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    

[mininet-discuss] Scalability

Philip Wette wette at mail.upb.de
Thu Apr 3 05:15:27 PDT 2014


As all the emulated switches are sharing the CPU of your vm they are competing for cycles. As long as your vm has enough cycles left during your experiment everything should be fine. However, if the vm runs at more than let's say 80% you can't really be sure that the obtained results are valid. 

The most simple way to get around this is to use the concept of time dilation. However, if you still need more computational power, you should have a look at maxinet which is a distributed version of mininet. 

http://www.cs.uni-paderborn.de/fachgebiete/fachgebiet-rechnernetze/people/philip-wette-msc/maxinet.html

Best,

Philip

Von meinem iPhone gesendet

> Am 03.04.2014 um 13:49 schrieb habib allah khosravi <habiballah_khosravi at yahoo.com>:
> 
> Excuse me, Can I create very big topologies in a VM with limited resources? Are the results valid in such invironment?
> On Tuesday, April 1, 2014 3:47 PM, habib allah khosravi <habiballah_khosravi at yahoo.com> wrote:
> Hi.
> I am using mininet in a VM. I need to know according my host computer's CPU and the resources given to the VM, how many switches or hosts I can have or how much bandwidth I can give to the links. Is there a way to calculate this?
>  
> Thanks
> Habib Allah Khosravi
> 
> 
> _______________________________________________
> mininet-discuss mailing list
> mininet-discuss at lists.stanford.edu
> https://mailman.stanford.edu/mailman/listinfo/mininet-discuss
> 
> 
> _______________________________________________
> mininet-discuss mailing list
> mininet-discuss at lists.stanford.edu
> https://mailman.stanford.edu/mailman/listinfo/mininet-discuss
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/mininet-discuss/attachments/20140403/318a6423/attachment.html>


More information about the mininet-discuss mailing list