pg_upgrade: Support for upgrading to checksums enabled

When upgrading between instances with different checksum settings, the
--copy (default) mode automatically sets (or unsets) the checksum on
the fly.

TODO: What to do about the Windows code path?

Author: petere

src/bin/pg_upgrade/controldata.c

@@ -735,18 +735,12 @@ check_control_data(ControlData *oldctrl,
 	 * check_for_isn_and_int8_passing_mismatch().
 	 */
 
-	/*
-	 * We might eventually allow upgrades from checksum to no-checksum
-	 * clusters.
-	 */
-	if (oldctrl->data_checksum_version == 0 &&
-		newctrl->data_checksum_version != 0)
-		pg_fatal("old cluster does not use data checksums but the new one does");
-	else if (oldctrl->data_checksum_version != 0 &&
-			 newctrl->data_checksum_version == 0)
-		pg_fatal("old cluster uses data checksums but the new one does not");
-	else if (oldctrl->data_checksum_version != newctrl->data_checksum_version)
-		pg_fatal("old and new cluster pg_controldata checksum versions do not match");
+	/* FIXME: what about upgrade from checksum to non-checksum? */
+	if (oldctrl->data_checksum_version != newctrl->data_checksum_version)
+	{
+		if (!user_opts.update_checksums)
+			pg_fatal("when upgrading between clusters with different data checksum settings, option %s must be used", "--update-checksums");
+	}
 }
 
 

src/bin/pg_upgrade/file.c

@@ -80,12 +80,14 @@ cloneFile(const char *src, const char *dst,
  */
 void
 copyFile(const char *src, const char *dst,
-		 const char *schemaName, const char *relName)
+		 const char *schemaName, const char *relName,
+		 int segno)
 {
 #ifndef WIN32
 	int			src_fd;
 	int			dest_fd;
 	char	   *buffer;
+	BlockNumber blocknum;
 
 	if ((src_fd = open(src, O_RDONLY | PG_BINARY, 0)) < 0)
 		pg_fatal("error while copying relation \"%s.%s\": could not open file \"%s\": %m",
@@ -101,6 +103,8 @@ copyFile(const char *src, const char *dst,
 
 	buffer = (char *) pg_malloc(COPY_BUF_SIZE);
 
+	blocknum = segno * old_cluster.controldata.largesz;
+
 	/* perform data copying i.e read src source, write to destination */
 	while (true)
 	{
@@ -113,6 +117,31 @@ copyFile(const char *src, const char *dst,
 		if (nbytes == 0)
 			break;
 
+		/*
+		 * Update checksums if requested
+		 */
+		if (user_opts.update_checksums)
+		{
+			/* must deal in whole blocks */
+			nbytes = nbytes / BLCKSZ * BLCKSZ;
+
+			for (int i = 0; i * BLCKSZ < nbytes; i++)
+			{
+				PageData   *page = buffer + i * BLCKSZ;
+				PageHeader	header = (PageHeader) page;
+
+				if (PageIsNew(page))
+					continue;
+
+				if (new_cluster.controldata.data_checksum_version == 1)
+					header->pd_checksum = pg_checksum_page(page, blocknum);
+				else
+					header->pd_checksum = 0;
+
+				blocknum++;
+			}
+		}
+
 		errno = 0;
 		if (write(dest_fd, buffer, nbytes) != nbytes)
 		{

src/bin/pg_upgrade/option.c

@@ -62,6 +62,7 @@ parseCommandLine(int argc, char *argv[])
 		{"sync-method", required_argument, NULL, 4},
 		{"no-statistics", no_argument, NULL, 5},
 		{"set-char-signedness", required_argument, NULL, 6},
+		{"update-checksums", no_argument, NULL, 7},
 
 		{NULL, 0, NULL, 0}
 	};
@@ -228,6 +229,11 @@ parseCommandLine(int argc, char *argv[])
 				else
 					pg_fatal("invalid argument for option %s", "--set-char-signedness");
 				break;
+
+			case 7:
+				user_opts.update_checksums = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						os_info.progname);
@@ -241,6 +247,9 @@ parseCommandLine(int argc, char *argv[])
 	if (!user_opts.sync_method)
 		user_opts.sync_method = pg_strdup("fsync");
 
+	if (user_opts.update_checksums && user_opts.transfer_mode != TRANSFER_MODE_COPY)
+		pg_fatal("option %s requires transfer mode %s", "--update-checksums", "--copy");
+
 	if (log_opts.verbose)
 		pg_log(PG_REPORT, "Running in verbose mode");
 

src/bin/pg_upgrade/pg_upgrade.h

@@ -337,6 +337,7 @@ typedef struct
 	int			char_signedness;	/* default char signedness: -1 for initial
 									 * value, 1 for "signed" and 0 for
 									 * "unsigned" */
+	bool		update_checksums;
 } UserOpts;
 
 typedef struct
@@ -414,7 +415,8 @@ bool		pid_lock_file_exists(const char *datadir);
 void		cloneFile(const char *src, const char *dst,
 					  const char *schemaName, const char *relName);
 void		copyFile(const char *src, const char *dst,
-					 const char *schemaName, const char *relName);
+					 const char *schemaName, const char *relName,
+					 int segno);
 void		copyFileByRange(const char *src, const char *dst,
 							const char *schemaName, const char *relName);
 void		linkFile(const char *src, const char *dst,

src/bin/pg_upgrade/relfilenumber.c

@@ -248,7 +248,7 @@ transfer_relfile(FileNameMap *map, const char *type_suffix, bool vm_must_add_fro
 				case TRANSFER_MODE_COPY:
 					pg_log(PG_VERBOSE, "copying \"%s\" to \"%s\"",
 						   old_file, new_file);
-					copyFile(old_file, new_file, map->nspname, map->relname);
+					copyFile(old_file, new_file, map->nspname, map->relname, segno);
 					break;
 				case TRANSFER_MODE_COPY_FILE_RANGE:
 					pg_log(PG_VERBOSE, "copying \"%s\" to \"%s\" with copy_file_range",