Skip to content Skip to site navigation Skip to service navigation

Frequently Asked Questions


Can I Access Oak from Sherlock?
Oak storage is available from all nodes on Sherlock under /oak. Like Sherlock’s /scratch, Oak is based on the Lustre parallel filesystem and is connected to Sherlock (2, 3 and 4) through a low-latency Infiniband network.

Important! You need an account on both Oak and Sherlock to access Oak from Sherlock. The environment variable $OAK should be defined on Sherlock and contains the path to your primary Oak group directory. You may also use the full path starting with /oak as described above.
Can I Access Oak from SCG?
As of January 2020, all SCG labs (in /labs) and projects (in /projects) are hosted on Oak. When you get access to a lab or project in SCG, you also get access to the corresponding space in Oak. SCG is connected to Oak using a pair of 100 Gigabit Ethernet Lustre routers.

Groups who directly rent Oak storage will be able to access that Oak storage under /oak, so long as SCG users are in the corresponding workgroup. The groups used to manage SCG labs and projects space are separate from the workgroups used to manage directly-rented Oak space.

The $OAK environment variable is not set on SCG.
Can I Archive files to Oak from Sherlock?
The mpiFileUtils utilities are designed to copy files in parallel so you can quickly archives terabytes of data from scratch to Oak. The example below shows how to launch screen and launch a job that uses the dcp tool to copy a large directory:

[login_node ~]$ screen
[login_node ~]$ module load system mpifileutils
[login_node ~]$ srun -p dev -n 2 dcp $SCRATCH/dir $OAK/scratch_archive/

If you’re a Sherlock owner, you may want to replace -p dev with -p your_partition and increase the number of MPI tasks (-n) to copy even faster!
Can I access Oak from my desktop/laptop?
Yes, please see the Oak Gateways page.
Can I mount Oak on my own Linux cluster at Stanford?
Yes, the SRCC team can deploy specific Oak NFSv4 gateway(s) to mount your Oak group/project directory on your Linux-based compute cluster (or desktop for specific applications). It is mandatory to use SUNet IDs on your cluster and Kerberos is required to access Oak. Such a service will incur additional costs to the PI.


What about automatic backups?
While the hardware configuration is quite robust, Oak does not provide local or remote data backup by default, and should be considered as a single copy. Research Computing now offers a managed backup service of your Oak space to cloud storage. See our Oak backup information page for more information and please don't hesitate to reach out. Such a service will incur additional costs to the PI.
Last modified July 1, 2024