[prev in list] [next in list] [prev in thread] [next in thread]
List: openmosix-general
Subject: Re: [openMosix-general] stress test fails
From: Deadpan110 <deadpan110 () gmail ! com>
Date: 2006-05-20 10:06:43
Message-ID: 2a7fc2e80605200306i4b01342fl71cf9229d9b43646 () mail ! gmail ! com
[Download RAW message or body]
Hello,
You mention the gentoo openMosix kernel 2.4.30
The official oM 2.4 kernel is version 2.4.26.
I have never had much success with the gentoo's attempt at an oM kernel...
but i do believe others have (proof?)
I would recomend that you build your own kernel using the om 2.4.26 patch.
Hopes that helps...
Martin
On 19/05/06, Roger Mason <rmason@esd.mun.ca> wrote:
>
> Hello,
>
> I have installed openmosix-2.4.30 on a cluster of 3 machines (1 P4 and
> two P2's) using Gentoo's Portage system. I also installed the stress
> tests on one of the machines in the same way. In the make.conf file I
> set the mcpu=... variable according to processor type before
> installing.
>
> When I run the stress tests I see:
>
> ./start_eatmem.sh: line 15: 29028 Segmentation fault ./eatmem
> ./start_eatmem.sh: line 15: 29030 Segmentation fault ./eatmem
> ./start_eatmem.sh: line 17: 29033 Segmentation fault ./eatmem
> ./start_eatmem.sh: line 18: 29032 Segmentation fault ./eatmem
>
> but the test continue until eventually the machine locks up. The
> last message in the openMosix-stress-test-output file is:
>
> starting 3 timewaster processes 1. time
> starting timewaster 0
> starting timewaster 1
> starting timewaster 2
>
> The last thing output on the console is:
>
> Unable to handle kernel NULL pointer derefernce at virtual address
> 0000004c
>
> printing eip:
> c0172b4d
> *pde = 00000000
>
> I looked through the archives but could not find anything that looked
> similar.
>
> Thanks for any help you can give,
>
> Roger Mason
>
>
>
> -------------------------------------------------------
> Using Tomcat but need to do more? Need to support web services, security?
> Get stuff done quickly with pre-integrated technology to make your job
> easier
> Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
> http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
> _______________________________________________
> openMosix-general mailing list
> openMosix-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/openmosix-general
>
[Attachment #3 (text/html)]
Hello,<br>
<br>
You mention the gentoo openMosix kernel 2.4.30<br>
<br>
The official oM 2.4 kernel is version 2.4.26.<br>
<br>
I have never had much success with the gentoo's attempt at an oM kernel... but i do \
believe others have (proof?)<br><br> I would recomend that you build your own kernel \
using the om 2.4.26 patch.<br> <br>
Hopes that helps...<br>
<br>
Martin<br>
<br>
<br><div><span class="gmail_quote">On 19/05/06, <b class="gmail_sendername">Roger \
Mason</b> <<a href="mailto:rmason@esd.mun.ca">rmason@esd.mun.ca</a>> \
wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, \
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"> Hello,<br><br>I have \
installed openmosix-2.4.30 on a cluster of 3 machines (1 P4 and<br>two P2's) using \
Gentoo's Portage system. I also installed the stress<br>tests on one of \
the machines in the same way. In the make.conf file I<br>set the mcpu=... \
variable according to processor type before<br>installing.<br><br>When I run the \
stress tests I see:<br><br>./start_eatmem.sh: line 15: 29028 Segmentation \
fault ./eatmem<br>./start_eatmem.sh: line 15: \
29030 Segmentation fault ./eatmem \
<br>./start_eatmem.sh: line 17: 29033 Segmentation \
fault ./eatmem<br>./start_eatmem.sh: line 18: \
29032 Segmentation fault ./eatmem<br><br> but the \
test continue until eventually the machine locks up. The<br> last message \
in the openMosix-stress-test-output file is: <br><br>starting 3 timewaster processes \
1. time<br>starting timewaster 0<br>starting timewaster 1<br>starting timewaster \
2<br><br>The last thing output on the console is:<br><br>Unable to handle kernel NULL \
pointer derefernce at virtual address <br>0000004c<br><br>printing \
eip:<br>c0172b4d<br>*pde = 00000000<br><br>I looked through the archives but could \
not find anything that looked<br>similar.<br><br>Thanks for any help you can \
give,<br><br>Roger Mason<br><br> \
<br><br>-------------------------------------------------------<br>Using Tomcat but \
need to do more? Need to support web services, security?<br>Get stuff done quickly \
with pre-integrated technology to make your job easier <br>Download IBM WebSphere \
Application Server v.1.0.1 based on Apache Geronimo<br><a \
href="http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=12 \
1642">http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
</a><br>_______________________________________________<br>openMosix-general mailing \
list<br><a href="mailto:openMosix-general@lists.sourceforge.net">openMosix-general@lists.sourceforge.net</a><br><a \
href="https://lists.sourceforge.net/lists/listinfo/openmosix-general"> \
https://lists.sourceforge.net/lists/listinfo/openmosix-general</a><br></blockquote></div><br>
-------------------------------------------------------
Using Tomcat but need to do more? Need to support web services, security?
Get stuff done quickly with pre-integrated technology to make your job easier
Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
_______________________________________________
openMosix-general mailing list
openMosix-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/openmosix-general
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic