[Paraview] Multi-block distribution in parallel

[John Biddiscombe]

When loading a multiblock dataset with 38 datasets from a series of xml 
vtu files, paraview splits each dataset among all processors. Since each 
block already represents a 'piece' of the data - is there a way I can 
tell paraview to load one or more blocks per process, rather than 
splitting all of them. The splitting is not such a big problem, but the 
files are huge and the IO overhead of having all blocks read by all 
processes is making the process much too slow to use.

If not, is there an easy way of converting a vtmb file that looks like 
this (below), into a parallel form, where the pieces are the blocks.

JB

<?xml version="1.0"?>
<VTKFile type="vtkMultiBlockDataSet" version="1.0" 
byte_order="LittleEndian" compressor="vtkZLibDataCompressor">
  <vtkMultiBlockDataSet>
    <Block index="0">
      <DataSet index="0" file="1800_001-00040/1800_001-00040_0.vtu"/>
      <DataSet index="1" file="1800_001-00040/1800_001-00040_1.vtu"/>
      <DataSet index="2" file="1800_001-00040/1800_001-00040_2.vtu"/>
      <DataSet index="3" file="1800_001-00040/1800_001-00040_3.vtu"/>
      <DataSet index="4" file="1800_001-00040/1800_001-00040_4.vtu"/>
      <DataSet index="5" file="1800_001-00040/1800_001-00040_5.vtu"/>
      <DataSet index="6" file="1800_001-00040/1800_001-00040_6.vtu"/>
      <DataSet index="7" file="1800_001-00040/1800_001-00040_7.vtu"/>
      <DataSet index="8" file="1800_001-00040/1800_001-00040_8.vtu"/>
      <DataSet index="9" file="1800_001-00040/1800_001-00040_9.vtu"/>
      <DataSet index="10" file="1800_001-00040/1800_001-00040_10.vtu"/>
      <DataSet index="11" file="1800_001-00040/1800_001-00040_11.vtu"/>
      <DataSet index="12" file="1800_001-00040/1800_001-00040_12.vtu"/>
      <DataSet index="13" file="1800_001-00040/1800_001-00040_13.vtu"/>
      <DataSet index="14" file="1800_001-00040/1800_001-00040_14.vtu"/>
      <DataSet index="15" file="1800_001-00040/1800_001-00040_15.vtu"/>
      <DataSet index="16" file="1800_001-00040/1800_001-00040_16.vtu"/>
    </Block>
    <Block index="1">
      <DataSet index="0" file="1800_001-00040/1800_001-00040_17.vtu"/>
      <DataSet index="1" file="1800_001-00040/1800_001-00040_18.vtu"/>
      <DataSet index="2" file="1800_001-00040/1800_001-00040_19.vtu"/>
      <DataSet index="3" file="1800_001-00040/1800_001-00040_20.vtu"/>
      <DataSet index="4" file="1800_001-00040/1800_001-00040_21.vtu"/>
      <DataSet index="5" file="1800_001-00040/1800_001-00040_22.vtu"/>
      <DataSet index="6" file="1800_001-00040/1800_001-00040_23.vtu"/>
      <DataSet index="7" file="1800_001-00040/1800_001-00040_24.vtu"/>
      <DataSet index="8" file="1800_001-00040/1800_001-00040_25.vtu"/>
      <DataSet index="9" file="1800_001-00040/1800_001-00040_26.vtu"/>
      <DataSet index="10" file="1800_001-00040/1800_001-00040_27.vtu"/>
      <DataSet index="11" file="1800_001-00040/1800_001-00040_28.vtu"/>
      <DataSet index="12" file="1800_001-00040/1800_001-00040_29.vtu"/>
      <DataSet index="13" file="1800_001-00040/1800_001-00040_30.vtu"/>
      <DataSet index="14" file="1800_001-00040/1800_001-00040_31.vtu"/>
      <DataSet index="15" file="1800_001-00040/1800_001-00040_32.vtu"/>
      <DataSet index="16" file="1800_001-00040/1800_001-00040_33.vtu"/>
      <DataSet index="17" file="1800_001-00040/1800_001-00040_34.vtu"/>
      <DataSet index="18" file="1800_001-00040/1800_001-00040_35.vtu"/>
      <DataSet index="19" file="1800_001-00040/1800_001-00040_36.vtu"/>
    </Block>
    <Block index="2">
      <DataSet index="0" file="1800_001-00040/1800_001-00040_37.vtu"/>
    </Block>
  </vtkMultiBlockDataSet>
</VTKFile>


-- 
John Biddiscombe,                            email:biddisco @ cscs.ch
http://www.cscs.ch/about/BJohn.php
CSCS, Swiss National Supercomputing Centre  | Tel:  +41 (91) 610.82.07
Via Cantonale, 6928 Manno, Switzerland      | Fax:  +41 (91) 610.82.82