All of lore.kernel.org
 help / color / mirror / Atom feed
* [ath9k-devel] Performance degradation when monitor mode interface is created
@ 2012-09-04  7:28 Ali Abedi
  2012-09-04 13:21 ` abhinav narain
  0 siblings, 1 reply; 3+ messages in thread
From: Ali Abedi @ 2012-09-04  7:28 UTC (permalink / raw)
  To: ath9k-devel

Hello,

In our experiments, we use iperf to saturate the wireless link. When we 
create the monitor mode interface on the "sender" client the throughput 
drops to 25Mbps from 29Mbps. The throughout is not affected if the 
monitor mode interface is created on the receiver client through. we 
have tried various versions of ATH9K but we observed the same behavior, 
Why the monitor mode interface on the sender client affects the 
throughput? Is this a bug? We are almost sure that this is not a 
performance limitation of our clients.

Thank you,
Ali Abedi

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [ath9k-devel] Performance degradation when monitor mode interface is created
  2012-09-04  7:28 [ath9k-devel] Performance degradation when monitor mode interface is created Ali Abedi
@ 2012-09-04 13:21 ` abhinav narain
  2012-09-04 13:43   ` Ali Abedi
  0 siblings, 1 reply; 3+ messages in thread
From: abhinav narain @ 2012-09-04 13:21 UTC (permalink / raw)
  To: ath9k-devel

monitor interface is a virtual interface. So, two interfaces are taking the
same physical resource and there is a context switch while going back and
forth !
This will decrease the throughput as the actual interface is getting less
time to sense the channel.
Thats what I think !
-
Abhinav Narain

On Tue, Sep 4, 2012 at 3:28 AM, Ali Abedi <a2abedi@uwaterloo.ca> wrote:

> Hello,
>
> In our experiments, we use iperf to saturate the wireless link. When we
> create the monitor mode interface on the "sender" client the throughput
> drops to 25Mbps from 29Mbps. The throughout is not affected if the
> monitor mode interface is created on the receiver client through. we
> have tried various versions of ATH9K but we observed the same behavior,
> Why the monitor mode interface on the sender client affects the
> throughput? Is this a bug? We are almost sure that this is not a
> performance limitation of our clients.
>
> Thank you,
> Ali Abedi
>
> _______________________________________________
> ath9k-devel mailing list
> ath9k-devel at lists.ath9k.org
> https://lists.ath9k.org/mailman/listinfo/ath9k-devel
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.ath9k.org/pipermail/ath9k-devel/attachments/20120904/02b27ec7/attachment.htm 

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [ath9k-devel] Performance degradation when monitor mode interface is created
  2012-09-04 13:21 ` abhinav narain
@ 2012-09-04 13:43   ` Ali Abedi
  0 siblings, 0 replies; 3+ messages in thread
From: Ali Abedi @ 2012-09-04 13:43 UTC (permalink / raw)
  To: ath9k-devel

So, why the monitor interface has no effect on the receiver client? What 
you mentioned should be true on the receiving side as well.

Thanks,
Ali

On 9/4/2012 9:21 AM, abhinav narain wrote:
> monitor interface is a virtual interface. So, two interfaces are 
> taking the same physical resource and there is a context switch while 
> going back and forth !
> This will decrease the throughput as the actual interface is getting 
> less time to sense the channel.
> Thats what I think !
> -
> Abhinav Narain
>
> On Tue, Sep 4, 2012 at 3:28 AM, Ali Abedi <a2abedi@uwaterloo.ca 
> <mailto:a2abedi@uwaterloo.ca>> wrote:
>
>     Hello,
>
>     In our experiments, we use iperf to saturate the wireless link.
>     When we
>     create the monitor mode interface on the "sender" client the
>     throughput
>     drops to 25Mbps from 29Mbps. The throughout is not affected if the
>     monitor mode interface is created on the receiver client through. we
>     have tried various versions of ATH9K but we observed the same
>     behavior,
>     Why the monitor mode interface on the sender client affects the
>     throughput? Is this a bug? We are almost sure that this is not a
>     performance limitation of our clients.
>
>     Thank you,
>     Ali Abedi
>
>     _______________________________________________
>     ath9k-devel mailing list
>     ath9k-devel at lists.ath9k.org <mailto:ath9k-devel@lists.ath9k.org>
>     https://lists.ath9k.org/mailman/listinfo/ath9k-devel
>
>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.ath9k.org/pipermail/ath9k-devel/attachments/20120904/07c61005/attachment.htm 

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2012-09-04 13:43 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-09-04  7:28 [ath9k-devel] Performance degradation when monitor mode interface is created Ali Abedi
2012-09-04 13:21 ` abhinav narain
2012-09-04 13:43   ` Ali Abedi

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.