IDE Software RAID5 with linux 2.4.20-pre

IDE Software RAID5 with linux 2.4.20-pre

[Gabor Z. Papp]

lo lo all,

I would like build a raid5 host with 4 IC35L060AVVA07-0
disks, running 0 spare disks.
Created 1-1 full size partition on each disk.
I have found Neil's wonderful mdadm tool, and ran the command:

mdadm -C /dev/md0 -l5 -x0 -n4 /dev/hd[aceg]1 2>&1 | tee log.raid5create

Here comes the logfile:

mdadm: /dev/hda1 appears to contain an ext2fs file system
    size=60050936K  mtime=Thu Jan  1 00:00:00 1970
mdadm: /dev/hdc1 appears to contain an ext2fs file system
    size=60050936K  mtime=Thu Jan  1 00:00:00 1970
mdadm: /dev/hdc1 appear to be part of a raid array:
    level=5 devices=4 ctime=Sat Sep 28 08:01:58 2002
mdadm: /dev/hde1 appears to contain an ext2fs file system
    size=60051568K  mtime=Thu Jan  1 00:00:00 1970
mdadm: /dev/hde1 appear to be part of a raid array:
    level=5 devices=4 ctime=Sat Sep 28 08:01:58 2002
mdadm: /dev/hdg1 appears to contain an ext2fs file system
    size=60051568K  mtime=Thu Jan  1 00:00:00 1970
mdadm: /dev/hdg1 appear to be part of a raid array:
    level=5 devices=4 ctime=Sat Sep 28 08:01:58 2002
Continue creating array? mdadm: array /dev/md0 started.

Well, I started... dmesg says:


ICH2: not 100% native mode: will probe irqs later
    ide0: BM-DMA at 0x9800-0x9807, BIOS settings: hda:DMA, hdb:pio
    ide1: BM-DMA at 0x9808-0x980f, BIOS settings: hdc:DMA, hdd:pio

PDC20268: (U)DMA Burst Bit ENABLED Primary MASTER Mode Secondary MASTER Mode.
    ide2: BM-DMA at 0xa400-0xa407, BIOS settings: hde:pio, hdf:pio
    ide3: BM-DMA at 0xa408-0xa40f, BIOS settings: hdg:pio, hdh:pio
hda: IC35L060AVVA07-0, ATA DISK drive
hdc: IC35L060AVVA07-0, ATA DISK drive
hde: IC35L060AVVA07-0, ATA DISK drive
hdg: IC35L060AVVA07-0, ATA DISK drive

blk: queue c037efa4, I/O limit 4095Mb (mask 0xffffffff)
hda: 120103200 sectors (61493 MB) w/1863KiB Cache, CHS=7476/255/63, UDMA(100)
blk: queue c037f308, I/O limit 4095Mb (mask 0xffffffff)
hdc: 120103200 sectors (61493 MB) w/1863KiB Cache, CHS=119150/16/63, UDMA(100)
blk: queue c037f66c, I/O limit 4095Mb (mask 0xffffffff)
hde: 120103200 sectors (61493 MB) w/1863KiB Cache, CHS=119150/16/63, UDMA(33)
blk: queue c037f9d0, I/O limit 4095Mb (mask 0xffffffff)
hdg: 120103200 sectors (61493 MB) w/1863KiB Cache, CHS=119150/16/63, UDMA(33)

md: bind<ide/host0/bus0/target0/lun0/part1,1>
md: bind<ide/host0/bus1/target0/lun0/part1,2>
md: bind<ide/host2/bus0/target0/lun0/part1,3>
md: bind<ide/host2/bus1/target0/lun0/part1,4>
md: ide/host2/bus1/target0/lun0/part1's event counter: 00000000
md: ide/host2/bus0/target0/lun0/part1's event counter: 00000000
md: ide/host0/bus1/target0/lun0/part1's event counter: 00000000
md: ide/host0/bus0/target0/lun0/part1's event counter: 00000000
md0: max total readahead window set to 768k
md0: 3 data-disks, max readahead per data-disk: 256k
raid5: spare disk ide/host2/bus1/target0/lun0/part1
raid5: device ide/host2/bus0/target0/lun0/part1 operational as raid disk 2
raid5: device ide/host0/bus1/target0/lun0/part1 operational as raid disk 1
raid5: device ide/host0/bus0/target0/lun0/part1 operational as raid disk 0
raid5: md0, not all disks are operational -- trying to recover array
raid5: allocated 4339kB for md0
raid5: raid level 5 set md0 active with 3 out of 4 devices, algorithm 2
RAID5 conf printout:
 --- rd:4 wd:3 fd:1
 disk 0, s:0, o:1, n:0 rd:0 us:1 dev:ide/host0/bus0/target0/lun0/part1
 disk 1, s:0, o:1, n:1 rd:1 us:1 dev:ide/host0/bus1/target0/lun0/part1
 disk 2, s:0, o:1, n:2 rd:2 us:1 dev:ide/host2/bus0/target0/lun0/part1
 disk 3, s:0, o:0, n:3 rd:3 us:1 dev:[dev 00:00]
RAID5 conf printout:
 --- rd:4 wd:3 fd:1
 disk 0, s:0, o:1, n:0 rd:0 us:1 dev:ide/host0/bus0/target0/lun0/part1
 disk 1, s:0, o:1, n:1 rd:1 us:1 dev:ide/host0/bus1/target0/lun0/part1
 disk 2, s:0, o:1, n:2 rd:2 us:1 dev:ide/host2/bus0/target0/lun0/part1
 disk 3, s:0, o:0, n:3 rd:3 us:1 dev:[dev 00:00]
md: updating md0 RAID superblock on device
md: ide/host2/bus1/target0/lun0/part1 [events: 00000001]<6>(write) ide/host2/bus1/target0/lun0/part1's sb offset: 60051456
md: recovery thread got woken up ...
md0: resyncing spare disk ide/host2/bus1/target0/lun0/part1 to replace failed disk
RAID5 conf printout:
 --- rd:4 wd:3 fd:1
 disk 0, s:0, o:1, n:0 rd:0 us:1 dev:ide/host0/bus0/target0/lun0/part1
 disk 1, s:0, o:1, n:1 rd:1 us:1 dev:ide/host0/bus1/target0/lun0/part1
 disk 2, s:0, o:1, n:2 rd:2 us:1 dev:ide/host2/bus0/target0/lun0/part1
 disk 3, s:0, o:0, n:3 rd:3 us:1 dev:[dev 00:00]
RAID5 conf printout:
 --- rd:4 wd:3 fd:1
 disk 0, s:0, o:1, n:0 rd:0 us:1 dev:ide/host0/bus0/target0/lun0/part1
 disk 1, s:0, o:1, n:1 rd:1 us:1 dev:ide/host0/bus1/target0/lun0/part1
 disk 2, s:0, o:1, n:2 rd:2 us:1 dev:ide/host2/bus0/target0/lun0/part1
 disk 3, s:0, o:0, n:3 rd:3 us:1 dev:[dev 00:00]
md: syncing RAID array md0
md: minimum _guaranteed_ reconstruction speed: 100 KB/sec/disc.
md: using maximum available idle IO bandwith (but not more than 100000 KB/sec) for reconstruction.
md: using 124k window, over a total of 60050816 blocks.
md: ide/host2/bus0/target0/lun0/part1 [events: 00000001]<6>(write) ide/host2/bus0/target0/lun0/part1's sb offset: 60051456
md: ide/host0/bus1/target0/lun0/part1 [events: 00000001]<6>(write) ide/host0/bus1/target0/lun0/part1's sb offset: 60051456
md: ide/host0/bus0/target0/lun0/part1 [events: 00000001]<6>(write) ide/host0/bus0/target0/lun0/part1's sb offset: 60050816

Personalities : [raid5] 
read_ahead 1024 sectors
md0 : active raid5 ide/host2/bus1/target0/lun0/part1[4] ide/host2/bus0/target0/lun0/part1[2] ide/host0/bus1/target0/lun0/part1[1] ide/host0/bus0/target0/lun0/part1[0]
      180154368 blocks level 5, 64k chunk, algorithm 2 [4/3] [UUU_]
      [>....................]  recovery =  3.3% (2023372/60051456) finish=27.4min speed=35245K/sec
unused devices: <none>

Seems like one of the disks failed? Or what happening?

Re: IDE Software RAID5 with linux 2.4.20-pre

[Michael Tokarev]

Gabor, before posting to a public mailing list,
set your email software correctly.  There is just
now way to send mail to <gzp@myhost.mynet> - there
is no such email address exists.

Gabor Z. Papp wrote:
> lo lo all,
> 
> I would like build a raid5 host with 4 IC35L060AVVA07-0
> disks, running 0 spare disks.
> Created 1-1 full size partition on each disk.
> I have found Neil's wonderful mdadm tool, and ran the command:
> 
> mdadm -C /dev/md0 -l5 -x0 -n4 /dev/hd[aceg]1 2>&1 | tee log.raid5create
[]
> Personalities : [raid5] 
> read_ahead 1024 sectors
> md0 : active raid5 ide/host2/bus1/target0/lun0/part1[4] ide/host2/bus0/target0/lun0/part1[2] ide/host0/bus1/target0/lun0/part1[1] ide/host0/bus0/target0/lun0/part1[0]
>       180154368 blocks level 5, 64k chunk, algorithm 2 [4/3] [UUU_]
>       [>....................]  recovery =  3.3% (2023372/60051456) finish=27.4min speed=35245K/sec
> unused devices: <none>
> 
> Seems like one of the disks failed? Or what happening?

And, before posting such questions, *wait* for mentioned
27.4min at least to see what'll happen.  No, it isn't
failed, this is expected behaviour.  Raid code is bringing
your array up by calculating necessary info to put to your
disks so that the whole thing will be consistent.  The "_"
disk shown above just don't have required information on
it yet, and raid code is working hard to initialize data
on it, at 35245K/sec speed (quite fast I'd say).  Failed
disk usually marked by F char.

/mjt