Re: problems with raid6, mdadm: RUN_ARRAY failed
Quoting Neil Brown ([EMAIL PROTECTED]): > On Friday June 2, [EMAIL PROTECTED] wrote: > > I have some old controler Mylex Acceleraid 170LP with 6 SCSI 36GB disks on > > it. Running hardware raid5 resulted with very poor performance (7Mb/sec in > > sequential writing, with horrid iowait). > > > > So I configured it to export 6 logical disks and tried creating raid6 and > > see > > if I can get better results. Trying to create an array with a missing > > component > > results in: > > > > ~/mdadm-2.5/mdadm -C /dev/md3 -l6 -n6 /dev/rd/c0d0p3 /dev/rd/c0d2p3 > > /dev/rd/c0d3p3 /dev/rd/c0d4p3 /dev/rd/c0d5p3 missing > > mdadm: RUN_ARRAY failed: Input/output error > > There should have been some messages in the kernel log when this > happened. Can you report them too? Ok. I tried this again and: ~/mdadm-2.5/mdadm -v -C /dev/md3 -l6 -n6 /dev/rd/c0d0p3 /dev/rd/c0d2p3 /dev/rd/c0d3p3 /dev/rd/c0d4p3 /dev/rd/c0d5p3 missing mdadm: layout defaults to left-symmetric mdadm: chunk size defaults to 64K mdadm: size set to 30595712K mdadm: RUN_ARRAY failed: Input/output error Jun 5 10:04:07 www1 kernel: md: bind Jun 5 10:04:07 www1 kernel: md: bind Jun 5 10:04:07 www1 kernel: md: bind Jun 5 10:04:07 www1 kernel: md: bind Jun 5 10:04:07 www1 kernel: md: bind Jun 5 10:04:07 www1 kernel: md: md3: raid array is not clean -- starting background reconstruction Jun 5 10:04:07 www1 kernel: raid6: device rd/c0d5p3 operational as raid disk 4 Jun 5 10:04:07 www1 kernel: raid6: device rd/c0d4p3 operational as raid disk 3 Jun 5 10:04:07 www1 kernel: raid6: device rd/c0d3p3 operational as raid disk 2 Jun 5 10:04:07 www1 kernel: raid6: device rd/c0d2p3 operational as raid disk 1 Jun 5 10:04:07 www1 kernel: raid6: device rd/c0d0p3 operational as raid disk 0 Jun 5 10:04:07 www1 kernel: raid6: cannot start dirty degraded array for md3 Jun 5 10:04:07 www1 kernel: RAID6 conf printout: Jun 5 10:04:07 www1 kernel: --- rd:6 wd:5 fd:1 Jun 5 10:04:07 www1 kernel: disk 0, o:1, dev:rd/c0d0p3 Jun 5 10:04:07 www1 kernel: disk 1, o:1, dev:rd/c0d2p3 Jun 5 10:04:07 www1 kernel: disk 2, o:1, dev:rd/c0d3p3 Jun 5 10:04:07 www1 kernel: disk 3, o:1, dev:rd/c0d4p3 Jun 5 10:04:07 www1 kernel: disk 4, o:1, dev:rd/c0d5p3 Jun 5 10:04:07 www1 kernel: raid6: failed to run raid set md3 Jun 5 10:04:07 www1 kernel: md: pers->run() failed ... Jun 5 10:04:07 www1 kernel: md: md3 stopped. Jun 5 10:04:07 www1 kernel: md: unbind Jun 5 10:04:07 www1 kernel: md: export_rdev(rd/c0d5p3) Jun 5 10:04:07 www1 kernel: md: unbind Jun 5 10:04:07 www1 kernel: md: export_rdev(rd/c0d4p3) Jun 5 10:04:07 www1 kernel: md: unbind Jun 5 10:04:07 www1 kernel: md: export_rdev(rd/c0d3p3) Jun 5 10:04:07 www1 kernel: md: unbind Jun 5 10:04:07 www1 kernel: md: export_rdev(rd/c0d2p3) Jun 5 10:04:07 www1 kernel: md: unbind Jun 5 10:04:07 www1 kernel: md: export_rdev(rd/c0d0p3) I tried creating raid6 with 5 disks (no missing member) and md started constructing array... -- Kresimir Kukulj [EMAIL PROTECTED] +--+ Remember, if you break Debian, you get to keep both parts. - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: problems with raid6, mdadm: RUN_ARRAY failed
On Friday June 2, [EMAIL PROTECTED] wrote: > I have some old controler Mylex Acceleraid 170LP with 6 SCSI 36GB disks on > it. Running hardware raid5 resulted with very poor performance (7Mb/sec in > sequential writing, with horrid iowait). > > So I configured it to export 6 logical disks and tried creating raid6 and see > if I can get better results. Trying to create an array with a missing > component > results in: > > ~/mdadm-2.5/mdadm -C /dev/md3 -l6 -n6 /dev/rd/c0d0p3 /dev/rd/c0d2p3 > /dev/rd/c0d3p3 /dev/rd/c0d4p3 /dev/rd/c0d5p3 missing > mdadm: RUN_ARRAY failed: Input/output error There should have been some messages in the kernel log when this happened. Can you report them too? Thanks, NeilBrown - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
problems with raid6, mdadm: RUN_ARRAY failed
I have some old controler Mylex Acceleraid 170LP with 6 SCSI 36GB disks on
it. Running hardware raid5 resulted with very poor performance (7Mb/sec in
sequential writing, with horrid iowait).
So I configured it to export 6 logical disks and tried creating raid6 and see
if I can get better results. Trying to create an array with a missing component
results in:
~/mdadm-2.5/mdadm -C /dev/md3 -l6 -n6 /dev/rd/c0d0p3 /dev/rd/c0d2p3
/dev/rd/c0d3p3 /dev/rd/c0d4p3 /dev/rd/c0d5p3 missing
mdadm: RUN_ARRAY failed: Input/output error
strace shows it barfed on some ioctl:
read(4, "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 1024) =
1024
ioctl(4, BLKGETSIZE64, 0xbffe64b0) = 0
ioctl(4, BLKFLSBUF, 0) = 0
_llseek(4, 4096, [4096], SEEK_SET) = 0
read(4, "\3\0\0\0\4\0\0\0\5\0\0\0\355]\325?\2\0\0\0\0\0\0\0\0\0"..., 1024) =
1024
close(4)= 0
open("/dev/rd/c0d5p3", O_RDWR|O_EXCL) = 4
ioctl(4, BLKGETSIZE64, 0xbffe66d0) = 0
_llseek(4, 31330009088, [31330009088], SEEK_SET) = 0
write(4, "\374N+\251\0\0\0\0Z\0\0\0\0\0\0\0\0\0\0\0\34\3077\262\353"..., 4096)
= 4096
fsync(4)= 0
close(4)= 0
ioctl(3, 0x40140921, 0xbffe67a0)= 0
ioctl(3, 0x400c0930, 0xbffe67a0)= -1 EIO (Input/output error)
write(2, "mdadm: RUN_ARRAY failed: Input/o"..., 44) = 44
fstat64(3, {st_mode=S_IFBLK|0660, st_rdev=makedev(9, 3), ...}) = 0
ioctl(3, 0x800c0910, 0xbffe6660)= 0
fstat64(3, {st_mode=S_IFBLK|0660, st_rdev=makedev(9, 3), ...}) = 0
ioctl(3, 0x800c0910, 0xbffe6660)= 0
ioctl(3, 0x932, 0) = 0
exit_group(1) = ?
Running:
vanilla 2.6.16.19
Personalities : [linear] [raid0] [raid1] [raid5] [raid4] [raid6]
mdadm-2.5
Creating a filesystem (mke2fs) on /dev/rd/c0d[0234]p3 works without a problem
so devices are accessible.
Any hints ?
--
Kresimir Kukulj [EMAIL PROTECTED]
+--+
Remember, if you break Debian, you get to keep both parts.
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
