🚀 go-pugleaf

From the web site:
>Q: How fast can messages be sent between applications? 
>A: We've timed this at about 1000 messages/replies per second. Of course,
>this will vary with the time you need to spnd actually
>processing the message, but raw send/recieves are fast. 

Thank you for caring about the speed of operations like this.  I hope
you will take the following criticism in the positive vein in which it
is offered.  :-)

On the Amiga, under SHADOW, I believe I got upwards of 2500 messages per
second on a 25Mhz 68030.  This is from memory, and I apologize if it's
not exactly correct.  However, it was well over the 1000 you've gotten.  I
suspect there's some work you need to do.

Understand, this example is not equivalent to the raw send/receive test
you've done on the Be.  It wouldn't be entirely fair that way either,
considering you've got a few more things to take into account.  The
messaging as tested does full resource tracking on the contents (which
would minimally consist of the object, class, the method id which is a
UID implemented as a pointer to a string, and a few other structure
pointers which need to be copied or otherwise USE()d).  The messaging
is asynchronous, so there's no funky re-use of allocated message
structures that one can get away with using synchronous delivery.  And the
message ports are a "protected"/"sanitized" variety (ppIPC) so that the
port destination is guaranteed (none of this Forbid()/Permit() single-
threading nonsense that ARexx uses).

If it sounds like the messages are going through several delivery layers in
this comparison -- you'd be correct.  The test is actually invoking a
method, which ends up delivering an asynchronous message and invoking the
function at the destination port.  Which is why your number looks
disconcertingly low.  I understand you have to possibly deal with crossing
a process/memory-space boundary.  Even so you're using a far more powerful
CPU at a far faster speed.

Have you researched what things are taking up the most time?

Once again, I appreciate the numbers and the obvious care that was taken
to collect them in the first place.

-- 
David Navas  jazz@netcom.com  dnavas@us.oracle.com     P11 -- your "friend"
Minbari: "bonehead" will never mean the same thing again. (season 1)
Minbari: Things are getting hairy on Babylon 5.           (season 2)