In pg_upgrade, only lock the old cluster if link mode is used, and do it

right after we restore the schema (a common failure point), and right
before we do the link operation.

Per suggesgtions from Robert and ^!C^!^@Lvaro

Author: bmomjian

contrib/pg_upgrade/check.c

@@ -148,9 +148,8 @@ report_clusters_compatible(void)
 	}
 
 	pg_log(PG_REPORT, "\n"
-		   "If pg_upgrade fails after this point, you must re-initdb the new cluster\n"
-		   "before continuing.  You will also need to remove the \".old\" suffix from\n"
-		   "%s/global/pg_control.old.\n", old_cluster.pgdata);
+		   "If pg_upgrade fails after this point, you must re-initdb the\n"
+		   "new cluster before continuing.\n");
 }
 
 
@@ -198,8 +197,8 @@ output_completion_banner(char *deletion_script_file_name)
 	/* Did we copy the free space files? */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 804)
 		pg_log(PG_REPORT,
-			   "Optimizer statistics are not transferred by pg_upgrade so consider\n"
-			   "running:\n"
+			   "Optimizer statistics are not transferred by pg_upgrade so\n"
+			   "consider running:\n"
 			   "    vacuumdb --all --analyze-only\n"
 			   "on the newly-upgraded cluster.\n\n");
 	else

contrib/pg_upgrade/controldata.c

@@ -516,16 +516,23 @@ check_control_data(ControlData *oldctrl,
 
 
 void
-rename_old_pg_control(void)
+disable_old_cluster(void)
 {
 	char		old_path[MAXPGPATH],
 				new_path[MAXPGPATH];
 
+	/* rename pg_control so old server cannot be accidentally started */
 	prep_status("Adding \".old\" suffix to old global/pg_control");
 
 	snprintf(old_path, sizeof(old_path), "%s/global/pg_control", old_cluster.pgdata);
 	snprintf(new_path, sizeof(new_path), "%s/global/pg_control.old", old_cluster.pgdata);
 	if (pg_mv_file(old_path, new_path) != 0)
 		pg_log(PG_FATAL, "Unable to rename %s to %s.\n", old_path, new_path);
 	check_ok();
+
+	pg_log(PG_REPORT, "\n"
+		   "If you want to start the old cluster, you will need to remove\n"
+		   "the \".old\" suffix from %s/global/pg_control.old.\n"
+		   "Because \"link\" mode was used, the old cluster cannot be safely\n"
+		   "started once the new cluster has been started.\n\n", old_cluster.pgdata);
 }

contrib/pg_upgrade/pg_upgrade.c

@@ -43,7 +43,6 @@
 #include <langinfo.h>
 #endif
 
-static void disable_old_cluster(void);
 static void prepare_new_cluster(void);
 static void prepare_new_databases(void);
 static void create_new_objects(void);
@@ -87,7 +86,6 @@ main(int argc, char **argv)
 	pg_log(PG_REPORT, "\nPerforming Upgrade\n");
 	pg_log(PG_REPORT, "------------------\n");
 
-	disable_old_cluster();
 	prepare_new_cluster();
 
 	stop_postmaster(false);
@@ -109,6 +107,16 @@ main(int argc, char **argv)
 
 	stop_postmaster(false);
 
+	/*
+	 *	Most failures happen in create_new_objects(), which has
+	 *	completed at this point.  We do this here because it is just
+	 *	before linking, which will link the old and new cluster data
+	 *	files, preventing the old cluster from being safely started
+	 *	once the new cluster is started.
+	 */
+	if (user_opts.transfer_mode == TRANSFER_MODE_LINK)
+		disable_old_cluster();
+
 	transfer_all_new_dbs(&old_cluster.dbarr, &new_cluster.dbarr,
 						 old_cluster.pgdata, new_cluster.pgdata);
 
@@ -176,14 +184,6 @@ setup(char *argv0, bool live_check)
 }
 
 
-static void
-disable_old_cluster(void)
-{
-	/* rename pg_control so old server cannot be accidentally started */
-	rename_old_pg_control();
-}
-
-
 static void
 prepare_new_cluster(void)
 {

contrib/pg_upgrade/pg_upgrade.h

@@ -282,8 +282,8 @@ void		create_script_for_old_cluster_deletion(char **deletion_script_file_name);
 /* controldata.c */
 
 void		get_control_data(ClusterInfo *cluster, bool live_check);
-void check_control_data(ControlData *oldctrl,
-				   ControlData *newctrl);
+void		check_control_data(ControlData *oldctrl, ControlData *newctrl);
+void		disable_old_cluster(void);
 
 
 /* dump.c */
@@ -298,7 +298,6 @@ int exec_prog(bool throw_error, const char *cmd, ...)
 	__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
 void		verify_directories(void);
 bool		is_server_running(const char *datadir);
-void		rename_old_pg_control(void);
 
 
 /* file.c */

doc/src/sgml/pgupgrade.sgml

@@ -182,7 +182,7 @@
 
     <para>
      If you are using a version-specific installation directory, e.g.
-     <filename>/opt/PostgreSQL/8.4</>, you do not need to move the old cluster. The
+     <filename>/opt/PostgreSQL/9.1</>, you do not need to move the old cluster. The
      one-click installers all use version-specific installation directories.
     </para>
 
@@ -254,7 +254,8 @@ gmake prefix=/usr/local/pgsql.new install
 
     <para>
      Install any custom shared object files (or DLLs) used by the old cluster
-     into the new cluster, e.g. <filename>pgcrypto.so</filename>, whether they are from <filename>contrib</filename>
+     into the new cluster, e.g. <filename>pgcrypto.so</filename>, 
+     whether they are from <filename>contrib</filename>
      or some other source. Do not install the schema definitions, e.g.
      <filename>pgcrypto.sql</>, because these will be upgraded from the old cluster.
     </para>
@@ -454,18 +455,14 @@ psql --username postgres --file script.sql postgres
 
       <listitem>
        <para>
-        If you
-        ran <command>pg_upgrade</command> <emphasis>without</> <option>--link</>
-        or did not start the new server, the old cluster was not
-        modified except that an <literal>.old</> suffix was appended
-        to <filename>$PGDATA/global/pg_control</> and perhaps
-        tablespace directories. To reuse the old cluster, remove
-        the <filename>.old</> suffix
-        from <filename>$PGDATA/global/pg_control</>. and, if upgrading
-        to 8.4 or earlier, remove the tablespace directories created
-        by the upgrade and remove the <filename>.old</> suffix from
-        the tablespace directory names; then you can restart the old
-        cluster.
+        If you ran <command>pg_upgrade</command> <emphasis>without</>
+        <option>--link</> or did not start the new server, the
+        old cluster was not modified except that, if linking
+        started, a <literal>.old</> suffix was appended to
+        <filename>$PGDATA/global/pg_control</>.  To reuse the old
+        cluster, possibly remove the <filename>.old</> suffix from
+        <filename>$PGDATA/global/pg_control</>; you can then restart the
+        old cluster.
        </para>
       </listitem>
      </itemizedlist>
@@ -582,9 +579,9 @@ psql --username postgres --file script.sql postgres
   </para>
 
   <para>
-   If you want to use link mode and you don't want your old cluster
+   If you want to use link mode and you do not want your old cluster
    to be modified when the new cluster is started, make a copy of the
-   old cluster and upgrade that with link mode. To make a valid copy
+   old cluster and upgrade that in link mode. To make a valid copy
    of the old cluster, use <command>rsync</> to create a dirty
    copy of the old cluster while the server is running, then shut down
    the old server and run <command>rsync</> again to update the copy with any