[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [ns] link capacity



Hi Lloyd
 I believe that the 'r' events in the trace file show
the time that the first bit of the packets received.

Best regards
Meow


--- Lloyd Wood <[email protected]> wrote:
> On Thu, 29 Nov 2001, H�kan Bystr�m wrote:
> 
> > With a bandwidth of only 5000 bits/s it takes 0.32
> seconds to send a 200
> > byte packet. You have to take this into account
> when calculating the
> > total bits sent within a second since the trace
> file only shows the time
> > when the packet is sent. Am I making myself clear?
> The last packet you
> > added into the total probably had not completely
> been sent within the
> > second.
> 
> but if you're working off r events in the tracefile
> this doesn't
> matter, right? The tracefile also shows when the
> packet is received...
> 
> L.
> 
> > Meow Chiow Chia wrote:
> >
> > >     I have a question.  In my simulation, a link
> > > between node 0 and node 1 has a bandwith of 5000
> > > bits/s, but if I checked the trace file, I
> noticed
> > > that the total number bits that are departured 
> to the
> > > link from the output queue of node 0 (assuming
> traffic
> > > from node 0 to node 1) within one second,
> actually
> > > exceeded 5000bits/sec, i.e. is about 5120
> bits/sec.  I
> > > am just wondering if anyone could tell me the
> reason
> > > of this .  Your help on this is very much
> appreciated.
> > >
> > > p/s:  I set a very huge queue limit, so that
> there is
> > > no buffer overflow
> 
>
<[email protected]>PGP<http://www.ee.surrey.ac.uk/Personal/L.Wood/>
> 


__________________________________________________
Do You Yahoo!?
Yahoo! GeoCities - quick and easy web site hosting, just $8.95/month.
http://geocities.yahoo.com/ps/info1