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

Per user report on mailing list.

configfile.c

@@ -1052,11 +1052,13 @@ parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemL
  * - repmgrd_standby_startup_timeout
  * - retry_promote_interval_secs
  *
- * non-changeable options
+ * non-changeable options (repmgrd references these from the "repmgr.nodes"
+ * table, not the configuration file)
  *
  * - node_id
  * - node_name
  * - data_directory
+ * - location
  * - priority
  * - replication_type
  *
@@ -1272,7 +1274,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
-	/* promote_delay */
+	/* promote_delay (for testing use only; not documented */
 	if (orig_options->promote_delay != new_options.promote_delay)
 	{
 		orig_options->promote_delay = new_options.promote_delay;

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.1.1.
+# Generated by GNU Autoconf 2.69 for repmgr 4.1.2.
 #
 # Report bugs to <pgsql-bugs@postgresql.org>.
 #
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.1.1'
+PACKAGE_VERSION='4.1.2'
-PACKAGE_STRING='repmgr 4.1.1'
+PACKAGE_STRING='repmgr 4.1.2'
 PACKAGE_BUGREPORT='pgsql-bugs@postgresql.org'
 PACKAGE_URL='https://2ndquadrant.com/en/resources/repmgr/'
 
@@ -1178,7 +1178,7 @@ 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 4.1.1 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.1.2 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1239,7 +1239,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.1.1:";;
+     short | recursive ) echo "Configuration of repmgr 4.1.2:";;
    esac
   cat <<\_ACEOF
 
@@ -1313,7 +1313,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.1.1
+repmgr configure 4.1.2
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1332,7 +1332,7 @@ 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 4.1.1, which was
+It was created by repmgr $as_me 4.1.2, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2359,7 +2359,7 @@ cat >>$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 4.1.1, which was
+This file was extended by repmgr $as_me 4.1.2, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2422,7 +2422,7 @@ _ACEOF
 cat >>$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 4.1.1
+repmgr config.status 4.1.2
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.1.1], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
+AC_INIT([repmgr], [4.1.2], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
 
 AC_COPYRIGHT([Copyright (c) 2010-2018, 2ndQuadrant Ltd.])
 

controldata.c

@@ -227,7 +227,15 @@ get_controlfile(const char *DataDir)
 
 	control_file_info->control_file_processed = true;
 
-	if (version_num >= 90500)
+	if (version_num >= 110000)
+	{
+		ControlFileData11 *ptr = (struct ControlFileData11 *)ControlFileDataPtr;
+		control_file_info->system_identifier = ptr->system_identifier;
+		control_file_info->state = ptr->state;
+		control_file_info->checkPoint = ptr->checkPoint;
+		control_file_info->data_checksum_version = ptr->data_checksum_version;
+	}
+	else if (version_num >= 90500)
 	{
 		ControlFileData95 *ptr = (struct ControlFileData95 *)ControlFileDataPtr;
 		control_file_info->system_identifier = ptr->system_identifier;

controldata.h

@@ -265,6 +265,71 @@ typedef struct ControlFileData95
 
 } ControlFileData95;
 
+/*
+ * Following field removed in 11:
+ *
+ *  XLogRecPtr	prevCheckPoint;
+ *
+ * In 10, following field appended *after* "data_checksum_version":
+ *
+ * 	char		mock_authentication_nonce[MOCK_AUTH_NONCE_LEN];
+ *
+ * (but we don't care about that)
+ */
+
+typedef struct ControlFileData11
+{
+	uint64		system_identifier;
+
+	uint32		pg_control_version;		/* PG_CONTROL_VERSION */
+	uint32		catalog_version_no;		/* see catversion.h */
+
+	DBState		state;			/* see enum above */
+	pg_time_t	time;			/* time stamp of last pg_control update */
+	XLogRecPtr	checkPoint;		/* last check point record ptr */
+
+	CheckPoint95	checkPointCopy; /* copy of last check point record */
+
+	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
+
+	XLogRecPtr	minRecoveryPoint;
+	TimeLineID	minRecoveryPointTLI;
+	XLogRecPtr	backupStartPoint;
+	XLogRecPtr	backupEndPoint;
+	bool		backupEndRequired;
+
+	int			wal_level;
+	bool		wal_log_hints;
+	int			MaxConnections;
+	int			max_worker_processes;
+	int			max_prepared_xacts;
+	int			max_locks_per_xact;
+	bool		track_commit_timestamp;
+
+	uint32		maxAlign;		/* alignment requirement for tuples */
+	double		floatFormat;	/* constant 1234567.0 */
+
+	uint32		blcksz;			/* data block size for this DB */
+	uint32		relseg_size;	/* blocks per segment of large relation */
+
+	uint32		xlog_blcksz;	/* block size within WAL files */
+	uint32		xlog_seg_size;	/* size of each WAL segment */
+
+	uint32		nameDataLen;	/* catalog name field width */
+	uint32		indexMaxKeys;	/* max number of columns in an index */
+
+	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
+	uint32		loblksize;		/* chunk size in pg_largeobject */
+
+	bool		enableIntTimes; /* int64 storage enabled? */
+
+	bool		float4ByVal;	/* float4 pass-by-value? */
+	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
+
+	uint32		data_checksum_version;
+
+} ControlFileData11;
+
 
 
 extern DBState get_db_state(const char *data_directory);

doc/appendix-release-notes.sgml

@@ -33,10 +33,9 @@
       <para>
         <itemizedlist>
 
-
           <listitem>
             <para>
-              <command><link linkend="repmgr-standby-clone">repmgr standby switchover --dry-run</link></command>
+              <command><link linkend="repmgr-standby-switchover">repmgr standby switchover --dry-run</link></command>
               no longer copies external configuration files to test they can be copied; this avoids making
               any changes to the target system. (GitHub #491).
             </para>
@@ -45,7 +44,7 @@
           <listitem>
             <para>
               <command><link linkend="repmgr-cluster-cleanup">repmgr cluster cleanup</link></command>:
-              add <literal>cluster_cleanup</literal> event. (GitHub #492)
+              add <literal>cluster_cleanup</literal> event. (GitHub #492).
             </para>
           </listitem>
 

doc/configuration-file-service-commands.sgml

@@ -17,15 +17,15 @@
     <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>.
   </para>
   <para>
-    By default, &repmgr; will use PostgreSQL's <command>pg_ctl</command> to control the PostgreSQL
+    By default, &repmgr; will use PostgreSQL's <command>pg_ctl</command> utility to control the PostgreSQL
     server. However this can lead to various problems, particularly when PostgreSQL has been
-    installed from packages, and expecially so if <application>systemd</application> is in use.
+    installed from packages, and especially so if <application>systemd</application> is in use.
   </para>
 
 
   <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>
@@ -99,7 +99,7 @@
       Defaults:postgres !requiretty
       postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.6, \
         /usr/bin/systemctl start postgresql-9.6, \
-        /usr/bin/systemctl restart postgresql-9.6 \
+        /usr/bin/systemctl restart postgresql-9.6, \
         /usr/bin/systemctl reload postgresql-9.6</programlisting>
   </para>
 

doc/install-packages.sgml

@@ -47,7 +47,7 @@
     <title>2ndQuadrant public RPM yum repository</title>
 
     <para>
-      Beginning with <ulink url="https://repmgr.org/docs/4.0/release-4.0.5.html">repmgr 4.0.5</ulink>,
+      Beginning with <ulink url="https://repmgr.org/docs/4.1/release-4.0.5.html">repmgr 4.0.5</ulink>,
       <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a dedicated <literal>yum</literal>
 	  <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> for 2ndQuadrant software,
 	  including &repmgr;. We recommend using this for all future &repmgr; releases.

doc/repmgr-cluster-show.sgml

@@ -81,36 +81,56 @@
 
   <refsect1>
     <title>Options</title>
-    <para>
+
-      <command>repmgr cluster show</command> accepts an optional parameter <literal>--csv</literal>, which
+    <variablelist>
-      outputs the replication cluster's status in a simple CSV format, suitable for
+
-      parsing by scripts:
+      <varlistentry>
-      <programlisting>
+        <term><option>--csv</option></term>
+        <listitem>
+		  <para>
+			<command>repmgr cluster show</command> accepts an optional parameter <literal>--csv</literal>, which
+			outputs the replication cluster's status in a simple CSV format, suitable for
+			parsing by scripts:
+			<programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show --csv
     1,-1,-1
     2,0,0
     3,0,1</programlisting>
-    </para>
+		  </para>
-    <para>
+		  <para>
-      The columns have following meanings:
+			The columns have following meanings:
-      <itemizedlist spacing="compact" mark="bullet">
+			<itemizedlist spacing="compact" mark="bullet">
-        <listitem>
+			  <listitem>
-          <simpara>
+				<simpara>
-            node ID
+				  node ID
-          </simpara>
+				</simpara>
-        </listitem>
+			  </listitem>
-        <listitem>
+			  <listitem>
-          <simpara>
+				<simpara>
             availability (0 = available, -1 = unavailable)
-          </simpara>
+				</simpara>
-        </listitem>
+			  </listitem>
+			  <listitem>
+				<simpara>
+				  recovery state (0 = not in recovery, 1 = in recovery, -1 = unknown)
+				</simpara>
+			  </listitem>
+			</itemizedlist>
+		  </para>
+		</listitem>
+	  </varlistentry>
+
+      <varlistentry>
+        <term><option>--verbose</option></term>
         <listitem>
-          <simpara>
+          <para>
-            recovery state (0 = not in recovery, 1 = in recovery, -1 = unknown)
+			Display the full text of any database connection error messages
-          </simpara>
+          </para>
         </listitem>
-      </itemizedlist>
+      </varlistentry>
-    </para>
+
+	</variablelist>
+
   </refsect1>
 
 

doc/repmgr-node-rejoin.sgml

@@ -67,10 +67,10 @@
         <term><option>--force-rewind[=/path/to/pg_rewind]</option></term>
         <listitem>
           <para>
-            Execute <application>pg_rewind</application> if necessary.
+            Execute <application>pg_rewind</application>.
           </para>
           <para>
-            It is only necessary to provide the <application>pg_rewind</application>
+            It is only necessary to provide the <application>pg_rewind</application> path
             if using PostgreSQL 9.3 or 9.4, and <application>pg_rewind</application>
             is not installed in the PostgreSQL <filename>bin</filename> directory.
           </para>
@@ -193,7 +193,7 @@
     </note>
 
     <para>
-      To have <command>repmgr node rejoin</command> use <command>pg_rewind</command> if required,
+      To have <command>repmgr node rejoin</command> use <command>pg_rewind</command>,
       pass the command line option <literal>--force-rewind</literal>, which will tell &repmgr;
       to execute <command>pg_rewind</command> to ensure the node can be rejoined successfully.
     </para>
@@ -226,6 +226,15 @@
     INFO: pg_rewind would now be executed
     DETAIL: pg_rewind command is:
       pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node1 dbname=repmgr user=repmgr'</programlisting>
+
+    <note>
+      <para>
+        If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
+        this checks the prerequisites for using <application>pg_rewind</application>, but cannot
+        predict the outcome of actually executing <application>pg_rewind</application>.
+      </para>
+    </note>
+
     <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node1 dbname=repmgr user=repmgr' \
          --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose

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-configuration.sgml

@@ -34,24 +34,6 @@
       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>
@@ -167,6 +149,203 @@
       </para>
     </sect2>
 
+    <sect2 id="repmgrd-reloading-configuration"xreflabel="reloading repmgrd configuration">
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>applying configuration changes</secondary>
+      </indexterm>
+      <title>Applying configuration changes to repmgrd</title>
+      <para>
+        To apply configuration file changes to a running <application>repmgrd</application>
+        daemon, execute the operating system's <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>
+      <tip>
+        <para>
+          Check the <application>repmgrd</application> log to see what changes were
+          applied, or if any issues were encountered when reloading the configuration.
+        </para>
+      </tip>
+      <para>
+        Note that only the following subset of configuration file parameters can be changed on a
+        running <application>repmgrd</application> daemon:
+      </para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <varname>async_query_timeout</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>bdr_local_monitoring_only</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>bdr_recovery_timeout</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>conninfo</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>degraded_monitoring_timeout</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>event_notification_command</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>event_notifications</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>failover</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>follow_command</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>log_facility</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>log_file</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>log_level</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>log_status_interval</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>monitor_interval_secs</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>monitoring_history</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>primary_notification_timeout</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>promote_command</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>reconnect_attempts</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>reconnect_interval</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>repmgrd_standby_startup_timeout</varname>
+          </simpara>
+        </listitem>
+
+      </itemizedlist>
+
+      <para>
+        The following set of configuration file parameters must be updated via
+        <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>,
+        as they require changes to the <literal>repmgr.nodes</literal> table so they are visible to
+        all nodes in the replication cluster:
+      </para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <varname>node_id</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>node_name</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>data_directory</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>location</varname>
+          </simpara>
+        </listitem>
+
+
+        <listitem>
+          <simpara>
+            <varname>priority</varname>
+          </simpara>
+        </listitem>
+
+      </itemizedlist>
+
+      <note>
+        <para>
+          After executing <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>,
+          <application>repmgrd</application> <emphasis>must</emphasis> be restarted for the changes to take effect.
+        </para>
+      </note>
+
+    </sect2>
+
   </sect1>
 
   <sect1 id="repmgrd-daemon">

repmgr-action-cluster.c

@@ -84,6 +84,7 @@ do_cluster_show(void)
 	ItemList	warnings = {NULL, NULL};
 	bool		success = false;
 	bool		error_found = false;
+	bool		connection_error_found = false;
 
 	/* Connect to local database to obtain cluster connection data */
 	log_verbose(LOG_INFO, _("connecting to database"));
@@ -141,14 +142,26 @@ do_cluster_show(void)
 		}
 		else
 		{
-			char		error[MAXLEN];
-
-			strncpy(error, PQerrorMessage(cell->node_info->conn), MAXLEN);
 			cell->node_info->node_status = NODE_STATUS_DOWN;
 			cell->node_info->recovery_type = RECTYPE_UNKNOWN;
-			item_list_append_format(&warnings,
+
-									"when attempting to connect to node \"%s\" (ID: %i), following error encountered :\n\"%s\"",
+			connection_error_found = true;
-									cell->node_info->node_name, cell->node_info->node_id, trim(error));
+
+			if (runtime_options.verbose)
+			{
+				char		error[MAXLEN];
+
+				strncpy(error, PQerrorMessage(cell->node_info->conn), MAXLEN);
+				item_list_append_format(&warnings,
+										"when attempting to connect to node \"%s\" (ID: %i), following error encountered :\n\"%s\"",
+										cell->node_info->node_name, cell->node_info->node_id, trim(error));
+			}
+			else
+			{
+				item_list_append_format(&warnings,
+										"unable to  connect to node \"%s\" (ID: %i)",
+										cell->node_info->node_name, cell->node_info->node_id);
+			}
 		}
 
 		initPQExpBuffer(&details);
@@ -437,6 +450,11 @@ do_cluster_show(void)
 		{
 			printf(_("  - %s\n"), cell->string);
 		}
+
+		if (runtime_options.verbose == false && connection_error_found == true)
+		{
+			log_hint(_("execute with --verbose option to see connection error messages"));
+		}
 	}
 
 	/*

repmgr.c

@@ -416,9 +416,9 @@ unset_bdr_failover_handler(PG_FUNCTION_ARGS)
 		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 
 		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
-
-		LWLockRelease(shared_state->lock);
 	}
 
+	LWLockRelease(shared_state->lock);
+
 	PG_RETURN_VOID();
 }

repmgr.conf.sample

@@ -161,7 +161,7 @@
 # Examples:
 #
 #   pg_ctl_options='-s'
-#   pg_basebackup_options='--label=repmgr_backup
+#   pg_basebackup_options='--label=repmgr_backup'
 #   rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
 #   ssh_options=-o "StrictHostKeyChecking no"
 
@@ -281,9 +281,9 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# a value of zero prevents the node being promoted to primary
 					# (default: 100)
 
-#reconnect_attempts=6			# Number attempts which will be made to reconnect to an unreachable
+#reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
-#reconnect_interval=10			# Interval between attempts  to reconnect to an unreachable
+#reconnect_interval=10			# Interval between attempts to reconnect to an unreachable
 					# primary (or other upstream node)
 #promote_command=			# command repmgrd executes when promoting a new primary; use something like:
 					#

repmgr_version.h.in

@@ -1,2 +1,2 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.1.1"
+#define REPMGR_VERSION "4.1.2"

repmgrd-physical.c

@@ -268,7 +268,12 @@ monitor_streaming_primary(void)
 		 * TODO: cache node list here, refresh at `node_list_refresh_interval`
 		 * also return reason for inavailability so we can log it
 		 */
-		if (is_server_available(local_node_info.conninfo) == false)
+
+		(void) connection_ping(local_conn);
+
+		check_connection(&local_node_info, &local_conn);
+
+		if (PQstatus(local_conn) != CONNECTION_OK)
 		{
 
 			/* local node is down, we were expecting it to be up */
@@ -308,6 +313,7 @@ monitor_streaming_primary(void)
 				if (local_node_info.node_status == NODE_STATUS_UP)
 				{
 					int			local_node_unreachable_elapsed = calculate_elapsed(local_node_unreachable_start);
+					int 		stored_local_node_id = UNKNOWN_NODE_ID;
 
 					initPQExpBuffer(&event_details);
 
@@ -324,6 +330,17 @@ monitor_streaming_primary(void)
 											  event_details.data);
 					termPQExpBuffer(&event_details);
 
+					/*
+					 * If the local node was restarted, we'll need to reinitialise values
+					 * stored in shared memory.
+					 */
+
+					stored_local_node_id = repmgrd_get_local_node_id(local_conn);
+					if (stored_local_node_id == UNKNOWN_NODE_ID)
+					{
+						repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
+					}
+
 					goto loop;
 				}
 
@@ -991,6 +1008,13 @@ monitor_streaming_standby(void)
 								continue;
 							}
 
+							/* skip witness node - we can't possibly "follow" that */
+
+							if (cell->node_info->type == WITNESS)
+							{
+								continue;
+							}
+
 							cell->node_info->conn = establish_db_connection(cell->node_info->conninfo, false);
 
 							if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
@@ -1013,6 +1037,7 @@ monitor_streaming_standby(void)
 							follow_new_primary(follow_node_id);
 						}
 					}
+
 					clear_node_info_list(&sibling_nodes);
 				}
 			}
@@ -1136,8 +1161,11 @@ loop:
 		}
 		else
 		{
+			/* we've reconnected to the local node after an outage */
 			if (local_node_info.active == false)
 			{
+				int stored_local_node_id = UNKNOWN_NODE_ID;
+
 				if (PQstatus(primary_conn) == CONNECTION_OK)
 				{
 					if (update_node_record_set_active(primary_conn, local_node_info.node_id, true) == true)
@@ -1153,19 +1181,29 @@ loop:
 										  local_node_info.node_name,
 										  local_node_info.node_id);
 
-						log_warning("%s", event_details.data)
+						log_notice("%s", event_details.data);
 
-
+						create_event_notification(primary_conn,
-							create_event_notification(primary_conn,
+												  &config_file_options,
-													  &config_file_options,
+												  local_node_info.node_id,
-													  local_node_info.node_id,
+												  "standby_recovery",
-													  "standby_recovery",
+												  true,
-													  true,
+												  event_details.data);
-													  event_details.data);
 
 						termPQExpBuffer(&event_details);
 					}
 				}
+
+				/*
+				 * If the local node was restarted, we'll need to reinitialise values
+				 * stored in shared memory.
+				 */
+
+				stored_local_node_id = repmgrd_get_local_node_id(local_conn);
+				if (stored_local_node_id == UNKNOWN_NODE_ID)
+				{
+					repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
+				}
 			}
 		}
 
@@ -1201,7 +1239,7 @@ monitor_streaming_witness(void)
 	/*
 	 * At this point we can't trust the local copy of "repmgr.nodes", as
 	 * it may not have been updated. We'll scan the cluster for the current
-	 * primary and refresh the copy from that before proceeding further.
+[''	 * primary and refresh the copy from that before proceeding further.
 	 */
 	primary_conn = get_primary_connection_quiet(local_conn, &primary_node_id, NULL);
 
@@ -1437,6 +1475,105 @@ monitor_streaming_witness(void)
 		}
 loop:
 
+		/*
+		 * handle local node failure
+		 *
+		 * currently we'll just check the connection, and try to reconnect
+		 *
+		 * TODO: add timeout, after which we run in degraded state
+		 */
+
+		(void) connection_ping(local_conn);
+
+		check_connection(&local_node_info, &local_conn);
+
+		if (PQstatus(local_conn) != CONNECTION_OK)
+		{
+			if (local_node_info.active == true)
+			{
+				bool success = true;
+				PQExpBufferData event_details;
+
+				initPQExpBuffer(&event_details);
+
+				local_node_info.active = false;
+
+				appendPQExpBuffer(&event_details,
+								  _("unable to connect to local node \"%s\" (ID: %i), marking inactive"),
+								  local_node_info.node_name,
+								  local_node_info.node_id);
+				log_notice("%s", event_details.data);
+
+				if (PQstatus(primary_conn) == CONNECTION_OK)
+				{
+					if (update_node_record_set_active(primary_conn, local_node_info.node_id, false) == false)
+					{
+						success = false;
+						log_warning(_("unable to mark node \"%s\" (ID: %i) as inactive"),
+									  local_node_info.node_name,
+									  local_node_info.node_id);
+					}
+				}
+
+				create_event_notification(primary_conn,
+										  &config_file_options,
+										  local_node_info.node_id,
+										  "standby_failure",
+										  success,
+										  event_details.data);
+
+				termPQExpBuffer(&event_details);
+			}
+		}
+		else
+		{
+			/* we've reconnected to the local node after an outage */
+			if (local_node_info.active == false)
+			{
+				int stored_local_node_id = UNKNOWN_NODE_ID;
+
+				if (PQstatus(primary_conn) == CONNECTION_OK)
+				{
+					if (update_node_record_set_active(primary_conn, local_node_info.node_id, true) == true)
+					{
+						PQExpBufferData event_details;
+
+						initPQExpBuffer(&event_details);
+
+						local_node_info.active = true;
+
+						appendPQExpBuffer(&event_details,
+										  _("reconnected to local node \"%s\" (ID: %i), marking active"),
+										  local_node_info.node_name,
+										  local_node_info.node_id);
+
+						log_notice("%s", event_details.data);
+
+						create_event_notification(primary_conn,
+												  &config_file_options,
+												  local_node_info.node_id,
+												  "standby_recovery",
+												  true,
+												  event_details.data);
+
+						termPQExpBuffer(&event_details);
+					}
+				}
+
+				/*
+				 * If the local node was restarted, we'll need to reinitialise values
+				 * stored in shared memory.
+				 */
+
+				stored_local_node_id = repmgrd_get_local_node_id(local_conn);
+				if (stored_local_node_id == UNKNOWN_NODE_ID)
+				{
+					repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
+				}
+			}
+		}
+
+
 		/* refresh repmgr.nodes after "witness_sync_interval" seconds */
 
 		{
@@ -1480,6 +1617,7 @@ loop:
 		}
 
 
+
 		if (got_SIGHUP)
 		{
 			handle_sighup(&local_conn, WITNESS);
@@ -2256,6 +2394,8 @@ follow_new_primary(int new_primary_id)
 	RecordStatus record_status = RECORD_NOT_FOUND;
 	bool		new_primary_ok = false;
 
+	log_verbose(LOG_DEBUG, "follow_new_primary(): new primary id is %i", new_primary_id);
+
 	record_status = get_node_record(local_conn, new_primary_id, &new_primary);
 
 	if (record_status != RECORD_FOUND)
@@ -2934,9 +3074,18 @@ check_connection(t_node_info *node_info, PGconn **conn)
 		}
 		else
 		{
+			int 		stored_local_node_id = UNKNOWN_NODE_ID;
+
 			log_info(_("reconnected to node \"%s\" (ID: %i)"),
 					 node_info->node_name,
 					 node_info->node_id);
+
+			stored_local_node_id = repmgrd_get_local_node_id(*conn);
+			if (stored_local_node_id == UNKNOWN_NODE_ID)
+			{
+				repmgrd_set_local_node_id(*conn, config_file_options.node_id);
+			}
+
 		}
 	}
 }