[P4-dev] iperf on heavy hitter example

Antonin Bas antonin at barefootnetworks.com
Wed Oct 11 15:23:49 EDT 2017


This has been covered before:
http://lists.p4.org/pipermail/p4-dev_lists.p4.org/2017-February/000715.html
While production performance has never been a design goal of bmv2, there is
no reason why you shouldn't at least get a couple hundred Mbps with such a
simple P4 program if you use the appropriate compile-time & runtime flags.

On Wed, Oct 11, 2017 at 11:07 AM, Mostafa Abdallah. Ammar <
mostafaammar at aast.edu> wrote:

>     ​Dear All,
>
>
> I am trying to measure  throughput between 2 hosts connected on P4
> simple_Switch, I used the iperf tool and used the heavy_hitter example. the
> measured throughput was 36.7 Mbps
>
> however when trying the same experiment on openvswitches the throughput
> was a lot higher.
>
>
>
>
> Best Regards,
>
> Eng. Mostafa Abdallah Ammar,Msc.
> Head of Information Security Department
> CCIE security #23971
> Arab Academy For Science And Technology & maritime Transport
> Computer Networks & Data Center (CNDC)
> Mobile: 002 01001983674
>
> _______________________________________________
> P4-dev mailing list
> P4-dev at lists.p4.org
> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
>



-- 
Antonin
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.p4.org/pipermail/p4-dev_lists.p4.org/attachments/20171011/8e8d15fe/attachment-0002.html>


More information about the P4-dev mailing list