FAQ

From ScientificComputing
Revision as of 08:27, 19 August 2016 by Sfux (talk | contribs) (Data management and file transfer)

Jump to: navigation, search

Contents

General

Who is ID SIS HPC ?

What services are provided ID SIS HPC ?

Do I need to pay or are the services for free ?

Where can I find more information ?

Can I join ID SIS HPC ?

Access

Who can use the services of ID SIS HPC ?

Do I need an account ?

How do I log in ?

X11-forwarding does not work, what am I doing wrong?

How can I change my password?

Can I change my default shell?

Software

Do you provide any software on your clusters ?

Why does my 32-bit executable not work on your cluster ?

Can I run Windows executables on the clusters ?

Can you please update GLIBC on the clusters ?

Is it necessary to recompile or can I just copy my application to a cluster ?

Are development tools available on the clusters ?

How do I compile MPI applications ?

What scientific libraries are available on the clusters ?

Can you please allow me to run sudo for installing my code ?

Why can't I install my application into /usr/bin and /usr/lib64 ?

Is there a license available for application XYZ ?

Environment modules

Can I automatically load modules on login ?

Is it possible to load modules in a script ?

Module load does not work properly, what am I doing wrong ?

In the application table version X is listed, why does module avail not list it ?

Version X is gone, why did you delete it ?

Submitting jobs

Can I run an application on the login nodes?

Can I access a compute node via ssh or rsh?

How do I execute a program on the cluster?

How do I submit a simple command ?

How do I submit a shell script ?

How do I submit a parallel job ?

What are the processor and time limits ?

What is the maximal amount of memory that I can use ?

Which queue should I choose ?

How many jobs can I submit ?

How much time should I request for my job ?

What happens when a job reaches its time limit ?

How do I submit a series of jobs (job chaining)?

Monitoring jobs

When does my job start ?

How can I check the status of my job(s) ?

Why is my job waiting for a long time in the queue ?

Where is my job's output ?

Can I see my job's output in real time ?

How do I know when my job is done ?

Can I see the resources used by my job(s) ?

How do I kill a job ?

Data management and file transfer

How much disk space is available on then clusters ?

How much space can I use ?

What happens when I reach my quota ?

What if I need more space ?

Why is there a limit for the number of files in my home/scratch directory ?

Why is storage in the cluster expensive ? I can buy a 6 TB external USB hard drive for 170 sFr. almost everywhere

How long can I keep files in the scratch directories ?

Why did you delete my files in scratch ?

Are my files backed up regularly ?

How do I restore a file from a backup ?

What is the fastest way to transfer files from/to the cluster ?

Why is file transfer very slow ?

Miscellaneous