On Sun, Dec 27, 2009 at 10:21 PM, Marc Herbert <marc.herb...@free.fr> wrote:
> 2009/12/26 Karthik Balaguru <karthikbalagur...@gmail.com>: > > I wonder why Iperf uses 1024*1024 for megabytes and 1000*1000 for > megabits ? > > > > I think, It should follow either 1000 * 1000 (International System of > > Units)convention or 1024 *1024 convention. > > Any specific reason for such a methodology ? Any ideas ? > > I think the historical reason is that memory relies on binary > addresses while telecommunication does not. > > A byte is by definition the smallest addressable unit of memory, > typically an octet. On the other hand, many wires are just pushing an > un-interrupted stream of bits. I guess that is why memory is usually > measured in *bytes* while throughput is often measured in *bits/s*. > > Memory addresses are binary. Take for instance a memory address with > 10 bits: it ranges from 0 to 1111111111 (1023). Since this is > accidentally very close to 1000, memory people have historically > abused the "kilo" prefix to mean 1024. While telecommunication people > have stick to the correct meaning. > > I'm afraid the "kibi" and "mebi" prefixes come too late. Would iperf > for instance switch to them where appropriate? > Yes, this confusion could be avoided and i think iPerf can upgrade this in its upcoming release. Would iPerf be upgrading it ? Thx in advans, Karthik Balaguru
------------------------------------------------------------------------------ This SF.Net email is sponsored by the Verizon Developer Community Take advantage of Verizon's best-in-class app development support A streamlined, 14 day to market process makes app distribution fast and easy Join now and get one step closer to millions of Verizon customers http://p.sf.net/sfu/verizon-dev2dev
_______________________________________________ Iperf-users mailing list Iperf-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/iperf-users
