Fix pg_upgrade, broken by the xlogid/segno -> 64-bit int refactoring.

The xlogid + segno representation of a particular WAL segment doesn't make
much sense in pg_resetxlog anymore, now that we don't use that anywhere
else. Use the WAL filename instead, since that's a convenient way to name a
particular WAL segment.

I did this partially for pg_resetxlog in the original xlogid/segno -> uint64
patch, but I neglected pg_upgrade and the docs. This should now be more
complete.

Author: hlinnaka

contrib/pg_upgrade/controldata.c

@@ -39,6 +39,7 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 	char	   *p;
 	bool		got_xid = false;
 	bool		got_oid = false;
+	bool		got_nextxlogfile = false;
 	bool		got_log_id = false;
 	bool		got_log_seg = false;
 	bool		got_tli = false;
@@ -61,6 +62,10 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 	char	   *language = NULL;
 	char	   *lc_all = NULL;
 	char	   *lc_messages = NULL;
+	uint32		logid = 0;
+	uint32		segno = 0;
+	uint32		tli = 0;
+
 
 	/*
 	 * Because we test the pg_resetxlog output as strings, it has to be in
@@ -166,6 +171,23 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 			p++;				/* removing ':' char */
 			cluster->controldata.cat_ver = str2uint(p);
 		}
+		else if ((p = strstr(bufin, "First log segment after reset:")) != NULL)
+		{
+			/* Skip the colon and any whitespace after it */
+			p = strchr(p, ':');
+			if (p == NULL || strlen(p) <= 1)
+				pg_log(PG_FATAL, "%d: controldata retrieval problem\n", __LINE__);
+			p = strpbrk(p, "01234567890ABCDEF");
+			if (p == NULL || strlen(p) <= 1)
+				pg_log(PG_FATAL, "%d: controldata retrieval problem\n", __LINE__);
+
+			/* Make sure it looks like a valid WAL file name */
+			if (strspn(p, "0123456789ABCDEF") != 24)
+				pg_log(PG_FATAL, "%d: controldata retrieval problem\n", __LINE__);
+
+			strlcpy(cluster->controldata.nextxlogfile, p, 25);
+			got_nextxlogfile = true;
+		}
 		else if ((p = strstr(bufin, "First log file ID after reset:")) != NULL)
 		{
 			p = strchr(p, ':');
@@ -174,7 +196,7 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 				pg_log(PG_FATAL, "%d: controldata retrieval problem\n", __LINE__);
 
 			p++;				/* removing ':' char */
-			cluster->controldata.logid = str2uint(p);
+			logid = str2uint(p);
 			got_log_id = true;
 		}
 		else if ((p = strstr(bufin, "First log file segment after reset:")) != NULL)
@@ -185,7 +207,7 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 				pg_log(PG_FATAL, "%d: controldata retrieval problem\n", __LINE__);
 
 			p++;				/* removing ':' char */
-			cluster->controldata.nxtlogseg = str2uint(p);
+			segno = str2uint(p);
 			got_log_seg = true;
 		}
 		else if ((p = strstr(bufin, "Latest checkpoint's TimeLineID:")) != NULL)
@@ -393,10 +415,25 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 	pg_free(lc_all);
 	pg_free(lc_messages);
 
+	/*
+	 * Before 9.3, pg_resetxlog reported the xlogid and segno of the first
+	 * log file after reset as separate lines. Starting with 9.3, it reports
+	 * the WAL file name. If the old cluster is older than 9.3, we construct
+	 * the WAL file name from the xlogid and segno.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 902)
+	{
+		if (got_log_id && got_log_seg)
+		{
+			snprintf(cluster->controldata.nextxlogfile, 24, "%08X%08X%08X",
+					 tli, logid, segno);
+			got_nextxlogfile = true;
+		}
+	}
+
 	/* verify that we got all the mandatory pg_control data */
 	if (!got_xid || !got_oid ||
-		(!live_check && !got_log_id) ||
-		(!live_check && !got_log_seg) ||
+		(!live_check && !got_nextxlogfile) ||
 		!got_tli ||
 		!got_align || !got_blocksz || !got_largesz || !got_walsz ||
 		!got_walseg || !got_ident || !got_index || !got_toast ||
@@ -411,11 +448,8 @@ get_control_data(ClusterInfo *cluster, bool live_check)
 		if (!got_oid)
 			pg_log(PG_REPORT, "  latest checkpoint next OID\n");
 
-		if (!live_check && !got_log_id)
-			pg_log(PG_REPORT, "  first log file ID after reset\n");
-
-		if (!live_check && !got_log_seg)
-			pg_log(PG_REPORT, "  first log file segment after reset\n");
+		if (!live_check && !got_nextxlogfile)
+			pg_log(PG_REPORT, "  first WAL segment after reset\n");
 
 		if (!got_tli)
 			pg_log(PG_REPORT, "  latest checkpoint timeline ID\n");

contrib/pg_upgrade/pg_upgrade.c

@@ -354,11 +354,9 @@ copy_clog_xlog_xid(void)
 	prep_status("Resetting WAL archives");
 	exec_prog(true, true, UTILITY_LOG_FILE,
 			  SYSTEMQUOTE
-			  "\"%s/pg_resetxlog\" -l %u,%u,%u \"%s\" >> \"%s\" 2>&1"
+			  "\"%s/pg_resetxlog\" -l %s \"%s\" >> \"%s\" 2>&1"
 			  SYSTEMQUOTE, new_cluster.bindir,
-			  old_cluster.controldata.chkpnt_tli,
-			  old_cluster.controldata.logid,
-			  old_cluster.controldata.nxtlogseg,
+			  old_cluster.controldata.nextxlogfile,
 			  new_cluster.pgdata, UTILITY_LOG_FILE);
 	check_ok();
 }

contrib/pg_upgrade/pg_upgrade.h

@@ -168,8 +168,7 @@ typedef struct
 {
 	uint32		ctrl_ver;
 	uint32		cat_ver;
-	uint32		logid;
-	uint32		nxtlogseg;
+	char		nextxlogfile[25];
 	uint32		chkpnt_tli;
 	uint32		chkpnt_nxtxid;
 	uint32		chkpnt_nxtoid;

doc/src/sgml/ref/pg_resetxlog.sgml

@@ -131,13 +131,8 @@ PostgreSQL documentation
       the directory <filename>pg_xlog</> under the data directory.
       These names are also in hexadecimal and have three parts.  The first
       part is the <quote>timeline ID</> and should usually be kept the same.
-      Do not choose a value larger than 255 (<literal>0xFF</>) for the third
-      part; instead increment the second part and reset the third part to 0.
       For example, if <filename>00000001000000320000004A</> is the
-      largest entry in <filename>pg_xlog</>, <literal>-l 0x1,0x32,0x4B</> will
-      work; but if the largest entry is
-      <filename>000000010000003A000000FF</>, choose <literal>-l 0x1,0x3B,0x0</>
-      or more.
+      largest entry in <filename>pg_xlog</>, use <literal>-l 00000001000000320000004B</> or higher.
      </para>
 
      <note>

src/bin/pg_resetxlog/pg_resetxlog.c

@@ -86,13 +86,9 @@ main(int argc, char *argv[])
 	Oid			set_oid = 0;
 	MultiXactId set_mxid = 0;
 	MultiXactOffset set_mxoff = (MultiXactOffset) -1;
-	uint32		minXlogTli = 0,
-				minXlogId = 0,
-				minXlogSeg = 0;
+	uint32		minXlogTli = 0;
 	XLogSegNo	minXlogSegNo = 0;
 	char	   *endptr;
-	char	   *endptr2;
-	char	   *endptr3;
 	char	   *DataDir;
 	int			fd;
 	char		path[MAXPGPATH];
@@ -204,28 +200,13 @@ main(int argc, char *argv[])
 				break;
 
 			case 'l':
-				minXlogTli = strtoul(optarg, &endptr, 0);
-				if (endptr == optarg || *endptr != ',')
+				if (strspn(optarg, "01234567890ABCDEFabcdef") != 24)
 				{
 					fprintf(stderr, _("%s: invalid argument for option -l\n"), progname);
 					fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
 					exit(1);
 				}
-				minXlogId = strtoul(endptr + 1, &endptr2, 0);
-				if (endptr2 == endptr + 1 || *endptr2 != ',')
-				{
-					fprintf(stderr, _("%s: invalid argument for option -l\n"), progname);
-					fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
-					exit(1);
-				}
-				minXlogSeg = strtoul(endptr2 + 1, &endptr3, 0);
-				if (endptr3 == endptr2 + 1 || *endptr3 != '\0')
-				{
-					fprintf(stderr, _("%s: invalid argument for option -l\n"), progname);
-					fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
-					exit(1);
-				}
-				minXlogSegNo = (uint64) minXlogId * XLogSegmentsPerXLogId + minXlogSeg;
+				XLogFromFileName(optarg, &minXlogTli, &minXlogSegNo);
 				break;
 
 			default:
@@ -1013,7 +994,7 @@ usage(void)
 	printf(_("Options:\n"));
 	printf(_("  -e XIDEPOCH      set next transaction ID epoch\n"));
 	printf(_("  -f               force update to be done\n"));
-	printf(_("  -l TLI,FILE,SEG  force minimum WAL starting location for new transaction log\n"));
+	printf(_("  -l xlogfile      force minimum WAL starting location for new transaction log\n"));
 	printf(_("  -m XID           set next multitransaction ID\n"));
 	printf(_("  -n               no update, just show extracted control values (for testing)\n"));
 	printf(_("  -o OID           set next OID\n"));