pg_upgrade: Add --set-char-signedness to set the default char signedness of new cluster.

This change adds a new option --set-char-signedness to pg_upgrade. It
enables user to set arbitrary signedness during pg_upgrade. This helps
cases where user who knew they copied the v17 source cluster from
x86 (signedness=true) to ARM (signedness=false) can pg_upgrade
properly without the prerequisite of acquiring an x86 VM.

Reviewed-by: Noah Misch <noah@leadboat.com>
Discussion: https://postgr.es/m/CB11ADBC-0C3F-4FE0-A678-666EE80CBB07%40amazon.com

5 files changed, 52 insertions, 2 deletions

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 7ca1d8fffc9..d6f629dd3a2 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -838,6 +838,18 @@ check_cluster_versions(void)
 		GET_MAJOR_VERSION(new_cluster.bin_version))
 		pg_fatal("New cluster data and binary directories are from different major versions.");
 
+	/*
+	 * Since from version 18, newly created database clusters always have
+	 * 'signed' default char-signedness, it makes less sense to use
+	 * --set-char-signedness option for upgrading from version 18 or later.
+	 * Users who want to change the default char signedness of the new
+	 * cluster, they can use pg_resetwal manually before the upgrade.
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1800 &&
+		user_opts.char_signedness != -1)
+		pg_fatal("%s option cannot be used to upgrade from PostgreSQL %s and later.",
+				 "--set-char-signedness", "18");
+
 	check_ok();
 }
 
diff --git a/src/bin/pg_upgrade/option.c b/src/bin/pg_upgrade/option.c
index 3fd487086a5..fe716c4c805 100644
--- a/src/bin/pg_upgrade/option.c
+++ b/src/bin/pg_upgrade/option.c
@@ -61,6 +61,7 @@ parseCommandLine(int argc, char *argv[])
 		{"copy-file-range", no_argument, NULL, 3},
 		{"sync-method", required_argument, NULL, 4},
 		{"no-statistics", no_argument, NULL, 5},
+		{"set-char-signedness", required_argument, NULL, 6},
 
 		{NULL, 0, NULL, 0}
 	};
@@ -72,6 +73,7 @@ parseCommandLine(int argc, char *argv[])
 	user_opts.do_sync = true;
 	user_opts.transfer_mode = TRANSFER_MODE_COPY;
 	user_opts.do_statistics = true;
+	user_opts.char_signedness = -1;
 
 	os_info.progname = get_progname(argv[0]);
 
@@ -218,6 +220,14 @@ parseCommandLine(int argc, char *argv[])
 				user_opts.do_statistics = false;
 				break;
 
+			case 6:
+				if (pg_strcasecmp(optarg, "signed") == 0)
+					user_opts.char_signedness = 1;
+				else if (pg_strcasecmp(optarg, "unsigned") == 0)
+					user_opts.char_signedness = 0;
+				else
+					pg_fatal("invalid argument for option %s", "--set-char-signedness");
+				break;
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						os_info.progname);
@@ -313,6 +323,8 @@ usage(void)
 	printf(_("  --copy                        copy files to new cluster (default)\n"));
 	printf(_("  --copy-file-range             copy files to new cluster with copy_file_range\n"));
 	printf(_("  --no-statistics               do not import statistics from old cluster\n"));
+	printf(_("  --set-char-signedness=OPTION  set new cluster char signedness to \"signed\" or\n"));
+	printf(_("                                \"unsigned\"\n"));
 	printf(_("  --sync-method=METHOD          set method for syncing files to disk\n"));
 	printf(_("  -?, --help                    show this help, then exit\n"));
 	printf(_("\n"
diff --git a/src/bin/pg_upgrade/pg_upgrade.c b/src/bin/pg_upgrade/pg_upgrade.c
index cc7357b5599..d95c491fb57 100644
--- a/src/bin/pg_upgrade/pg_upgrade.c
+++ b/src/bin/pg_upgrade/pg_upgrade.c
@@ -399,8 +399,14 @@ set_new_cluster_char_signedness(void)
 {
 	bool		new_char_signedness;
 
-	/* Inherit the source database's signedness */
-	new_char_signedness = old_cluster.controldata.default_char_signedness;
+	/*
+	 * Use the specified char signedness if specified. Otherwise we inherit
+	 * the source database's signedness.
+	 */
+	if (user_opts.char_signedness != -1)
+		new_char_signedness = (user_opts.char_signedness == 1);
+	else
+		new_char_signedness = old_cluster.controldata.default_char_signedness;
 
 	/* Change the char signedness of the new cluster, if necessary */
 	if (new_cluster.controldata.default_char_signedness != new_char_signedness)
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 6937d49b5e7..f4e375d27c7 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -334,6 +334,9 @@ typedef struct
 	char	   *socketdir;		/* directory to use for Unix sockets */
 	char	   *sync_method;
 	bool		do_statistics;	/* carry over statistics from old cluster */
+	int			char_signedness;	/* default char signedness: -1 for initial
+									 * value, 1 for "signed" and 0 for
+									 * "unsigned" */
 } UserOpts;
 
 typedef struct
diff --git a/src/bin/pg_upgrade/t/005_char_signedness.pl b/src/bin/pg_upgrade/t/005_char_signedness.pl
index 05c3014a27d..c024106863e 100644
--- a/src/bin/pg_upgrade/t/005_char_signedness.pl
+++ b/src/bin/pg_upgrade/t/005_char_signedness.pl
@@ -40,6 +40,23 @@ command_like(
 	qr/Default char data signedness:\s+unsigned/,
 	'updated default char signedness is unsigned in control file');
 
+# Cannot use --set-char-signedness option for upgrading from v18+
+command_fails(
+	[
+		'pg_upgrade', '--no-sync',
+		'-d', $old->data_dir,
+		'-D', $new->data_dir,
+		'-b', $old->config_data('--bindir'),
+		'-B', $new->config_data('--bindir'),
+		'-s', $new->host,
+		'-p', $old->port,
+		'-P', $new->port,
+		'-set-char-signedness', 'signed',
+		$mode
+	],
+	'--set-char-signedness option cannot be used for upgrading from v18 or later'
+);
+
 # pg_upgrade should be successful.
 command_ok(
 	[