Fix assembling of raid10 in the face of missing devices.

We now check if enough devices are present properly, so
--force can be used to good effect.

Signed-off-by: Neil Brown <neilb@suse.de>

Assemble.c

@@ -118,6 +118,7 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 	mddev_dev_t tmpdev;
 	struct mdinfo info;
 	struct mddev_ident_s ident2;
+	char *avail;
 	
 	vers = md_get_version(mdfd);
 	if (vers <= 0) {
@@ -359,6 +360,8 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 	/* now we have some devices that might be suitable.
 	 * I wonder how many
 	 */
+	avail = malloc(info.array.raid_disks);
+	memset(avail, 0, info.array.raid_disks);
 	okcnt = 0;
 	sparecnt=0;
 	for (i=0; i< bestcnt ;i++) {
@@ -377,13 +380,16 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 		if (devices[j].events+event_margin >=
 		    devices[most_recent].events) {
 			devices[j].uptodate = 1;
-			if (i < info.array.raid_disks)
+			if (i < info.array.raid_disks) {
 				okcnt++;
-			else
+				avail[i]=1;
+			} else
 				sparecnt++;
 		}
 	}
-	while (force && !enough(info.array.level, info.array.raid_disks, okcnt)) {
+	while (force && !enough(info.array.level, info.array.raid_disks,
+				info.array.layout,
+				avail, okcnt)) {
 		/* Choose the newest best drive which is
 		 * not up-to-date, update the superblock
 		 * and add it.
@@ -434,6 +440,7 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 		close(fd);
 		devices[chosen_drive].events = devices[most_recent].events;
 		devices[chosen_drive].uptodate = 1;
+		avail[chosen_drive] = 1;
 		okcnt++;
 		free(super);
 	}
@@ -599,7 +606,7 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 		
 		if (runstop == 1 ||
 		    (runstop == 0 && 
-		     ( enough(info.array.level, info.array.raid_disks, okcnt) &&
+		     ( enough(info.array.level, info.array.raid_disks, info.array.layout, avail, okcnt) &&
 		       (okcnt >= req_cnt || start_partial_ok)
 			     ))) {
 			if (ioctl(mdfd, RUN_ARRAY, NULL)==0) {
@@ -627,7 +634,7 @@ int Assemble(struct supertype *st, char *mddev, int mdfd,
 			fprintf(stderr, Name ": %s assembled from %d drive%s", mddev, okcnt, okcnt==1?"":"s");
 			if (sparecnt)
 				fprintf(stderr, " and %d spare%s", sparecnt, sparecnt==1?"":"s");
-			if (!enough(info.array.level, info.array.raid_disks, okcnt))
+			if (!enough(info.array.level, info.array.raid_disks, info.array.layout, avail, okcnt))
 				fprintf(stderr, " - not enough to start the array.\n");
 			else {
 				if (req_cnt == info.array.raid_disks)

ChangeLog

@@ -1,4 +1,11 @@
 Changes Prior to this release
+    -   Fix assembling of raid10 array when devices are missing.
+	  mdadm now correctly detects if a array is workable or not
+	  depending on which devices are present, and so will correctly
+	  handle "--assemble --force"  if multiple devices have failed.
+    -   Report raid10 layout in --examine output.
+
+Changes Prior to 2.0
     -   Support assembling from byte-swapped superblocks
 	metadata type "0.swap" and --update=byteorder
     -   write-mostly and write-behind support for raid1.

mdadm.h

@@ -291,7 +291,8 @@ extern void uuid_from_super(int uuid[4], mdp_super_t *super);
 extern int same_uuid(int a[4], int b[4], int swapuuid);
 /* extern int compare_super(mdp_super_t *first, mdp_super_t *second);*/
 extern unsigned long calc_csum(void *super, int bytes);
-extern int enough(int level, int raid_disks, int avail_disks);
+extern int enough(int level, int raid_disks, int layout,
+		   char *avail, int avail_disks);
 extern int ask(char *mesg);
 
 

super0.c

@@ -131,6 +131,10 @@ static void examine_super0(void *sbv)
 		c = map_num(r5layout, sb->layout);
 		printf("         Layout : %s\n", c?c:"-unknown-");
 	}
+	if (sb->level == 10) {
+		printf("         Layout : near=%d, far=%d\n",
+		       sb->layout&255, (sb->layout>>8)&255);
+	}
 	switch(sb->level) {
 	case 0:
 	case 4:
@@ -234,6 +238,7 @@ static void getinfo_super0(struct mdinfo *info, mddev_ident_t ident, void *sbv)
 	info->array.patch_version = sb->patch_version;
 	info->array.raid_disks = sb->raid_disks;
 	info->array.level = sb->level;
+	info->array.layout = sb->layout;
 	info->array.md_minor = sb->md_minor;
 	info->array.ctime = sb->ctime;
 

super1.c

@@ -180,6 +180,11 @@ static void examine_super1(void *sbv)
 		c = map_num(r5layout, __le32_to_cpu(sb->layout));
 		printf("         Layout : %s\n", c?c:"-unknown-");
 	}
+	if (__le32_to_cpu(sb->level) == 10) {
+		int lo = __le32_to_cpu(sb->layout);
+		printf("         Layout : near=%d, far=%d\n",
+		       lo&255, (lo>>8)&255);
+	}
 	switch(__le32_to_cpu(sb->level)) {
 	case 0:
 	case 4:
@@ -290,6 +295,7 @@ static void getinfo_super1(struct mdinfo *info, mddev_ident_t ident, void *sbv)
 	info->array.patch_version = 0;
 	info->array.raid_disks = __le32_to_cpu(sb->raid_disks);
 	info->array.level = __le32_to_cpu(sb->level);
+	info->array.layout = __le32_to_cpu(sb->layout);
 	info->array.md_minor = -1;
 	info->array.ctime = __le64_to_cpu(sb->ctime);
 

util.c

@@ -118,10 +118,31 @@ int get_linux_version()
 	return (a*1000000)+(b*1000)+c;
 }
 
-int enough(int level, int raid_disks, int avail_disks)
+int enough(int level, int raid_disks, int layout,
+	   char *avail, int avail_disks)
 {
+	int copies, first;
 	switch (level) {
-	case 10: return 1; /* a lie, but it is hard to tell */
+	case 10:
+		/* This is the tricky one - we need to check
+		 * which actual disks are present.
+		 */
+		copies = (layout&255)* (layout>>8);
+		first=0;
+		do {
+			/* there must be one of the 'copies' form 'first' */
+			int n = copies;
+			int cnt=0;
+			while (n--) {
+				if (avail[first])
+					cnt++;
+				first = (first+1) % raid_disks;
+			}
+			if (cnt == 0)
+				return 0;
+
+		} while (first != 0);
+		return 1;
 
 	case -4:
 		return avail_disks>= 1;