[Beowulf] Racing kernels

Stuart Midgley stuart.midgley at anu.edu.au
Mon Apr 4 18:46:36 PDT 2005


Yes.  We run a static kernel on our cluster with only the necessary 
stuff for our hardware configure in (along with a few in-house kernel 
hacks).  We also run a very very very cut down version of RH8.0 (lots 
of rpm -e --nodeps --force stuff) which fits in around 600MB.  It can 
be a pain to get working :)  You go through the

	1) build kernel
	2) install kernel
	3) reboot
	4) "bugger, forgot something"
	5) goto 1)

a lot :)

Stu.



On 04/04/2005, at 18:04, Fringe Dweller wrote:

> G'day all.
>
> Is anyone out there running a "racing" kernel on their nodes?
>
> By "racing" I mean removing all unnecessary components (SCSI, USB et 
> al), tweaked buffer values, pre-empting, stripped, helium filled, 
> brushed aluminum etc?
>
> Yes, it's a loaded question. I'm contemplating performance tweaking 
> when I realized that there's a bucket load of stuff in the default 
> kernel config I don't need.
>
> Now anyone that's ever been exposed to that strange subspecies known 
> as "overclockers" knows you can go to ridiculous lengths ("Duuude, 
> it's fully sick, I can get another 2.3MHz if I take the box outside 
> and hit it with a hose").
>
> I'd like to think we're giving priority to stability. But still... I 
> think there's scope for "safe" improvement?
>
> Also need to include the type of target app(s) I s'pose. My Nbody apps 
> are smokin' math stuff but the IO is quite light. So there'd be a fair 
> range of variation in "optimal" config I'd imagine.
>
> Thoughts appreciated.
>
> Cheers
> Steve

--
<--------------------------------------------------------------------->
   Dr Stuart Midgley                   |  stuart.midgley at anu.edu.au
   Supercomputer Facility              |  smidgley at netspace.net.au
   Leonard Huxley Building 56          |  +61 (0)2 6125 5988   Work
   Australian National University      |  +61 (0)2 6125 8199   Fax
   CANBERRA   ACT   0200               |  +61 (0)4 1125 2488   Mob




More information about the Beowulf mailing list