DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 03BB220875
Subject: Re: [PATCH 0/5] rt2800mmio txdone/interrupts/flush rework
To:     Stanislaw Gruszka <sgruszka@redhat.com>,
        =?UTF-8?Q?Tomislav_Po=c5=beega?= <pozega.tomislav@gmail.com>
Cc:     linux-wireless@vger.kernel.org,
        Daniel Golle <daniel@makrotopia.org>,
        Mathias Kresin <dev@kresin.me>
References: <1537957497-7790-1-git-send-email-sgruszka@redhat.com>
 <1538697102-3764-1-git-send-email-pozega.tomislav@gmail.com>
 <20181005074422.GA1931@redhat.com>
From:   Felix Fietkau <nbd@nbd.name>
Openpgp: preference=signencrypt
Autocrypt: addr=nbd@nbd.name; prefer-encrypt=mutual; keydata=
 xsDiBEah5CcRBADIY7pu4LIv3jBlyQ/2u87iIZGe6f0f8pyB4UjzfJNXhJb8JylYYRzIOSxh
 ExKsdLCnJqsG1PY1mqTtoG8sONpwsHr2oJ4itjcGHfn5NJSUGTbtbbxLro13tHkGFCoCr4Z5
 Pv+XRgiANSpYlIigiMbOkide6wbggQK32tC20QxUIwCg4k6dtV/4kwEeiOUfErq00TVqIiEE
 AKcUi4taOuh/PQWx/Ujjl/P1LfJXqLKRPa8PwD4j2yjoc9l+7LptSxJThL9KSu6gtXQjcoR2
 vCK0OeYJhgO4kYMI78h1TSaxmtImEAnjFPYJYVsxrhay92jisYc7z5R/76AaELfF6RCjjGeP
 wdalulG+erWju710Bif7E1yjYVWeA/9Wd1lsOmx6uwwYgNqoFtcAunDaMKi9xVQW18FsUusM
 TdRvTZLBpoUAy+MajAL+R73TwLq3LnKpIcCwftyQXK5pEDKq57OhxJVv1Q8XkA9Dn1SBOjNB
 l25vJDFAT9ntp9THeDD2fv15yk4EKpWhu4H00/YX8KkhFsrtUs69+vZQwc0cRmVsaXggRmll
 dGthdSA8bmJkQG5iZC5uYW1lPsJgBBMRAgAgBQJGoeQnAhsjBgsJCAcDAgQVAggDBBYCAwEC
 HgECF4AACgkQ130UHQKnbvXsvgCgjsAIIOsY7xZ8VcSm7NABpi91yTMAniMMmH7FRenEAYMa
 VrwYTIThkTlQzsFNBEah5FQQCACMIep/hTzgPZ9HbCTKm9xN4bZX0JjrqjFem1Nxf3MBM5vN
 CYGBn8F4sGIzPmLhl4xFeq3k5irVg/YvxSDbQN6NJv8o+tP6zsMeWX2JjtV0P4aDIN1pK2/w
 VxcicArw0VYdv2ZCarccFBgH2a6GjswqlCqVM3gNIMI8ikzenKcso8YErGGiKYeMEZLwHaxE
 Y7mTPuOTrWL8uWWRL5mVjhZEVvDez6em/OYvzBwbkhImrryF29e3Po2cfY2n7EKjjr3/141K
 DHBBdgXlPNfDwROnA5ugjjEBjwkwBQqPpDA7AYPvpHh5vLbZnVGu5CwG7NAsrb2isRmjYoqk
 wu++3117AAMFB/9S0Sj7qFFQcD4laADVsabTpNNpaV4wAgVTRHKV/kC9luItzwDnUcsZUPdQ
 f3MueRJ3jIHU0UmRBG3uQftqbZJj3ikhnfvyLmkCNe+/hXhPu9sGvXyi2D4vszICvc1KL4RD
 aLSrOsROx22eZ26KqcW4ny7+va2FnvjsZgI8h4sDmaLzKczVRIiLITiMpLFEU/VoSv0m1F4B
 FtRgoiyjFzigWG0MsTdAN6FJzGh4mWWGIlE7o5JraNhnTd+yTUIPtw3ym6l8P+gbvfoZida0
 TspgwBWLnXQvP5EDvlZnNaKa/3oBes6z0QdaSOwZCRA3QSLHBwtgUsrT6RxRSweLrcabwkkE
 GBECAAkFAkah5FQCGwwACgkQ130UHQKnbvW2GgCfTKx80VvCR/PvsUlrvdOLsIgeRGAAn1ee
 RjMaxwtSdaCKMw3j33ZbsWS4
Message-ID: <363e4d1a-2a1f-2ab9-dad6-91d36fe38d53@nbd.name>
Date:   Fri, 5 Oct 2018 12:05:56 +0200
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:52.0)
 Gecko/20100101 Thunderbird/52.9.1
MIME-Version: 1.0
In-Reply-To: <20181005074422.GA1931@redhat.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 8bit
Sender: linux-wireless-owner@vger.kernel.org
Precedence: bulk

On 2018-10-05 09:44, Stanislaw Gruszka wrote:
> (adding back removed CCs)
> 
> On Fri, Oct 05, 2018 at 01:51:42AM +0200, Tomislav Požega wrote:
>> Hi
> 
> Hi.
> 
>> As suspected this changeset causes throughput regression.
> 
> You seems to have prejudice against my work :-)
> 
>> Below screenshots show iperf test from MS150N (RF5370) device connected to RT3070 adapter running AP mode:
>> 
>> This is with standard openwrt build without any rt2x00 changes:
>> 
>> [url=https://postimg.cc/BtYQLf6r][img]https://i.postimg.cc/BtYQLf6r/shot-2018-10-04_17-23-56.jpg[/img][/url]
>> 
>> And this printscreen show iperf test with your changes:
>> 
>> [url=https://postimg.cc/D8Sf1p48][img]https://i.postimg.cc/D8Sf1p48/shot-2018-10-04_17-42-09.jpg[/img][/url]
> 
> My experience is that performance between two rt2800 devices vary with
> no apparent reason. There are two problems I know that maigh affect
> performance at random (and I think there are also some other low level
> problems that I'm not aware of that cause performance fluctuations).
> 
> First problem is that HW aggregate RATE_PROBE frames with other frames
> at different rate, so we can not do rate probing properly for rate
> control algorithm.
I believe this is fixable. On MT76x2, I was able to use the QSEL field
in the DMA descriptor to force the hw to send it out as a single frame.
It is normally set to 2, you can set it to 0 for frames with
IEEE80211_TX_CTL_RATE_CTRL_PROBE set.
Theoretically, the same should also work on RT2800 devices.

> Second problem: we send BAR when we fail to send a frame and this might
> have positive and negative effect, depend what remote hardware do when it
> gets BAR. This seems to be problem when two rt2800 devices are connected
> and not a problem if rt2800 is connected with ath or iwl devices.
On the receiver side, BAR is typically processed in software. mac80211
handles that, so I don't think there is a lot of room for chipset
specific behavior here.

- Felix