Merge pull request #799 from EnterpriseDB/validate-repmgr-options

Validate repmgr options

.github/workflows/sonarqube-scan.yml

@@ -1,37 +0,0 @@
-name: SonarQube Scan
-on:
-  pull_request:
-  push:
-    branches: [ master ]
-  workflow_dispatch:  
-jobs:
-  sonarQube:
-    name: SonarQube-Job
-    runs-on: ubuntu-latest
-    steps:
-    
-      - name: Checkout source repo
-        uses: actions/checkout@v1
-        with:
-          ref: '${{ github.head_ref }}'
-    
-      - name: Checkout GitHub Action Repo
-        uses: actions/checkout@master
-        with:
-          repository: EnterpriseDB/edb-github-actions.git
-          ref: master
-          token: ${{ secrets.GH_SLONIK }}
-          path: .github/actions/edb-github-actions
-          
-      - name: SonarQube Scan
-        uses: ./.github/actions/edb-github-actions/sonarqube
-        with:
-            REPO_NAME: '${{github.event.repository.name}}'
-            SONAR_PROJECT_KEY: EnterpriseDB_repmgr
-            SONAR_URL: '${{secrets.SONARQUBE_URL}}'
-            SONAR_LOGIN: '${{secrets.SONARQUBE_LOGIN}}'
-            PULL_REQUEST_KEY: '${{github.event.number}}'
-            PULL_REQUEST_BRANCH: '${{github.head_ref}}'
-            PULL_REQUEST_BASE_BRANCH: '${{github.base_ref}}'
-            REPO_DEFAULT_BRANCH: '${{github.event.repository.default_branch}}'
-            REPO_EXCLUDE_FILES: '*properties*,**/src/test/**/*,**/*.sql,**/docs/**/*,**/*/*.java'

.github/workflows/sonarqube/configure-env.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-
-DEBIAN_FRONTEND=noninteractive sudo apt-get -y install debhelper curl autoconf zlib1g-dev \
-  libedit-dev libxml2-dev libxslt1-dev libkrb5-dev libssl-dev libpam0g-dev systemtap-sdt-dev \
-  libselinux1-dev build-essential bison apt-utils lsb-release devscripts \
-  software-properties-common git shellcheck flex
-
-sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
-wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
-sudo apt-get update
-
-sudo apt-get -y install libpq-dev postgresql-13 postgresql-server-dev-13
-
-./configure
-
-export PG_CONFIG=/usr/bin/pg_config
-
-/home/buildfarm/sonar/depends/build-wrapper-linux-x86/build-wrapper-linux-x86-64 --out-dir build_wrapper_output_directory make 

HISTORY

@@ -1,7 +1,15 @@
-5.3.2   2022-??-??
+5.3.3   2022-10-17
+        Support for PostgreSQL added
+        repmgrd: ensure event notification script is called for event
+          "repmgrd_upstream_disconnect"; GitHub #760 (Ian)
+
+5.3.2   2022-05-25
         standby clone: don't error out if unable to determine cluster size (Ian)
         node check: fix --downstream --nagios output; GitHub #749 (Ian)
         repmgrd: ensure witness node marked active (hslightdb)
+        repmgrd: improve walsender disable check (Ian)
+        general: ensure replication slots can be dropped by a
+          replication-only user (Ian)
 
 5.3.1   2022-02-15
         repmgrd: fixes for potential connection leaks (hslightdb)
@@ -66,7 +74,7 @@
           "standby clone" (Ian)
         repmgr: add --upstream option to "node check"
         repmgr: report error code on follow/rejoin failure due to non-available
-0          replication slot (Ian)
+          replication slot (Ian)
         repmgr: ensure "node rejoin" checks for available replication slots (Ian)
         repmgr: improve "standby switchover" completion checks (Ian)
         repmgr: add replication configuration file ownership check to

Makefile.global.in

@@ -22,7 +22,7 @@ GIT_WORK_TREE=${repmgr_abs_srcdir}
 GIT_DIR=${repmgr_abs_srcdir}/.git
 export GIT_DIR
 export GIT_WORK_TREE
-
+PG_LDFLAGS=-lcurl -ljson-c
 include $(PGXS)
 
 -include ${repmgr_abs_srcdir}/Makefile.custom

Makefile.in

@@ -66,7 +66,7 @@ REPMGR_CLIENT_OBJS = repmgr-client.o \
 	repmgr-action-primary.o repmgr-action-standby.o repmgr-action-witness.o \
 	repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
 	configdata.o configfile.o configfile-scan.o log.o strutil.o controldata.o dirutil.o compat.o \
-	dbutils.o sysutils.o
+	dbutils.o sysutils.o pgbackupapi.o
 REPMGRD_OBJS = repmgrd.o repmgrd-physical.o configdata.o configfile.o configfile-scan.o log.o \
 	dbutils.o strutil.o controldata.o compat.o sysutils.o
 
@@ -81,10 +81,10 @@ configfile-scan.c: configfile-scan.l
 $(REPMGR_CLIENT_OBJS): repmgr-client.h repmgr_version.h
 
 repmgr: $(REPMGR_CLIENT_OBJS)
-	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
 
 repmgrd: $(REPMGRD_OBJS)
-	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
 
 $(REPMGR_CLIENT_OBJS): $(HEADERS)
 $(REPMGRD_OBJS): $(HEADERS)

README.md

@@ -7,8 +7,8 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-The most recent `repmgr` version (5.2.1) supports all PostgreSQL versions from
-9.5 to 13. PostgreSQL 9.4 is also supported, with some restrictions.
+The most recent `repmgr` version (5.3.2) supports all PostgreSQL versions from
+9.5 to 14. PostgreSQL 9.4 is also supported, with some restrictions.
 
 `repmgr` is distributed under the GNU GPL 3 and maintained by EnterpriseDB.
 
@@ -19,14 +19,6 @@ The full `repmgr` documentation is available here:
 
 > [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
-The old `README` file for `repmgr` 3.x is available here:
-
-> https://github.com/EnterpriseDB/repmgr/blob/REL3_3_STABLE/README.md
-
-Note that the `repmgr` 3.x series is no longer supported and contains known bugs;
-please upgrade to the [current repmgr version](https://repmgr.org/docs/current/appendix-release-notes.html)
-as soon as possible.
-
 Versions
 --------
 
@@ -48,7 +40,6 @@ Directories
  - `contrib/`: additional utilities
  - `doc/`: DocBook-based documentation files
  - `expected/`: expected regression test output
- - `scripts/`: example scripts
  - `sql/`: regression test input
 
 
@@ -78,7 +69,6 @@ news are always welcome.
 
 Thanks from the repmgr core team.
 
-* Ian Barwick
 * Jaime Casanova
 * Abhijit Menon-Sen
 * Simon Riggs

configdata.c

@@ -291,6 +291,46 @@ struct ConfigFileSetting config_file_settings[] =
 		{},
 		{}
 	},
+	/* pg_backupapi_backup_id*/
+	{
+		"pg_backupapi_backup_id",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_backupapi_backup_id },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_backupapi_backup_id) },
+		{}
+	},
+	/* pg_backupapi_host*/
+	{
+		"pg_backupapi_host",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_backupapi_host },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_backupapi_host) },
+		{}
+	},
+	/* pg_backupapi_node_name */
+	{
+		"pg_backupapi_node_name",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_backupapi_node_name },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_backupapi_node_name) },
+		{}
+	},
+	/* pg_backupapi_remote_ssh_command */
+	{
+		"pg_backupapi_remote_ssh_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_backupapi_remote_ssh_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_backupapi_remote_ssh_command) },
+		{}
+	},
 
 	/* =======================
 	 * standby follow settings

configfile.h

@@ -164,6 +164,10 @@ typedef struct
 	char		archive_cleanup_command[MAXLEN];
 	bool		use_primary_conninfo_password;
 	char		passfile[MAXPGPATH];
+	char		pg_backupapi_backup_id[NAMEDATALEN];
+	char		pg_backupapi_host[NAMEDATALEN];
+	char		pg_backupapi_node_name[NAMEDATALEN];
+	char		pg_backupapi_remote_ssh_command[MAXLEN];
 
 	/* standby promote settings */
 	int			promote_check_timeout;

configure.in

@@ -60,6 +60,7 @@ AC_SUBST(vpath_build)
 AC_CHECK_PROG(HAVE_GNUSED,gnused,yes,no)
 AC_CHECK_PROG(HAVE_GSED,gsed,yes,no)
 AC_CHECK_PROG(HAVE_SED,sed,yes,no)
+AC_CHECK_PROG(HAVE_FLEX,flex,yes,no)
 
 if test "$HAVE_GNUSED" = yes; then
  SED=gnused
@@ -72,6 +73,25 @@ else
 fi
 AC_SUBST(SED)
 
+AS_IF([test x"$HAVE_FLEX" != x"yes"], AC_MSG_ERROR([flex should be installed first]))
+
+#Checking libraries
+GENERIC_LIB_FAILED_MSG="library should be installed"
+
+AC_CHECK_LIB(selinux, is_selinux_enabled, [],
+     [AC_MSG_ERROR(['selinux' $GENERIC_LIB_FAILED_MSG])])
+
+AC_CHECK_LIB(lz4, LZ4_compress_default, [],
+     [AC_MSG_ERROR(['Z4' $GENERIC_LIB_FAILED_MSG])])
+
+AC_CHECK_LIB(xslt, xsltCleanupGlobals, [],
+     [AC_MSG_ERROR(['xslt' $GENERIC_LIB_FAILED_MSG])])
+
+AC_CHECK_LIB(pam, pam_start, [],
+     [AC_MSG_ERROR(['pam' $GENERIC_LIB_FAILED_MSG])])
+
+AC_CHECK_LIB(gssapi_krb5, gss_init_sec_context, [],
+     [AC_MSG_ERROR([gssapi_krb5 $GENERIC_LIB_FAILED_MSG])])
 
 AC_CONFIG_FILES([Makefile])
 AC_CONFIG_FILES([Makefile.global])

dbutils.c

@@ -1888,6 +1888,42 @@ can_execute_pg_promote(PGconn *conn)
 }
 
 
+/*
+ * Determine if the user associated with the current connection
+ * has sufficient permissions to disable the walsender
+ */
+bool
+can_disable_walsender(PGconn *conn)
+{
+	/*
+	 * Requires PostgreSQL 9.5 or later, because ALTER SYSTEM
+	 */
+	if (PQserverVersion(conn) < 90500)
+	{
+		log_warning(_("\"standby_disconnect_on_failover\" specified, but not available for this PostgreSQL version"));
+		/* TODO: format server version */
+		log_detail(_("available from PostgreSQL 9.5; this PostgreSQL version is %i"), PQserverVersion(conn));
+
+		return false;
+	}
+
+	/*
+	 * Superusers can do anything
+	 */
+	if (is_superuser_connection(conn, NULL) == true)
+		return true;
+
+	/*
+	 * As of PostgreSQL 14, it is not possible for a non-superuser
+	 * to execute ALTER SYSTEM, so further checks are superfluous.
+	 * This will need modifying for PostgreSQL 15.
+	 */
+	log_warning(_("\"standby_disconnect_on_failover\" specified, but repmgr user is not a superuser"));
+	log_detail(_("superuser permission required to disable standbys on failover"));
+
+	return false;
+}
+
 /*
  * Determine if the user associated with the current connection is
  * a member of the "pg_monitor" default role, or optionally one
@@ -4580,17 +4616,17 @@ drop_replication_slot_replprot(PGconn *repl_conn, char *slot_name)
 	initPQExpBuffer(&query);
 
 	appendPQExpBuffer(&query,
-					  "DROP_REPLICATION_SLOT %s",
+					  "DROP_REPLICATION_SLOT %s;",
 					  slot_name);
 
 	log_verbose(LOG_DEBUG, "drop_replication_slot_replprot():\n  %s", query.data);
 
 	res = PQexec(repl_conn, query.data);
 
-	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	if (PQresultStatus(res) != PGRES_TUPLES_OK || !PQntuples(res))
 	{
 		log_db_error(repl_conn, query.data,
-					 _("drop_replication_slot_sql(): unable to drop replication slot \"%s\""),
+					 _("drop_replication_slot_replprot(): unable to drop replication slot \"%s\""),
 					 slot_name);
 
 		success = false;

dbutils.h

@@ -454,6 +454,7 @@ pid_t		get_wal_receiver_pid(PGconn *conn);
 
 /* user/role information functions */
 bool		can_execute_pg_promote(PGconn *conn);
+bool		can_disable_walsender(PGconn *conn);
 bool		connection_has_pg_monitor_role(PGconn *conn, const char *subrole);
 bool		is_replication_role(PGconn *conn, char *rolname);
 bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);

doc/appendix-release-notes.xml

@@ -14,12 +14,47 @@
   <para>
     See also: <xref linkend="upgrading-repmgr"/>
   </para>
+
+  <!-- remember to update the release date in ../repmgr_version.h.in -->
+  <sect1 id="release-5.3.3">
+    <title id="release-current">Release 5.3.3</title>
+    <para><emphasis>Mon 17 October, 2022</emphasis></para>
+    <para>
+      &repmgr; 5.3.3 is a minor release providing support for
+      <ulink url="https://www.postgresql.org/docs/15/release-15.html">PostgreSQL 15</ulink>
+      and a &repmgrd; bug fix.
+    </para>
+    <para>
+      If upgrading from an earlier &repmgr; version, any running &repmgrd; instances should be restarted.
+    </para>
+    <para>
+      If upgrading from &repmgr; 5.2.1 or earlier, a PostgreSQL restart <emphasis>is</emphasis> required.
+    </para>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              &repmgrd;: ensure <link linkend="event-notifications">event notification</link> script is called for event
+              <literal>repmgrd_upstream_disconnect</literal>.  GitHub #760.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+
   <sect1 id="release-5.3.2">
-    <title id="release-current">Release 5.3.2</title>
-    <para><emphasis>??? ??? ???, 2022</emphasis></para>
+    <title>Release 5.3.2</title>
+    <para><emphasis>Wed 25 May, 2022</emphasis></para>
     <para>
       &repmgr; 5.3.2 is a minor release.
     </para>
+    <para>
+      Any running &repmgrd; instances should be restarted following this upgrade.
+    </para>
     <para>
       If upgrading from &repmgr; 5.2.1 or earlier, a PostgreSQL restart <emphasis>is</emphasis> required.
     </para>
@@ -53,12 +88,24 @@
               GitHub #754.
             </para>
           </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: if <varname>standby_disconnect_on_failover</varname> is set, verify
+              &repmgr; is a superuser before attempting to disable the WAL receiver.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              If the &repmgr; user is a non-superuser, and a replication-only user exists,
+              ensure redundant replication slots are dropped correctly even
+              if the <option>-S/--superuser</option> option is not provided.
+            </para>
+          </listitem>
         </itemizedlist>
       </para>
     </sect2>
   </sect1>
 
-<!-- remember to update the release date in ../repmgr_version.h.in -->
   <sect1 id="release-5.3.1">
     <title>Release 5.3.1</title>
     <para><emphasis>Tue 15 February, 2022</emphasis></para>

doc/install-requirements.xml

@@ -108,10 +108,31 @@
             <entry>
               Supported PostgreSQL versions
             </entry>
+            <entry>
+              Notes
+            </entry>
           </row>
         </thead>
 
         <tbody>
+          <row>
+            <entry>
+              &repmgr; 5.4
+            </entry>
+            <entry>
+              (dev)
+            </entry>
+            <entry>
+              <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
+            </entry>
+            <entry>
+              9.4, 9.5, 9.6, 10, 11, 12, 13, 15
+            </entry>
+            <entry>
+              &nbsp;
+            </entry>
+          </row>
+
           <row>
             <entry>
               &repmgr; 5.3
@@ -123,7 +144,10 @@
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
             <entry>
-              9.4, 9.5, 9.6, 10, 11, 12, 13, 14
+              9.4, 9.5, 9.6, 10, 11, 12, 13, 14, 15
+            </entry>
+            <entry>
+              PostgreSQL 15 supported from &repmgr; 5.3.3
             </entry>
           </row>
 
@@ -140,6 +164,9 @@
             <entry>
               9.4, 9.5, 9.6, 10, 11, 12, 13
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -155,6 +182,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -170,6 +200,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
 
@@ -186,6 +219,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -201,6 +237,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -216,6 +255,9 @@
             <entry>
               9.0, 9.1, 9.2, 9.3, 9.4
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
         </tbody>
 

doc/repmgr-node-rejoin.xml

@@ -73,16 +73,16 @@
       </varlistentry>
 
       <varlistentry>
-        <term><option>--force-rewind[=/path/to/pg_rewind]</option></term>
+        <term><option>--force-rewind</option></term>
         <listitem>
           <para>
             Execute <application>pg_rewind</application>.
           </para>
           <para>
-            It is only necessary to provide the <application>pg_rewind</application> path
-            if using PostgreSQL 9.4, and <application>pg_rewind</application>
-            is not installed in the PostgreSQL <filename>bin</filename> directory.
+            See <xref linkend="repmgr-node-rejoin-pg-rewind"/> for more details on using
+            <application>pg_rewind</application>.
           </para>
+
         </listitem>
       </varlistentry>
 
@@ -261,8 +261,6 @@
     <para>
       <command>repmgr node rejoin</command> can optionally use <command>pg_rewind</command> to re-integrate a
       node which has diverged from the rest of the cluster, typically a failed primary.
-      <command>pg_rewind</command> is available in PostgreSQL 9.5 and later as part of the core distribution,
-      and can be installed from external sources for PostgreSQL 9.4.
     </para>
     <note>
       <para>
@@ -271,6 +269,10 @@
         data checksums were enabled when the cluster was initialized. See the
         <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
       </para>
+      <para>
+        Additionally, <varname>full_page_writes</varname> must be enabled; this is the default and
+        normally should never be disabled.
+      </para>
     </note>
 
     <para>
@@ -382,6 +384,29 @@
     DETAIL: node 2 is now attached to node 3</programlisting>
       </para>
     </refsect2>
+
+    <refsect2 id="repmgr-node-rejoin-postgresql-94" xreflabel="pg_rewind and PostgreSQL 9.4">
+
+      <title><command>pg_rewind</command> and PostgreSQL 9.4</title>
+
+      <indexterm>
+        <primary>pg_rewind</primary>
+        <secondary>PostgreSQL 9.4</secondary>
+      </indexterm>
+
+      <para>
+        <application>pg_rewind</application> is available in PostgreSQL 9.5 and later as part of the core distribution.
+        Users of PostgreSQL 9.4 will need to manually install it; the source code is available here:
+        <ulink url="https://github.com/vmware/pg_rewind">https://github.com/vmware/pg_rewind</ulink>.
+        If the <application>pg_rewind</application>
+        binary is not installed in the PostgreSQL <filename>bin</filename> directory, provide
+        its full path  on the demotion candidate  with <option>--force-rewind</option>.
+      </para>
+      <para>
+        Note that building the 9.4 version of <application>pg_rewind</application> requires the PostgreSQL
+        source code.
+      </para>
+    </refsect2>
   </refsect1>
 
   <refsect1 id="repmgr-node-rejoin-caveats" xreflabel="Caveats">
@@ -426,7 +451,7 @@
 
    <warning>
      <para>
-       In all current PostgreSQL versions (as of September 2020), <application>pg_rewind</application>
+       In all PostgreSQL released before February 2021, <application>pg_rewind</application>
        contains a corner-case bug which affects standbys in a very specific situation.
      </para>
      <para>
@@ -456,8 +481,7 @@
      <para>
        Currently it is not possible to resolve this situation using <application>pg_rewind</application>.
        A <ulink url="https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=2b4f3130382fe2f8705863e4d38589d4d69cd695">patch</ulink>
-       has been successfully submitted and will be included the next PostgreSQL minor release round, scheduled for
-       February 2021.
+       was submitted and is included in all PostgreSQL versions released in February 2021 or later.
      </para>
      <para>
        As a workaround, start the primary server the standby was previously attached to,
@@ -475,7 +499,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-standby-follow"/>
+     <xref linkend="repmgr-standby-follow"/>, <xref linkend="repmgr-standby-switchover"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-standby-switchover.xml

@@ -154,9 +154,12 @@
           <para>
             Use <application>pg_rewind</application> to reintegrate the old primary if necessary
             (and the prerequisites for using <application>pg_rewind</application> are met).
+          </para>
+          <para>
             If using PostgreSQL 9.4, and the <application>pg_rewind</application>
             binary is not installed in the PostgreSQL <filename>bin</filename> directory,
-            provide its full path. For more details see also <xref linkend="switchover-pg-rewind"/>.
+            provide its full path. For more details see also <xref linkend="switchover-pg-rewind"/>
+            and <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
           </para>
         </listitem>
       </varlistentry>

doc/repmgr.xml

@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.4 - PostgreSQL 14.
+   use with PostgreSQL 9.4 - PostgreSQL 15.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the

doc/repmgrd-configuration.xml

@@ -345,14 +345,18 @@
             </indexterm>
 
             <para>
-              Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes;
-			  a value of zero prevents the node being promoted to primary.
+              Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes.
             </para>
             <para>
               Note that the priority setting is only applied if two or more nodes are
               determined as promotion candidates; in that case the node with the
               higher priority is selected.
             </para>
+            <para>
+              A value of zero will always prevent the node being promoted to primary, even if there
+              is no other promotion candidate.
+            </para>
+
           </listitem>
         </varlistentry>
 

doc/repmgrd-overview.xml

@@ -29,7 +29,7 @@
 
        <listitem>
          <simpara>
-           option to execute custom scripts (&quot;<link linkend="event-notifications">event notifications</link>
+           option to execute custom scripts (&quot;<link linkend="event-notifications">event notifications</link>&quot;)
            at different points in the failover sequence
          </simpara>
        </listitem>

doc/switchover.xml

@@ -242,21 +242,12 @@
       </simpara>
     </note>
     <para>
-      For more details on <application>pg_rewind</application>, see:
+      For more details on <application>pg_rewind</application>, see section <xref linkend="repmgr-node-rejoin-pg-rewind"/>
+      in the <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link> documentation and
+      the PostgreSQL documentation at
       <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html">https://www.postgresql.org/docs/current/app-pgrewind.html</ulink>.
     </para>
-    <para>
-      <application>pg_rewind</application> has been part of the core PostgreSQL distribution since
-      version 9.5. Users of PostgreSQL 9.4 will need to manually install it; the source code is available here:
-      <ulink url="https://github.com/vmware/pg_rewind">https://github.com/vmware/pg_rewind</ulink>.
-      If the <application>pg_rewind</application>
-      binary is not installed in the PostgreSQL <filename>bin</filename> directory, provide
-      its full path  on the demotion candidate  with <option>--force-rewind</option>.
-    </para>
-    <para>
-      Note that building the 9.4 version of <application>pg_rewind</application> requires the PostgreSQL
-      source code.
-    </para>
+
   </sect2>
 
 

doc/upgrading-repmgr.xml

@@ -71,6 +71,12 @@
 	  <secondary>minor release</secondary>
 	</indexterm>
 
+    <para>
+	  A minor release upgrade involves updating &repmgr; from one minor release to another
+	  minor release within the same major release (e.g. <literal>5.3.1</literal> to <literal>5.3.2</literal>).
+	  An upgrade between minor releases of differing major releases (e.g. <literal>5.2.1</literal> to <literal>5.3.2</literal>)
+	  is a <link linkend="upgrading-major-version">major upgrade</link>.
+    </para>
     <para>
       The process for installing minor version upgrades is quite straightforward:
 
@@ -105,15 +111,17 @@
 	</para>
 
 	<para>
-	  A PostgreSQL restart is <emphasis>not</emphasis> required for minor version upgrades.
+	  A PostgreSQL restart is usually <emphasis>not</emphasis> required for minor version upgrades
+	  within the same major version (e.g. <literal>5.3.1</literal> to <literal>5.3.2</literal>).
+	  Be sure to check the <link linkend="appendix-release-notes">release notes</link>.
 	</para>
 
     <note>
 	  <para>
-	    The same &repmgr; &quot;major version&quot; (e.g. <literal>4.2</literal>) must be
-	    installed on all nodes in the replication cluster. While it's possible to have differing
-	    &repmgr; &quot;minor versions&quot; (e.g. <literal>4.2.1</literal>)  on different nodes,
-	    we strongly recommend updating all nodes to the latest minor version.
+		The same &repmgr; &quot;major version&quot; (e.g. <literal>5.3</literal>) must be
+		installed on all nodes in the replication cluster. While it's possible to have differing
+		&repmgr; &quot;minor versions&quot; (e.g. <literal>5.3.1</literal> and <literal>5.3.2</literal>)
+		on different nodes, we strongly recommend updating all nodes to the latest minor version.
 	  </para>
     </note>
 

errcode.h

@@ -49,5 +49,6 @@
 #define ERR_NODE_STATUS 25
 #define ERR_REPMGRD_PAUSE 26
 #define ERR_REPMGRD_SERVICE 27
+#define ERR_PGBACKUPAPI_SERVICE 28
 
 #endif							/* _ERRCODE_H_ */

pgbackupapi.c

@@ -0,0 +1,147 @@
+/*
+ * pgbackupapi.c
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <string.h>
+
+#include <curl/curl.h>
+#include <json-c/json.h>
+
+#include "repmgr.h"
+#include "pgbackupapi.h"
+
+
+size_t receive_operations_cb(void *content, size_t size, size_t nmemb, char *buffer) {
+	short int max_chars_to_copy = MAX_BUFFER_LENGTH -2;
+	short int i = 0;
+	int operation_length = 0;
+	json_object *value;
+
+	json_object *root = json_tokener_parse(content);
+	json_object *operations = json_object_object_get(root, "operations");
+
+	operation_length = strlen(json_object_get_string(operations));
+	if (operation_length < max_chars_to_copy) {
+		max_chars_to_copy = operation_length;
+	}
+
+	strncpy(buffer, json_object_get_string(operations), max_chars_to_copy);
+
+	fprintf(stdout, "Success! The following operations were found\n");
+	for (i=0; i<json_object_array_length(operations); i++) {
+		value = json_object_array_get_idx(operations, i);
+		printf("%s\n", json_object_get_string(value));
+	}
+	return size * nmemb;
+}
+
+char * define_base_url(operation_task *task) {
+	char *format = "http://%s:7480/servers/%s/operations";
+	char *url = malloc(MAX_BUFFER_LENGTH);
+
+	snprintf(url, MAX_BUFFER_LENGTH-1, format, task->host, task->node_name);
+
+	//`url` is freed on the function that called this
+	return url;
+}
+
+CURLcode get_operations_on_server(CURL *curl, operation_task *task) {
+	char buffer[MAX_BUFFER_LENGTH];
+	char *url = define_base_url(task);
+	CURLcode ret;
+
+	curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, receive_operations_cb);
+	curl_easy_setopt(curl, CURLOPT_WRITEDATA, &buffer);
+	curl_easy_setopt(curl, CURLOPT_URL, url);
+
+	ret = curl_easy_perform(curl);
+	free(url);
+
+	return ret;
+}
+
+size_t receive_operation_id(void *content, size_t size, size_t nmemb, char *buffer) {
+	json_object *root = json_tokener_parse(content);
+	json_object *operation = json_object_object_get(root, "operation_id");
+
+	if (operation != NULL) {
+		strncpy(buffer, json_object_get_string(operation), MAX_BUFFER_LENGTH-2);
+	}
+
+	return size * nmemb;
+}
+
+
+CURLcode create_new_task(CURL *curl, operation_task *task) {
+	PQExpBufferData payload;
+	char *url = define_base_url(task);
+	CURLcode ret;
+	json_object *root = json_object_new_object();
+	struct curl_slist *chunk = NULL;
+
+	json_object_object_add(root, "operation_type", json_object_new_string(task->operation_type));
+	json_object_object_add(root, "backup_id", json_object_new_string(task->backup_id));
+	json_object_object_add(root, "remote_ssh_command", json_object_new_string(task->remote_ssh_command));
+	json_object_object_add(root, "destination_directory", json_object_new_string(task->destination_directory));
+
+	initPQExpBuffer(&payload);
+	appendPQExpBufferStr(&payload, json_object_to_json_string(root));
+
+	chunk = curl_slist_append(chunk, "Content-type: application/json");
+	curl_easy_setopt(curl, CURLOPT_HTTPHEADER, chunk);
+	curl_easy_setopt(curl, CURLOPT_URL, url);
+	curl_easy_setopt(curl, CURLOPT_POSTFIELDS, payload.data);
+	curl_easy_setopt(curl, CURLOPT_FAILONERROR, 1L);
+	//curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L);
+	curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, receive_operation_id);
+	curl_easy_setopt(curl, CURLOPT_WRITEDATA, task->operation_id);
+	ret = curl_easy_perform(curl);
+	free(url);
+	termPQExpBuffer(&payload);
+
+	return ret;
+}
+
+
+size_t receive_operation_status(void *content, size_t size, size_t nmemb, char *buffer) {
+	json_object *root = json_tokener_parse(content);
+	json_object *status = json_object_object_get(root, "status");
+	if (status != NULL) {
+		strncpy(buffer, json_object_get_string(status), MAX_BUFFER_LENGTH-2);
+	}
+	else {
+		fprintf(stderr, "Incorrect reply received for that operation ID.\n");
+		strcpy(buffer, "\0");
+	}
+	return size * nmemb;
+}
+
+CURLcode get_status_of_operation(CURL *curl, operation_task *task) {
+	CURLcode ret;
+	char *url = define_base_url(task);
+
+	strcat(url, "/");
+	strcat(url, task->operation_id);
+	curl_easy_setopt(curl, CURLOPT_URL, url);
+	curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, receive_operation_status);
+	curl_easy_setopt(curl, CURLOPT_WRITEDATA, task->operation_status);
+
+	ret = curl_easy_perform(curl);
+	free(url);
+
+	return ret;
+}

pgbackupapi.h

@@ -0,0 +1,46 @@
+/*
+ * pgbackupapi.h
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <curl/curl.h>
+#include <json-c/json.h>
+
+typedef struct operation_task {
+        char *backup_id;
+        char *destination_directory;
+        char *operation_type;
+	char *operation_id;
+	char *operation_status;
+        char *remote_ssh_command;
+	char *host;
+	char *node_name;
+} operation_task;
+
+//Default simplebuffer size in most of operations
+#define MAX_BUFFER_LENGTH 72
+
+//Callbacks to send/receive data from pg-backup-api endpoints
+size_t receive_operations_cb(void *content, size_t size, size_t nmemb, char *buffer);
+size_t receive_operation_id(void *content, size_t size, size_t nmemb, char *buffer);
+size_t receive_operation_status(void *content, size_t size, size_t nmemb, char *buffer);
+
+//Functions that implement the logic and know what to do and how to comunnicate wuth the API
+CURLcode get_operations_on_server(CURL *curl, operation_task *task);
+CURLcode create_new_task(CURL *curl, operation_task *task);
+CURLcode get_status_of_operation(CURL *curl, operation_task *task);
+
+//Helper to make simpler to read the handler where we set the URL
+char * define_base_url(operation_task *task);

repmgr-action-standby.c

@@ -21,6 +21,7 @@
 
 #include <sys/stat.h>
 #include <time.h>
+#include <unistd.h>
 
 #include "repmgr.h"
 #include "dirutil.h"
@@ -29,7 +30,7 @@
 
 #include "repmgr-client-global.h"
 #include "repmgr-action-standby.h"
-
+#include "pgbackupapi.h"
 
 typedef struct TablespaceDataListCell
 {
@@ -113,6 +114,7 @@ static void check_recovery_type(PGconn *conn);
 static void initialise_direct_clone(t_node_info *local_node_record, t_node_info *upstream_node_record);
 static int	run_basebackup(t_node_info *node_record);
 static int	run_file_backup(t_node_info *node_record);
+static int	run_pg_backupapi(t_node_info *node_record);
 
 static void copy_configuration_files(bool delete_after_copy);
 
@@ -687,19 +689,18 @@ do_standby_clone(void)
 		exit(SUCCESS);
 	}
 
-	if (mode != barman)
-	{
-		initialise_direct_clone(&local_node_record, &upstream_node_record);
-	}
-
 	switch (mode)
 	{
 		case pg_basebackup:
+			initialise_direct_clone(&local_node_record, &upstream_node_record);
 			log_notice(_("starting backup (using pg_basebackup)..."));
 			break;
 		case barman:
 			log_notice(_("retrieving backup from Barman..."));
 			break;
+		case pg_backupapi:
+			log_notice(_("starting backup (using pg_backupapi)..."));
+			break;
 		default:
 			/* should never reach here */
 			log_error(_("unknown clone mode"));
@@ -721,6 +722,9 @@ do_standby_clone(void)
 		case barman:
 			r = run_file_backup(&local_node_record);
 			break;
+		case pg_backupapi:
+			r = run_pg_backupapi(&local_node_record);
+			break;
 		default:
 			/* should never reach here */
 			log_error(_("unknown clone mode"));
@@ -814,7 +818,6 @@ do_standby_clone(void)
 	}
 
 	/* Write the recovery.conf file */
-
 	if (create_recovery_file(&local_node_record,
 							 &recovery_conninfo,
 							 source_server_version_num,
@@ -846,6 +849,9 @@ do_standby_clone(void)
 		case barman:
 			log_notice(_("standby clone (from Barman) complete"));
 			break;
+		case pg_backupapi:
+			log_notice(_("standby clone (from pg_backupapi) complete"));
+			break;
 	}
 
 	/*
@@ -937,6 +943,9 @@ do_standby_clone(void)
 		case barman:
 			appendPQExpBufferStr(&event_details, "barman");
 			break;
+		case pg_backupapi:
+			appendPQExpBufferStr(&event_details, "pg_backupapi");
+			break;
 	}
 
 	appendPQExpBuffer(&event_details,
@@ -3348,10 +3357,9 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 			update_node_record_slot_name(primary_conn, config_file_options.node_id, local_node_record.slot_name);
 		}
 
-
 		if (create_replication_slot(follow_target_conn,
 									local_node_record.slot_name,
-									NULL,
+									follow_target_node_record,
 									output) == false)
 		{
 			log_error("%s", output->data);
@@ -7771,6 +7779,117 @@ stop_backup:
 }
 
 
+/*
+ * Perform a call to pg_backupapi endpoint to ask barman to write the backup
+ * for us. This will ensure that no matter the format on-disk of new backups,
+ * barman will always find a way how to read and write them.
+ * From repmgr 4 this is only used for Barman backups.
+ */
+static int
+run_pg_backupapi(t_node_info *local_node_record)
+{
+	int r = ERR_PGBACKUPAPI_SERVICE;
+	long http_return_code = 0;
+	short seconds_to_sleep = 3;
+	operation_task *task = malloc(sizeof(operation_task));
+	CURL *curl = curl_easy_init();
+	CURLcode ret;
+
+	check_pg_backupapi_standby_clone_options();
+
+	task->host = malloc(strlen(config_file_options.pg_backupapi_host)+1);
+	task->remote_ssh_command = malloc(strlen(config_file_options.pg_backupapi_remote_ssh_command)+1);
+	task->node_name = malloc(strlen(config_file_options.pg_backupapi_node_name)+1);
+	task->operation_type = malloc(strlen(DEFAULT_STANDBY_PG_BACKUPAPI_OP_TYPE)+1);
+	task->backup_id = malloc(strlen(config_file_options.pg_backupapi_backup_id)+1);
+	task->destination_directory = malloc(strlen(local_data_directory)+1);
+
+	task->operation_id = malloc(MAX_BUFFER_LENGTH);
+	task->operation_status = malloc(MAX_BUFFER_LENGTH);
+
+	strcpy(task->host, config_file_options.pg_backupapi_host);
+	strcpy(task->remote_ssh_command, config_file_options.pg_backupapi_remote_ssh_command);
+	strcpy(task->node_name, config_file_options.pg_backupapi_node_name);
+	strcpy(task->operation_type, DEFAULT_STANDBY_PG_BACKUPAPI_OP_TYPE);
+	strcpy(task->backup_id, config_file_options.pg_backupapi_backup_id);
+	strcpy(task->destination_directory, local_data_directory);
+	strcpy(task->operation_id, "\0");
+
+	ret = create_new_task(curl, task);
+
+	if ((ret != CURLE_OK) || (strlen(task->operation_id) == 0)) {
+		curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &http_return_code);
+		if (499 > http_return_code && http_return_code >= 400) {
+			log_error("Cannot find backup '%s' for node '%s'.", task->backup_id, task->node_name);
+		} else {
+			log_error("whilst reaching out pg_backup service: %s\n", curl_easy_strerror(ret));
+		}
+        }
+	else
+	{
+		log_info("Success creating the task: operation id '%s'", task->operation_id);
+
+		//We call init again because previous call included POST calls
+		curl_easy_cleanup(curl);
+		curl = curl_easy_init();
+		while (true)
+		{
+			ret = get_status_of_operation(curl, task);
+			if (strlen(task->operation_status) == 0) {
+				log_info("Retrying...");
+			}
+			else
+			{
+				log_info("status %s", task->operation_status);
+			}
+			if (strcmp(task->operation_status, "FAILED") == 0) {
+				break;
+			}
+			if (strcmp(task->operation_status, "DONE") == 0) {
+				r = SUCCESS;
+				break;
+			}
+
+			sleep(seconds_to_sleep);
+		}
+	}
+
+	curl_easy_cleanup(curl);
+	free(task);
+	return r;
+}
+
+/*
+ * pg_backupapi mode is enabled when config_file_options.pg_backupapi_host is set hence, we
+ * should also check the other required variables too.
+ */
+
+void check_pg_backupapi_standby_clone_options() {
+
+	bool error = false;
+
+	if (*config_file_options.pg_backupapi_remote_ssh_command == '\0') {
+		log_hint("Check config: remote ssh command is required");
+		error = true;
+	}
+	if (*config_file_options.pg_backupapi_node_name == '\0') {
+		log_hint("Check config: node name is required");
+		error = true;
+	}
+	if (*config_file_options.pg_backupapi_backup_id == '\0') {
+		log_hint("Check config: backup_id is required");
+		error = true;
+	}
+
+	if (error == true) {
+		log_error("Please fix the errors and try again");
+		exit(ERR_BAD_CONFIG);
+	}
+
+}
+
+
+
 static char *
 make_barman_ssh_command(char *buf)
 {

repmgr-action-standby.h

@@ -30,6 +30,6 @@ extern void do_standby_help(void);
 
 extern bool do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_node_info *follow_target_node_record, PQExpBufferData *output, int general_error_code, int *error_code);
 
-
+void check_pg_backupapi_standby_clone_options(void);
 
 #endif							/* _REPMGR_ACTION_STANDBY_H_ */

repmgr-client-global.h

@@ -193,7 +193,8 @@ typedef struct
 typedef enum
 {
 	barman,
-	pg_basebackup
+	pg_basebackup,
+	pg_backupapi
 } standy_clone_mode;
 
 typedef enum

repmgr-client.c

@@ -90,17 +90,22 @@ char		pg_bindir[MAXPGPATH] = "";
  */
 t_node_info target_node_info = T_NODE_INFO_INITIALIZER;
 
-/* used by create_replication_slot() */
+/* set by the first call to _determine_replication_slot_user() */
 static t_user_type ReplicationSlotUser = USER_TYPE_UNKNOWN;
 
 /* Collate command line errors and warnings here for friendlier reporting */
 static ItemList cli_errors = {NULL, NULL};
 static ItemList cli_warnings = {NULL, NULL};
 
+
 static void _determine_replication_slot_user(PGconn *conn,
 											 t_node_info *upstream_node_record,
 											 char **replication_user);
 
+static PGconn *_get_replication_slot_connection(PGconn *conn,
+												char *replication_user,
+												bool *use_replication_protocol);
+
 int
 main(int argc, char **argv)
 {
@@ -3091,9 +3096,14 @@ get_standby_clone_mode(void)
 
 	if (*config_file_options.barman_host != '\0' && runtime_options.without_barman == false)
 		mode = barman;
-	else
-		mode = pg_basebackup;
-
+	else {
+		if (*config_file_options.pg_backupapi_host != '\0') {
+			log_info("Attempting to use `pg_backupapi` new restore mode");
+			mode = pg_backupapi;
+		}
+		else
+			mode = pg_basebackup;
+	}
 	return mode;
 }
 
@@ -3629,8 +3639,8 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 	/* "full_page_writes" must be on in any case */
 	if (guc_set(conn, "full_page_writes", "=", "off"))
 	{
-		appendPQExpBuffer(reason,
-						  _("\"full_page_writes\" must be set to \"on\""));
+		appendPQExpBufferStr(reason,
+							 _("\"full_page_writes\" must be set to \"on\""));
 
 		can_use = false;
 	}
@@ -3648,18 +3658,18 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 		if (data_checksum_version == UNKNOWN_DATA_CHECKSUM_VERSION)
 		{
 			if (can_use == false)
-				appendPQExpBuffer(reason, "; ");
+				appendPQExpBufferStr(reason, "; ");
 
-			appendPQExpBuffer(reason,
-							  _("\"wal_log_hints\" is set to \"off\" but unable to determine data checksum version"));
+			appendPQExpBufferStr(reason,
+								 _("\"wal_log_hints\" is set to \"off\" but unable to determine data checksum version"));
 			can_use = false;
 		}
 		else if (data_checksum_version == 0)
 		{
 			if (can_use == false)
-				appendPQExpBuffer(reason, "; ");
+				appendPQExpBufferStr(reason, "; ");
 
-			appendPQExpBuffer(reason,
+			appendPQExpBufferStr(reason,
 							  _("\"wal_log_hints\" is set to \"off\" and data checksums are disabled"));
 
 			can_use = false;
@@ -3739,6 +3749,7 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 	char *replication_user = NULL;
 
 	_determine_replication_slot_user(conn, upstream_node_record, &replication_user);
+
 	/*
 	 * If called in --dry-run context, if the replication slot user is not the
 	 * repmgr user, attempt to validate the connection.
@@ -3750,7 +3761,7 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 			case USER_TYPE_UNKNOWN:
 				log_error("unable to determine user for replication slot creation");
 				return false;
-			case  REPMGR_USER:
+			case REPMGR_USER:
 				log_info(_("replication slots will be created by user \"%s\""),
 						 PQuser(conn));
 				return true;
@@ -3796,65 +3807,12 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 				PQfinish(superuser_conn);
 			}
 		}
-
 	}
 
-	/*
-	 * If we can't create a replication slot with the connection provided to
-	 * the function, create an connection with appropriate permissions.
-	 */
-	switch (ReplicationSlotUser)
-	{
-		case USER_TYPE_UNKNOWN:
-			log_error("unable to determine user for replication slot creation");
-			return false;
-		case  REPMGR_USER:
-			slot_conn = conn;
-			log_info(_("creating replication slot as user \"%s\""),
-					 PQuser(conn));
-			break;
+	slot_conn = _get_replication_slot_connection(conn, replication_user, &use_replication_protocol);
 
-		case REPLICATION_USER_NODE:
-		case REPLICATION_USER_OPT:
-		{
-			slot_conn = duplicate_connection(conn,
-											 replication_user,
-											 true);
-			if (slot_conn == NULL || PQstatus(slot_conn) != CONNECTION_OK)
-			{
-				log_error(_("unable to create replication connection as user \"%s\""),
-						  runtime_options.replication_user);
-				log_detail("%s", PQerrorMessage(slot_conn));
-
-				PQfinish(slot_conn);
-					return false;
-			}
-			use_replication_protocol = true;
-			log_info(_("creating replication slot as replication user \"%s\""),
-					 replication_user);
-		}
-			break;
-
-		case SUPERUSER:
-		{
-			slot_conn = duplicate_connection(conn,
-											 runtime_options.superuser,
-											 false);
-			if (slot_conn == NULL || PQstatus(slot_conn )!= CONNECTION_OK)
-			{
-				log_error(_("unable to create super connection as user \"%s\""),
-						  runtime_options.superuser);
-				log_detail("%s", PQerrorMessage(slot_conn));
-
-				PQfinish(slot_conn);
-
-				return false;
-			}
-			log_info(_("creating replication slot as superuser \"%s\""),
-					 runtime_options.superuser);
-		}
-			break;
-	}
+	if (slot_conn == NULL)
+		return false;
 
 	if (use_replication_protocol == true)
 	{
@@ -3897,34 +3855,53 @@ drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name)
 
 	if (record_status != RECORD_FOUND)
 	{
-		/* this is not a bad good thing */
+		/* no slot, no problem */
 		log_verbose(LOG_INFO,
 					_("slot \"%s\" does not exist on node %i, nothing to remove"),
 					slot_name, node_id);
 		return true;
 	}
 
-	if (slot_info.active == false)
+	if (slot_info.active == true)
 	{
-		if (drop_replication_slot_sql(conn, slot_name) == true)
+		/*
+		 * If an active replication slot exists, bail out as we have a problem
+		 * we can't solve here.
+		 */
+		log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
+		success = false;
+	}
+	else
+	{
+		/*
+		 * Create the appropriate connection with which to drop the slot
+		 */
+
+		bool use_replication_protocol = false;
+		PGconn *slot_conn = _get_replication_slot_connection(conn,
+															 replication_user,
+															 &use_replication_protocol);
+
+		if (use_replication_protocol == true)
+		{
+			success = drop_replication_slot_replprot(slot_conn, slot_name);
+		}
+		else
+		{
+			success = drop_replication_slot_sql(slot_conn, slot_name);
+		}
+
+		if (success == true)
 		{
 			log_notice(_("replication slot \"%s\" deleted on node %i"), slot_name, node_id);
 		}
 		else
 		{
 			log_error(_("unable to delete replication slot \"%s\" on node %i"), slot_name, node_id);
-			success = false;
 		}
-	}
 
-	/*
-	 * If an active replication slot exists, call Houston as we have a
-	 * problem.
-	 */
-	else
-	{
-		log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
-		success = false;
+		if (slot_conn != conn)
+			PQfinish(slot_conn);
 	}
 
 	return success;
@@ -3986,10 +3963,88 @@ _determine_replication_slot_user(PGconn *conn, t_node_info *upstream_node_record
 			ReplicationSlotUser = REPLICATION_USER_NODE;
 			*replication_user = upstream_node_record->repluser;
 		}
+		else
+		{
+			/* This should never happen */
+			log_error("unable to determine replication slot user");
+			if (upstream_node_record != NULL)
+			{
+				log_debug("%i %s %s", upstream_node_record->node_id, upstream_node_record->repluser, PQuser(conn));
+			}
+			else
+			{
+				log_debug("upstream_node_record not provided");
+			}
+		}
 	}
 }
 
 
+static PGconn *
+_get_replication_slot_connection(PGconn *conn, char *replication_user, bool *use_replication_protocol)
+{
+	PGconn *slot_conn = NULL;
+	/*
+	 * If we can't create a replication slot with the connection provided to
+	 * the function, create an connection with appropriate permissions.
+	 */
+	switch (ReplicationSlotUser)
+	{
+		case USER_TYPE_UNKNOWN:
+			log_error("unable to determine user for managing replication slots");
+			return NULL;
+
+		case  REPMGR_USER:
+			slot_conn = conn;
+			log_verbose(LOG_INFO, _("managing replication slot as user \"%s\""),
+						PQuser(conn));
+			break;
+
+		case REPLICATION_USER_NODE:
+		case REPLICATION_USER_OPT:
+		{
+			slot_conn = duplicate_connection(conn,
+											 replication_user,
+											 true);
+			if (slot_conn == NULL || PQstatus(slot_conn) != CONNECTION_OK)
+			{
+				log_error(_("unable to manage replication connection as replication user \"%s\""),
+						  runtime_options.replication_user);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+				return NULL;
+			}
+			*use_replication_protocol = true;
+			log_verbose(LOG_INFO, _("managing replication slot as replication user \"%s\""),
+						replication_user);
+		}
+		break;
+
+		case SUPERUSER:
+		{
+			slot_conn = duplicate_connection(conn,
+											 runtime_options.superuser,
+											 false);
+			if (slot_conn == NULL || PQstatus(slot_conn )!= CONNECTION_OK)
+			{
+				log_error(_("unable to create superuser connection as user \"%s\""),
+						  runtime_options.superuser);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+
+				return NULL;
+			}
+			log_verbose(LOG_INFO, _("creating replication slot as superuser \"%s\""),
+						runtime_options.superuser);
+		}
+		break;
+	}
+
+	return slot_conn;
+}
+
 bool
 check_replication_slots_available(int node_id, PGconn* conn)
 {

repmgr.c

@@ -86,7 +86,6 @@ static shmem_request_hook_type prev_shmem_request_hook = NULL;
 static shmem_startup_hook_type prev_shmem_startup_hook = NULL;
 
 void		_PG_init(void);
-void		_PG_fini(void);
 
 #if (PG_VERSION_NUM >= 150000)
 static void repmgr_shmem_request(void);
@@ -145,21 +144,6 @@ _PG_init(void)
 
 }
 
-
-/*
- * Module unload callback
- */
-void
-_PG_fini(void)
-{
-	/* Uninstall hook */
-#if (PG_VERSION_NUM >= 150000)
-	shmem_request_hook = prev_shmem_request_hook;
-#endif
-
-	shmem_startup_hook = prev_shmem_startup_hook;
-}
-
 #if (PG_VERSION_NUM >= 150000)
 /*
  * shmem_requst_hook: request shared memory
@@ -177,7 +161,7 @@ repmgr_shmem_request(void)
 #endif
 
 /*
- * shmem_ hook: allocate or attach to shared memory,
+ * shmem_startup hook: allocate or attach to shared memory
  */
 static void
 repmgr_shmem_startup(void)

repmgr.h

@@ -116,6 +116,7 @@
 #define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
 #define DEFAULT_STANDBY_FOLLOW_RESTART       false
 #define DEFAULT_SHUTDOWN_CHECK_TIMEOUT       60  /* seconds */
+#define DEFAULT_STANDBY_PG_BACKUPAPI_OP_TYPE "recovery"
 #define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */
 #define DEFAULT_NODE_REJOIN_TIMEOUT          60  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */

repmgrd-physical.c

@@ -1587,22 +1587,22 @@ monitor_streaming_standby(void)
 					/* TODO: possibly add pre-action event here */
 					if (upstream_node_info.type == STANDBY)
 					{
-						create_event_record(primary_conn,
-											&config_file_options,
-											config_file_options.node_id,
-											"repmgrd_upstream_disconnect",
-											true,
-											event_details.data);
+						create_event_notification(primary_conn,
+												  &config_file_options,
+												  config_file_options.node_id,
+												  "repmgrd_upstream_disconnect",
+												  true,
+												  event_details.data);
 					}
 					else
 					{
 						/* primary connection lost - script notification only */
-						create_event_record(NULL,
-											&config_file_options,
-											config_file_options.node_id,
-											"repmgrd_upstream_disconnect",
-											true,
-											event_details.data);
+						create_event_notification(NULL,
+												  &config_file_options,
+												  config_file_options.node_id,
+												  "repmgrd_upstream_disconnect",
+												  true,
+												  event_details.data);
 					}
 
 					log_warning("%s", event_details.data);
@@ -2482,12 +2482,12 @@ monitor_streaming_witness(void)
 									  _("unable to connect to primary node \"%s\" (ID: %i)"),
 									  upstream_node_info.node_name, upstream_node_info.node_id);
 
-					create_event_record(NULL,
-										&config_file_options,
-										config_file_options.node_id,
-										"repmgrd_upstream_disconnect",
-										true,
-										event_details.data);
+					create_event_notification(NULL,
+											  &config_file_options,
+											  config_file_options.node_id,
+											  "repmgrd_upstream_disconnect",
+											  true,
+											  event_details.data);
 					termPQExpBuffer(&event_details);
 				}
 
@@ -2862,6 +2862,7 @@ do_primary_failover(void)
 	bool final_result = false;
 	NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 	int new_primary_id = UNKNOWN_NODE_ID;
+	bool standby_disconnect_on_failover = false;
 
 	/*
 	 * Double-check status of the local connection
@@ -2874,20 +2875,20 @@ do_primary_failover(void)
 	 */
 	if (config_file_options.standby_disconnect_on_failover == true)
 	{
-		NodeInfoListCell *cell = NULL;
-		NodeInfoList check_sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
-		int i;
+		/*
+		 * Determine whether we can actually disable the walsender; this depends
+		 * on PostgreSQL version and user permissions.
+		 */
+		standby_disconnect_on_failover = can_disable_walsender(local_conn);
 
-		bool sibling_node_wal_receiver_connected = false;
+		if (standby_disconnect_on_failover == true)
+		{
+			NodeInfoListCell *cell = NULL;
+			NodeInfoList check_sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
+			int i;
+
+			bool sibling_node_wal_receiver_connected = false;
 
-		if (PQserverVersion(local_conn) < 90500)
-		{
-			log_warning(_("\"standby_disconnect_on_failover\" specified, but not available for this PostgreSQL version"));
-			/* TODO: format server version */
-			log_detail(_("available from PostgreSQL 9.5, this PostgreSQL version is %i"), PQserverVersion(local_conn));
-		}
-		else
-		{
 			disable_wal_receiver(local_conn);
 
 			/*
@@ -2971,7 +2972,7 @@ do_primary_failover(void)
 	log_debug("election result: %s", _print_election_result(election_result));
 
 	/* Reenable WAL receiver, if disabled */
-	if (config_file_options.standby_disconnect_on_failover == true)
+	if (standby_disconnect_on_failover == true)
 	{
 		/* adjust "wal_retrieve_retry_interval" but don't wait for WAL receiver to start */
 		enable_wal_receiver(local_conn, false);