From: "Luis R. Rodriguez" <mcgrof@gmail.com>
To: "Tomas Winkler" <tomasw@gmail.com>
Cc: "Johannes Berg" <johannes@sipsolutions.net>,
Sujith <Sujith.Manoharan@atheros.com>,
"linville@tuxdriver.com" <linville@tuxdriver.com>,
"linux-wireless@vger.kernel.org" <linux-wireless@vger.kernel.org>,
"Luis Rodriguez" <Luis.Rodriguez@atheros.com>
Subject: Re: [RFC] mac80211: Re-enable aggregation
Date: Thu, 23 Oct 2008 13:18:44 -0700 [thread overview]
Message-ID: <43e72e890810231318t2ef200e4wed96b48efefa62bb@mail.gmail.com> (raw)
In-Reply-To: <1ba2fa240810231131l9c9597au2acf166a13a8c03b@mail.gmail.com>
On Thu, Oct 23, 2008 at 11:31 AM, Tomas Winkler <tomasw@gmail.com> wrote:
> On Thu, Oct 23, 2008 at 7:23 PM, Luis R. Rodriguez <mcgrof@gmail.com> wrote:
>> I checked internally to verify where you would decide when to AMPDU
>> and to try to get different reviews and opinions, and it seems that
>> the path we take right now is correct as there is not much overhead so
>> we always use AMPDU with whoever supports it with data frames. If
>> you're a STA you do it all the time with the AP for data frames.
>>
>> I noticed iwlagn had some more logic within the RC but I gave up
>> trying to follow the logic. I suspect they do the same though, Tomas?
Thanks for the feedback!
> I got different output from our system engineering. APMDU has overhead
Is that because of the interactions required in firmware for scheduling BTW?
> and if there is not requirement
> for high throughput we don't initiate one.
This makes sense to me regardless.
> What is for sure we shounld
> not have aggregation enabled for VO AC.
Any particular reason? I'll review this too, but my guess would be the
buffering required before TXing. I'll see how we perform with aggr on
VO AC.
> I've payed attention that there are different APs do that differently
> some opens BA session on BE AC immediately upon association some do it
> on high throughput I haven't seen in the second case it will be opened
> on simple ping.
> Anyhow if we would implement the triggering on throughput simply
> setting starting and stopping thresholds to small values will have
> same effect as your solution and setting it to 0 and maximum will
> respectively will have effect on opening BA session upon association.
Seems reasonable. If this is set then as a hw configurable option in
mac80211 then we can even allow RC control this, should this ever be
needed (we don't).
Luis
next prev parent reply other threads:[~2008-10-23 20:18 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-20 8:22 [RFC] mac80211: Re-enable aggregation Sujith
2008-10-20 8:31 ` Johannes Berg
2008-10-20 8:35 ` Luis R. Rodriguez
2008-10-20 8:45 ` Johannes Berg
2008-10-20 8:47 ` Sujith
2008-10-20 8:55 ` Luis R. Rodriguez
2008-10-20 8:57 ` Johannes Berg
2008-10-20 9:01 ` Luis R. Rodriguez
2008-10-20 9:04 ` Johannes Berg
2008-10-20 9:05 ` Luis R. Rodriguez
2008-10-20 9:11 ` Sujith
2008-10-20 8:57 ` Luis R. Rodriguez
2008-10-20 8:58 ` Sujith
2008-10-20 9:12 ` Johannes Berg
2008-10-20 9:31 ` Sujith
2008-10-20 9:38 ` Johannes Berg
2008-10-20 10:35 ` Sujith
2008-10-20 12:22 ` Johannes Berg
2008-10-20 18:03 ` Sujith
2008-10-20 21:46 ` Tomas Winkler
2008-10-21 6:46 ` Johannes Berg
2008-10-21 7:18 ` Sujith
2008-10-22 10:03 ` Johannes Berg
2008-10-22 11:59 ` Tomas Winkler
2008-10-22 17:22 ` Johannes Berg
2008-10-23 8:57 ` Sujith
2008-10-23 14:46 ` Johannes Berg
2008-10-27 14:25 ` Sujith
2008-10-27 15:04 ` Johannes Berg
2008-10-27 15:56 ` Tomas Winkler
2008-10-27 16:04 ` Johannes Berg
2008-10-28 14:24 ` Tomas Winkler
2008-10-22 10:00 ` Johannes Berg
2008-10-22 11:41 ` Tomas Winkler
2008-10-22 17:24 ` Johannes Berg
2008-10-23 9:31 ` Sujith
2008-10-23 14:45 ` Johannes Berg
2008-10-23 17:23 ` Luis R. Rodriguez
2008-10-23 18:31 ` Tomas Winkler
2008-10-23 20:18 ` Luis R. Rodriguez [this message]
2008-10-23 21:17 ` Tomas Winkler
2008-10-31 1:26 ` Luis R. Rodriguez
2008-10-27 14:11 ` Sujith
2008-10-27 15:07 ` Johannes Berg
2008-10-20 9:14 ` Luis R. Rodriguez
2008-10-20 9:24 ` Johannes Berg
2008-10-20 10:07 ` Sujith
2008-10-20 10:15 ` Johannes Berg
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=43e72e890810231318t2ef200e4wed96b48efefa62bb@mail.gmail.com \
--to=mcgrof@gmail.com \
--cc=Luis.Rodriguez@atheros.com \
--cc=Sujith.Manoharan@atheros.com \
--cc=johannes@sipsolutions.net \
--cc=linux-wireless@vger.kernel.org \
--cc=linville@tuxdriver.com \
--cc=tomasw@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox