User Tools

Site Tools


cluster:4

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

cluster:4 [2006/12/07 14:10] (current)
Line 1: Line 1:
 +\\
 +**[[cluster:​0|Home]]**
  
 +===== Cluster Configuration =====
 +
 +
 +In general, the cluster configuration should remain as "​standard"​ as possible; this is not be a bleeding edge venture.  ​
 +
 +Some general information gleaned from our anticipated user base:
 +
 +  * Software: mostly home grown code, C/C++ and Fortran programs (probably a Portland suite of compilers), Matlab (and MatlabMPI), AMBER, NAMD, CHARMM, and Gaussian.
 +
 +  * 64 bit compilations will be required, as is a 64-bit operating system with 32-bit backward compatibility
 +
 +  * Most application programs will be floating point and CPU intensive versus relatively few integer and data intensive applications
 +
 +  * A Linux operating system is required. ​
 +  ​
 +  * A ROCKS based implementation is preferrable with PBS as the scheduler (at least most users had experience with this). ​
 +
 +  * MPI will be required, preferably to as many work nodes as possible
 +
 +  * Any other cluster management tools for monitoring, administration,​ etc., will be a plus.
 +
 +----
 +
 +Here is a rough hardware configuration guide ...
 +
 +  * 1 head node (Dual Intel 5148 processors, 2 GB RAM, mirrored 80 GB HD, 2 channel FC HBA) on private & public network
 +
 +  * 1 NFS node (Dual Intel 5148 processors, 2 GB RAM, mirrored 80 GB HD, 2 channel FC HBA) on private & public network
 +
 +  * 60 lightweight work nodes (Dual Intel 5148 processors, 2 GB RAM, single 80 GB HD (or smaller)) on private network
 +
 +  * 4 heavyweight work nodes (Dual Intel 5160 processors, 16 GB RAM, single 80 GB HD (or smaller)) on private network
 +
 +  * Sixteen of the lightweight work nodes should be interconnected via Infiniband for low latency. The rest should be interconnected via gigabit ethernet.
 +
 +  * Although local disk space is available, our NAS/SAN filesystems will provide the storage area for datasets and home directories
 +
 +----
 +
 +The quote should include all racks, power distribution,​ and UPS equipment needed to house and run the cluster. The quote should also include the network switch equipment required for internode communication.
 +
 +We will want the equipment to be assembled, racked, and imaged by the vendor either onsite or prior to delivery (no preference). We will require 24/7/4hr support for the master and NFS nodes, and 24/7 support for OS/​software. NBD
 +support will be sufficient for the compute nodes. The duration of all support should be three years. After
 +delivery/​installation,​ we will require cluster administration training/​knowledge transfer for our UNIX administrators. All these costs should be reflected in the quote.
 +
 +\\
 +**[[cluster:​0|Home]]**
cluster/4.txt ยท Last modified: 2006/12/07 14:10 (external edit)