<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Verdana
}
--></style>
</head>
<body class='hmmessage'>
Dear all,<BR>
<BR>
i'm doing parallel rendering using 2 machines (np4), i notice an obvious difference between using offscreen-rendering (faster) and without offscreen-rendering (much slower). i realize this from the timer log:<BR>
<BR>
<BR>
<STRONG>Case 1: with offscreen-rendering</STRONG><BR>
----------------------------------------------------------<BR>
<SPAN lang=EN> <BR>
Local Process<BR>
Still Render, 0.666444 seconds<BR>
Execute vtkMPIMoveData id: 519, 0.000199 seconds<BR>
Execute vtkPolyDataMapper id: 311, 0.000106 seconds<BR>
<BR>
<BR>
Server, Process 0<BR>
Execute vtkFileSeriesReader id: 238, 0.645881 seconds<BR>
Execute vtkPVGeometryFilter id: 305, 0.005891 seconds<BR>
Execute vtkPVCacheKeeper id: 516, 7.8e-05 seconds<BR>
Execute vtkMPIMoveData id: 519, 0.000212 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000152 seconds<BR>
Execute vtkPolyDataMapper id: 311, 0.000274 seconds<BR>
<BR>
Server, Process 1<BR>
Execute vtkFileSeriesReader id: 238, 0.000275 seconds<BR>
Execute vtkPVGeometryFilter id: 305, 0.005299 seconds<BR>
Execute vtkPVCacheKeeper id: 516, 7.7e-05 seconds<BR>
Execute vtkMPIMoveData id: 519, 0.000147 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000117 seconds<BR>
Execute vtkPolyDataMapper id: 311, 9.9e-05 seconds<BR>
<BR>
Server, Process 2<BR>
Execute vtkFileSeriesReader id: 238, 0.000258 seconds<BR>
Execute vtkPVGeometryFilter id: 305, 0.004765 seconds<BR>
Execute vtkPVCacheKeeper id: 516, 7.7e-05 seconds<BR>
Execute vtkMPIMoveData id: 519, 0.000147 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000111 seconds<BR>
Execute vtkPolyDataMapper id: 311, 9.5e-05 seconds<BR>
<BR>
Server, Process 3<BR>
Execute vtkFileSeriesReader id: 238, 0.000352 seconds<BR>
Execute vtkPVGeometryFilter id: 305, 0.005351 seconds<BR>
Execute vtkPVCacheKeeper id: 516, 7.7e-05 seconds<BR>
Execute vtkMPIMoveData id: 519, 0.000168 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000111 seconds<BR>
Execute vtkPolyDataMapper id: 311, 0.000108 seconds<BR>
<BR>
---------------------------------------------------------------<BR>
<BR>
<BR>
<BR>
<STRONG>Case 2: without offscreen-rendering</STRONG><BR>
---------------------------------------------------------------<BR>
<BR><SPAN lang=EN>
Local Process<BR>
Still Render, 4.86495 seconds<BR>
Execute vtkMPIMoveData id: 520, 2.81566 seconds<BR>
Execute vtkPolyDataMapper id: 312, 0.00012 seconds<BR>
Execute vtkPolyDataMapper id: 148, 7.6e-05 seconds <BR>
<BR>
<BR>
Server, Process 0<BR>
Execute vtkFileSeriesReader id: 239, 0.659133 seconds<BR>
Execute vtkPVGeometryFilter id: 306, 0.026125 seconds<BR>
Execute vtkPVCacheKeeper id: 517, 7.8e-05 seconds<BR>
Execute vtkMPIMoveData id: 520, 2.53214 seconds<BR>
Dataserver gathering to 0, 1.98166 seconds<BR>
Dataserver sending to client, 0.549715 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000175 seconds<BR>
<BR>
Server, Process 1<BR>
Execute vtkFileSeriesReader id: 239, 0.000446 seconds<BR>
Execute vtkPVGeometryFilter id: 306, 0.026313 seconds<BR>
Execute vtkPVCacheKeeper id: 517, 7.3e-05 seconds<BR>
Execute vtkMPIMoveData id: 520, 0.232435 seconds<BR>
Dataserver gathering to 0, 0.232117 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.00012 seconds<BR>
<BR>
Server, Process 2<BR>
Execute vtkFileSeriesReader id: 239, 0.000519 seconds<BR>
Execute vtkPVGeometryFilter id: 306, 0.026063 seconds<BR>
Execute vtkPVCacheKeeper id: 517, 7e-05 seconds<BR>
Execute vtkMPIMoveData id: 520, 1.31373 seconds<BR>
Dataserver gathering to 0, 1.31341 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000119 seconds<BR>
<BR>
Server, Process 3<BR>
Execute vtkFileSeriesReader id: 239, 0.000459 seconds<BR>
Execute vtkPVGeometryFilter id: 306, 0.004905 seconds<BR>
Execute vtkPVCacheKeeper id: 517, 6.9e-05 seconds<BR>
Execute vtkMPIMoveData id: 520, 0.764289 seconds<BR>
Dataserver gathering to 0, 0.740679 seconds<BR>
Execute vtkOrderedCompositeDistributor , 0.000136 seconds<BR></SPAN>
<BR>
--------------------------------------------------------------------<BR>
<BR>
<BR>
Unlike Case 2, Case 1 does not show any 'Dataserver gathering to 0' or 'Dataserver sending to client'<BR>
so i guess what makes Case 2 slower is because the vtkMPIMoveData is doing extra thing to move data amongst processes<BR>
<BR>
btw, whenever i run it without -offscreen-rendering, i get this message:<BR>
"Display is not accessible on the server side. Remote rendering will be disabled."<BR>
<BR>
based on what i read from paraview tutorial, what i understand is that the <FONT face=CMR12>parallel rendering algorithm allows each process to independently render its partition of the geometry and then </FONT><FONT face=CMBX12>composites </FONT><FONT face=CMR12>the partial images together to form the final image. Is this what happened in Case 2 because it has 'Dataserver gathering to 0' or 'Dataserver sending to client'?</FONT><BR>
<BR>
actually what i dont understand is why case 2 is much slower than case 1? <BR>
is it because different 'things' are going on in the processes when offscreen-rendering is on/off?<BR>
<BR>
<BR>
any help / reply is highly appreciated<BR>
<BR>
Best Regards,<BR>
chewping<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR>
<BR></SPAN> </body>
</html>