[Spread-users] spread performance testing

Ryan Caudy caudy at jhu.edu
Tue Feb 25 23:33:55 EST 2003

Check the archives for this list; I recall seeing such numbers in the 
past.  However, in order to do some testing of your own, examine the 
spflooder program included with Spread.  The source is in flooder.c 
(which may be under the daemon directory, depending on what you 
downloaded).  You can use this to push a large number of packets of some 
specified size through spread using multiple senders/receivers.  Only 
small modifications to the code should be necessary to add timing and 
other data gathering.  Alternatively, you could write your own very 
simple application to do approximately the same thing... one key thing 
you might consider, if you do so, is making sure the set of 
sending/receiving nodes waits until all other nodes have been started 
and joined some specified group before they begin the experiment.

Just to give you something rough to know if you're on the right track 
with your own testing, I ran a quick test of my own, using spflooder and 
the unix time command.  With two spread daemons running on different 
machines (on a 100 Mbit ethernet), a receive-only spflooder on one 
machine, and a send/receive spflooder on the other, I sent 10000 packets 
of 1000 bytes each in 0.928 seconds.  Running several such tests in an 
automated fashion should give you a decent average, but the result of 
the time command will always be a little higher than simply the 
transmission and receipt time for the messages, since it measures total 
process execution time.  So, I would suggest embedding gettimeofday() 
calls in the code.

If you do generate such results, let us know what you found.  Also, I'd 
be interested to hear what kind of application you're building.

Good luck,
Ryan Caudy

jayesh wrote:

>i'm currently doing my masters thesis and a part of developing my project (a
>collaborative application) is implementing SPREAD into the application to
>serve as a multicast communication. My question is has anyone done any kind
>of performance / network / bandwidth / packet , testing on spread and a
>comparison with other network (internal and external networks). If yes can
>anyone share those results with me. The reason i need those results is to
>show prove to my supervisor that spread is better so that i can proceed in
>developing my project. If no results are available can anyone please guide
>me on how to get one. Thanks.
>Spread-users mailing list
>Spread-users at lists.spread.org

More information about the Spread-users mailing list