ath9k-devel.lists.ath9k.org archive mirror
 help / color / mirror / Atom feed
From: <bogus@does.not.exist.com>
To: ath9k-devel@lists.ath9k.org
Subject: No subject
Date: Fri, 24 Sep 2010 14:53:54 -0000	[thread overview]
Message-ID: <mailman.18.1289553679.6785.ath9k-devel@lists.ath9k.org> (raw)

Like you said, it is low because both interfaces share the medium but if I don??t change the rate using iwconfig, this values or at least the first one goes down until 1,5 MBits. That??s way I wonder if there is something that keeps the rate low by the time a virtual interface is created. 

Thanks for your response

Best regards

Lorna 


-------- Original-Nachricht --------
> Datum: Thu, 11 Nov 2010 09:00:45 -0800
> Von: Ben Greear <greearb@candelatech.com>
> An: "Lorna Gonz??lez" <lorna.glez@gmx.net>
> CC: Jouni Malinen <jouni.malinen@atheros.com>, ath9k-devel at venema.h4ckr.net
> Betreff: Re: [ath9k-devel] ath9k: Virtual interface as AP

> On 11/11/2010 07:06 AM, "Lorna Gonz??lez" wrote:
> >
> > Hello
> >
> > I finally got a station an a virtual AP working on the same channel
> using the setup below. I made some test sending TCP through iperf between the
> AP and the station and the VAP to a station associated with it.
> > Using an AP operating with Ieee802.11n, an atheros AR928X and without
> virtual interfaces I get a max throughput of 50 MBits/s.
> > As soon as I start using my desired setup, the thoughput of the station
> is about 15 MBits/s... I actually need to make the rate fixed using
> iwconfig to get this max. Otherwise the traffic is sent at 1 MBit/s.
> >
> > Can someone please tell me how is the behaviour of the rate control in
> case of virtual interfaces on mac80211?
> 
> Can you give a more detailed description/diagram of your virtual AP setup
> and
> network throughput test?  It sounds like you are using the same radio as
> AP
> and STA?  If so, then of course you are going to get less bandwidth on the
> VIFS because they have to share the radio.
> 
> I'm not sure it should drop all the way to 15Mbps, though.  We haven't
> done a lot of throughput
> testing yet, but if we use two STA vifs on the ath9k box connected to an
> 80211n AP (trendnet),
> then we can set a max of about 9Mbps tx + rx across each STA (the STAs are
> sending to each other).
> That is around 40Mbps total tx + rx across the radio.
> 
> Thanks,
> Ben
> 
> -- 
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc  http://www.candelatech.com
> 

-- 
Neu: GMX De-Mail - Einfach wie E-Mail, sicher wie ein Brief!  
Jetzt De-Mail-Adresse reservieren: http://portal.gmx.net/de/go/demail

             reply	other threads:[~2010-09-24 14:53 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-24 14:53 bogus [this message]
  -- strict thread matches above, loose matches on Subject: below --
2016-11-19 18:31 No subject bogus
2016-11-19 18:31 bogus
2016-11-19 18:31 bogus
2016-11-19 18:31 bogus
2016-06-13  6:24 bogus
2016-06-13  6:24 bogus
2016-02-09  7:29 bogus
2015-11-16 16:13 bogus
2015-10-12 17:26 bogus
2014-09-13 19:40 bogus
2014-09-13 19:40 bogus
2014-09-13 19:40 bogus
2014-09-13 19:40 bogus
2014-09-13 19:40 bogus
2013-09-15  9:49 bogus
2013-09-15  9:49 bogus
2013-09-15  9:49 bogus
2013-04-03 10:31 bogus
2013-04-03 10:31 bogus
2013-04-03 10:31 bogus
2013-04-03 10:31 bogus
2013-01-16 21:46 bogus
2013-01-16 21:46 bogus
2012-11-08  9:33 bogus
2012-05-25 15:26 bogus
2012-05-25 15:26 bogus
2012-04-05  7:54 bogus
2012-04-05  7:54 bogus
2012-02-27  5:00 bogus
2012-02-27  5:00 bogus
2012-02-27  5:00 bogus
2012-01-15  8:24 bogus
2011-11-12 14:39 bogus
2011-11-12 14:39 bogus
2011-08-05  3:08 bogus
2011-08-05  3:08 bogus
2011-08-05  3:08 bogus
2011-08-05  3:08 bogus
2011-08-05  3:08 bogus
2011-06-04 23:16 bogus
2011-06-04 23:16 bogus
2011-04-07  5:55 bogus
2011-04-07  5:55 bogus
2011-04-07  5:55 bogus
2011-04-07  5:55 bogus
2011-04-07  5:55 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-12-19 23:59 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-09-24 14:53 bogus
2010-07-23 10:05 bogus
2010-03-25 17:02 bogus
2010-03-25 17:02 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-27 19:01 bogus
2009-02-15  8:49 bogus
2009-01-04 17:33 bogus
2009-01-04 17:33 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-10-14 11:50 bogus
2008-07-28  4:41 bogus

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=mailman.18.1289553679.6785.ath9k-devel@lists.ath9k.org \
    --to=bogus@does.not.exist.com \
    --cc=ath9k-devel@lists.ath9k.org \
    /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;
as well as URLs for NNTP newsgroup(s).