<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=us-ascii">
<META content="MSHTML 6.00.2900.2873" name=GENERATOR></HEAD>
<BODY>
<DIV dir=ltr align=left>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial
color=#0000ff size=2>Okay here's my general response, with more specific
responses below.</FONT></SPAN></DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial
color=#0000ff size=2></FONT></SPAN> </DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial
color=#0000ff size=2>Sandia runs ParaView in client/server probably more than
any other institution in the world. ParaView client/server is run about 500
times a month on 16 different servers(clusters), by about 40 different users
(not including the vis people).</FONT></SPAN></DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial
color=#0000ff size=2></FONT></SPAN> </DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial><FONT
color=#0000ff><FONT size=2>Running ParaView server with Mesa runs absolutely
fine! In fact for small data you can actually see small performance ^increases^
over OpenGL<SPAN class=050295019-16052006> because grabbing the frame buffer is
instantaneous.</SPAN></FONT></FONT></FONT></SPAN></DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial><FONT
color=#0000ff><FONT size=2><SPAN
class=050295019-16052006></SPAN></FONT></FONT></FONT></SPAN> </DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial><FONT
color=#0000ff><FONT size=2><SPAN class=050295019-16052006>So my recommendation
for everyone is if you don't have graphics cards, simply compile ParaView server
with mesa. Period. Double stamp. No take
backs.</SPAN></FONT></FONT></FONT></SPAN></DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006><FONT face=Arial
color=#0000ff size=2></FONT></SPAN> </DIV>
<DIV dir=ltr align=left><SPAN class=058592919-16052006>
<BLOCKQUOTE class=gmail_quote
style="PADDING-LEFT: 1ex; MARGIN: 0pt 0pt 0pt 0.8ex; BORDER-LEFT: rgb(204,204,204) 1px solid">
<DIV><FONT face=Arial color=#0000ff size=2>...</FONT><BR><BR>That mode is
useful if you do not want to move data from one cluster to another. If you are
running on around 10 nodes, there is a huge difference in rendering
performance between software and hardware accelerated OpenGL. So it makes
sense to render on a cluster with hardware support. <BR></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN class=058592919-16052006>I
agree, I wasn't arguing that you don't want graphics cards, I was asserting
that splitting up the server into data and render is not useful in my opinion.
If you have a cluster that has graphics cards on it, have that cluster mount
the disk where the data is and your done.</SPAN></FONT></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN
class=058592919-16052006></SPAN></FONT> </DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN class=058592919-16052006>If
mounting the disk isn't possible, then you have three options
</SPAN></FONT></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN class=058592919-16052006>1)
The first and best option is to run paraview server with
Mesa.</SPAN></FONT></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN class=058592919-16052006>2)
FTP, SCP the data over to the render cluster (I don't like this option just
have it for completeness)</SPAN></FONT></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN class=058592919-16052006>3)
Set up data server on the computation cluster, start up the render server on
the graphics cluster, and set up all the sockets between the
two.</SPAN></FONT></DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN
class=058592919-16052006></SPAN></FONT> </DIV>
<DIV><FONT face=Arial color=#0000ff size=2><SPAN
class=058592919-16052006>Here's my problem with option 3. First it's complex,
second you are moving ALL the geometry over the sockets from data server
to the render server. Moving data (even polygonal) is a major no,
no. Again take my use case of 400 timesteps and the user hits 'play'.
Even worse, the sockets connections from the data server to the render
server are most likely a shared 100T hubbed
connection. </SPAN></FONT></DIV><FONT face=Arial color=#0000ff
size=2><SPAN class=058592919-16052006></SPAN></FONT><FONT face=Arial><FONT
color=#0000ff><FONT size=2><SPAN
class=058592919-16052006></SPAN></FONT></FONT></FONT>
<DIV><BR> Also, there is a sweet spot when you have, let's say, 128 nodes
data server and 16 nodes hardware accelerated render server where you should
get better performance because Mesa is an order of magnitude slower than
hardware accelerated rendering. To boot, compositing with 128 nodes degrades
performance further. On the other hand, you obviously get a lot of performance
improvement if you process data with 128 nodes as opposed to 16. </DIV>
<DIV> </DIV>
<DIV><SPAN class=058592919-16052006></SPAN><FONT face=Arial><FONT
color=#0000ff><FONT size=2><SPAN class=050295019-16052006>I bet if you
actually ran this test and you compared having the 128 nodes just render their
small part of the data locally vs. having the 128 nodes send their data
down to the 16 to have them render it. That for many, many operations the
first would be faster...</SPAN></FONT></FONT></FONT></DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006></SPAN></FONT></FONT></FONT> </DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006>1) I'm cutting, I'm clipping, I'm changing time
steps, I'm animating iso surface values, I'm basically trying to get my job
done... :)</SPAN></FONT></FONT></FONT></DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006></SPAN></FONT></FONT></FONT> </DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006>2) I'm just timing rendering speed because I'm
writing a paper on why data server / render server is a good
idea</SPAN></FONT></FONT></FONT></DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006></SPAN></FONT></FONT></FONT> </DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006>ALL the operations in category 1 will
be faster with 128 nodes and mesa.</SPAN></FONT></FONT></FONT></DIV>
<DIV><FONT face=Arial><FONT color=#0000ff><FONT size=2><SPAN
class=050295019-16052006>I don't care about category
2.</SPAN></FONT></FONT></FONT><BR><BR>Another use case is when you want to
render data from a compute server on a tiled display. The only fast way to do
that is to use data server/render server. <BR></SPAN></DIV></BLOCKQUOTE></DIV>
<DIV><SPAN class=050295019-16052006><FONT face=Arial color=#0000ff
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=050295019-16052006><FONT face=Arial color=#0000ff size=2>If you
have a separate cluster to drive your tiled display and your can't mount the
disk and you can't copy the data and the data is too big to load on to 16 nodes,
then I concede, the data server / render server would be your option
of last resort. :) </FONT></SPAN></DIV>
<DIV><SPAN class=050295019-16052006><FONT face=Arial color=#0000ff
size=2></FONT></SPAN> </DIV><!-- Converted from text/rtf format -->
<P><B><FONT face=Fixedsys size=1>Brian Wylie - Org 9227</FONT></B> <BR><B><FONT
face=Fixedsys size=1>Sandia National Laboratories</FONT></B> <BR><B><FONT
face=Fixedsys size=1>MS 0822 - Building 880/A1-J</FONT></B> <BR><B><FONT
face=Fixedsys size=1>(505)844-2238
FAX(505)845-0833
</FONT></B><BR><FONT face="Courier New" size=1>
____
_ __</FONT> <BR><FONT face="Courier New"
size=1> / __ \____ _________ | | / (_)__
_ __ </FONT><BR><FONT face="Courier New"
size=1> / /_/ / __ `/ ___/ __ `/ | / / / _ \ | /| / /</FONT>
<BR><FONT face="Courier New" size=1> / ____/ /_/ / / / /_/ /| |/ /
/ __/ |/ |/ /</FONT> <BR><FONT face="Courier New"
size=1> /_/ \__,_/_/ \__,_/
|___/_/\___/|__/|__/
</FONT><BR><FONT face="Courier New"
size=1>
Unleash the Beast</FONT> </P>
<DIV> </DIV><BR>
<BLOCKQUOTE
style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #0000ff 2px solid; MARGIN-RIGHT: 0px">
<DIV class=OutlookMessageHeader lang=en-us dir=ltr align=left>
<HR tabIndex=-1>
<FONT face=Tahoma size=2><B>From:</B> Berk Geveci
[mailto:berk.geveci@gmail.com] <BR><B>Sent:</B> Tuesday, May 16, 2006 1:25
PM<BR><B>To:</B> Wylie, Brian<BR><B>Cc:</B> Renato N. Elias;
paraview@paraview.org<BR><B>Subject:</B> Re: [Paraview] client/server display
problem<BR></FONT><BR></DIV>
<DIV></DIV><BR>
<DIV>
<BLOCKQUOTE class=gmail_quote
style="PADDING-LEFT: 1ex; MARGIN: 0pt 0pt 0pt 0.8ex; BORDER-LEFT: rgb(204,204,204) 1px solid">Sandia
runs on LOTS of clusters that don't have graphics cards. We NEVER run in
data server mode (I personally believe that mode is not useful...ever...
(waiting for the flames on that statement... :) ) </BLOCKQUOTE>
<DIV><BR>It has been a while since I had the opportunity to flame Brian :-)
<BR><BR>That mode is useful if you do not want to move data from one cluster
to another. If you are running on around 10 nodes, there is a huge difference
in rendering performance between software and hardware accelerated OpenGL. So
it makes sense to render on a cluster with hardware support.
<BR><BR> Also, there is a sweet spot when you have, let's say, 128 nodes
data server and 16 nodes hardware accelerated render server where you should
get better performance because Mesa is an order of magnitude slower than
hardware accelerated rendering. To boot, compositing with 128 nodes degrades
performance further. On the other hand, you obviously get a lot of performance
improvement if you process data with 128 nodes as opposed to 16.
<BR><BR>Another use case is when you want to render data from a compute server
on a tiled display. The only fast way to do that is to use data server/render
server. <BR><BR><BR></DIV><BR></DIV><BR></BLOCKQUOTE></DIV>
<DIV> </DIV><!-- Converted from text/rtf format -->
<P><B><FONT face=Fixedsys size=1>Brian Wylie - Org 9227</FONT></B> <BR><B><FONT
face=Fixedsys size=1>Sandia National Laboratories</FONT></B> <BR><B><FONT
face=Fixedsys size=1>MS 0822 - Building 880/A1-J</FONT></B> <BR><B><FONT
face=Fixedsys size=1>(505)844-2238
FAX(505)845-0833
</FONT></B><BR><FONT face="Courier New" size=1>
____
_ __</FONT> <BR><FONT face="Courier New"
size=1> / __ \____ _________ | | / (_)__
_ __ </FONT><BR><FONT face="Courier New"
size=1> / /_/ / __ `/ ___/ __ `/ | / / / _ \ | /| / /</FONT>
<BR><FONT face="Courier New" size=1> / ____/ /_/ / / / /_/ /| |/ /
/ __/ |/ |/ /</FONT> <BR><FONT face="Courier New"
size=1> /_/ \__,_/_/ \__,_/
|___/_/\___/|__/|__/
</FONT><BR><FONT face="Courier New"
size=1>
Unleash the Beast</FONT> </P>
<DIV> </DIV><BR>
<BLOCKQUOTE
style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #0000ff 2px solid; MARGIN-RIGHT: 0px">
<DIV class=OutlookMessageHeader lang=en-us dir=ltr align=left>
<HR tabIndex=-1>
<FONT face=Tahoma size=2><B>From:</B> Berk Geveci
[mailto:berk.geveci@gmail.com] <BR><B>Sent:</B> Tuesday, May 16, 2006 1:25
PM<BR><B>To:</B> Wylie, Brian<BR><B>Cc:</B> Renato N. Elias;
paraview@paraview.org<BR><B>Subject:</B> Re: [Paraview] client/server display
problem<BR></FONT><BR></DIV>
<DIV></DIV><BR>
<DIV>
<BLOCKQUOTE class=gmail_quote
style="PADDING-LEFT: 1ex; MARGIN: 0pt 0pt 0pt 0.8ex; BORDER-LEFT: rgb(204,204,204) 1px solid">Sandia
runs on LOTS of clusters that don't have graphics cards. We NEVER run in
data server mode (I personally believe that mode is not useful...ever...
(waiting for the flames on that statement... :) ) </BLOCKQUOTE>
<DIV><BR>It has been a while since I had the opportunity to flame Brian :-)
<BR><BR>That mode is useful if you do not want to move data from one cluster
to another. If you are running on around 10 nodes, there is a huge difference
in rendering performance between software and hardware accelerated OpenGL. So
it makes sense to render on a cluster with hardware support.
<BR><BR> Also, there is a sweet spot when you have, let's say, 128 nodes
data server and 16 nodes hardware accelerated render server where you should
get better performance because Mesa is an order of magnitude slower than
hardware accelerated rendering. To boot, compositing with 128 nodes degrades
performance further. On the other hand, you obviously get a lot of performance
improvement if you process data with 128 nodes as opposed to 16.
<BR><BR>Another use case is when you want to render data from a compute server
on a tiled display. The only fast way to do that is to use data server/render
server. <BR><BR><BR></DIV><BR></DIV><BR></BLOCKQUOTE></BODY></HTML>