Avogadro

Revision as of 14:19, 7 August 2021

Description

Avogadro is the largest, but oldest, cluster in the C3P facility. It is equipped with the following hardware/software:

• 71 nodes with 2 x CPU Intel Woodcrest Dual Core 2.6 GHz (4 cores), 2 x HD SAS 72 GB, 8 GB RAM, Infiniband, OS Red Hat Enterprise Linux WS release 4
• 9 nodes with 2 x CPU Intel Woodcrest Quad Core 2.6 GHz (8 cores), 2 x HD SAS 72 GB, 16 GB RAM, Infiniband, OS Red Hat Enterprise Linux WS release 4

for a total of 80 nodes, 356 cores.

Access

• Linux and Mac OS users can login using a terminal. Windows 10 users can use the PowerShell.

The first step si to open a tunnel. Within the DiSC internet this can be simply done as:

ssh -L 2000:192.168.16.253:22 account@192.168.9.15 -p 7000

or from outside the Department using

ssh -L 2000:192.168.16.253:22 account@147.162.63.10 -p 7000

where "account" is the user's account.

Then, in a different shell, login as:

ssh -p 2000 account@localhost

Queues

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

• avogadro: max nodes 40, max walltime 336:00:00 (2 weeks)
• avogadro-test: max nodes 1, max walltime 10 min
• avogadro-long: max 10 nodes, 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 this penalty is applied: a maximum of total 2 jobs can run at the same time on this queue.

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 queue
#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.