POV-Ray : Newsgroups : povray.unix : Multi-machine rendering... Server Time
28 Jul 2024 18:26:26 EDT (-0400)
  Multi-machine rendering... (Message 11 to 17 of 17)  
<<< Previous 10 Messages Goto Initial 10 Messages
From: Adrien Beau
Subject: Re: Multi-machine rendering...
Date: 23 Oct 2000 03:40:23
Message: <39F3EB2B.CEE5B259@free.fr>
Simon Lemieux wrote:
> 
> Yes, that's what I thought...  I'll be looking for old used Pentiums instead!

I think it'll be much better.
How many machines do you think you can host?


Post a reply to this message

From: Simon Lemieux
Subject: Re: Multi-machine rendering...
Date: 23 Oct 2000 08:44:47
Message: <39F43344.3ED25F8E@yahoo.com>
> I think it'll be much better.
> How many machines do you think you can host?

I can host as many as I find 'em... The problem is to pay them... and for now,
I'd say none!  But I could easily host a dozen pentiums, make them a super
computer with Mosix and then I'd work on my CGI script to make another POV-Ray
render farm available for all on the net!

-- 
+-------------------------+----------------------------------+
| Simon Lemieux           | Website : http://www.666Mhz.net  |
| Email : Sin### [at] 666Mhznet | POV-Ray, OpenGL, C++ and more... |
+-------------------------+----------------------------------+


Post a reply to this message

From: Frank Nikolajsen
Subject: Re: Multi-machine rendering...
Date: 25 Oct 2000 17:14:02
Message: <39F74D98.E991ACAC@warpspace.com>
Simon Lemieux wrote:
> 
> > You can still do a lot of things with such machines, but I don't think
> > rendering is one of them, unless you get several dozens of such PCs and
> > have the space at home to set-up such a rendering farm (and watch for
> > the electricity bill!).
> 
> Yes, that's what I thought...  I'll be looking for old used Pentiums instead!
> 
> Thanks,
>         Simon

  Just want to add my 2 cents in this discussion.

  I also considered salvaging older machines to do the grunt work for
me, and came to the conclusion that for me it wasn't worth it. If an
individual doesn't have the finances for buying any new hardware, then
it might be a good idea, as old hardware is certainly better than none.

  What I did realize however, was that todays machines are *so* much
faster than even the P100's or so of yesteryear, that it will take a
bunch of them to compete.

  A P133 scores around 50 of the infamous Linux BogoMips, while a
PII-350 comes in at 700. This is not the whole story obviously, but it
shows what you are up against. In addition to the raw CPU speed the
motherboard busses, chipset and RAM speeds are also a very influential
factor. My experience with distributed.net, Povray and similar number
crunchers shows that the raw speed scales roughly as the BogoMips
rating. Not precisely, but in the same ballpark.

  So if you took one of the new MB's with a pair of FC-PGA P-III sockets
and threw a pair of 700MHz P-III's, a stick of SDRAM, a network- and a
graphics card on it making it boot diskless, then you would in essence
have something that let a room full of P1XX's in the dust. It would be
worth at least 2800 BogoMips. Give the P133 the benefit of the doubt
worth a factor of two, and it would still take 28 of them to compete.
That is not considering the noise, heat output, electricity bill,
reliability (or lack of same), networking components, setup and
administration time, additionally needed expansion cards and RAM modules
etc, etc.

  I consider building two of these crunchers in a pair of ATX
miditowers, which are already standing next to the server that will feed
them. But right now my time doesn't even allow me to participate in this
discussion in a timely fashion, so time will tell if my interest in
raytracing gets strong enough for me to implement this idea.

  Regards

    Frank.


Post a reply to this message

From: Frank Nikolajsen
Subject: Re: Multi-machine rendering...
Date: 25 Oct 2000 18:19:02
Message: <39F75CD6.A948C1C3@warpspace.com>
Just did some testing, as I couldn't really believe the numbers from
my previous post myself. So I installed/compiled Povray 3.1g on one of
my servers, an old P120/32 and compared the render time of skyvase.pov
on this platform with a dual PII-350/256 using only one processor.

  Pentium 120:

Time For Parse:    0 hours  0 minutes   1.0 seconds (1 seconds)
Time For Trace:    0 hours  5 minutes  60.0 seconds (360 seconds)
    Total Time:    0 hours  6 minutes   1.0 seconds (361 seconds)
360.01user 0.10system 6:00.23elapsed 99%CPU (0avgtext+0avgdata
0maxresident)k
0inputs+0outputs (266major+281minor)pagefaults 0swaps

  Pentium II-350:

Time For Trace:    0 hours  1 minutes  33.0 seconds (93 seconds)
    Total Time:    0 hours  1 minutes  33.0 seconds (93 seconds)
93.21user 0.12system 1:33.32elapsed 100%CPU (0avgtext+0avgdata
0maxresident)k
0inputs+0outputs (235major+282minor)pagefaults 0swaps

  Not nearly as bad as I made it sound. Thus if the dual PIII 700MHz
scales linearly, then it would roughly be 'worth' 15-16 P120's.

  Frank.


Post a reply to this message

From: Steve
Subject: Re: Multi-machine rendering...
Date: 25 Oct 2000 20:48:36
Message: <slrn8vevol.a3q.steve@zero-pps.localdomain>
On Thu, 26 Oct 2000 00:21:10 +0200, Frank Nikolajsen wrote:
>
>  Not nearly as bad as I made it sound. Thus if the dual PIII 700MHz
>scales linearly, then it would roughly be 'worth' 15-16 P120's.

I don't think it scales all that linearly, my PII 266/64 does skyvase
in 4min 59,  (in X with other windows open) that's only one minute faster for
twice the clock speed, and in theory your 350 should be doing this in 4 minutes 
if it's linear, say a minute faster for every 133Mhz or so.  

-- 
Cheers
Steve              email mailto:ste### [at] zeroppsuklinuxnet

%HAV-A-NICEDAY Error not enough coffee  0 pps. 

web http://www.zeropps.uklinux.net/

or  http://start.at/zero-pps

  1:21am  up 15 days,  2:42,  2 users,  load average: 1.00, 1.00, 1.00


Post a reply to this message

From: Thomas Charron
Subject: Re: Multi-machine rendering...
Date: 7 Nov 2000 13:03:10
Message: <3a0843de$1@news.povray.org>
In article <39F### [at] yahoocom>, "Simon Lemieux"
<lem### [at] yahoocom> wrote:
> Me too.. I currently have only one machine, but I could easily write a
> cgi script that could do everything that Povray does (except the
> pre/post render exections ;)...  that would be available for anyone...
> the program would run under linux only (since I use the command system()
> that might not work properly on other machines...)

  What would be nice is if we could combine the ability for a CGI
application to serve as a frontend for a distributed rendering 'farm'
that individuals could submit their machines to be part of in order to
access.  Perhaps a small client utility that would login to the backend
and accept rendering jobs, and in exchange for doing this, you would have
access to the entire distributed 'farm'..

  Not sure if I'm wording this well, but basically a system such as what
you are saying, but with a more open backend that anyone could 'hook'
into.


Post a reply to this message

From: Thomas Charron
Subject: Re: Multi-machine rendering...
Date: 7 Nov 2000 13:04:33
Message: <3a084431$1@news.povray.org>
In article <39F43344.3ED25F8E@yahoo.com>, "Simon Lemieux"
<lem### [at] yahoocom> wrote:
>> I think it'll be much better. How many machines do you think you can
>> host?
> I can host as many as I find 'em... The problem is to pay them... and
> for now, I'd say none!  But I could easily host a dozen pentiums, make
> them a super computer with Mosix and then I'd work on my CGI script to
> make another POV-Ray render farm available for all on the net!

  Guess I shoulda ready farther then I did in the thread..  ;-P

  Question is, could you make this 'farm' open, so any individuals could
add their home machine to this network..  ;-P


Post a reply to this message

<<< Previous 10 Messages Goto Initial 10 Messages

Copyright 2003-2023 Persistence of Vision Raytracer Pty. Ltd.