[Make-wifi-fast] Netpower, iper2, BBR

[Bob McMahon]

Another interesting paper with a power metric.

Bob

On Sat, Aug 4, 2018 at 5:10 PM, Bob McMahon <bob.mcmahon at broadcom.com>
wrote:

> It's a metric to determine if network congestion is being optimized.
> Here's just one of many papers that use.  This paper says that flow
> controlled, per network power, can't be optimized with local information
> only.
>
> Bob
>
> On Sat, Aug 4, 2018 at 3:47 PM, Jeremy Harris <jgh at wizmail.org> wrote:
>
>> On 08/04/2018 06:55 PM, Bob McMahon wrote:
>> > FYI, I've added a netpower metric to iperf 2.
>> >
>> > Below are two runs over wired GigE comparing Google's BBR
>> > <https://ai.google/research/pubs/pub45646> with cubic.  Note, for the
>> > network power the delay units are microseconds while the throughput are
>> > seconds.
>>
>> Why is it useful?
>>
>> It appears to be calculated as bandwidth divided by latency, so the
>> units are bits / time^2.  The word "power" in the naming feels
>> misleading.
>> --
>> Cheers,
>>   Jeremy
>>
>> _______________________________________________
>> Make-wifi-fast mailing list
>> Make-wifi-fast at lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/make-wifi-fast
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/make-wifi-fast/attachments/20180804/ba6ea0b9/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Internet Congestion Control Using the Power Metric-Keep the Pipe Just Full, But No Fuller July 2018.pdf
Type: application/pdf
Size: 3845380 bytes
Desc: not available
URL: <https://lists.bufferbloat.net/pipermail/make-wifi-fast/attachments/20180804/ba6ea0b9/attachment-0001.pdf>