Re: weird problem

["Paweł Staszewski" <pstaszewski@itcare.pl>]

Jarek Poplawski pisze:
> On 26-06-2009 19:45, Pawe. Staszewski wrote:
>   
>> Eric Dumazet pisze:
>>     
> ...
>   
>>> Pawel made some reports errors in fib thread, so I am not sure he really
>>>  tried 2.6.30 and had same oprofile results.
>>>
>>> rt_worker_func() taking 13% of cpu0 is an alarm for me :)
>>> And 21% of cpu0 and 34% of cpu6 taken by oprofiled seems odd too...
>>>
>>> Pawel, could you give us :
>>>
>>> grep . /proc/sys/net/ipv4/route/*
>>> cat /proc/interrupts
>>>
>>> on your various kernels (previous to 2.6.29, 2.6.29, 2.6.30, ...)
>>>
>>> I suspect a change in hash table size, and/or change in interrupt affinities...
>>>       
>
> Btw., Pawel these eth0's don't look like affined or I miss something?
>
> Jarek P.
> ...
>   
>> cat /proc/interrupts
>>            CPU0       CPU1       CPU2       CPU3       CPU4       
>> CPU5       CPU6       CPU7
>>     
> ...
>   
>>  29:    1139988   18351004      89662          3          0          
>> 1          0          3   PCI-MSI-edge      eth0
>>  30:          0          2   20221692          1          0          
>> 3          0          0   PCI-MSI-edge      eth1
>>     
> ...
>   
Yes
it don't look because i switch a little later after some seconds with 
traffic on this host

Cpu1 - 18351004 interrupts on eth0 (and yes here i forgot to change on boot so there are some interrupts cpu0 1139988 / cpu2 89662)
Cpu2 - 20221692 interrupts on eth1


in attached file are new stats with more counters from /cat /proc/interrupts



>> second machine:
>> Linux TM_02_C1 2.6.30 #1 SMP Thu Jun 25 21:49:58 CEST 2009 i686 Intel(R) 
>> Xeon(R) CPU 3075 @ 2.66GHz GenuineIntel GNU/Linux
>>
>> cat /proc/interrupts
>>            CPU0       CPU1
>>     
> ...
>   
>>  28:      13482      11260   PCI-MSI-edge      eth2
>>  29:          3 1326457765   PCI-MSI-edge      eth1
>>  30: 1240943198  137973134   PCI-MSI-edge      eth0
>>     
>
>
>