[Spread-users] Spread Performance Questions

[Daniel Marques]

Now its getting even more confusing.

On my system here, Java is not suffering the same Safe message penalty
that I'm seeing for C, i.e. the Java time for safe messages is about
what would be expected.


Java

message type 0 time 2 seconds and 625 milliseconds
message type 1 time 2 seconds and 563 milliseconds
message type 2 time 2 seconds and 609 milliseconds
message type 3 time 2 seconds and 594 milliseconds
message type 4 time 2 seconds and 594 milliseconds
message type 5 time 3 seconds and 500 milliseconds


C

msg type 0: elapsed time is 2 second 562000 milliseconds
msg type 1: elapsed time is 2 second 531000 milliseconds
msg type 2: elapsed time is 2 second 578000 milliseconds
msg type 3: elapsed time is 2 second 532000 milliseconds
msg type 4: elapsed time is 2 second 515000 milliseconds
msg type 5: elapsed time is 126 second 344000 milliseconds

Where the message types are as follows:
					    case 0:
						message.setUnreliable();
						break;
					    case 1:
						message.setReliable();
						break;
					    case 2:
						message.setFifo();
						break;
					    case 3:
						message.setCausal();
						break;
					    case 4:
						message.setAgreed();
						break;
					    case 5:
						message.setSafe();
						break;


Does anyone have any idea of why this could be?

Dan



On 7/26/07, Daniel Marques <marques77 at gmail.com> wrote:
> Thanks for testing.  I'll wait until we have a supported environment
> up and running and try again.
>
> I was mainly interested in seeing the results you presented.
>
> Thanks.
>
> On 7/26/07, Jacob Green <jgreen at spreadconcepts.com> wrote:
> > Tried your code you sent on 2 machines here and can't reproduce your
> > results. 1024 messages each round for each msg service type.
> >
> > Message type 5 == safe msg
> >
> > For 1K:
> > msg type 0: elapsed time is 0 second 510353 miliseconds
> > msg type 1: elapsed time is 0 second 444963 miliseconds
> > msg type 2: elapsed time is 0 second 451711 miliseconds
> > msg type 3: elapsed time is 0 second 498556 miliseconds
> > msg type 4: elapsed time is 0 second 536050 miliseconds
> > msg type 5: elapsed time is 1 second 16429 miliseconds
> >
> > For 8K:
> > msg type 0: elapsed time is 0 second 916291 miliseconds
> > msg type 1: elapsed time is 0 second 848697 miliseconds
> > msg type 2: elapsed time is 0 second 850083 miliseconds
> > msg type 3: elapsed time is 0 second 851529 miliseconds
> > msg type 4: elapsed time is 0 second 899387 miliseconds
> > msg type 5: elapsed time is 1 second 763684 miliseconds
> >
> > Jacob
> >
> > -----Original Message-----
> > From: spread-users-bounces at lists.spread.org
> > [mailto:spread-users-bounces at lists.spread.org] On Behalf Of John Lane
> > Schultz
> > Sent: Thursday, July 26, 2007 3:40 PM
> > To: spread-users at lists.spread.org
> > Subject: Re: [Spread-users] Spread Performance Questions
> >
> > We will take a look and see if we can reproduce and diagnose the issue here.
> >
> > Daniel Marques wrote:
> > > Yes, this behavior is consistent.
> > >
> >
> > Cheers!
> >
> > --
> > John Schultz
> > Spread Concepts LLC
> > Phn: 443 838 2200
> > Fax: 301 560 8875
> >
> > _______________________________________________
> > Spread-users mailing list
> > Spread-users at lists.spread.org
> > http://lists.spread.org/mailman/listinfo/spread-users
> >
> >
> > _______________________________________________
> > Spread-users mailing list
> > Spread-users at lists.spread.org
> > http://lists.spread.org/mailman/listinfo/spread-users
> >
>