What is it about?

Large-scale simulation often generates an extensive volume of transitional data that is only needed during the runtime of jobs. Efficient management of temporary storage space for transitional data is critical for HPC centers. An automated tool cleans up temporary storage and significantly increases storage usage.

Featured Image

Why is it important?

We create a tool with automatic workflow to manage two parallel filesystems: GPFS and Lustre by periodically cleaning up the storage space. This tool significantly reduced staff time on storage management and enforced the policy.

Read the Original

This page is a summary of: A Fully Automated Scratch Storage Cleanup Tool for Heterogeneous Parallel Filesystems, July 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3491418.3530761.
You can read the full text:

Read

Contributors

The following have contributed to this page