Limit CPUs

Jerry Feldman gaf at blu.org
Thu May 14 09:11:08 EDT 2009


I'd like to see your results.
I did a similar thing on HP-UX 10 years ago, but I was looking at stress 
and locking not performance, per se. At the time I found an interesting 
bug where (if I recall), open(2) erroneously returned 0. (Normally file 
descriptor 0 is used for stdin, and in my test case, open should have 
returned a -1). Bug report was filed and accepted, but this was a rather 
extreme case where I was stressing kernel file locking across NFS an 
local on a multi-CPU system (either 4 or 8 at the time).

On 05/13/2009 07:02 PM, Kenneth Lussier wrote:
> -----Original Message-----
>
>
>   
>> That's not a kernel param... :)
>>
>> I believe 'maxcpus=x' is what we're >looking for here.
>>     
>
> THAT'S  the one ;-)
>
>   


-- 
Jerry Feldman <gaf at blu.org>
Boston Linux and Unix
PGP key id: 537C5846
PGP Key fingerprint: 3D1B 8377 A3C0 A5F2 ECBB  CA3B 4607 4319 537C 5846


-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 251 bytes
Desc: OpenPGP digital signature
Url : http://mail.gnhlug.org/mailman/private/gnhlug-discuss/attachments/20090514/2fdba4a3/attachment.bin 


More information about the gnhlug-discuss mailing list