At 13:00 5-2-2003 +0100, Kai Leibrandt wrote:
Of course, this is nowhere near a scientific study. It's also
interesting to see how badly the DAC does in comparison to an ata md
raid 5, even though there's only one disk per scsi channel in active
use. Oh and _do_ remember this is mostly focussing on sequential i/o!
Hope this is interesting to anyone,
3 disk software raid 5 over 2 promise ultra ata 100 controllers. 1 Disk per
channel.
kernel 2.4.18-19-1.2pre5 , XFS with version 2 logs.
PIII 450 with 256MB ram, 1 Seagate Barracuda IV 80GB, 2 IBM Deathstar 60GXP
80GB.
No extra mount options given. I can probably get better scores using sunit
and swidth options.
[root@lsautom raid]# xfs_info /raid
meta-data=/raid isize=256 agcount=37, agsize=1048568 blks
data = bsize=4096 blocks=38399936, imaxpct=25
= sunit=8 swidth=16 blks, unwritten=0
naming =version 2 bsize=4096
log =internal bsize=4096 blocks=32768 version=2
= sunit=8 blks
realtime =none extsz=65536 blocks=0, rtextents=0
[seth@lsautom seth]$ cat /etc/raidtab
raiddev /dev/md0
raid-level 5
nr-raid-disks 3
nr-spare-disks 0
persistent-superblock 1
parity-algorithm left-symmetric
chunk-size 32
device /dev/hdg1
raid-disk 0
device /dev/hdk1
raid-disk 1
device /dev/hdi2
raid-disk 2
-------Sequential Output-------- ---Sequential Input--
--Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block---
--Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
512 5466 89.9 29453 30.2 14302 23.9 5681 94.7 89181 89.1
216.4 5.0
1024 5479 90.0 25155 27.5 16346 27.4 5834 97.7 83500 92.5
192.6 4.2
This is by no means a extremely fast array, but it should give you a
pointer what to expect from yours.
Cheers
--
Seth
It might just be your lucky day, if you only knew.
|