frost user document heading  
               
NCAR
Last update: 11/20/2007

Frost user doc contents

User access

Interactive access

Frost has two login nodes for interactive use. Note that to compute on the TeraGrid, you must log in to the proper node using the method below. Interactive computing on frost is similar to working in any other UNIX environment.

Logging in with an NCAR account

NCAR users need a CryptoCard to log in to Frost. To log in, use the following instructions:

  1. ssh to frost.ucar.edu
  2. Log in using your UCAS login name and password
  3. At the CryptoCard Challenge prompt,enter your PIN on your CryptoCard and press ENT
  4. Type the number that appears on the card at the CryptoCard Challenge prompt.

Example:

$ ssh joeuser@frost.ucar.edu
gatekeeper password: 
CryptoCard Challenge "71975212": 000-0000

Logging in with a TeraGrid account

The recommended method of logging in to TeraGrid resources is to obtain a single sign-on certificate. Single Sign-On refers to the ability to log in from one location, authenticating yourself so that you will be recognized by all TeraGrid resources without having to repeatedly enter your login information for each command or resource. All TeraGrid users can log in via Single Sign-on, which is based on Grid Security Infrastructure (GSI), a part of the Globus Toolkit. Authentication on TeraGrid resources is accomplished through user certificates and recognized certificate authorities (CAs).

To set up single-sign on, please see the document:

    http://www.teragrid.org/userinfo/access/sso_quickstart.php

You can also use gsissh from a TeraGrid system to log in to frost via the addresses below:

 tg-login.frost.ncar.teragrid.org 	|    User Logins
 gridftp.frost.ncar.teragrid.org 	|    GridFTP
 gatekeeper.frost.ncar.teragrid.org 	|    Globus/GRAM. (Use the 'jobmanager-cobalt' job manager).

Batch access

The Cobalt scheduler, designed by Argonne National Laboratory, provides batch job management for frost. Cobalt currently supports partition sizes between 32 and 1024 nodes. A partition of the appropriate size will be automatically selected based on the number of nodes you request for your job. However, when using partitions of 512 nodes or less, the 3D-torus network is reduced to a 3D mesh (i.e. the wrap-around edges are inaccessible.) Cobalt on frost is currently configured with these partition sizes: 32, 64, 128, 256, 512, and 1024. For information about using Cobalt to submit jobs, see Job submission on frost in this document.

Wallclock time limits

To expedite turnaround in the batch queues, please specify a time limit for your job that is smaller that the default maximum time limit if possible.

Time limits apply to the frost queues. These are specified at Queues for batch jobs on frost. You may pre-arrange longer wallclock limits by contacting CISL Consulting Services (consult1@ucar.edu, 303-497-1278) and explaining your need, including the desired wallclock limit and the calendar interval for which you need it.


Next page | Table of contents - Frost user guide

If you have questions about this document, please contact CISL Customer Support. You can also reach us by telephone 24 hours a day, seven days a week at 303-497-1278. Additional contact methods: consult1@ucar.edu and during business hours in NCAR Mesa Lab Suite 39.

© Copyright 2004-2007. University Corporation for Atmospheric Research (UCAR). All Rights Reserved.

Address of this page: http://www.cisl.ucar.edu/docs/frost/access.jsp