[Beowulf] Repeated Dell SC1435 crash / hang. How to get the vendor to resolve the issue when 20% of the servers fail in first year?
Gerry Creager
gerry.creager at tamu.edu
Mon Apr 6 12:53:33 PDT 2009
Jan Heichler wrote:
> Hallo Rahul,
>
>
> Montag, 6. April 2009, meintest Du:
>
>
> RN> On Mon, Apr 6, 2009 at 7:46 AM, Chris Samuel <csamuel at vpac.org
> <mailto:csamuel at vpac.org>> wrote:
>
>> > Even though we could reproduce it on 64-bit Debian
>
>> > and 32-bit CentOS they wouldn't escalate the issue
>
>> > until we could reproduce it on RHEL5 - which we did
>
>> > today.
>
>
>
> RN> Thanks for sharing the anecdote Chris. I wonder if there is any clause
>
> RN> in the contracts restricting us to run certain OS's.
>
>
> RN> So long as we are using a "reputable" well-tested OS I find it unfair
>
> RN> that the vendors engage in so much arm-twisting. Is there any
>
> RN> scientific evidence that the core kernels of Debian or Fedora or CenOS
>
> RN> (that *is* essentially RHEL isn't it?) are any less reliable then
>
> RN> RHEL? What is / are the distros of choice on the Beowulf community?
>
> RN> Just getting a feel.
>
>
> RN> I have tried out cutting edge distros meant for scientific
>
> RN> applications like ScientificLinux or ComputeNodeLinux but I've found
>
>
> ScientificLinux is - in fact - RHEL. So it is not more "cutting edge"
> than CentOS...
>
>
> RN> it more practical to stick to a larger, well used distro. No doubt I
>
> RN> might take some performance cuts on the benchmarks but the simple
>
> RN> reality of a larger user community out there makes it easier to debug
>
> RN> stuff and get well-tested apps and code that will run on my Distro
>
> RN> out-of-the box.
>
>
> I See that ScientificLinux has a huge community using it - at least in
> Europe. Some big research institutes are using it (CERN for example) -
> some projects set it as the default distro (D-Grid - a german GRID
> project).
>
>
> So i don't see you point here ;-)
And in the US, the Tier2 and Tier3 LHC participants are using
ScientificLinux, too. In fact, we've a couple of researchers here who
will use no other distro. you know, like RHEL or CentOS. Too dangerous
in their eyes.
gc
More information about the Beowulf
mailing list