aoe disk not recognized as part of raid

aoe disk not recognized as part of raid

[Lars Täuber]

Hallo!

It seems mdadm doesn't recognises aoe block devices automatically as part of raid:

monosan:~ # fgrep md9 /etc/mdadm.conf 
ARRAY /dev/md9 level=raid1 num-devices=2 UUID=23882ab5:8346ffa3:0e2e4f1e:419f2ac9

monosan:~ # cat /proc/partitions 
major minor  #blocks  name
[...]
 253    16 1074790400 dm-16
 253    17 8589934592 dm-17
 152  2832 1074790400 etherd/e11.1

monosan:~ # mdadm -As
mdadm: /dev/md9 has been started with 1 drive (out of 2).

monosan:~ # cat /proc/mdstat 
Personalities : [raid1] [raid0] [raid6] [raid5] [raid4] 
md9 : active (auto-read-only) raid1 dm-16[0]
      1074790336 blocks [2/1] [U_]

monosan:~ # mdadm /dev/md9 -a /dev/etherd/e11.1 
mdadm: re-added /dev/etherd/e11.1

monosan:~ # cat /proc/mdstat 
Personalities : [raid1] [raid0] [raid6] [raid5] [raid4] 
md9 : active raid1 etherd/e11.1[1] dm-16[0]
      1074790336 blocks [2/2] [UU]


mdadm version 2.6.6 although it is reported as:
monosan:~ # mdadm -V
mdadm - v2.6 - 21 December 2006
monosan:~ # uname -r
2.6.25-default

Why isn't it scanned automatically?
Is this a bug to be filed?

Thanks
Lars
-- 
                            Informationstechnologie
Berlin-Brandenburgische Akademie der Wissenschaften
Jägerstrasse 22-23                     10117 Berlin
Tel.: +49 30 20370-352           http://www.bbaw.de
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: aoe disk not recognized as part of raid

[Lars Täuber]

[-- Attachment #1: Type: text/plain, Size: 301 bytes --]

Sorry!

> mdadm version 2.6.6 although it is reported as:
> monosan:~ # mdadm -V
> mdadm - v2.6 - 21 December 2006

I accidentally compiled mdadm 2.6 instead of 2.6.6. But this is even worse:

monosan:~ # mdadm -V
mdadm - v2.6.6 - 19th May 2008
monosan:~ # mdadm -As
Segmentation fault


Regards
Lars

[-- Attachment #2: mdadm.strace --]
[-- Type: text/plain, Size: 5435 bytes --]

execve("/sbin/mdadm", ["mdadm", "-As"], [/* 54 vars */]) = 0
brk(0)                                  = 0x636000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6034276000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6034275000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY)      = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=39565, ...}) = 0
mmap(NULL, 39565, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f603426b000
close(3)                                = 0
open("/lib64/libc.so.6", O_RDONLY)      = 3
read(3, "\177ELF\2\1\1\0\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0p\334\1\0\0\0\0\0"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=1354000, ...}) = 0
mmap(NULL, 3424568, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f6033d17000
fadvise64(3, 0, 3424568, POSIX_FADV_WILLNEED) = 0
mprotect(0x7f6033e53000, 2093056, PROT_NONE) = 0
mmap(0x7f6034052000, 20480, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x13b000) = 0x7f6034052000
mmap(0x7f6034057000, 16696, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x7f6034057000
close(3)                                = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f603426a000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6034269000
arch_prctl(ARCH_SET_FS, 0x7f60342696f0) = 0
mprotect(0x7f6034052000, 12288, PROT_READ) = 0
mprotect(0x62f000, 4096, PROT_READ)     = 0
munmap(0x7f603426b000, 39565)           = 0
getpid()                                = 7052
brk(0)                                  = 0x636000
brk(0x657000)                           = 0x657000
open("/etc/mdadm.conf", O_RDONLY)       = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=358, ...}) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6034274000
read(3, "DEVICE /dev/sd[ab][0-9] /dev/dm-"..., 4096) = 358
read(3, "", 4096)                       = 0
read(3, "", 4096)                       = 0
close(3)                                = 0
munmap(0x7f6034274000, 4096)            = 0
open("/dev", O_RDONLY|O_NONBLOCK|O_DIRECTORY) = 3
fstat(3, {st_mode=S_IFDIR|0755, st_size=8180, ...}) = 0
fcntl(3, F_SETFD, FD_CLOEXEC)           = 0
getdents64(3, /* 154 entries */, 4096)  = 4080
getdents64(3, /* 138 entries */, 4096)  = 4088
getdents64(3, /* 117 entries */, 4096)  = 3672
getdents64(3, /* 0 entries */, 4096)    = 0
close(3)                                = 0
open("/dev", O_RDONLY|O_NONBLOCK|O_DIRECTORY) = 3
fstat(3, {st_mode=S_IFDIR|0755, st_size=8180, ...}) = 0
fcntl(3, F_SETFD, FD_CLOEXEC)           = 0
getdents64(3, /* 154 entries */, 4096)  = 4080
getdents64(3, /* 138 entries */, 4096)  = 4088
getdents64(3, /* 117 entries */, 4096)  = 3672
getdents64(3, /* 0 entries */, 4096)    = 0
close(3)                                = 0
stat("/dev/md2", {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 2), ...}) = 0
open("/dev/md2", O_RDWR)                = 3
fstat(3, {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 2), ...}) = 0
ioctl(3, 0x800c0910, 0x7fff3c274fb0)    = 0
ioctl(3, 0x80480911, 0x7fff3c275260)    = 0
close(3)                                = 0
stat("/dev/md3", {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 3), ...}) = 0
open("/dev/md3", O_RDWR)                = 3
fstat(3, {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 3), ...}) = 0
ioctl(3, 0x800c0910, 0x7fff3c274fb0)    = 0
ioctl(3, 0x80480911, 0x7fff3c275260)    = 0
close(3)                                = 0
stat("/dev/md4", {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 4), ...}) = 0
open("/dev/md4", O_RDWR)                = 3
fstat(3, {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 4), ...}) = 0
ioctl(3, 0x800c0910, 0x7fff3c274fb0)    = 0
ioctl(3, 0x80480911, 0x7fff3c275260)    = 0
close(3)                                = 0
stat("/dev/md9", {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 9), ...}) = 0
open("/dev/md9", O_RDWR)                = 3
fstat(3, {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 9), ...}) = 0
ioctl(3, 0x800c0910, 0x7fff3c274fb0)    = 0
ioctl(3, 0x80480911, 0x7fff3c275260)    = -1 ENODEV (No such device)
uname({sys="Linux", node="monosan", ...}) = 0
fstat(3, {st_mode=S_IFBLK|0640, st_rdev=makedev(9, 9), ...}) = 0
ioctl(3, 0x800c0910, 0x7fff3c274c30)    = 0
ioctl(3, 0x80480911, 0x7fff3c274eb0)    = -1 ENODEV (No such device)
ioctl(3, 0x932, 0)                      = 0
open("/dev", O_RDONLY|O_NONBLOCK|O_DIRECTORY) = 4
fstat(4, {st_mode=S_IFDIR|0755, st_size=8180, ...}) = 0
fcntl(4, F_SETFD, FD_CLOEXEC)           = 0
getdents64(4, /* 154 entries */, 4096)  = 4080
getdents64(4, /* 138 entries */, 4096)  = 4088
getdents64(4, /* 117 entries */, 4096)  = 3672
getdents64(4, /* 0 entries */, 4096)    = 0
close(4)                                = 0
open("/dev", O_RDONLY|O_NONBLOCK|O_DIRECTORY) = 4
fstat(4, {st_mode=S_IFDIR|0755, st_size=8180, ...}) = 0
fcntl(4, F_SETFD, FD_CLOEXEC)           = 0
getdents64(4, /* 154 entries */, 4096)  = 4080
getdents64(4, /* 138 entries */, 4096)  = 4088
getdents64(4, /* 117 entries */, 4096)  = 3672
getdents64(4, /* 0 entries */, 4096)    = 0
close(4)                                = 0
open("/dev/sdb2", O_RDONLY|O_EXCL)      = -1 EBUSY (Device or resource busy)
--- SIGSEGV (Segmentation fault) @ 0 (0) ---
+++ killed by SIGSEGV +++

Re: aoe disk not recognized as part of raid

[NeilBrown]

On Sat, May 24, 2008 1:00 am, Lars Täuber wrote:
> Sorry!
>
>> mdadm version 2.6.6 although it is reported as:
>> monosan:~ # mdadm -V
>> mdadm - v2.6 - 21 December 2006
>
> I accidentally compiled mdadm 2.6 instead of 2.6.6. But this is even
> worse:
>
> monosan:~ # mdadm -V
> mdadm - v2.6.6 - 19th May 2008
> monosan:~ # mdadm -As
> Segmentation fault

That's bad.
What do you get from:

 ulimit -c unlimited
 mdadm -As
 gdb `which mdadm` core
 where

??

NeilBrown

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

Re: aoe disk not recognized as part of raid

[Richard Scobie]

NeilBrown wrote:
> On Sat, May 24, 2008 1:00 am, Lars Täuber wrote:
>> Sorry!
>>
>>> mdadm version 2.6.6 although it is reported as:
>>> monosan:~ # mdadm -V
>>> mdadm - v2.6 - 21 December 2006
>> I accidentally compiled mdadm 2.6 instead of 2.6.6. But this is even
>> worse:
>>
>> monosan:~ # mdadm -V
>> mdadm - v2.6.6 - 19th May 2008
>> monosan:~ # mdadm -As
>> Segmentation fault
> 
> That's bad.
> What do you get from:
> 
>  ulimit -c unlimited
>  mdadm -As
>  gdb `which mdadm` core
>  where
> 
> ??
> 
> NeilBrown

I saw this last week, but can unfortunately only offer limited 
information - for various reasons, this system is no longer available.

On an up to date Fedora 8 x86_64 2.6.24.7-92.fc8 sytem, I replaced mdadm 
with a locally built mdadm 2.6.5 - compiled with -O2.

On the next reboot, the md RAID1 / failed to assemble, with mdadm 
errors. When I accessed from a rescue disk, running mdadm -A /dev/mdX 
(can't rember exact dev), returned "Segmentation fault".

If it's any use, I do still have a complete mdadm 2.6.5 tree containing 
the faulty objects from this system.

Regards,

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

Re: aoe disk not recognized as part of raid

[Lars Täuber]

Hallo Neil!

"NeilBrown" <neilb@suse.de> schrieb:
> On Sat, May 24, 2008 1:00 am, Lars Täuber wrote:
> > Sorry!
> >
> >> mdadm version 2.6.6 although it is reported as:
> >> monosan:~ # mdadm -V
> >> mdadm - v2.6 - 21 December 2006
> >
> > I accidentally compiled mdadm 2.6 instead of 2.6.6. But this is even
> > worse:
> >
> > monosan:~ # mdadm -V
> > mdadm - v2.6.6 - 19th May 2008
> > monosan:~ # mdadm -As
> > Segmentation fault
> 
> That's bad.
> What do you get from:
> 
>  ulimit -c unlimited
>  mdadm -As
>  gdb `which mdadm` core
>  where
> 
monosan:~ # ulimit -c unlimited
monosan:~ # mdadm -As
Speicherzugriffsfehler (core dumped)
monosan:~ # gdb `which mdadm` core
GNU gdb 6.6.50.20070726-cvs
Copyright (C) 2007 Free Software Foundation, Inc.
GDB is free software, covered by the GNU General Public License, and you are
welcome to change it and/or distribute copies of it under certain conditions.
Type "show copying" to see the conditions.
There is absolutely no warranty for GDB.  Type "show warranty" for details.
This GDB was configured as "x86_64-suse-linux"...
Using host libthread_db library "/lib64/libthread_db.so.1".

warning: Can't read pathname for load map: Input/output error.
Reading symbols from /lib64/libc.so.6...done.
Loaded symbols for /lib64/libc.so.6
Reading symbols from /lib64/ld-linux-x86-64.so.2...done.
Loaded symbols for /lib64/ld-linux-x86-64.so.2
Core was generated by `mdadm -As'.
Program terminated with signal 11, Segmentation fault.
#0  0x000000000040cd72 in Assemble (st=0x0, mddev=0x6364f0 "/dev/md4", mdfd=3, 
    ident=0x636630, devlist=0x636b90, backup_file=0x0, readonly=0, runstop=0, 
    update=0x0, homehost=0x0, verbose=0, force=0) at Assemble.c:370
370                     tst->ss->free_super(tst);
(gdb) where
#0  0x000000000040cd72 in Assemble (st=0x0, mddev=0x6364f0 "/dev/md4", mdfd=3, 
    ident=0x636630, devlist=0x636b90, backup_file=0x0, readonly=0, runstop=0, 
    update=0x0, homehost=0x0, verbose=0, force=0) at Assemble.c:370
#1  0x00000000004058a4 in main (argc=2, argv=0x7fff2317c6d8) at mdadm.c:1086
(gdb) 

I hope this helps.

Any idea on the actual subject?

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

Re: aoe disk not recognized as part of raid

[Neil Brown]

On Monday May 26, taeuber@bbaw.de wrote:
> (gdb) where
> #0  0x000000000040cd72 in Assemble (st=0x0, mddev=0x6364f0 "/dev/md4", mdfd=3, 
>     ident=0x636630, devlist=0x636b90, backup_file=0x0, readonly=0, runstop=0, 
>     update=0x0, homehost=0x0, verbose=0, force=0) at Assemble.c:370
> #1  0x00000000004058a4 in main (argc=2, argv=0x7fff2317c6d8) at mdadm.c:1086
> (gdb) 
> 
> I hope this helps.

Yes it does thanks.  I'll get that fixed.

> 
> Any idea on the actual subject?

I need you to try the --assemble with --verbose to find out what is
happening.
Use an earlier version of mdadm.  (e.g. 2.6.4).

NeilBrown

Re: aoe disk not recognized as part of raid

[Lars Täuber]

Hi Neil,

Neil Brown <neilb@suse.de> schrieb:
> > Any idea on the actual subject?
> 
> I need you to try the --assemble with --verbose to find out what is
> happening.
> Use an earlier version of mdadm.  (e.g. 2.6.4).

this is the output:

monosan:/usr/local/src/mdadm-2.6.4 # ./mdadm -Av /dev/md9
mdadm: looking for devices for /dev/md9
mdadm: cannot open device /dev/sdb2: Device or resource busy
mdadm: /dev/sdb2 has wrong uuid.
mdadm: cannot open device /dev/sdb1: Device or resource busy
mdadm: /dev/sdb1 has wrong uuid.
mdadm: cannot open device /dev/sda3: Device or resource busy
mdadm: /dev/sda3 has wrong uuid.
mdadm: cannot open device /dev/sda2: Device or resource busy
mdadm: /dev/sda2 has wrong uuid.
mdadm: cannot open device /dev/sda1: Device or resource busy
mdadm: /dev/sda1 has wrong uuid.
mdadm: cannot open device /dev/dm-9: Device or resource busy
mdadm: /dev/dm-9 has wrong uuid.
mdadm: cannot open device /dev/dm-8: Device or resource busy
mdadm: /dev/dm-8 has wrong uuid.
mdadm: cannot open device /dev/dm-7: Device or resource busy
mdadm: /dev/dm-7 has wrong uuid.
mdadm: cannot open device /dev/dm-6: Device or resource busy
mdadm: /dev/dm-6 has wrong uuid.
mdadm: cannot open device /dev/dm-5: Device or resource busy
mdadm: /dev/dm-5 has wrong uuid.
mdadm: cannot open device /dev/dm-4: Device or resource busy
mdadm: /dev/dm-4 has wrong uuid.
mdadm: cannot open device /dev/dm-3: Device or resource busy
mdadm: /dev/dm-3 has wrong uuid.
mdadm: cannot open device /dev/dm-2: Device or resource busy
mdadm: /dev/dm-2 has wrong uuid.
mdadm: /dev/dm-17 has wrong uuid.
mdadm: cannot open device /dev/dm-15: Device or resource busy
mdadm: /dev/dm-15 has wrong uuid.
mdadm: cannot open device /dev/dm-14: Device or resource busy
mdadm: /dev/dm-14 has wrong uuid.
mdadm: cannot open device /dev/dm-13: Device or resource busy
mdadm: /dev/dm-13 has wrong uuid.
mdadm: cannot open device /dev/dm-12: Device or resource busy
mdadm: /dev/dm-12 has wrong uuid.
mdadm: cannot open device /dev/dm-11: Device or resource busy
mdadm: /dev/dm-11 has wrong uuid.
mdadm: cannot open device /dev/dm-10: Device or resource busy
mdadm: /dev/dm-10 has wrong uuid.
mdadm: cannot open device /dev/dm-1: Device or resource busy
mdadm: /dev/dm-1 has wrong uuid.
mdadm: /dev/dm-0 has wrong uuid.
mdadm: /dev/dm-16 is identified as a member of /dev/md9, slot 0.
mdadm: no uptodate device for slot 1 of /dev/md9
mdadm: added /dev/dm-16 to /dev/md9 as 0
mdadm: /dev/md9 has been started with 1 drive (out of 2).

# cat /proc/partitions 
major minor  #blocks  name

   8     0  160836480 sda
   8     1   14354046 sda1
   8     2   48829567 sda2
   8     3   48829567 sda3
   8    16  160836480 sdb
   8    17   14354046 sdb1
   8    18   48829567 sdb2
   8    32  976762584 sdc
...
  65   144  976762584 sdz
  65   160  976762584 sdaa
...
  66    16  976762584 sdah
   9     2   14353920 md2
 253     0  976762584 dm-0
...
 253    15  976762584 dm-15
   9     3   48829440 md3
   9     4 12697912448 md4
   9     9 1074790336 md9
 152  2832 1074790400 etherd/e11.1
 253    16 1074790400 dm-16
 253    17 8589934592 dm-17


dm-16 and etherd/e11.1 are the two parts of md9.

monosan:/usr/local/src/mdadm-2.6.4 # cat /proc/mdstat 
Personalities : [raid1] [raid0] [raid6] [raid5] [raid4] 
md9 : active (auto-read-only) raid1 dm-16[0]
      1074790336 blocks [2/1] [U_]

Sorry for the voluminous outputs. :)
Good luck.
Lars

Re: aoe disk not recognized as part of raid - solution!

[Lars Täuber]

Hi Neil,

it was my fault!

I added the following »/dev/etherd/e*.*« to the DEVICE list in /etc/mdadm.conf.

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

Re: aoe disk not recognized as part of raid

[NeilBrown]

On Fri, May 23, 2008 10:25 pm, Lars Täuber wrote:
> Hallo!
>
> It seems mdadm doesn't recognises aoe block devices automatically as part
> of raid:
>
> monosan:~ # fgrep md9 /etc/mdadm.conf
> ARRAY /dev/md9 level=raid1 num-devices=2
> UUID=23882ab5:8346ffa3:0e2e4f1e:419f2ac9
>
> monosan:~ # cat /proc/partitions
> major minor  #blocks  name
> [...]
>  253    16 1074790400 dm-16
>  253    17 8589934592 dm-17
>  152  2832 1074790400 etherd/e11.1
>
> monosan:~ # mdadm -As
> mdadm: /dev/md9 has been started with 1 drive (out of 2).
>

What does
   mdadm -Asv

show ??

NeilBrown

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