Search Google Appliance

Home >> Advanced Research Computing >> ARC Quick Start Guide

ARC Quick Start Guide

This page contains the information you need to start using ARC systems. 

arcus-b is our largest and newest compute cluster and is the one we recommend to all new users. All of the compute nodes have 16 cores and a range of memory sizes, from 64GB to 256GB; there are also some nodes with GPU capability (Nvidia Tesla K40). Please contact us if you believe your requirements are not satisfied by arcus-b and you need to use one of our other clusters (see Services for more details).

Operating system

arcus-b runs the CentOS 6 Linux operating system; we do not have any clusters running Windows so your software must work on Linux if you want to use ARC systems. If you are unfamiliar with using Linux, please consider:

  • Finding introduction to Linux resources online (through Google/Bing/Yahoo etc).
  • Working through our brief Introduction to Linux course.
  • Atttending our Introduction to ARC training course (this does not teach you how to use Linux but the examples will help you gain a greater understanding).

Connecting to ARC

All ARC systems run the Linux Operating System (as opposed to Windows, MacOS). Linux is commonly used in HPC as a reliable , cost effective operating system. Follow this link for an Introduction to Linux :  http://www.arc.ox.ac.uk/content/introduction-linux

Access to arcus-b (and other ARC systems) is over Secure SHell (SSH). 

How do I login to my account?

Remote access : Once you get your account you need to remotely access ARC systems. Linux, Mac users (and other Unix/Unix-like) should use ssh (secure shell) to connect to the ARC systems from a terminal 

ssh -X username@arcus-b.arc.ox.ac.uk

Windows users should download and install an application called PuTTY (ssh client for windows) and Xming (or VcXsrv) for X11 support . You can find information about installing PuTTY on your PC :  

https://help.it.ox.ac.uk/services/linux/putty/index

 

For HostName enter arcus-b.arc.ox.ac.uk

Enter your arc userid and password. 

If you need to configure PuTTY to open arc remote server for graphical display work then: In the PuTTY configuration window, select [Connection] [SSH] [X11]" and make sure the [Enable X11 forwarding] box is checked, then return to the [Session] category and click [Open] when you are ready to connect to the specified machine.

arcus-b is only accessible from within the University of Oxford network. If you are not on the University network, please read our page on Connecting to ARC from outside the University network.

How do I copy data to/from ARC ?

You can use either scp (secure copy) or secure file transfer protocol (sftp) . MacOS (terminal) and Linux have scp and sftp built in.

Windows users can use an application like WinSCP

How do I change my password?

User account management is performed on myaccount.arc.ox.ac.uk (use ssh to connect) . Passwords can be changed by running the “passwd” Command from a terminal on login node

user@myaccount:~$ passwd Enter login(LDAP) password:

Enter new passwd: Re-enter new passwd: Forwarding email addresses can be changed, please ask the arc team : support@arc.ox.ac.uk

Batch vs Interactive job ?

An interactive job starts when you logo on to the system and ends when you logout. During the run, you interact with the system, for example, when you can choose an option .

A batch job is a predefined group of processing actions that require little or no interaction between you and the system. When you submit the batch job, the job enters a queue where it waits until the system is ready to process the job.

SLURM – Queueing system in arcus-b

Job scheduling and workload management on arcus-b is managed by SLURM ( Simple Linux Utility for Resource Management).

 

How do I submit a batch job ?

You need to use a shell script with instructions to SLURM instructions. Shell commands indicate what is to be done in the job.

Edit your script on the login node . At the prompt use a standard editor such as nano .

Prompt> nano job1.run

Add the following lines as an example , requesting two compute nodes, running 16 processes per

node with a two hour wall time, enter the following lines:

#!/bin/bash

#SBATCH --nodes=2 

#SBATCH --ntasks-per-node=16 

#SBATCH --time=02:00:00 

#SBATCH --job-name=myjob . enable_arcus-b_mpi.sh 

mpirun myprogram

 

Basic SLURM Commands

  •  sbatch: Submit job (text file) to queue for example sbatch job1.run
  •  squeue: Monitor the queue
  •  scancel: Cancel the job (made a mistake?)
  •  srun: used to submit a job for execution in real time
  •  sinfo: reports the state of partitions and nodes managed by SLURM
  •  sacct: report job accounting information for active or completed jobs
  •  salloc: allocate resources in real time

ARC Accounts

All jobs (regardless of whether they are free or charged) consume credits. Credits are usually consumed at the project level , Use the command mybalance to check your credits

Common problem on arcus-b cluster:

“JobHeldAdmin” = normally means your project has run out of credit

Further help

Manual (or man) pages

Works for many Linux commands , e.g. man sbatch (Quit the man page with the 'q' key)

For support email support@arc.ox.ac.uk

Disk space

Users have a $HOME area with a 15GB quota; this is where you log in to. Users also have a $DATA area which shares a 5TB quota with your project colleagues. As a rule we recommend that you use your $DATA area for your work. For more details on where you can store files, please see our Storage page.

Software

There are many software packages already installed; these are managed through the environment modules system. You will find advice on how to run some of the more popular applications under the applications & software section of our support pages. You can also build your own software in your home or data directories using one of the compilers provided (which are also available through the environment modules system).

Running jobs

To do work on arcus-b, you will need to submit a job to the job scheduler; the login nodes are for preparing the work that you need to run and should not be used for performing computational work. arcus-b uses the slurm job scheduler and you will find information on preparing your job submission script on our slurm pages. When requesting resources in your job submission script, it is important to know that the smallest unit you can request is a single node (or a single GPU) so please contact us if you need help with getting more out of your requested resources.

Running jobs consume credits on ARC. Please read our Accounting System and our Requesting Credits pages for an explanation as to how credits are calculated and how to request more.

Training

ARC run a number of training courses that can help you get more from the ARC facility, and teach you parallel programming (for example). For a full list of courses please see our Training page.

Service area: 

Written by IT Services. Latest revision 30 November 2017