[P4-dev] Maximum queue Length in simple switch bmv2

Vikas Kumar mailvikasnow at gmail.com
Sat Mar 24 05:37:56 EDT 2018


Thanks Antonin. Is it possible to identify and get a count of packets of a
particular flow that are present in the egress port queue?


‌
<https://mailtrack.io/> Sent with Mailtrack
<https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality&>

On Sat, Mar 24, 2018 at 2:57 AM, Antonin Bas <antonin at barefootnetworks.com>
wrote:

> It's a software queue and there is no hard-coded limit, you can grow it as
> much as your memory allows. There is also no dependency on the packet sizes.
> Obviously good buffering practices should apply when picking the queue
> sizes: very deep queues impact latency.
>
> On Fri, Mar 23, 2018 at 12:28 PM, Vikas Kumar <mailvikasnow at gmail.com>
> wrote:
>
>> Hello everyone,
>>
>> I want to know what is the Maximum Queue length possible in the per
>> egress port buffer for the simple_switch ? Also does this depend on the
>> packet size?
>>
>> Thanks
>> --
>>
>>
>> <http://moodi.org/>
>> *Vikas Kumar | ** Hospitality & PR Coordinator*
>> *Mood Indigo, IIT Bombay*
>> *+91-9694532954 <+91%2096945%2032954> | mailvikasnow at gmail.com
>> <mailvikasnow at gmail.com>*
>> [image: Facebook] <https://www.facebook.com/vikas.cse.iitb>
>>
>>>> <https://mailtrack.io/> Sent with Mailtrack
>> <https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality&>
>>
>> _______________________________________________
>> P4-dev mailing list
>> P4-dev at lists.p4.org
>> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
>>
>
>
>
> --
> Antonin
>



-- 


<http://moodi.org/>
*Vikas Kumar | ** Hospitality & PR Coordinator*
*Mood Indigo, IIT Bombay*
*+91-9694532954 | mailvikasnow at gmail.com <mailvikasnow at gmail.com>*
[image: Facebook] <https://www.facebook.com/vikas.cse.iitb>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.p4.org/pipermail/p4-dev_lists.p4.org/attachments/20180324/5a306dfb/attachment-0001.html>


More information about the P4-dev mailing list