Questions on processing smaller frame size

[Ivan Voras]

Siquijor Philips wrote:
> Hello Eugene,
> 
>> Traffic bandwidth does not matter (or much less), PPS rate matters.
>> Packets drop due to high pps rate. Higher packet size, lesser pps
>> saturates link and pps just can't grow high. It can with smaller packets.
>>
> 
> All the test scenarios here are bombarded with 1-Gig of network
> traffic. When packet drops due to high pps rate, meaning to say that
> the current FreeBSD system can't still handle this kind of situation
> with high packet rate? 

Not unlikely. See other similar findings by other users, usually also
with em cards.

> Or just it depends on your hardware? I just
> can't imagine that with 2x quad-core system processing on high packet
> rate, average CPU utilization consumes a total of 98%.

Total = across all CPUs? Try reducing the number of CPUs, it might help
by reducing contention.

>> I've tried to make FreeBSD 7.1 act as packet generator
>> with Intel dualcore 2.8Ghz processor and onboard gigabit ethernet em0
>> using ng_source(4) low-overhead packet emitter. And it can't saturate
>> gigabit link with UDP packets (64 bytes payload, 130 bytes at wire -
>> including inter-packet gaps, FCSs etc.)
>>
>> It takes all CPU cycles of one 2.8Ghz core to send 750Kpps -
> 
> Maybe there's a way we can optimize this, but just don't know how and
> what particular component to optimize?

There is a very experimental patch to the em driver, not endorsed by the
em driver author (for unknown reasons) that some users claim helps with
SMP performance. See
http://lists.freebsd.org/pipermail/freebsd-net/2008-December/020441.html



-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 252 bytes
Desc: OpenPGP digital signature
Url : http://lists.freebsd.org/pipermail/freebsd-net/attachments/20090225/53b3d9fc/signature.pgp