{"id":343,"date":"2013-04-26T12:39:17","date_gmt":"2013-04-26T12:39:17","guid":{"rendered":"http:\/\/ri.itservices.manchester.ac.uk\/csf-apps\/?page_id=343"},"modified":"2016-11-25T12:47:00","modified_gmt":"2016-11-25T12:47:00","slug":"paraview","status":"publish","type":"page","link":"https:\/\/ri.itservices.manchester.ac.uk\/csf-apps\/software\/applications\/paraview\/","title":{"rendered":"ParaView"},"content":{"rendered":"

Overview<\/h2>\n

ParaView<\/a> is an open-source, multi-platform data analysis and visualization application. Versions 3.14.1 and 4.0.1 were compiled on the CSF using gcc (default version) and OpenMPI 1.6. The 3.14.1 installation includes ParaView development files and the Paraview GUI. Version 4.0.1 contains only the pvserver<\/code> and pvbatch<\/code> off-screen executables only.<\/p>\n

ParaView will not<\/strong> use any GPU hardware in the CSF. Instead all rendering is performed in software on the compute nodes.<\/p>\n

There are three ways to run ParaView:<\/p>\n

    \n
  1. The preferred method of running ParaView is to install and run the GUI (paraview<\/code>) on your local PC<\/strong> and run the parallel processing and rendering part of ParaView (pvserver<\/code> processes) on the CSF in batch. Your local copy of paraview<\/code> will then connect to the CSF and use the pvserver<\/code> processes. This is efficient because only the final rendered image is sent to your PC over the network (no remote X11 used). Your datasets (which could be huge) are stored and processed entirely on the CSF. The remainder of this page describes this method.<\/li>\n
  2. Running the paraview<\/code> GUI on the CSF over a remote X connection: this is not<\/em> the best way to run ParaView. However, if you cannot install ParaView on your local PC then this method will work. But do not<\/strong> simply run paraview<\/code> on the login node. Please follow the instructions<\/a> for running everything on the CSF.<\/li>\n
  3. For non-interactive (scripted) use, the pvbatch<\/code> executable is available. See below<\/a> for how to run this process in batch.<\/li>\n<\/ol>\n

     <\/p>\n\n\n
    Please do not run ParaView directly on the login node. Such processes will be killed without warning.<\/em><\/td>\n<\/tr>\n<\/table>\n

     <\/p>\n

    Restrictions on use<\/h2>\n

    There are no access restrictions as it is free software.<\/p>\n

    <\/a><\/p>\n

    Installing ParaView on your local PC<\/h2>\n

    You are going to run the paraview<\/code> GUI on your PC and connect it to the CSF. To install ParaView on your PC please download version 4.0.1<\/strong> or version 3.14.1<\/strong> from the ParaView Download page<\/a> for your platform. You can use the Windows\/Linux 32\/64bit versions.<\/p>\n

    Once installed on your PC, do not run ParaView just yet. You first need to start the pvserver<\/code> MPI job on the CSF and then set up an SSH tunnel on your PC. Full instructions are given below.<\/p>\n

    Running pvserver in batch on the CSF<\/h2>\n

    The pvserver<\/code> MPI processes can be run on multiple compute nodes with fast InfiniBand networking (for large jobs) or a single compute node for smaller jobs. When using InfiniBand connected nodes there is a minimum number of processes and the number must be a multiple of 12 or 24 depending which nodes are used – see example jobscripts below for details. On a single compute node a smaller number of cores can be used (up to 24 cores).<\/p>\n

    See the Paraview Hints<\/a> below for how to work out how many cores to run.<\/p>\n

    The modulefile to load and a suitable jobscript for each option are described below. Choose one of these. The modulefile will also load the appropriate MPI and python modules.<\/p>\n

    Note: If you’ve attended the ParaView Course<\/a> and have a temporary course account you should choose the SMP single-node method<\/a>.<\/p>\n

    pvserver over InfiniBand (large multi-node jobs)<\/h3>\n

    Setup the environment by loading an InfiniBand version of the available modulefiles – choose one:<\/p>\n

    module load apps\/gcc\/paraview\/4.0.1-ib<\/pre>\n
    or<\/p>\n
    module load apps\/gcc\/paraview\/3.14.1-ib<\/pre>\n
    Create the following jobscript (e.g., naming it pvserver-ib.sh<\/code>):<\/p>\n
    \r\n#!\/bin\/bash\r\n#$ -S \/bin\/bash\r\n#$ -V\r\n#$ -cwd\r\n\r\n#$ -pe orte-24-ib.pe 48   # Change number of cores, must be 48 or more\r\n                          # and a multiple of 24.\r\n\r\n#### Run pvserver ($NSLOTS is automatically set to number of cores given above)\r\n\r\nmpirun -n $NSLOTS pvserver --use-offscreen-rendering\r\n\r\n<\/pre>\n
    Then submit the above jobscript using<\/p>\n
    \r\nqsub jobscript<\/em>\r\n<\/pre>\n
    where jobscript<\/em> is the name of your file (e.g., pvserver-ib.sh<\/code>)<\/p>\n
    <\/a><\/p>\n
    pvserver in SMP (small single-node jobs)<\/h3>\n
    Setup the environment by loading an non-InfiniBand version of the available modulefiles – choose one:<\/p>\n
    module load apps\/gcc\/paraview\/4.0.1<\/pre>\n
    or<\/p>\n
    module load apps\/gcc\/paraview\/3.14.1<\/pre>\n
    Create the following jobscript (e.g., naming it pvserver.sh<\/code>):<\/p>\n
    \r\n#$ -S \/bin\/bash\r\n#$ -V\r\n#$ -cwd\r\n#$ -pe smp.pe 4         # Change number of cores (max 24)\r\n\r\n#$ -l short             #  Optional (max 12 cores) - depends how long you'll\r\n                        #  leave your local paraview GUI running.\r\n\r\n#### Run pvserver ($NSLOTS is automatically set to number of cores given above)\r\n\r\nmpirun -n $NSLOTS pvserver --use-offscreen-rendering\r\n\r\n<\/pre>\n
    Then submit the above jobscript using<\/p>\n
    \r\nqsub jobscript<\/em>\r\n<\/pre>\n
    where jobscript<\/em> is the name of your file (e.g., pvserver.sh<\/code>)<\/p>\n
    Find where the pvserver batch job runs<\/h3>\n
    You must now wait<\/strong> until the pvserver jobs are running. Use qstat<\/code> to check the job queue. Once the state<\/code> reported by qstat<\/code> has changed from qw<\/code> to r<\/code> you will see something like:<\/p>\n
    \r\njob-ID  prior   name     user     state submit\/start at     queue                          slots \r\n------------------------------------------------------------------------------------------------\r\n5724  0.05534 pvserver.q xxxxxxxx r     08\/28\/2012 17:06:57 C6220-II-STD.q@node537<\/strong>.prv.csf     4\r\n<\/pre>\n
    Make a note of the queue<\/strong> value, specifically the hostname<\/strong> after the @<\/strong>. In this example we see node537<\/code><\/strong> (you don’t need the .prv.csf....<\/code>). <\/p>\n
    We are now going to run the paraview<\/code> GUI on your local PC and connect it to the pvserver<\/code> batch job.<\/p>\n
    Running paraview On Your Local PC and Connecting to CSF<\/h2>\n
    This is a two step procedure<\/p>\n
      \n
    1. Set up the SSH tunnel to the CSF (if off campus run the VPN first)<\/li>\n
    2. Run paraview<\/code> and connect to the SSH tunnel<\/li>\n<\/ol>\n
      Separate instructions are given for Windows and Linux. At this stage you must have ParaView installed on your local PC (see above<\/a>).<\/p>\n
      SSH Tunnel on Linux<\/h3>\n
      In a shell on your<\/strong> PC, create a tunnel between your local port 11111 and the CSF backend node’s port 1111 where pvserver<\/code> is running. This will go via the CSF login node. In this example we assume the pvserver<\/code> is running on node node537<\/code><\/strong>.<\/p>\n