finding optimal ipfw strategy

[Victor Gamov]

On 27/08/2019 21:50, Eugene Grosbein wrote:
> 28.08.2019 1:46, Eugene Grosbein wrote:
> 
>> 28.08.2019 1:03, Andrey V. Elsukov wrote:
>>
>>> As you can see, when ipfw produces high load, interrupt column is more
>>> than system.
>>
>> Interrupt numbers higher than others generally mean that traffic is processed without netisr queueing mostly.
>> That is expected for plain routing. I'm not sure if this would be same in case of bridging.
>>
>> Victor, do you have some non-default tuning in your /boot/loader.conf or /etc/sysctl.conf?
>> If yes, could you show them? If not, you should try something like this. For loader.conf:
>>
>> hw.igb.rxd=4096
>> hw.igb.txd=4096
>> net.isr.bindthreads=1
>> net.isr.defaultqlimit=4096
>> #substitute total number of CPU cores in the system here
>> net.isr.maxthreads=4
>> # EOF
> 
> Also, you should monitor interrupt numbers shown by "systat -vm 3" for igb* devices
> at hours of most load. If they approach 8000 limit but not exceed it,
> you may be suffering from this and should raise the limit with /boot/loader.conf:
> 
> hw.igb.max_interrupt_rate=32000

It's about 5000-7000 per rxq

--
CU,
Victor Gamov