repmgr node rejoin: add --dry-run option

doc/repmgr-node-rejoin.sgml

@@ -43,17 +43,72 @@
     <filename>repmgr.conf</filename> for the stopped node *must* be supplied explicitly if not
     otherwise available.
   </para>
-  <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.
-  </para>
-  <note>
-    <para>
-      <command>pg_rewind</command> *requires* 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.
 
+  <sect1 id="repmgr-node-rejoin-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
+      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.
     </para>
-  </note>
+    <note>
+      <para>
+        <command>pg_rewind</command> *requires* 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>
+    </note>
+
+    <para>
+      To have <command>repmgr node rejoin</command> use <command>pg_rewind</command> if required,
+      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>
+
+    <para>
+      Be aware that if <command>pg_rewind</command> is executed and actually performs a
+      rewind operation, any configuration files in the PostgreSQL data directory will be
+      overwritten with those from the source server.
+    </para>
+    <para>
+      To prevent this happening, provide a comma-separated list of files to retain
+      using the <literal>--config-file</literal> command line option; the specified files
+      will be archived in a temporary directory (whose parent directory can be specified with
+      <literal>--config-archive-dir</literal>) and restored once the rewind operation is
+      complete.
+    </para>
+
+    <para>
+      Example, first using <literal>--dry-run</literal>, then actually executing the
+      <literal>node rejoin command</literal>.
+    <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 --dry-run
+    NOTICE: using provided configuration file "/etc/repmgr.conf"
+    INFO: prerequisites for using pg_rewind are met
+    INFO: file "postgresql.local.conf" would be copied to "/tmp/repmgr-config-archive-node1/postgresql.local.conf"
+    INFO: file "postgresql.conf" would be copied to "/tmp/repmgr-config-archive-node1/postgresql.local.conf"
+    INFO: 2 files would have been copied to "/tmp/repmgr-config-archive-node1"
+    INFO: directory "/tmp/repmgr-config-archive-node1" deleted
+    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>
+    <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
+    NOTICE: using provided configuration file "/etc/repmgr.conf"
+    INFO: prerequisites for using pg_rewind are met
+    INFO: 2 files copied to "/tmp/repmgr-config-archive-node1"
+    NOTICE: executing pg_rewind
+    NOTICE: 2 files copied to /space/sda1/ibarwick/repmgr-test/node_1/data
+    INFO: directory "/tmp/repmgr-config-archive-node1" deleted
+    INFO: deleting "recovery.done"
+    INFO: setting node 1's primary to node 2
+    NOTICE: starting server using "pg_ctl-l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' start"
+    waiting for server to start.... done
+    server started
+    NOTICE: NODE REJOIN successful
+    DETAIL: node 1 is now attached to node 2</programlisting>
+    </para>
+  </sect1>
 </chapter>

repmgr-action-node.c

@@ -1821,7 +1821,7 @@ do_node_rejoin(void)
 
 
 /*
- * Intended mainly for "internal" use by `node rejoin` on the local node when
+ * For "internal" use by `node rejoin` on the local node when
  * called by "standby switchover" from the remote node.
  *
  * This archives any configuration files in the data directory, which may be
@@ -1865,8 +1865,6 @@ _do_node_archive_config(void)
 			termPQExpBuffer(&archive_dir);
 			exit(ERR_BAD_CONFIG);
 		}
-
-
 	}
 	else if (!S_ISDIR(statbuf.st_mode))
 	{
@@ -1876,7 +1874,6 @@ _do_node_archive_config(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-
 	arcdir = opendir(archive_dir.data);
 
 	if (arcdir == NULL)
@@ -1888,42 +1885,46 @@ _do_node_archive_config(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/*
+	if (runtime_options.dry_run == false)
-	 * attempt to remove any existing files in the directory TODO: collate
-	 * problem files into list
-	 */
-	while ((arcdir_ent = readdir(arcdir)) != NULL)
 	{
-		PQExpBufferData arcdir_ent_path;
 
-		initPQExpBuffer(&arcdir_ent_path);
+		/*
-
+		 * attempt to remove any existing files in the directory TODO: collate
-		appendPQExpBuffer(&arcdir_ent_path,
+		 * problem files into list
-						  "%s/%s",
+		 */
-						  archive_dir.data,
+		while ((arcdir_ent = readdir(arcdir)) != NULL)
-						  arcdir_ent->d_name);
-
-		if (stat(arcdir_ent_path.data, &statbuf) == 0 && !S_ISREG(statbuf.st_mode))
 		{
+			PQExpBufferData arcdir_ent_path;
+
+			initPQExpBuffer(&arcdir_ent_path);
+
+			appendPQExpBuffer(&arcdir_ent_path,
+							  "%s/%s",
+							  archive_dir.data,
+							  arcdir_ent->d_name);
+
+			if (stat(arcdir_ent_path.data, &statbuf) == 0 && !S_ISREG(statbuf.st_mode))
+			{
+				termPQExpBuffer(&arcdir_ent_path);
+				continue;
+			}
+
+			if (unlink(arcdir_ent_path.data) == -1)
+			{
+				log_error(_("unable to delete file in temporary archive directory"));
+				log_detail(_("file is:  \"%s\""), arcdir_ent_path.data);
+				log_detail("%s", strerror(errno));
+				closedir(arcdir);
+				termPQExpBuffer(&arcdir_ent_path);
+				exit(ERR_BAD_CONFIG);
+			}
+
 			termPQExpBuffer(&arcdir_ent_path);
-			continue;
 		}
 
-		if (unlink(arcdir_ent_path.data) == -1)
+		closedir(arcdir);
-		{
-			log_error(_("unable to delete file in temporary archive directory"));
-			log_detail(_("file is:  \"%s\""), arcdir_ent_path.data);
-			log_detail("%s", strerror(errno));
-			closedir(arcdir);
-			termPQExpBuffer(&arcdir_ent_path);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		termPQExpBuffer(&arcdir_ent_path);
 	}
 
-	closedir(arcdir);
-
 	/*
 	 * extract list of config files from --config-files
 	 */
@@ -1999,18 +2000,53 @@ _do_node_archive_config(void)
 		}
 		else
 		{
-			log_verbose(LOG_DEBUG, "copying \"%s\" to \"%s\"",
+			if (runtime_options.dry_run == true)
-						cell->key, dest_file.data);
+			{
-			copy_file(cell->value, dest_file.data);
+				log_info("file \"%s\" would be copied to \"%s\"",
-			copied_count++;
+						 cell->key, dest_file.data);
+				copied_count++;
+			}
+			else
+			{
+				log_verbose(LOG_DEBUG, "copying \"%s\" to \"%s\"",
+							cell->key, dest_file.data);
+				copy_file(cell->value, dest_file.data);
+				copied_count++;
+			}
 		}
 
 		termPQExpBuffer(&dest_file);
 	}
 
+	if (runtime_options.dry_run == true)
+	{
+		log_verbose(LOG_INFO, _("%i files would have been copied to \"%s\""),
+					copied_count, archive_dir.data);
+	}
+	else
+	{
+		log_verbose(LOG_INFO, _("%i files copied to \"%s\""),
+					copied_count, archive_dir.data);
+	}
 
-	log_verbose(LOG_INFO, _("%i files copied to \"%s\""),
+	if (runtime_options.dry_run == true)
-				copied_count, archive_dir.data);
+	{
+		/*
+		 * Delete directory in --dry-run mode  - it should be empty unless it's been
+		 * interfered with for some reason, in which case manual intervention is
+		 * required
+		 */
+		if (rmdir(archive_dir.data) != 0 && errno != EEXIST)
+		{
+			log_warning(_("unable to delete directory \"%s\""), archive_dir.data);
+			log_detail("%s", strerror(errno));
+			log_hint(_("directory may need to be manually removed"));
+		}
+		else
+		{
+			log_verbose(LOG_INFO, "directory \"%s\" deleted", archive_dir.data);
+		}
+	}
 
 	termPQExpBuffer(&archive_dir);
 }