[Nfd-dev] NFD benchmarking results?

[John DeHart]

Chengyu,

The scripts are set up to run the installed version of nfd on ONL.
Right now that is still 0.1.0.

You can build your own version and modify the start_*.sh scripts to
use a local copy or update your PATH variable to point to your local 
nfd/nrd before
the installed version.

The repo is at
https://github.com/WU-ARL/NFD_Performance_Testing_on_ONL

I'll also see if I can find time to update ONL to the latest version of nfd.

John

On 8/5/14, 8:26 PM, Chengyu Fan wrote:
> John,
>
> There is a nfd task (http://redmine.named-data.net/issues/1819) 
> created for the forwarding benchmark, and I'll do it using your 
> script. Any suggestions?
>
>
> On Tue, Aug 5, 2014 at 7:11 PM, John DeHart <jdd at seas.wustl.edu 
> <mailto:jdd at seas.wustl.edu>> wrote:
>
>     Jeff,
>
>     As others have mentioned, I did some benchmarking on a very early
>     version of NFD.
>     I will try to re-run those tests when I get back from vacation.
>
>     Can  you describe what you are seeing?
>     Are the problems you are seeing always present or do they come and go?
>     Do you have problems if you are just using one node? For example,
>     if your producer
>     and consumer are both homed off REMAP, do you still have the problem?
>     Does the problem get worse as your producer and consumer are
>     farther apart?
>
>     John
>
>
>     On 8/5/14, 11:22 AM, Burke, Jeff wrote:
>>     Hi Junxiao,
>>
>>     Thanks.  I was aware of this tool but asking if any benchmarks
>>     had already been generated as part of the development and testing
>>     process?
>>
>>     Jeff
>>
>>     From: Junxiao Shi <shijunxiao at email.arizona.edu
>>     <mailto:shijunxiao at email.arizona.edu>>
>>     Date: Tue, 5 Aug 2014 09:20:27 -0700
>>     To: Jeff Burke <jburke at remap.ucla.edu <mailto:jburke at remap.ucla.edu>>
>>     Cc: "nfd-dev at lists.cs.ucla.edu
>>     <mailto:nfd-dev at lists.cs.ucla.edu>" <nfd-dev at lists.cs.ucla.edu
>>     <mailto:nfd-dev at lists.cs.ucla.edu>>
>>     Subject: Re: [Nfd-dev] NFD benchmarking results?
>>
>>         Hi Jeff
>>
>>         You may use ndn-traffic-generator
>>         <https://github.com/named-data/ndn-traffic-generator> to run
>>         benchmarks as you need.
>>         Please be sure to define a traffic pattern that reflects the
>>         reality of the application you are trying to model.
>>
>>         Contact John DeHart if you want generic benchmark results
>>         collected on ONL testbed.
>>
>>         Yours, Junxiao
>>
>>
>>         On Tue, Aug 5, 2014 at 8:46 AM, Burke, Jeff
>>         <jburke at remap.ucla.edu <mailto:jburke at remap.ucla.edu>> wrote:
>>
>>
>>             Hi,
>>
>>             We are trying to track down what is causing packet loss /
>>             delay when using ndnrtc over NFD.   We will prepare
>>             something to replicate the results later this week after
>>             the Cisco visit.  In the meantime, are there any
>>             benchmarks for NFD (on the testbed or not) that would
>>             give us some sense of packet processing times and
>>             expected throughput on various platforms in comparison to
>>             ndnx?  I seem to recall that there was some internal
>>             testing of this awhile ago.  If not, would it be possible
>>             for the NFD team to perform some basic benchmarks and
>>             comparisons?  This would help us troubleshoot this problem.
>>
>>             Thanks,
>>             Jeff
>>
>>
>>
>>     _______________________________________________
>>     Nfd-dev mailing list
>>     Nfd-dev at lists.cs.ucla.edu  <mailto:Nfd-dev at lists.cs.ucla.edu>
>>     http://www.lists.cs.ucla.edu/mailman/listinfo/nfd-dev
>
>
>     _______________________________________________
>     Nfd-dev mailing list
>     Nfd-dev at lists.cs.ucla.edu <mailto:Nfd-dev at lists.cs.ucla.edu>
>     http://www.lists.cs.ucla.edu/mailman/listinfo/nfd-dev
>
>
>
>
> -- 
> Thanks,
>
> Chengyu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.lists.cs.ucla.edu/pipermail/nfd-dev/attachments/20140806/db30b159/attachment.html>