Re: random system crashes

On Tue, 15 Oct 2002, Alex Kramarov wrote:
> everyone who is successfully running tux and willing to provide that info,
> please reply to the list.
> i believe we need at least 10 ppl to get started ...

Running tux here just fine:

1. 4 boxes; IBM x300; single P3-1000; single 18Gb IDE disk
2. RedHat 7.3; kernel-smp-2.4.18-4SGI_XFS_1.1 (stock RH7.3 SMP kernel with
   SGI XFS patches merged in; running on XFS filesystems); tux-2.2.5-1
3. Tux on 0.0.0.0:80, Apache on 127.0.0.1:8080
4. Loadbalancing the 4 boxes using LVS 0.9.7 (stock RH)
5. Successfully served a peak of 400k hits/min or 7k hits/sec accross all 4
   boxes; this equals a peak of 150k hits/min or 2.5k hits/sec on a single
   box (load is not equally spreaded; two of the boxes take 2/3 of the
   total load together)


Before I have been using RH7.1, again with SGI XFS patches merged in using
it's stock Tux and LVS versions. I have experienced the described system
crashes several times on different boxes. It seemed to have no relation
with (a high) load. In this RH7.3 configuration I have yet to experience
the system crashes. LVS is used for loadbalancing as well as redundancy.


Regards,

-- 
Matthijs van der Klip
Netherlands Public Broadcasting