Received-SPF: pass (google.com: best guess record for domain of linux-wireless-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
To:     Felix Fietkau <nbd@nbd.name>, linux-wireless@vger.kernel.org
Cc:     johannes@sipsolutions.net
Subject: Re: [PATCH 2/2] mac80211: minstrel_ht: replace rate stats ewma with a better moving average
In-Reply-To: <b2566142-a7ea-50e8-e683-a3702b75ea6f@nbd.name>
References: <20190929154646.90901-1-nbd@nbd.name> <20190929154646.90901-2-nbd@nbd.name> <87zhinx7u7.fsf@toke.dk> <b2566142-a7ea-50e8-e683-a3702b75ea6f@nbd.name>
Date:   Sun, 29 Sep 2019 21:46:28 +0200
Message-ID: <87k19qyjfv.fsf@toke.dk>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Sender: linux-wireless-owner@vger.kernel.org
Precedence: bulk

Felix Fietkau <nbd@nbd.name> writes:

> On 2019-09-29 20:42, Toke H=C3=B8iland-J=C3=B8rgensen wrote:
>> Felix Fietkau <nbd@nbd.name> writes:
>>=20
>>> Rate success probability usually fluctuates a lot under normal conditio=
ns.
>>> With a simple EWMA, noise and fluctuation can be reduced by increasing =
the
>>> window length, but that comes at the cost of introducing lag on sudden
>>> changes.
>>>
>>> This change replaces the EWMA implementation with a moving average that=
's
>>> designed to significantly reduce lag while keeping a bigger window size
>>> by being better at filtering out noise.
>>>
>>> It is only slightly more expensive than the simple EWMA and still avoid=
s
>>> divisions in its calculation.
>>>
>>> The algorithm is adapted from an implementation intended for a complete=
ly
>>> different field (stock market trading), where the tradeoff of lag vs
>>> noise filtering is equally important. It is based on the "smoothing fil=
ter"
>>> from http://www.stockspotter.com/files/PredictiveIndicators.pdf.
>>>
>>> I have adapted it to fixed-point math with some constants so that it us=
es
>>> only addition, bit shifts and multiplication
>>>
>>> To better make use of the filtering and bigger window size, the update
>>> interval time is cut in half.
>>>
>>> For testing, the algorithm can be reverted to the older one via
>>> debugfs
>>=20
>> This looks interesting! Do you have any performance numbers from your
>> own testing to share? :)
> To show the difference, I also generated some random data, ran it
> through minstrel's EWMA and the new code and made a plot:
> http://nbd.name/ewma-filter-plot.png

Oh, wow, yeah, that looks way more responsive...

> The real world test that I did was using mt76x2:
> I ran 3 iperf TCP streams from an AP to a station in a cable setup with
> an attenuator.
> I switched from 70 dB attenuation to 40 dB and measured the time it
> takes for TCP throughput to stabilize at a higher rate.
> Without my changes it takes about 5-6 seconds, with my changes it's only
> 2-3 seconds.

Very cool. Thanks!

-Toke