Skip to content

Elm documentation#

Welcome to Elm!#

Elm Tree Icon

Elm is an innovative tape-based object store project designed at the Stanford Research Computing (SRC) to address the large data archiving needs of the Stanford research community. Architected and administered by Stanford Research Computing (SRC), Elm provides affordable and scalable storage facilitated through the S3 API.

Why use Elm?#

Elm was designed with the following objectives in mind:

Objectives

On-prem data archiving service for research

Extreme scalability (>200 PB of data)

Optimized for large files, with the capacity to store up to 2,000 objects (files) for every 1 TiB

High throughput and high capacity

Interoperability via S3 object store API (cloud-like) service interface

Protect from vendor lock-in and cost escalation through open source software

Designed for

  • Archiving research data for future reference, such as field studies, simulations, and image data

  • Preserving research data to meet project or institutional requirements, such as data for regulatory/policy compliance

  • Backing up research data in the long term, such as one-time or annual backups of large datasets

Elm is supported by the Stanford School of Medicine, the Office of the Vice Provost and Dean of Research and University IT.