On Fri, 11 Jan 2002 13:53, Pascal Haakmat wrote:
> > Steve
> >
> > p.s. can you send me the script, I could look back in the xfs maillist,
> > but I am feeling
> > lazy, I am currently using something I wrote based on the brief
> > description in this
> > thread.
>
> dd if=/dev/urandom of=01 bs=1024 count=8192
>
> #!/bin/bash
> cp -fr 01 2
>
> for (( i=80; i!=2; i-- )) ; do
> cp -fr 01 $i &
> # echo $i
> done
Back around the 18/12/2001 the 2.4.16-xfs kernel would die for me when
running the test above (80 cp processes). Eric sugested that I go with the
CVS at the time which was 2.4.17-xfs and the fixes that Steve checked into
the CVS helped a lot.
http://marc.theaimsgroup.com/?t=100819465500006&r=1&w=2
http://marc.theaimsgroup.com/?t=100810400700001&r=1&w=2
Using the 2.4.17-xfs CVS kernel it would survive the 80 cp process test but
would die at 160 cp processes whereas ext2/3 and resierfs would chug away
until finished.
The test on my box takes forever (8hr+) but I intend to start testing the
current CVS tonight.
The composition of the file sizes seem to make an issue as I have done the
same test with a single 650M iso image and it was fine.
Pascal - what type and make are your drives? and what brand & make of
controllers are you using? I have never got an interrupt error but was
wondering if the hardware was simular.
--
Adrian Head
(Public Key available on request.)
|