Re: Raid5 Failure

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Neil -

You are the man; the array went w/o force - and is rebuilding now!

-(root@abyss)-(/)- # mdadm --detail /dev/md0
/dev/md0:
       Version : 01.00.01
 Creation Time : Wed Dec 31 19:00:00 1969
    Raid Level : raid5
    Array Size : 1935556992 (1845.89 GiB 1982.01 GB)
   Device Size : 71687296 (68.37 GiB 73.41 GB)
  Raid Devices : 28
 Total Devices : 28
Preferred Minor : 0
   Persistence : Superblock is persistent

   Update Time : Thu Jul 14 22:07:18 2005
         State : active, resyncing
Active Devices : 28
Working Devices : 28
Failed Devices : 0
 Spare Devices : 0

        Layout : left-asymmetric
    Chunk Size : 128K

Rebuild Status : 0% complete

          UUID : 4e2b6b0a8e:92e91c0c:018a4bf0:9bb74d
        Events : 172760

   Number   Major   Minor   RaidDevice State
      0       8        0        0      active sync   /dev/evms/.nodes/sda
      1       8       16        1      active sync   /dev/evms/.nodes/sdb
      2       8       32        2      active sync   /dev/evms/.nodes/sdc
      3       8       48        3      active sync   /dev/evms/.nodes/sdd
      4       8       64        4      active sync   /dev/evms/.nodes/sde
      5       8       80        5      active sync   /dev/evms/.nodes/sdf
      6       8       96        6      active sync   /dev/evms/.nodes/sdg
      7       8      112        7      active sync   /dev/evms/.nodes/sdh
      8       8      128        8      active sync   /dev/evms/.nodes/sdi
      9       8      144        9      active sync   /dev/evms/.nodes/sdj
     10       8      160       10      active sync   /dev/evms/.nodes/sdk
     11       8      176       11      active sync   /dev/evms/.nodes/sdl
     12       8      192       12      active sync   /dev/evms/.nodes/sdm
     13       8      208       13      active sync   /dev/evms/.nodes/sdn
     14       8      224       14      active sync   /dev/evms/.nodes/sdo
     15       8      240       15      active sync   /dev/evms/.nodes/sdp
     16      65        0       16      active sync   /dev/evms/.nodes/sdq
     17      65       16       17      active sync   /dev/evms/.nodes/sdr
     18      65       32       18      active sync   /dev/evms/.nodes/sds
     19      65       48       19      active sync   /dev/evms/.nodes/sdt
     20      65       64       20      active sync   /dev/evms/.nodes/sdu
     21      65       80       21      active sync   /dev/evms/.nodes/sdv
     22      65       96       22      active sync   /dev/evms/.nodes/sdw
     23      65      112       23      active sync   /dev/evms/.nodes/sdx
     24      65      128       24      active sync   /dev/evms/.nodes/sdy
     25      65      144       25      active sync   /dev/evms/.nodes/sdz
     26      65      160       26      active sync   /dev/evms/.nodes/sdaa
     27      65      176       27      active sync   /dev/evms/.nodes/sdab


-- David M. Strang

----- Original Message ----- From: Neil Brown
To: David M. Strang
Cc: linux-raid@xxxxxxxxxxxxxxx
Sent: Thursday, July 14, 2005 9:43 PM
Subject: Re: Raid5 Failure


On Thursday July 14, dstrang@xxxxxxxxxxxxxx wrote:

It looks like the first 'segment of discs' sda->sdm are all marked clean;
while sdn->sdab are marked active.

What can I do to resolve this issue? Any assistance would be greatly
appreciated.


Apply the following patch to mdadm-2.0-devel2 (it fixes a few bugs and
particularly make --assemble work) then try:

mdadm -A /dev/md0 /dev/sd[a-z] /dev/sd....

Just list all 28 SCSI devices, I'm not sure what their names are.

This will quite probably fail.
If it does, try again with
  --force

NeilBrown



Signed-off-by: Neil Brown <neilb@xxxxxxxxxxxxxxx>

### Diffstat output
./Assemble.c |   13 ++++++++++++-
./Query.c    |   33 +++++++++++++++++++--------------
./mdadm.h    |    2 +-
./super0.c   |    1 +
./super1.c   |    4 ++--
5 files changed, 35 insertions(+), 18 deletions(-)

diff ./Assemble.c~current~ ./Assemble.c
--- ./Assemble.c~current~ 2005-07-15 10:13:04.000000000 +1000
+++ ./Assemble.c 2005-07-15 10:37:59.000000000 +1000
@@ -473,6 +473,7 @@ int Assemble(struct supertype *st, char
 if (!devices[j].uptodate)
 continue;
 info.disk.number = i;
+ info.disk.raid_disk = i;
 info.disk.state = desired_state;

 if (devices[j].uptodate &&
@@ -526,7 +527,17 @@ int Assemble(struct supertype *st, char

 /* Almost ready to actually *do* something */
 if (!old_linux) {
- if (ioctl(mdfd, SET_ARRAY_INFO, NULL) != 0) {
+ int rv;
+ if ((vers % 100) >= 1) { /* can use different versions */
+ mdu_array_info_t inf;
+ memset(&inf, 0, sizeof(inf));
+ inf.major_version = st->ss->major;
+ inf.minor_version = st->minor_version;
+ rv = ioctl(mdfd, SET_ARRAY_INFO, &inf);
+ } else
+ rv = ioctl(mdfd, SET_ARRAY_INFO, NULL);
+
+ if (rv) {
 fprintf(stderr, Name ": SET_ARRAY_INFO failed for %s: %s\n",
 mddev, strerror(errno));
 return 1;

diff ./Query.c~current~ ./Query.c
--- ./Query.c~current~ 2005-07-07 09:19:53.000000000 +1000
+++ ./Query.c 2005-07-15 11:38:18.000000000 +1000
@@ -105,26 +105,31 @@ int Query(char *dev)
 if (superror == 0) {
 /* array might be active... */
 st->ss->getinfo_super(&info, super);
- mddev = get_md_name(info.array.md_minor);
- disc.number = info.disk.number;
- activity = "undetected";
- if (mddev && (fd = open(mddev, O_RDONLY))>=0) {
- if (md_get_version(fd) >= 9000 &&
-     ioctl(fd, GET_ARRAY_INFO, &array)>= 0) {
- if (ioctl(fd, GET_DISK_INFO, &disc) >= 0 &&
-     makedev((unsigned)disc.major,(unsigned)disc.minor) == stb.st_rdev)
- activity = "active";
- else
- activity = "mismatch";
+ if (st->ss->major == 0) {
+ mddev = get_md_name(info.array.md_minor);
+ disc.number = info.disk.number;
+ activity = "undetected";
+ if (mddev && (fd = open(mddev, O_RDONLY))>=0) {
+ if (md_get_version(fd) >= 9000 &&
+     ioctl(fd, GET_ARRAY_INFO, &array)>= 0) {
+ if (ioctl(fd, GET_DISK_INFO, &disc) >= 0 &&
+     makedev((unsigned)disc.major,(unsigned)disc.minor) == stb.st_rdev)
+ activity = "active";
+ else
+ activity = "mismatch";
+ }
+ close(fd);
 }
- close(fd);
+ } else {
+ activity = "unknown";
+ mddev = "array";
 }
- printf("%s: device %d in %d device %s %s md%d. Use mdadm --examine for more detail.\n", + printf("%s: device %d in %d device %s %s %s. Use mdadm --examine for more detail.\n",
        dev,
        info.disk.number, info.array.raid_disks,
        activity,
        map_num(pers, info.array.level),
-        info.array.md_minor);
+        mddev);
 }
 return 0;
}

diff ./mdadm.h~current~ ./mdadm.h
--- ./mdadm.h~current~ 2005-07-07 09:19:53.000000000 +1000
+++ ./mdadm.h 2005-07-15 10:15:51.000000000 +1000
@@ -73,7 +73,7 @@ struct mdinfo {
 mdu_array_info_t array;
 mdu_disk_info_t disk;
 __u64 events;
- unsigned int uuid[4];
+ int uuid[4];
};

#define Name "mdadm"

diff ./super0.c~current~ ./super0.c
--- ./super0.c~current~ 2005-07-07 09:19:53.000000000 +1000
+++ ./super0.c 2005-07-15 11:27:12.000000000 +1000
@@ -205,6 +205,7 @@ static void getinfo_super0(struct mdinfo
 info->disk.major = sb->this_disk.major;
 info->disk.minor = sb->this_disk.minor;
 info->disk.raid_disk = sb->this_disk.raid_disk;
+ info->disk.number = sb->this_disk.number;

 info->events = md_event(sb);


diff ./super1.c~current~ ./super1.c
--- ./super1.c~current~ 2005-07-07 09:19:53.000000000 +1000
+++ ./super1.c 2005-07-15 11:25:04.000000000 +1000
@@ -278,7 +278,7 @@ static void getinfo_super1(struct mdinfo

 info->disk.major = 0;
 info->disk.minor = 0;
-
+ info->disk.number = __le32_to_cpu(sb->dev_number);
 if (__le32_to_cpu(sb->dev_number) >= __le32_to_cpu(sb->max_dev) ||
     __le32_to_cpu(sb->max_dev) > 512)
 role = 0xfffe;
@@ -303,7 +303,7 @@ static void getinfo_super1(struct mdinfo

 for (i=0; i< __le32_to_cpu(sb->max_dev); i++) {
 role = __le16_to_cpu(sb->dev_roles[i]);
- if (role == 0xFFFF || role < info->array.raid_disks)
+ if (/*role == 0xFFFF || */role < info->array.raid_disks)
 working++;
 }

-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [Linux RAID Wiki]     [ATA RAID]     [Linux SCSI Target Infrastructure]     [Linux Block]     [Linux IDE]     [Linux SCSI]     [Linux Hams]     [Device Mapper]     [Device Mapper Cryptographics]     [Kernel]     [Linux Admin]     [Linux Net]     [GFS]     [RPM]     [git]     [Yosemite Forum]


  Powered by Linux