Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[openflow-discuss] Traditional WLAN works better than openflow enabled OpenWRT

Sayed Qaiser Ali Shah 11msitqshah at seecs.edu.pk
Tue Mar 18 00:28:40 PDT 2014


Dear Andrew can you please provide me the link of "how to?"
 I have been through the link
https://github.com/zhengpenghou/openvswitchbut didn't get what to do.
I searched a lot but didn't find anything which
I can get help from.


On Mon, Mar 17, 2014 at 3:55 AM, Sayed Qaiser Ali Shah <
11msitqshah at seecs.edu.pk> wrote:

> Oh thanks didn't know about this. I will definitely this.
>
>
> On Mon, Mar 17, 2014 at 3:41 PM, Andrew Ferguson <adf at cs.brown.edu> wrote:
>
>>
>> On Mar 17, 2014, at 4:10 PM, Sayed Qaiser Ali Shah <
>> 11msitqshah at seecs.edu.pk> wrote:
>>
>> I am working with wireless networks and just want to confirm behavior of
>> Openflow enabled OpenWRT and Traditional WLAN.
>> I am using TP-Link 1043ND device with Openflow enabled OpenWRT and using
>> D-ITG Traffic Generator to generate different types of traffic. I defined
>> flows send that flows via Openflow enabled OpenWRT and check stats then I
>> used same flows for traditional WLAN and check stats. When I compare those
>> stats I got better performance for Traditional WLAN than WLAN with Openflow
>> enabled OpenWRT.
>> Can anybody tell what is the reason behind this? Why is openflow not
>> working better than Traditional WLAN in wireless scenarios?
>>
>>
>>
>> seems reasonable.  if you are using the Pantou image, then the 1043ND is
>> running the OpenFlow reference switch in user space, so it can be quite
>> slow, and it will be limited by the performance of the embedded CPU.
>>
>> if you need better performance, you could trying using Open vSwitch in
>> kernel space instead of the reference switch.  do a search for "openvswitch
>> openwrt" and you should see some promising results, although I haven't
>> tried any of those configurations myself.
>>
>>
>> good luck,
>> Andrew
>>
>
>
>
> --
>
>
>
>
> *Regards Sayed Qaiser Ali ShahMSIT-12 NUST (SEECS)*
>



-- 




*RegardsSayed Qaiser Ali ShahMSIT-12NUST (SEECS)*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/openflow-discuss/attachments/20140318/7a99a07b/attachment.html>


More information about the openflow-discuss mailing list