Are you sharing the same mount point for samba and nfs?  If so, that 
might be the problem, they both use a different locking mechanism, so 
you can get into locking contention.

A couple of links:

http://www.rootninja.com/disable-oplocks-in-a-heterogeneous-samba-nfs-environment/


http://utcc.utoronto.ca/~cks/space/blog/linux/NFSSambaLocking


On 07/29/2011 09:04 PM, Jon Schewe wrote:
> The load is due to lots of nfs transactions on the system. So the load
> average is 7 because 7 nfs processes are stuck in I/O.
>
> On Fri, Jul 29, 2011 at 9:52 AM, Marc Skinner<marc at e-skinner.net>  wrote:
>>
>> Is the load due to samba or something else?  If you do a top, what are the "top" processes running when your at a load of 7?  smbd? nmbd? are you using software raid? could it be doing a rebuild at that time?
>>
>> Thanks!
>>
>> On 07/29/2011 08:19 AM, Jon Schewe wrote:
>>>
>>> I've got a fileserver that from time to time it's load climbs to
>>> around 7. When this happens samba refuses more connections stating
>>> that the maximum number of connections has been reached. I've not set
>>> any connection maximums, so I shouldn't have any limits as the
>>> defaults are all unlimited. Has anyone else run into this?
>>>
>>> Jon
>>> _______________________________________________
>>> TCLUG Mailing List - Minneapolis/St. Paul, Minnesota
>>> tclug-list at mn-linux.org
>>> http://mailman.mn-linux.org/mailman/listinfo/tclug-list
>>
>> _______________________________________________
>> TCLUG Mailing List - Minneapolis/St. Paul, Minnesota
>> tclug-list at mn-linux.org
>> http://mailman.mn-linux.org/mailman/listinfo/tclug-list
>>
> _______________________________________________
> TCLUG Mailing List - Minneapolis/St. Paul, Minnesota
> tclug-list at mn-linux.org
> http://mailman.mn-linux.org/mailman/listinfo/tclug-list