Installing Cluster Development Kit, problems you might face, and how to over-come those problems:

From athena

Installing Cluster Development Kit, problems you might face, and how to over-come those problems:

In order to configure and “check out” the entire cluster and install OpenPBS you need to log in as root:

            zahra@venus:~$ sudo bash 
            Password: 

Then try to go to the /opt/pgi directory:

           root@venus:~# cd /opt 
           root@venus:/opt# cd pgi 

If you recieve a message such as:

           bash: cd: pgi: No such file or directory 

then check to see whther this directory exits or not:

            root@venus:/opt# ls 
            intel

As you can see, “pgi” is not in “opt”. Try to go check the information on your CD regarding installation:

           root@venus:/opt# cd /media/cdrom0 
           root@venus:/media/cdrom0# ./install 
           bash: ./install: No such file or directory 
           root@venus:/media/cdrom0# ls 
           common     installcdk      linux86     postinstall  uninstallcdk 
           index.htm  INSTALLCDK.txt  linux86-64  README 
           root@venus:/media/cdrom0# ./installcdk 
           bash: ./installcdk: /bin/sh: bad interpreter: Permission denied 
           root@venus:/media/cdrom0# more INSTALLCDK.txt 

You will see the following information:

                Copyright 2007 The Portland Group, Inc. 
                       All rights reserved. 

1 PGI CDK 7.0 Installation Notes A cluster is a collection of compatible computers connected by a network. The PGI CDK Cluster Development Kit supports parallel computation on clusters of 32-bit and 64-bit x86-compatible AMD and Intel processor-based Linux workstations or servers interconnected by a TCP/IP-based network such as Ethernet. The PGI CDK software is installed on a working cluster--it is not the purpose of this product to create a cluster, or to troubleshoot one. The PGI CDK release can be installed on a single node, and the node can be treated as if it is a cluster. Note that support for cluster programming does not extend to clusters combining AMD64 or EM64T CPU-based systems with IA32 CPU-based systems, unless all are running 32-bit applications built for a common set of working x86 instructions. Release 7.0 is the production release of the PGI CDK that supports 64-bit x64 (Opteron, Athlon64, EM64T) processor-based systems, with large array addressing in PGF77, PGF95, PGC++, and PGCC. These systems can utilize a 64-bit address space while retaining the ability to run legacy 32-bit x86 executables at full speed. For multi-process programming, like message-passing programs set to execute on a cluster, we provide both a 32-bit and a 64-bit set of MPICH libraries, built with added information useful in the cluster debugger PGDBG and the cluster profiler PGPROF, as well as being the inter-process communication standard. 1.1 Introduction You can view the online HTML interface to the PGI CDK using any web browser. Enter the following URL in a web browser:

  file:/mnt/cdrom/index.htm 

running on a Linux system with the PGI CDK CD-ROM inserted and mounted on the CD-ROM drive. If you do not know how to insert and mount a CD-ROM on your Linux system, see Step 3 below in section 1.2 or contact your system administrator. Generally, clusters are configured with a "master" node from which jobs are launched and "slave" nodes that are used only for computation. Typically, the master node is accessible from the general-purpose or "public" network and shares a file system with the other computers on your network using NFS. The master node and all of the slave nodes are interconnected using a second "private" network that is only accessible from computers that are part of the cluster. There are two common cluster configurations: 1) The master node is used only for compilation and job submission, and

 only the slave nodes are used for computation. 

2) All nodes are used for computation, including the master node To use MPICH in the first configuration, OpenPBS (TORQUE) should be installed. Otherwise, the master node will be used as one of the computation nodes by the mpirun command by default; it is possible to exclude the master node in the second configuration if mpirun is invoked with the -nolocal option (see the man page for mpirun). If you are using the first configuration, it is possible to install MPICH and run parallel MPI or HPF jobs without installing any of the other components. However, if you will have multiple users running jobs on your cluster simultaneously, you will likely want to use OpenPBS to ensure your cluster nodes are allocated and used efficiently. Typically, a master node has two network cards to allow communication to the outside network as well as to the cluster nodes themselves, which may be on their own subnet. If this is the case on your cluster, then when the installation script prompts you for the name of the master node, you should use the name associated with the network card connected to the cluster nodes. Also, it is important to note that in order for MPICH and OpenPBS to run correctly, access from each node to every other node must be available via the 'rsh' or 'ssh' command. During installation, if install as root, root must have this access during installation. For example, if a 3-node cluster consists of a master and 2 slaves named master, node1, node2, then as a user you should be able to issue the commands:

  % rsh master date 
  % rsh node2 date 

or

  % ssh master date 
  % ssh node2 date 

From node1, and similarly from node2 and master. By default, all of the PGI compilers and tools will be installed on your system. You will select which of the open source components to install. At this point, you should have determined:

   * Which PGI CDK open source components you will install.
   * The hostnames of all the nodes that will be included in your cluster. 
You will need a list of these during the installation 
   * Whether the master node will be strictly a front-end for compilation, 
job launching, etc or whether it will participate as a compute node 
   * If you are installing OpenPBS (TORQUE), which users at your site will 
have OpenPBS queue manager permissions (you will need their usernames) 
   * Whether the compute nodes can share files with the master node (this 
is strongly recommended) 

Section 1.2 below describes how to install the PGI Fortran, C and C++ root@venus:/opt# compilers and tools on Linux using the installcdk script from the PGI CDK CD-ROM. NOTE: Some, but not all, parts of the PGI CDK require root permissions to successfully execute the installcdk script. You can create a compilers, tools and MPICH library installation on a single platform that will allow for multi-process/multi-threaded development, without root permissions. For OpenPBS and multi-platform cluster installations, you will need root permissions. You must install the software as specified in section 1.2 and then follow the instructions in section 1.3 for configuring and starting the FLEXlm license daemon. The FLEXlm license daemon enables use of the PGI compilers and tools by any user on any system networked to the system on which the PGI software is installed. For example, users can compile, debug, and profile using the PGI CDK compilers and tools on any system on your general-purpose network, subject to the constraints on concurrent usage for the product you have purchased. Sections 2.1 - 2.5 describe basic usage of the open source components of the PGI CDK, including MPICH, the OpenPBS batch queuing system, ScaLAPACK libraries, and the example benchmark programs and tutorials. For the first 60 days after your purchase, you may submit technical questions about the PGI CDK compilers and tools to the online problem reporting site at http://www.pgroup.com/support/index.htm. If you have purchased PGI Subscription Service, you will have access to service for an additional 12 months and will be notified by email when maintenance releases occur. Contact PGI at sales@pgroup.com for information about the PGI Subscription Service for the products you have purchased. MPICH, MPICH2, TORQUE, and ScaLAPACK, are all open source software packages that are not formally supported by The Portland Group. Each of these components has end-user and implementer documentation, generally in the form of printable PostScript, along with the source code. Support for these products is generally provided by their respective user communities, which you can learn more about at the following URLs:

   * MPICH - http://www-unix.mcs.anl.gov/mpi/mpich1 contains a wealth of 
information, including online documentation, tutorials, FAQ files, 
patch distributions, and information on how to submit bug reports to 
the MPICH developers. 
   * MPICH2 - http://www-unix.mcs.anl.gov/mpi/mpich2 contains a wealth of 
information, including online documentation, tutorials, FAQ files, 
patch distributions, and information on how to submit bug reports to 
the MPICH2 developers. 
   * TORQUE - the primary site for TORQUE, a version of OpenPBS, is 
http://www.supercluster.org/projects/torque. 
   * ScaLAPACK - http://www.netlib.org/scalapack contains FAQ files and 
current distributions of ScaLAPACK 

1.2 Installing on Linux86 or Linux86-64 For installation on an x64 (Opteron, Athlon64, EM64T) processor-based system running a linux86-64 execution and development environment, the PGI CDK installation script will attempt to install both the linux86 version and linux86-64 version of the compiler products requested. If you specify /opt/pgi as the base directory for installation, the following directory structure will be created by the PGI installation script: Name of directory Contents /opt/pgi/linux86/7.0/bin linux86 32-bit compilers & tools /opt/pgi/linux86/7.0/lib linux86 32-bit runtime libraries /opt/pgi/linux86/7.0/liblf linux86 32-bit large-file support libs (-Mlfs) /opt/pgi/linux86-64/7.0/bin linux86-64 compilers & tools /opt/pgi/linux86-64/7.0/lib linux86-64 -mcmodel=small libs /opt/pgi/linux86-64/7.0/libso linux86-64 -fpic shared libraries for

-mcmodel=medium development 

/opt/pgi/linux86-64/7.0/include linux86-64 header files /opt/pgi/linux86/7.0/REDIST Re-distributable runtime libraries /opt/pgi/linux86-64/7.0/REDIST /opt/pgi/linux86/7.0/PORTABLE /opt/pgi/linux86-64/7.0/PORTABLE /opt/pgi/linux86/7.0/EXAMPLES Compiler examples /opt/pgi/linux86-64/7.0/EXAMPLES /opt/pgi/linux86/7.0/doc Documentation /opt/pgi/linux86-64/7.0/doc /opt/pgi/linux86/7.0/man UNIX-style man pages /opt/pgi/linux86-64/7.0/man /opt/pgi/linux86/7.0/jre JAVA environment for PGDBG and PGPROF /opt/pgi/linux86-64/7.0/jre graphical user interfaces /opt/pgi/linux86/7.0/src PGHPF MPI interface file, mpi.c /opt/pgi/linux86-64/7.0/src /opt/pgi/linux86/7.0/bench MPI examples /opt/pgi/linux86-64/7.0/bench /opt/pgi/linux86/7.0/mpi/mpich MPICH scripts and libraries /opt/pgi/linux86/7.0/mpi2/mpich MPICH2 scripts and libraries /opt/pgi/linux86/7.0/osc tutorials /opt/pgi/linux86-64/7.0/osc /opt/pgi/linux86/7.0/cdk OpenPBS TORQUE components /opt/pgi/linux86-64/7.0/cdk The linux86-64 and linux86 compilers and supporting components have the same names. On an AMD64 or EM64T processor-based system running 64-bit Linux, the environment you target by default (linux86-64 or linux86) will depend on the version of the compiler that comes first in your path. Bring up a shell command window on your system. The instructions below assume you are using csh, sh, ksh, or some compatible shell. Appropriate modifications will be necessary when setting environment variables if you are using a shell that is not compatible with one of these three. Step 1 -- Create the directory in which you wish to install the PGI CDK compilers and tools. NOTE: The installation directory you choose must be accessible from all nodes in the cluster using a uniform pathname. In the example below, we assume /opt/pgi which is the default installation directory. However, installation can occur in any directory. Please make sure that the installation directory has the necessary ownership and permissions appropriate for your site by using the chown and chmod commands. Set the environment variable PGI to the name of the installation directory. Assuming csh:

  % setenv PGI /opt/pgi 

Or, assuming sh, ksh, or bash:

  % export PGI=/opt/pgi 

Step 2 -- All software should fit into 250 MB of disk space. If you wish to install all of the source code for the open source components of the PGI CDK, about 350 MB of disk space is required. If you are installing on a linux86-64 environment, add another 250MB of disk space. Verify that you have sufficient space on the disk where your installation directory will be located. Step 3 -- The installcdk script must be run to properly install the software. If you are not logged in as root, the PGI CDK compilers and tools and MPICH libraries can be installed on your current machine, and will be configured for that machine only (i.e., a single node cluster, or a cross development installation). If logged in as root, the entire cluster can be configured and "checked out.", and OpenPBS' can be installed. If you are updating a previous release, or wish to reinstall, it is a good practice to run uninstallcdk before running installcdk. If you are installing from a CD-ROM and you're not sure how to access the CD-ROM drive on your system, check with your system administrator. Typically, you must insert the CD-ROM into the CD-ROM drive on the master node and issue the following command:

 % mount /mnt/cdrom 

while logged in as root to make the data on the CD-ROM accessible. Next, issue the following command from your root window on the master node:

% /mnt/cdrom/installcdk 

The install script will install all of the binaries for the PGI compilers and tools, MPICH, and ScaLAPACK in the $PGI directory tree in the appropriate bin, include, lib, and man subdirectories. It will also install OpenPBS in the /usr/local/pbs and /var/spool/pbs directories, and start the OpenPBS daemons running on the master node and all of the compute nodes in your cluster. You will be prompted for various information about how to configure your cluster as the script executes. Once the installation script has completed, exit the root login. Step 4 -- All of the PGI CDK compilers and development tools are license-managed. The other components of the PGI CDK, including MPICH, ScaLAPACK, and the OpenPBS batch scheduler, are open source products that are not license-managed. If you choose to create a temporary demo license for the PGI compilers and tools, the install script asks for your real name, your username, and your email address. It then creates a fifteen-day license and prints a message like this:

NOTE: your evaluation license will expire in 14 days, 23.6 hours.

  For a permanent license, please read the order acknowledgement that 
  you received. Connect to https://www.pgroup.com/License with the 
  username and password in the order acknowledgement. 

Name: <your name>

  User: <your username> 
  Email: <your email address> 
  Hostid: PGI=9BF378E0131FF0C3CD37F6 
  FLEXlm hostid: 00a024a3dfe7 
  Hostname: yourhost.yourdomain.com 
  Installation: /opt/pgi 
  PGI Release: 7.0 

The message above is also saved to the file $PGI/license.info for retrieval at a later time. Once you have obtained your permanent license keys using your personalized account on the PGI web page, place them in the file $PGI/license.dat. Until the permanent license is obtained, the PGI CDK compilers will only be usable under the username specified above during generation of the temporary keys. Step 5 -- You can view the online HTML interface to the PGI CDK documentation and tutorial materials using any web browser. Enter the following URL in a web browser: file:$PGI/index.htm You can view the online HTML manuals for the PGI compilers and tools directly by entering the following URL in a web browser: file:$PGI/doc/index.htm You may want to place a bookmark on these locations for easy future reference to the online manuals. Step 6 -- Once the temporary or permanent license file is in place, execute the following commands to make the PGI CDK compilers accessible from a normal user shell window. Assuming MPICH1 is installed and you have csh, for linux86 executable development tools: % set path = ( opt/pgi/linux86/7.0/bin /opt/pgi/linux86/7.0/mpi/mpich/bin /usr/local/pbs/bin $path ) Alternatively, for linux86-64 executable development tools:

% set path = ( opt/pgi/linux86-64/7.0/bin /opt/pgi/linux86-64/7.0/mpi/mpich/bin /usr/local/pbs/bin $path )

and for the common documentation:

% setenv MANPATH "$MANPATH":/opt/pgi/linux86/7.0/man:/opt/pgi/linux86/7.0/mpi/mpich/man:/usr/local/pbs/man

Or, assuming sh or ksh, for linux86 executable development tools:

% export PATH=/opt/pgi/linux86/7.0/bin:/opt/pgi/linux86/7.0/mpi/mpich/bin:/usr/local/pbs/bin:$PATH 

Alternatively, for linux86-64 executable development tools: --More--(44%)


As it is mentioned in this manual, we should creatle the direcoty:

root@venus:/opt# mkdir pgi

TO BE CONTINUED!