From: [EMAIL PROTECTED] on behalf of Bernard Li
Sent: Wed 04/01/2006 20:14
To: Bruce Becker; Aquarijen
Cc: [email protected]; OSCAR users
Subject: RE: [Oscar-users] Re: [Mauiusers] jobs stuck in Q
From: [EMAIL PROTECTED] on behalf of Bruce Becker
Sent: Wed 04/01/2006 00:29
To: Aquarijen
Cc: [email protected]; OSCAR users
Subject: [Oscar-users] Re: [Mauiusers] jobs stuck in Q
Hi all,
sorry for the delay in getting back. New Years
and such... Anyway I
have since figured the problem out but the issue was not
with
MAUI, but with the TORQUE server setup. The
parameter
resources_default.nodes was not set. I had to set it to 1 for the
jobs
to start running automatically, else MAUI would claim "not
enough
resources for job".
This should have been set by OSCAR when it
was installed, but didn't.
If other people have noticed the same behaviour -
having to set
resources_default.nodes - then perhaps it is an OSCAR bug. The
cluster
is running OSCAR 4.2.1-1:3482M-20051214 on Scientific Linux
4.2
x86_64, but I remember seeing similar issues when installing our
other
system - Fedora Core 3 x86 and OSCAR 4.1b1r2995. It's not a
major
hassle if you know how to fix it, but it took me a
while...
Thanks
Bruce
On 03/01/06, Aquarijen
<[EMAIL PROTECTED]> wrote:
> Hey Bruce - I had the same
problem. I ended up having to reconfigure
> maui. I don't
remember exactly what I did as I just reconfigured from
> scratch to use
options I needed, but I just wanted to let you know
> that you are not the
only one to have seen this with OSCAR. I can
> send you my maui.cfg
if you like.
> -Jen
>
> On 12/28/05, Bruce Becker
<[EMAIL PROTECTED]> wrote:
> > Hi mauiusers
>
>
> > We have a small cluster of opterons clustered with OSCAR,
running
> > scientific linux 4.2 x86_64. I am trying to run some simple
jobs using
> > TORQUE + MAUI (standard OSCAR installation) which get
put directly
> > into the Q state. If I force them to run with qrun,
they get accepted,
> > but do not run automatically. I have tried
looking through the
> > mauiusers list for similar symptoms, but have
not found exactly the
> > same thing. So, I'm not really sure even how
to diagnose the problem,
> > so
> > 1) What information is
needed to find out what's going on ?
> > 2) Obviously, how can I sort
this problem out ?
> >
> > Thanks
> > Bruce
>
> _______________________________________________
> > mauiusers
mailing list
> > [email protected]
> > http://www.supercluster.org/mailman/listinfo/mauiusers
>
>
>
-------------------------------------------------------
This
SF.net email is sponsored by: Splunk Inc. Do you grep through log files
for
problems? Stop! Download the new AJAX search engine that
makes
searching your log files as easy as surfing the web.
DOWNLOAD SPLUNK!
http://ads.osdn.com/?ad_idv37&alloc_id865&op=ick
_______________________________________________
Oscar-users
mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/oscar-users
