You are viewing an old version of this page. View the current version.

Compare with Current View Page History

Version 1 Next »

The following tables shows HPC filesystems, ordered by confirmed performance.  Some adjustment has been made for "likely perceived performance".

RankFilesystemSize (GiB)Retention
1/tmp 30030 days
2/fast 7,15030 days
3/gpfs01 528,384Determined by QCIF/ARDC
4/scratch 81,917365 days
5/home524,285Duration of your association with JCU research 

Most researchers will probably simply run their computational workflows under /home - for simplicity.  Generally speaking, the performance of a /home  filesystem will be not part of any purchasing consider. 

The /gpfs01 filesystem is only accessible to researchers associated with a QRISCloud/ARDC storage allocation (data housed in/near Brisbane).  It's performance ranking is based on files held on the local cache.

Researchers with workflows that are I/O intensive would benefit from using /tmp/fast, or /scratch for execution of their workflows.  A typical I/O intensive workflow (commands in PBS script files) should follow:

  1. Create a subdirectory which will be used to run your workflow (e.g., mkdir -p /fast/jc012345/workflow_name).
  2. Copy files into the created subdirectory.
  3. Execute job(s) associated with your worfklow.
  4. Copy files that have long-term value back to your somewhere within your home directory.
  5. Remove the subdirectory that your created (e.g., rm -rf /fast/jc012345/workflow_name).
  • No labels