Very bad FreeBSD SCSI RAID5 write speed performance

[Andreas Braukmann]

--On Donnerstag, 13. November 2003 15:15 Uhr +0100 Andreas Braukmann <braukmann at tse-online.de> wrote:

well, ... I had a really bad time updating the opteron -current box,
but it's up and running again since yesterday.


> --On Donnerstag, 13. November 2003 14:29 Uhr +0100 Martin Blapp <mb at imp.ch> wrote:
>>> On Thu, Nov 13, 2003 at 06:38:53AM -0500, Gary Stanley wrote:
>>> > root at 64:[/tmp/blah]>dd if=/dev/zero of=/tmp/blah/blah
>>> > 89472+0 records in
>>> > 89471+0 records out
>>> > 45809152 bytes transferred in 8.546312 secs (5360108 bytes/sec)

> Another system: Tyan K8S, Adaptec 2200S, RAID-5 over five spindles
> (Fujitsu U320, 10kUPM disks, write-cache off) across both channels,
> -current from end of september (i386):
>
> opti#  dd if=/dev/zero of=./test bs=128k count=20000
> 20000+0 records in
> 20000+0 records out
> 2621440000 bytes transferred in 57.648042 secs (45473184 bytes/sec)
>
> I'll update the Opteron box to a recent kernel and will check again.

bad news: I've lost my five spindle raid-5 volume, because I have
to put two drives to another box. The result using a 3 spindle raid-5
(-current kernel; 3 days old)

opti% dd if=/dev/zero of=test.dd bs=128k count=20000
20000+0 records in
20000+0 records out
2621440000 bytes transferred in 62.211180 secs (42137764 bytes/sec)

The performance seems pretty normal to me.


-Andreas