Malcolm Beattie wrote:
>
> The only archive of this list that AltaVista found me was a local one
> which didn't go back far enough. I suggest you look at your "Random
> Seeks" figure in bonnie, not the bandwidth figures. I would suggest
> recreating the whole thing from scratch with
> chunk-size 64
> in your /etc/raidtab. Then use
> mke2fs -b 4096 -R stride=16 /dev/md0
> to create the filesystem (and wait until /proc/mdstat shows the
> rebuild has finished). Then try bonnie again and see if the "Random
> Seeks" figure has improved. Then try putting on lots of data and
> testing fsck times. Oh, and since you're not using SCSI disks, check
> that "hdparm /dev/hda" (and the other disks) shows you have using_dma
> and unmaskirq set to 1.
The situation now is that I'm building a second
RAID array, based on SCSI. The old array is at
another company, and I'm sure they don't want
to reformat it. However, I'll get bonnie benchmarks
for the new array once it's finished initial
building. I've noticed that the RAID5.HOWTO has
been much updated since about 1.5 yrs ago when I
set up the last one, and I'm using a chunk size
of 32KB and:
/sbin/mke2fs -b 4096 -R stride=8 /dev/md0
as suggested in the HOWTO. With 22,219,760 (4K) blocks
formatted over 6 drives, this system is considerably
quicker at mounting - just about 10 seconds, so the
block size change has made a massive improvement as you
predicted. Double the size of array, less than 1/10th
the time. I've yet to see an fsck (thankfully :-)
Rich.
--
Bibliotech Ltd., 631-633 Fulham Rd., London SW6 5UQ. +44 171 460 4646
http://www.bibliotech.co.uk Home page: http://www.annexia.demon.co.uk
Home email: [EMAIL PROTECTED] Work: [EMAIL PROTECTED]
Original message content Copyright © 1999 Richard Jones
