perfsonar development work

[Stephan Kraft <>]

Hi Nemanja,

is it possible to have a look at this new PerfsonarUI  version?


Kind regards,

Stephan

Nemanja Zutic schrieb:
> Hi Nicolas,
>  
> Changes have been made to the BWCTL tab as proposed by point 1. of the
> PerfsonarUI - New Features page. For now, user can enter RTT manually
> or he can call for 2 ippm requests to be performed to retrieve
> the last known one way delay in each direction. Nina told us that the
> bwctl service and ippm service run on diferent machines so that this
> measurement may not be accurate. Often the calculated maximum BW is
> less than the measured BW. Is it possible that BWCTL returns the BW
> value on the physical layer while we are calculating the max BW on the
> transport layer or is the RTT measurement at fault? The formula we use
> is maxBW=(windowsize*8)/rtt where windowsize is in bytes and rtt in
> seconds.
>  
> Best regards,
>
> Nemanja Zutic
> Universitiy of Belgrade Computing Center


-- 
Dr. Stephan Kraft, DFN-Labor
Friedrich-Alexander-Universität Erlangen-Nürnberg
Regionales RechenZentrum Erlangen (RRZE)
Martensstraße 1, 91058 Erlangen, Germany
Tel. +49 9131 85-28735 -28800, Fax +49 9131 302941

www.win-labor.dfn.de