[Rocks-Discuss]Kernel error issues

Philip Papadopoulos phil at sdsc.edu
Tue Nov 19 20:47:46 PST 2002


Pail,
I've seen this on other systems and only have a hunch --- I believe it 
is an error in some
of the common code of the network drivers. I recommend getting redhat's 
errata kernel.
Have run this on a heavily used NFS server and have not seen these sorts of
errors (they might still be there, by the frequency is reduced)

Try the following

In the "force" directory eg.
/home/install/rocks-dist/7.2/en/os/i386/force/RPMS

do the following:
wget ftp://acs-mirror.ucsd.edu/linux/redhat/updates/7.2/en/os/i686/'kernel*'

(you can pick a different redhat mirror)

The re-run rocks-dist form /home/install

(verify the soft links in
/home/install/rocks-dist/7.3/en/os/i386/RedHat/RPMS point to the
RPMS you just downloaded).

re-kickstart your nodes -- they will have the latest kernel
installed.

-Phil


Paul Zimdars wrote:

> Hi,
>  
> Our nodes keep crashing with the following error:
>  
> Unable to handle kernel null pointer deference at virtual address 
> 00000000 and 00000014
> #pde=00000000
> Oops:    0000
> Kernel 2.4.9-31smp
> CPU:     0
> EIP:     0010 : [<00000000>]  Tainted: P
> EFLAGS:  00010292  and 00010246
> EIPS is at unresolved  and  EIPS is at sys_getpid [kernel] 0x0
> stack dump...
> call trace...
> code: Bade EIP value
>
> One node looks like it had  "swap_free" kernel error as well.
> I am running rocks 2.2.1 with the standard configuration with kernel 
> 2.4.9-31smp (two Xeon 2.2GHZ processors). I am loosing 5-10 nodes at a 
> time sometimes.
>  
> Thanks,
>  
> Paul
> __________________________________________________________________
> Paul Zimdars
> ICQ#: 153472395
> Current ICQ status:  
>
> +  More ways to contact me <http://wwp.icq.com/153472395>
> i  See more about me: 
> <http://web.icq.com/whitepages/about_me?Uin=153472395>
> __________________________________________________________________


-- 
== Philip Papadopoulos, Ph.D.            
== Program Director for                  San Diego Supercomputer Center 
==    Grid and Cluster Computing         9500 Gilman Drive
== Ph:  (858) 822-3628                   University of California, San Diego
== FAX: (858) 822-5407                   La Jolla, CA 92093-0505      
           


-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://lists.sdsc.edu/pipermail/npaci-rocks-discussion/attachments/20021119/fa2ef272/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 4034 bytes
Desc: S/MIME Cryptographic Signature
Url : https://lists.sdsc.edu/pipermail/npaci-rocks-discussion/attachments/20021119/fa2ef272/smime-0001.p7s 


More information about the npaci-rocks-discussion mailing list