Changes between Version 4 and Version 5 of LimulusSoftware


Ignore:
Timestamp:
01/19/11 17:14:12 (13 years ago)
Author:
admin
Comment:

updated software list and added power control topic

Legend:

Unmodified
Added
Removed
Modified
  • LimulusSoftware

    v4 v5  
    1 The following is a list of basic cluster RPMS that will be included in the software stack. We plan on  
    2 creating a custom Fedora Spin for Limulus. This list is certainly going to change.  
     1== Automatic Power Control == 
    32 
    4  * [http://fedora.redhat.com Fedora 8] 
    5  * [http://www.perceus.org/portal/project/warewulf Warewulf Cluster Toolkit] - Cluster administration and monitoring (A move to [http://www.perceus.org/portal/project/perceus Perceus] is planned) 
     3One key design component of the new Limulus case is aoftware controlled power to the nodes. This will allow nodes to be powered-on only when needed. As an experiment, a simpel script was written that monitors the Grid Engine queue. If there are jobs waiting in the queue, nodes are powered-on. Once the work is done (i.e. nothing more in the queue) the nodes are powered off). 
     4 
     5As an example, an 8 core job was run on the Norbert cluster (in the Limulus case). The head node has 4 cores and each worker node has 2 cores for a total of 10 cores. An 8 node job was submitted via Grid Engine with only the head node powered-on. The script noticed the job waiting in the queue and turned on a single worker node to give 6 cores total, which were still not enough. Another node was powered-on and the total cores reached 8 and the job started to run. After completeion, the script noticed that there was nothing in the queue and shutdown the nodes.  
     6 
     7== Update January 2011 ==  
     8The following is a list of basic cluster RPMS that will be included in the software stack. The base distribution will be Scientific Linux. 
     9 
     10 * [https://www.scientificlinux.org/ Scientific Linux V5.4] 
     11 * [http://www.perceus.org/ Perceus Cluster Toolkit] - Cluster administration  
    612 * [http://www.llnl.gov/linux/pdsh/pdsh.html PDSH] - Parallel Distributed Shell for collective administration 
    713 * [http://gridengine.sunsource.net Sun Grid Engine] - Resource Scheduler  
     
    1117 * [http://modules.sourceforge.net Modules] - Manages User Environments  
    1218 * [http://www.csm.ornl.gov/pvm/pvm_home.html PVM] - Parallel Virtual Machine (message passing middleware) 
    13  * [http://www-unix.mcs.anl.gov/mpi/mpich1 MPICH] - MPI Library (message passing middleware) 
    1419 * [http://www-unix.mcs.anl.gov/mpi/mpich2 MPICH2] - MPI Library (message passing middleware) 
    15  * [http://www.lam-mpi.org LAM/MPI] - MPI Library (message passing middleware) 
    1620 * [http://www.open-mpi.org OPEN-MPI] - MPI Library (message passing middleware) 
    1721 * [http://math-atlas.sourceforge.net ATLAS] - host tuned BLAS library