ndt-users list created

[Rich Carlson <>]

Hi Justin;

I think I'll need more info.  Please run the server process with the 
--snaplog and --tcpdump options.  Also on the client side start a 
tcpdump on ports 3002 and 3003.  Then send a tarball directly to me with 
these files.  I'll see if I can understand what is going on.

Rich

On 10/7/2010 5:20 PM, Hao, Justin C wrote:
> Howdy Rich,
>
> So we have moved our 10Gig NDT servers into a production environment 
> (connected via Cisco Nexus 5k and 7k switches) and we're still seeing the odd 
> asynch results from ndt.  Server 1 is running ndt 3.6.3 and Server 2 is 
> running ndt 3.6.4.  Each server has identical tcp configurations and 
> hardware.  And as you can see in the attached results C2S is close to 10Gig 
> as expected, but S2C in each case is not.  Let me know if you'd like me to 
> test any changes on the servers to improve the ndt results or provide 
> additional debugging information, thanks!