configuration file
-    settings and command line options for consistency and clarity.
+    repmgr 4.0.1 is a bugfix release.
   </para>
-  <para>
-    For detailed instructions on upgrading from repmgr 3.x, see
-    <xref linkend="upgrading-from-repmgr-3">.
-  </para>
-
-  <note>
+  <sect2>
+    <title>Bug fixes</title>
     <para>
+      <itemizedlist>
+        <listitem>
+          <para>
+            ensure correct return codes are returned for
+            <command><link linkend="repmgr-node-check">repmgr node check --action=</link></command> operations
+            (GitHub #340)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Fix <xref linkend="repmgr-cluster-show"> when <literal>repmgr</literal> schema not set in search path
+            (GitHub #341)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            When using <literal>--force-rewind</literal> with <xref linkend="repmgr-node-rejoin">
+            delete any replication slots copied by <application>pg_rewind</application>
+            (GitHub #334)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Only perform sanity check on accessibility of configuration files outside
+            the data directory when <literal>--copy-external-config-files</literal>
+            provided (GitHub #342)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Initialise "voting_term" table in application, not extension SQL
+            (GitHub #344)
+          </para>
+        </listitem>
+
+      </itemizedlist>
+    </para>
+  </sect2>
+ </sect1>
+
+
+
+ <sect1 id="release-4.0.0">
+  <title>Release 4.0.0</title>
+
+  <para><emphasis>Tue Nov 21, 2017</emphasis></para>
+
+  <para>
+    repmgr 4.0 is an entirely new version of &repmgr;, implementing &repmgr;
+    as a native PostgreSQL extension, adding new and improving existing features,
+    and making &repmgr; more user-friendly and intuitive to use. The new code base
+    will make it easier to add additional functionality for future releases.
+  </para>
+  <note>
+    <simpara>
+      With the new version, the opportunity has been taken to
+      make some changes in the way &repmgr; is set up and
+      configured. In particular changes have been made to some
+      configuration file settings consistency for and clarity.
+      Changes are covered in detail below
+    </simpara>
+    <simpara>
       To standardise terminology, from this release <literal>primary</literal> is used to
       denote the read/write node in a streaming replication cluster. <literal>master</literal>
       is still accepted as an alias for &repmgr; commands
       (e.g. <link linkend="repmgr-primary-register"><command>repmgr master register</command></link>).
-    </para>
+    </simpara>
   </note>
+
+  <para>
+    For detailed instructions on upgrading from repmgr 3.x, see <xref linkend="upgrading-from-repmgr-3">.
+  </para>
+
+  <sect2>
+    <title>Features and improvements</title>
+    <para>
+
+      <itemizedlist>
+        <listitem>
+          <para>
+            <emphasis>improved switchover</emphasis>:
+            the <command>switchover</command> process has been improved and streamlined,
+            speeding up the switchover process and can also instruct other standbys
+            to follow the new primary once the switchover has completed. See
+             <xref linkend="performing-switchover"> for more details.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+           <emphasis>"--dry-run" option</emphasis>: many &repmgr; commands now provide
+           a <literal>--dry-run</literal> option which will execute the command as far
+           as possible without making any changes, which will enable possible issues
+           to be identified before the intended operation is actually carried out.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <emphasis>easier upgrades</emphasis>: &repmgr; is now implemented as a native
+            PostgreSQL extension, which means future upgrades can be carried out by
+            installing the upgraded package and issuing
+            <ulink url="https://www.postgresql.org/docs/current/static/sql-alterextension.html">ALTER EXTENSION repmgr UPDATE</ulink>.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>improved logging output</emphasis>:
+            &repmgr; (and <application>repmgrd</application>) now provide more explicit
+            logging output giving a better picture of what is going on. Where appropriate,
+            <literal>DETAIL</literal> and <literal>HINT</literal> log lines provide additional
+            detail and suggestions for resolving problems. Additionally, <application>repmgrd</application>
+            now emits informational log lines at regular, configurable intervals
+            to confirm that it's running correctly and which node(s) it's monitoring.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <emphasis>automatic configuration file location in packages</emphasis>:
+            Many operating system packages place the &repmgr; configuration files
+            in a version-specific subdirectory, e.g. <filename>/etc/repmgr/9.6/repmgr.conf</filename>;
+            &repmgr; now makes it easy for package maintainers to provide a patch
+            with the actual file location, meaning <filename>repmgr.conf</filename>
+            does not need to be provided explicitly. This is currently the case
+            for 2ndQuadrant-provided <literal>.deb</literal> and <literal>.rpm</literal> packages.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>monitoring and status checks</emphasis>:
+            New commands <xref linkend="repmgr-node-check"> and
+            <xref linkend="repmgr-node-status"> providing information
+            about a node's status and replication-related monitoring
+            output.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>node rejoin</emphasis>:
+            New commands <xref linkend="repmgr-node-rejoin"> enables a failed
+            primary to be rejoined to a replication cluster, optionally using
+            <application>pg_rewind</application> to synchronise its data,
+            (note that <application>pg_rewind</application> may not be useable
+            in some circumstances).
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>automatic failover</emphasis>:
+            improved detection of node status; promotion decision based on a consensual
+            model, with the promoted primary explicitly informing other standbys to
+            follow it. The <application>repmgrd</application> daemon will continue
+            functioning even if the monitored PostgreSQL instance is down, and resume
+            monitoring if it reappears. Additionally, if the instance's role has changed
+            (typically from a primary to a standby, e.g. following reintegration of a
+            failed primary using <xref linkend="repmgr-node-rejoin">) <application>repmgrd</application>
+            will automatically resume monitoring it as a standby.
+          </para>
+        </listitem>
+
+
+
+        <listitem>
+          <para>
+            <emphasis>new documentation</emphasis>:
+            the existing documentation spread over multiple text files
+            has been consolidated into DocBook format (as used by the
+            main PostgreSQL project) and is now available online in
+            HTML format.
+          </para>
+          <para>
+            The DocBook files can easily be used to create versions
+            of the documentation in other formats such as PDF.
+          </para>
+        </listitem>
+
+      </itemizedlist>
+
+    </para>
+  </sect2>
   <sect2>
     <title>New command line options</title>
     <para>

doc/event-notifications.sgml

@@ -126,6 +126,9 @@
    <listitem>
     <simpara><literal>primary_register</literal></simpara>
    </listitem>
+   <listitem>
+    <simpara><literal>primary_unregister</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>standby_register</literal></simpara>
    </listitem>
@@ -144,6 +147,15 @@
    <listitem>
     <simpara><literal>standby_disconnect_manual</literal></simpara>
    </listitem>
+   <listitem>
+    <simpara><literal>witness_register</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>witness_unregister</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>node_rejoin</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>repmgrd_start</literal></simpara>
    </listitem>

doc/install-packages.sgml

@@ -16,7 +16,7 @@
   <para>
    RPM packages for &repmgr; are available via Yum through
    the PostgreSQL Global Development Group RPM repository
-   (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</>).
+   (<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>
@@ -24,11 +24,117 @@
    <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 here for details:
-   <ulink url="http://repmgr.org/yum-repository.html">http://repmgr.org/yum-repository.html</>
+   them to become available via the main PGDG repository. See following section for details:
   </para>
+
+
+  <sect3 id="installation-packages-redhat-2ndq">
+    <title>2ndQuadrant repmgr yum repository</title>
+    <para>
+      Beginning with <ulink url="http://repmgr.org/release-notes-3.1.3.html">repmgr 3.1.3</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>
+    <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>
+            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>
+
+        <listitem>
+          <para>
+            Install the repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr96</literal>), e.g.:
+            <programlisting>
+              $ yum install repmg96</programlisting>
+          </para>
+        </listitem>
+      </itemizedlist>
+    </para>
+
+    <para>
+      <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.
+    </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.
+    </para>
+    <para>
+      To ensure the 2ndQuadrant repository is always prioritised, install <literal>yum-plugin-priorities</literal>
+      and set the repository priorities accordingly.
+    </para>
+
+    <para>
+      <emphasis>Installing a specific package version</emphasis>
+    </para>
+    <para>
+      To install a specific package version, execute <command>yum --showduplicates list</command>
+      for the package in question:
+      <programlisting>
+        [root@localhost ~]# yum --showduplicates list repmgr96
+        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>
+      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>
+    </para>
+  </sect3>
  </sect2>
 
+
+
  <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
 
   <indexterm>
@@ -38,9 +144,9 @@
 
   <title>Debian/Ubuntu</title>
   <para>.deb packages for &repmgr; are available from the
-  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</>).
+  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
   Instructions can be found in the APT section of the PostgreSQL Wiki
-  (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</>).
+  (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink>).
   </para>
  </sect2>
 

doc/quickstart.sgml

@@ -103,11 +103,11 @@
     # ignores archiving. Use something more sensible.
     archive_command = '/bin/true'
 
-    # If you have configured `pg_basebackup_options`
-    # in `repmgr.conf` to include the setting `--xlog-method=fetch` (from
-    # PostgreSQL 10 `--wal-method=fetch`), *and* you have not set
-    # `restore_command` in `repmgr.conf`to fetch WAL files from another
-    # source such as Barman, you'll need to set `wal_keep_segments` to a
+    # If you have configured "pg_basebackup_options"
+    # in "repmgr.conf" to include the setting "--xlog-method=fetch" (from
+    # PostgreSQL 10 "--wal-method=fetch"), *and* you have not set
+    # "restore_command" in "repmgr.conf"to fetch WAL files from another
+    # source such as Barman, you'll need to set "wal_keep_segments" to a
     # high enough value to ensure that all WAL files generated while
     # the standby is being cloned are retained until the standby starts up.
     #
@@ -121,6 +121,11 @@
      <command>include 'postgresql.replication.conf</command>.
     </simpara>
    </tip>
+   <para>
+     Additionally, if you are intending to use <application>pg_rewind</application>,
+     and the cluster was not initialised using data checksums, you may want to consider enabling
+     <varname>wal_log_hints</varname>; for more details see <xref linkend="repmgr-node-rejoin-pg-rewind">.
+   </para>
  </sect1>
 
  <sect1 id="quickstart-repmgr-user-database">
@@ -306,11 +311,10 @@
    (and possibly <literal>data_directory</literal>) adjusted accordingly, e.g.:
   </para>
   <programlisting>
-    node=2
+    node_id=2
     node_name=node2
     conninfo='host=node2 user=repmgr dbname=repmgr connect_timeout=2'
-    data_directory='/var/lib/postgresql/data'
-  </programlisting>
+    data_directory='/var/lib/postgresql/data'</programlisting>
   <para>
    Use the <command>--dry-run</command> option to check the standby can be cloned:
   </para>

doc/repmgr-node-rejoin.sgml

@@ -45,6 +45,13 @@
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>node_rejoin</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Notes</title>
     <para>
@@ -69,7 +76,7 @@
     </tip>
   </refsect1>
 
-  <refsect1 id="repmgr-node-rejoin-pg-rewind">
+  <refsect1 id="repmgr-node-rejoin-pg-rewind" xreflabel="Using pg_rewind">
     <title>Using <command>pg_rewind</command></title>
     <para>
       <command>repmgr node rejoin</command> can optionally use <command>pg_rewind</command> to re-integrate a
@@ -78,7 +85,8 @@
     </para>
     <note>
       <para>
-        <command>pg_rewind</command> *requires* that either <varname>wal_log_hints</varname> is enabled, or that
+        <command>pg_rewind</command> <emphasis>requires</emphasis> that either
+        <varname>wal_log_hints</varname> is enabled, or that
         data checksums were enabled when the cluster was initialized. See the
         <ulink url="https://www.postgresql.org/docs/current/static/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
       </para>

doc/repmgr-primary-register.sgml

@@ -48,4 +48,11 @@
     </note>
   </refsect1>
 
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>primary_register</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/repmgr-primary-unregister.sgml

@@ -31,4 +31,12 @@
       <command>repmgr primary unregister</command>/
     </para>
   </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>primary_unregister</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/repmgr-standby-clone.sgml

@@ -99,5 +99,13 @@
     </simpara>
    </note>
   </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_clone</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>
 

doc/repmgr-standby-follow.sgml

@@ -48,6 +48,13 @@
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_follow</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
  <refsect1>
     <title>See also</title>
     <para>

doc/repmgr-standby-promote.sgml

@@ -41,4 +41,12 @@
       DETAIL: server "node2" (ID: 2) was successfully promoted to primary</programlisting>
     </para>
   </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_promote</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/repmgr-standby-register.sgml

@@ -74,4 +74,13 @@
     <literal>-F/--force</literal> option does not result in an incorrectly configured cluster.
    </para>
   </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_register</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/repmgr-standby-switchover.sgml

@@ -40,6 +40,15 @@
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_promote</literal> event notification will be generated on the new primary,
+      and a <literal>node_rejoin</literal> event notification on the former primary (new standby).
+    </para>
+  </refsect1>
+
+
   <refsect1>
     <title>See also</title>
     <para>

doc/repmgr-standby-unregister.sgml

@@ -42,5 +42,13 @@
         repmgr standby unregister -f /etc/repmgr.conf --node-id=3</programlisting>
     </para>
   </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_unregister</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>
 

doc/repmgr-witness-register.sgml

@@ -49,4 +49,12 @@
     </para>
   </refsect1>
 
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>witness_register</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/repmgr-witness-unregister.sgml

@@ -41,7 +41,7 @@
     <para>
       Unregistering a non-running witness node:
       <programlisting>
-        $ repmgr -f /etc/repmgr.conf witness unregister -h localhost -p 5501  -F
+        $ repmgr -f /etc/repmgr.conf witness unregister -h node1 -p 5501  -F
         INFO: connecting to witness node "node3" (ID: 3)
         NOTICE: unable to connect to witness node "node3" (ID: 3), removing node record on cluster primary only
         INFO: unregistering witness node 3
@@ -61,4 +61,13 @@
       <link linkend="repmgr-witness-register">repmgr witness register --force</link>.
     </para>
   </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>witness_unregister</literal> event notification will be generated.
+    </para>
+  </refsect1>
+
 </refentry>

doc/switchover.sgml

@@ -101,7 +101,7 @@
     <programlisting>
       $ repmgr standby switchover -f /etc/repmgr.conf --siblings-follow --dry-run
       NOTICE: checking switchover on node "node2" (ID: 2) in --dry-run mode
-      INFO: SSH connection to host "localhost" succeeded
+      INFO: SSH connection to host "node1" succeeded
       INFO: archive mode is "off"
       INFO: replication lag on this standby is 0 seconds
       INFO: all sibling nodes are reachable via SSH
@@ -133,7 +133,7 @@
     INFO: searching for primary node
     INFO: checking if node 1 is primary
     INFO: current primary node is 1
-    INFO: SSH connection to host "localhost" succeeded
+    INFO: SSH connection to host "node1" succeeded
     INFO: archive mode is "off"
     INFO: replication lag on this standby is 0 seconds
     NOTICE: local node "node2" (ID: 2) will be promoted to primary; current primary "node1" (ID: 1) will be demoted to standby

doc/upgrading-repmgr.sgml

@@ -151,7 +151,7 @@
         be ignored.</simpara>
       </listitem>
       <listitem>
-        <simpara><varname>upstream_node_id</varname>:  is replaced by the
+        <simpara><varname>upstream_node</varname>:  is replaced by the
         command-line parameter <literal>--upstream-node-id</literal></simpara>
       </listitem>
      </itemizedlist>
@@ -167,7 +167,7 @@
     $ ./convert-config.pl /etc/repmgr.conf
     node_id=2
     node_name=node2
-    conninfo=host=localhost dbname=repmgr user=repmgr connect_timeout=2
+    conninfo=host=node2 dbname=repmgr user=repmgr connect_timeout=2
     pg_ctl_options='-l /var/log/postgres/startup.log'
     rsync_options=--exclude=postgresql.local.conf --archive
     log_level=INFO

doc/version.sgml

@@ -1 +1 @@
-<!ENTITY repmgrversion "4.0.0">
+<!ENTITY repmgrversion "4.0.1">

repmgr--4.0.sql

@@ -91,9 +91,6 @@ CREATE RULE voting_term_delete AS
    ON DELETE TO repmgr.voting_term
    DO INSTEAD NOTHING;
 
-/* XXX do this in "repmgr primary register" */
-INSERT INTO repmgr.voting_term (term) VALUES (1);
-
 
 /* ================= */
 /* repmgrd functions */

repmgr--unpackaged--4.0.sql

@@ -71,6 +71,17 @@ INSERT INTO repmgr.voting_term (term) VALUES (1);
 
 -- convert "repmgr_$cluster.repl_monitor" to "monitoring_history"
 
+
+DO $repmgr$
+DECLARE
+  DECLARE server_version_num INT;
+BEGIN
+  SELECT setting
+    FROM pg_catalog.pg_settings
+   WHERE name = 'server_version_num'
+    INTO server_version_num;
+  IF server_version_num >= 90400 THEN
+    EXECUTE $repmgr_func$
 CREATE TABLE repmgr.monitoring_history (
   primary_node_id                INTEGER NOT NULL,
   standby_node_id                INTEGER NOT NULL,
@@ -80,12 +91,32 @@ CREATE TABLE repmgr.monitoring_history (
   last_wal_standby_location      PG_LSN,
   replication_lag                BIGINT NOT NULL,
   apply_lag                      BIGINT NOT NULL
-);
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
+  ELSE
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      TEXT NOT NULL,
+  last_wal_standby_location      TEXT,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
 
-INSERT INTO repmgr.monitoring_history
-  (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
-SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
-  FROM repmgr.repl_monitor;
+  END IF;
+END$repmgr$;
 
 CREATE INDEX idx_monitoring_history_time
           ON repmgr.monitoring_history (last_monitor_time, standby_node_id);

repmgr-action-node.c

@@ -559,10 +559,20 @@ do_node_check(void)
 
 	t_node_info node_info = T_NODE_INFO_INITIALIZER;
 
+	CheckStatus return_code;
 	CheckStatusList status_list = {NULL, NULL};
 	CheckStatusListCell *cell = NULL;
 
 
+	/* internal */
+	if (runtime_options.has_passfile == true)
+	{
+		return_code = has_passfile() ? 0 : 1;
+
+		exit(return_code);
+	}
+
+
 	if (strlen(config_file_options.conninfo))
 		conn = establish_db_connection(config_file_options.conninfo, true);
 	else
@@ -585,38 +595,51 @@ do_node_check(void)
 	 */
 	if (runtime_options.archive_ready == true)
 	{
-		(void) do_node_check_archive_ready(conn, runtime_options.output_mode, NULL);
+		return_code = do_node_check_archive_ready(conn,
+												  runtime_options.output_mode,
+												  NULL);
 		PQfinish(conn);
-		return;
+		exit(return_code);
 	}
 
 	if (runtime_options.downstream == true)
 	{
-		(void) do_node_check_downstream(conn, runtime_options.output_mode, NULL);
+		return_code = do_node_check_downstream(conn,
+											   runtime_options.output_mode,
+											   NULL);
 		PQfinish(conn);
-		return;
+		exit(return_code);
 	}
 
 
 	if (runtime_options.replication_lag == true)
 	{
-		(void) do_node_check_replication_lag(conn, runtime_options.output_mode, &node_info, NULL);
+		return_code = do_node_check_replication_lag(conn,
+													runtime_options.output_mode,
+													&node_info,
+													NULL);
 		PQfinish(conn);
-		return;
+		exit(return_code);
 	}
 
 	if (runtime_options.role == true)
 	{
-		(void) do_node_check_role(conn, runtime_options.output_mode, &node_info, NULL);
+		return_code = do_node_check_role(conn,
+										 runtime_options.output_mode,
+										 &node_info,
+										 NULL);
 		PQfinish(conn);
-		return;
+		exit(return_code);
 	}
 
 	if (runtime_options.slots == true)
 	{
-		(void) do_node_check_slots(conn, runtime_options.output_mode, &node_info, NULL);
+		return_code = do_node_check_slots(conn,
+										  runtime_options.output_mode,
+										  &node_info,
+										  NULL);
 		PQfinish(conn);
-		return;
+		exit(return_code);
 	}
 
 	if (runtime_options.output_mode == OM_NAGIOS)
@@ -1755,19 +1778,72 @@ do_node_rejoin(void)
 				log_detail("%s", strerror(errno));
 			}
 		}
-
 		termPQExpBuffer(&filebuf);
+
+		/* delete any replication slots copied in by pg_rewind */
+		{
+			PQExpBufferData slotdir_path;
+			DIR			  *slotdir;
+			struct dirent *slotdir_ent;
+
+			initPQExpBuffer(&slotdir_path);
+
+			appendPQExpBuffer(&slotdir_path,
+							  "%s/pg_replslot",
+							  config_file_options.data_directory);
+
+			slotdir = opendir(slotdir_path.data);
+
+			if (slotdir == NULL)
+			{
+				log_warning(_("unable to open replication slot directory \"%s\""),
+							slotdir_path.data);
+				log_detail("%s", strerror(errno));
+			}
+			else
+			{
+				while ((slotdir_ent = readdir(slotdir)) != NULL) {
+					struct stat statbuf;
+					PQExpBufferData slotdir_ent_path;
+
+					if(strcmp(slotdir_ent->d_name, ".") == 0 || strcmp(slotdir_ent->d_name, "..") == 0)
+						continue;
+
+					initPQExpBuffer(&slotdir_ent_path);
+
+					appendPQExpBuffer(&slotdir_ent_path,
+									  "%s/%s",
+									  slotdir_path.data,
+									  slotdir_ent->d_name);
+
+					if (stat(slotdir_ent_path.data, &statbuf) == 0 && !S_ISDIR(statbuf.st_mode))
+					{
+						termPQExpBuffer(&slotdir_ent_path);
+						continue;
+					}
+
+					log_debug("deleting slot directory \"%s\"", slotdir_ent_path.data);
+					if (rmdir_recursive(slotdir_ent_path.data) != 0 && errno != EEXIST)
+					{
+						log_warning(_("unable to delete replication slot directory \"%s\""), slotdir_ent_path.data);
+						log_detail("%s", strerror(errno));
+						log_hint(_("directory may need to be manually removed"));
+					}
+
+					termPQExpBuffer(&slotdir_ent_path);
+				}
+			}
+			termPQExpBuffer(&slotdir_path);
+		}
 	}
 
 	initPQExpBuffer(&follow_output);
 
-	success = do_standby_follow_internal(
-										 upstream_conn,
+	success = do_standby_follow_internal(upstream_conn,
 										 &primary_node_record,
 										 &follow_output);
 
-	create_event_notification(
-							  upstream_conn,
+	create_event_notification(upstream_conn,
 							  &config_file_options,
 							  config_file_options.node_id,
 							  "node_rejoin",

repmgr-action-node.h

@@ -22,7 +22,6 @@
 extern void do_node_status(void);
 extern void do_node_check(void);
 
-
 extern void do_node_rejoin(void);
 extern void do_node_service(void);
 

repmgr-action-primary.c

@@ -74,7 +74,11 @@ do_primary_register(void)
 
 	log_verbose(LOG_INFO, _("server is not in recovery"));
 
-	/* create the repmgr extension if it doesn't already exist */
+	/*
+	 * create the repmgr extension if it doesn't already exist;
+	 * note that create_repmgr_extension() will take into account
+	 * the --dry-run option
+	 */
 	if (!create_repmgr_extension(conn))
 	{
 		PQfinish(conn);
@@ -92,6 +96,7 @@ do_primary_register(void)
 		return;
 	}
 
+	initialize_voting_term(conn);
 
 	/* Ensure there isn't another registered node which is primary */
 	primary_conn = get_primary_connection(conn, &current_primary_id, NULL);

repmgr-action-standby.c

@@ -359,7 +359,7 @@ do_standby_clone(void)
 	 * If copying of external configuration files requested, and any are
 	 * detected, perform sanity checks
 	 */
-	if (PQstatus(source_conn) == CONNECTION_OK)
+	if (PQstatus(source_conn) == CONNECTION_OK && runtime_options.copy_external_config_files == true)
 	{
 		PGconn	   *superuser_conn = NULL;
 		PGconn	   *privileged_conn = NULL;
@@ -549,7 +549,7 @@ do_standby_clone(void)
 	 * This won't run in Barman mode as "config_files" is only populated in
 	 * "initialise_direct_clone()", which isn't called in Barman mode.
 	 */
-	if (runtime_options.copy_external_config_files && config_files.entries)
+	if (runtime_options.copy_external_config_files == true && config_files.entries > 0)
 	{
 		copy_configuration_files();
 	}

repmgr-client-global.h

@@ -101,6 +101,7 @@ typedef struct
 	bool		replication_lag;
 	bool		role;
 	bool		slots;
+	bool		has_passfile;
 
 	/* "node join" options */
 	char		config_files[MAXLEN];
@@ -151,7 +152,7 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, \
+		false, false, false, false, false, false, \
 		/* "node join" options */ \
 		"", \
 		/* "node service" options */ \

repmgr-client.c

@@ -447,6 +447,10 @@ main(int argc, char **argv)
 				runtime_options.slots = true;
 				break;
 
+			case OPT_HAS_PASSFILE:
+				runtime_options.has_passfile = true;
+				break;
+
 				/*--------------------
 				 * "node rejoin" options
 				 *--------------------
@@ -1316,7 +1320,7 @@ check_cli_parameters(const int action)
 
 					/*
 					 * XXX if -D/--pgdata provided, and also
-					 * config_file_options.pgdaga, warn -D/--pgdata will be
+					 * config_file_options.pgdata, warn -D/--pgdata will be
 					 * ignored
 					 */
 
@@ -1356,6 +1360,12 @@ check_cli_parameters(const int action)
 				}
 			}
 			break;
+		case NODE_CHECK:
+			if (runtime_options.has_passfile == true)
+			{
+				config_file_required = false;
+			}
+			break;
 		case NODE_STATUS:
 			if (runtime_options.node_id != UNKNOWN_NODE_ID)
 			{

repmgr-client.h

@@ -81,6 +81,7 @@
 #define OPT_DOWNSTREAM					   1032
 #define OPT_SLOTS						   1033
 #define OPT_CONFIG_ARCHIVE_DIR			   1034
+#define OPT_HAS_PASSFILE                   1035
 /* deprecated since 3.3 */
 #define OPT_DATA_DIR						999
 #define OPT_NO_CONNINFO_PASSWORD			998
@@ -153,6 +154,7 @@ static struct option long_options[] =
 	{"replication-lag", no_argument, NULL, OPT_REPLICATION_LAG},
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
+	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},

repmgr.h

@@ -56,6 +56,7 @@
 #define NO_UPSTREAM_NODE	-1
 #define UNKNOWN_NODE_ID		-1
 
+#define VOTING_TERM_NOT_SET -1
 
 /*
  * various default values - ensure repmgr.conf.sample is update

repmgr_version.h.in

@@ -1,3 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.0.0"
+#define REPMGR_VERSION "4.0.1"
 

strutil.h

@@ -33,12 +33,17 @@
 #define MAXLEN_STR STR(MAXLEN)
 
 
+/*
+ * These values must match the Nagios return codes defined here:
+ *
+ * https://assets.nagios.com/downloads/nagioscore/docs/nagioscore/3/en/pluginapi.html
+ */
 typedef enum
 {
-	CHECK_STATUS_OK = 0,
-	CHECK_STATUS_WARNING,
-	CHECK_STATUS_CRITICAL,
-	CHECK_STATUS_UNKNOWN
+	CHECK_STATUS_OK       = 0,
+	CHECK_STATUS_WARNING  = 1,
+	CHECK_STATUS_CRITICAL = 2,
+	CHECK_STATUS_UNKNOWN  = 3
 } CheckStatus;
 
 typedef enum