Newsgroups: comp.parallel.pvm
From: crispin@csd.uwo.ca (Crispin Cowan)
Subject: Re: Questions on communication times
Organization: Department of Computer Science, University of Western Ontario, London, Ontario, Canada
Date: 6 Jun 1994 14:09:00 GMT
Message-ID: <2svals$sbo@falcon.ccs.uwo.ca>

In article <2sunic$h6f@serra.unipi.it>,
Nicola Menchiari <menchiar@di.unipi.it> wrote:
>We implemented a program in C-code which simulates a pharmacokinetic model.
...
>The system that we used is composed of two SUN 4 workstations interconnected
>by way of an ethernet network (10 Mbit/s).
...
>with l = latency or delay incurred in communicating a message on the network, 
>     o = overhead, defined as the length of time that a processor is engaged 
>         in the trasmission or reception of each message,
>we estimated, considering the characteristics of the network and the running 
>times of the program,  
>  l ~= 0.5 ms
>  o ~= 0.6 ms .

These strike me as highly unrealistic estimates.  They are low just for
the Ethernet physical layer, even without the overhead of UNIX sockets
and PVM software.  Just running the timing example included in the
distribution shows a cost of 20 ms to send a minimal message between
a Sun 3 and a Sun 4 on our ethernet.

Crispin
-----
Crispin Cowan, CS PhD student, searching for a research position
University of Western Ontario
Phyz-mail:  Middlesex College, MC28-C, London, Ontario, N6A 5B7
E-mail:     crispin@csd.uwo.ca          Voice:  519-661-3342
"A distributed system is one in which I cannot get something done
because a machine I've never heard of is down"   --Leslie Lamport

