Gibbs

Revision as of 15:19, 12 September 2018

Description

Gibbs is equipped with the following software/hardware:

• 6 nodes with 2 x CPU Intel Xeon Octa Core (16 cores), 128 GB of RAM, 2 x 300 GB HD SAS (10 krpm), OS Red Hat Enterprise Linux Server release 6.3
• 4 nodes with 2 x CPU Intel Xeon 10 Core (20 cores), 128 GB of RAM, 2 x 300 GB HD SAS (10 krpm), OS Scientific Linux release 6.6
• 4 nodes with 1 x CPU Intel Xeon 24 Core, 256 GB of RAM, 2 x 300 GB HD SAS (10 krpm), OS Scientific Linux release 6.6

for a total of 14 nodes, 272 cores.

Access

• Linux and Mac OS users can login within the DiSC internet connection using a terminal with the command:

ssh account@192.168.9.15

or from outside the Department using

ssh -p 50000 account@147.162.63.10

where "account" is the user's account.

• Windows users can use an interface program to the ssh service, e.g. Putty.

Queues

The queue manager is PBS and the following queues are available:

• gibbs: max nodes 4, max walltime 336:00:00 (2 weeks)
• gibbs-long: max 1 node, max walltime 1500:00:00 (ca. 2 months). This queue is to be used strictly to run jobs that do not allow checkpointing of the status of the calculation. This is considered an exceptional case, thus penalties are applied: i) a maximum of total 1 jobs can run at the same time on this queue, and ii) the initial priority is set to -1440 minutes, meaning that with respect to the normal queues, jobs on the avogadro-long queue shall wait for an additional day.

Example PBS file

A typical PBS input file script will be as follow (see the Support page for more help):

#!/bin/sh --login
#PBS -N jobname
#PBS -A account
#PBS -q gibbs
#PBS -l nodes=n
#PBS -w time in hh:mm:ss format

commands to execute

where the parts in italic should be changed as appropriate.