The confluence migration is currently ongoing. Please note that any modifications made right now will not be transferred or preserved in the new instance. Plan your activities accordingly to accommodate this limitation. For details on the migration please click here

Transferring Files

You must use SCP (secure copy protocol) to transfer data and other program files between your local machine and Ginsburg. Unix/Linux and Cygwin users can use the scp command, Windows users can use WinSCP, and Mac users can use Fugu. For large file transfers we recommend the use of Globus, documented below.

Please use the server when transferring files. 

For example, this is how you would transfer "MyDataFile" to the cluster using scp from the command line.


If you specify no path after the colon, the file will end up in your home directory (no check for the existence of its older version is performed in this case).

Globus Connect

Globus is a utility (technically, SaaS, or Software as a Service) which among others allows file transfer between personal computers and HPC clusters. It is particularly useful for fast and reliable transfer of very large files, as well as a large number of small files.

To transfer data to/from the HPC clusters, submit our request form to join Columbia's Globus subscription group (you will need to log in first - new users should select Columbia University from the drop-down). Email [email protected] with any questions.

Globus moves data between "endpoints". An endpoint is a unique name representing a Globus resource like a computer or a cluster, typically in the following format: <globus-username>#<machine name>. The endpoints for the resources you'll be using for transferring data need to be added to your account.

Ginsburg's Globus endpoint name: "Columbia Ginsburg"

Terremoto's Globus endpoint name: "Columbia Dixon"

Before connecting, you will need to create your own endpoint on the machine from which or to which you will be transferring data to and from Ginsburg. In order to to this, you'll need to download and run 'Globus Connect Personal' as described in:

Choose between Mac, Linux, or Windows, and follow the instructions for the download.

Once you run the downloaded software, you will be able to, via the online interface, enter the two endpoints of your transfer, specify the paths of the files/directories on the source and destination systems, and launch the transfer. Once it starts, it will take place in the background and you do not need to supervise it or even be logged in. 

Globus is a fairly sophisticated system which allows you also to work via Command Line Interface and programming API, and has other useful features. For details, please visit the site.

Copying files from Habanero or Terremoto

Users that have an account on the Habanero cluster may access Habanero's storage system (/rigel) by navigating to the /rigel directory on Ginsburg transfer and login nodes.

Terremoto users can access their storage system (/moto) by navigating to /moto on the Ginsburg transfer and login nodes.

Note that neither /rigel nor /moto are accessible on Ginsburg's compute nodes.

Managing Jobs

To view all jobs on the system, use the squeue command.

$ squeue

To view information about a particular job, use scontrol.

$ scontrol show job [job ID]

To cancel a job, use scancel.

$ scancel [job ID]

To view fair share information, use sshare.

$ sshare

Other useful commands 

Here's a partial list of useful Slurm commands.

sbatch       # submit a job

sinfo       # list of partitions/queues on the cluster

scontrol show job <jobID>      # see status of running job

sacct -j <jobID>      # see status of completed job

scontrol show node <nodeName>      # information about a node

sshare      # information about fair share

Each command on both systems is naturally replete with flags and optional arguments which customize its functionality. For reference on Slurm. please refer to:

Slurm reference

Using Groups for Collaborative Research

Researchers will often wish to share access to a set of directories and files with a group of users. One mechanism that can be used to accomplish this is Unix groups. Habanero users can create and modify groups without assistance from HPC support by using the group command on Cunix.

To use the group command log in to cunix.columbia.eduThe group command is not available on Habanero itself.

To create a new group:

$ group -c <GROUP_NAME>

To view group members and owners:

$ group -i <GROUP_NAME>

To add a user to a group:

$ group -m <GROUP_NAME> <UNI>

To remove a user from a group:

$ group -M <GROUP_NAME> <UNI>

Group owners can add and remove owners and users. To add a group owner:

$ group -o <GROUP_NAME> <UNI>

To remove an owner:

$ group -O <GROUP_NAME>

Note that existing user sessions will not be affected by changes in group membership. If a user is added or removed from a group they will have to log out and log back in to Ginsburg. Note also that in some cases group changes can take up to an hour to propagate to Ginsburg.

There are many ways to view your group membership. One way is to use the groups command.

$ groups
user burglab

Once a group has been created and users have been added, group members can use the chgrp and chmod commands to set group ownership and permissions on files and directories to values appropriate for sharing. For more information see the manual pages for the two commands.

$ man chgrp
$ man chmod
  • No labels