Caringo Swarm Deployed in Jasmin Super Data Cluster Environment

Caringo, Inc. announced that Swarm Object Storage has been deployed by the JASMIN facility, a super-data-cluster that delivers infrastructure for data analysis funded by the Natural Environment Research Council (NERC) the UK Space Agency (UKSA), educational institutions and private industry.

JASMIN is managed jointly by the UK’s Science and Technology Facilities Council (STFC) Scientific Computing Department (SCD) and the Centre for Environmental Data Analysis (CEDA), which is part of STFC’s RAL Space research and technology development facility.

Due to increasing capacity needs, a growing researcher base and a shift in access from traditional file protocols to RESTful interfaces, the infrastructure managers at STFC started looking for methods to streamline infrastructure management, tenant management, access controls, and private and public file sharing. Their research led them to object storage.

The object storage solution selected needed to achieve read performance characteristics similar to existing parallel file systems. In the benchmark testing, Caringo Swarm delivered 35GB/s read and 12.5 GB/s write aggregate S3 throughput. Additionally, NFS throughput benchmarks via a single instance of SwarmNFS delivered 1.6GB/s sustained streaming (3PB+ per month) with no caching or spooling.

“The performance figures achieved are the result of Swarm’s unique parallel architecture that’s free of the bottlenecks inherent in other object storage solutions on the market,” said Tony Barbagallo, Caringo CEO. “These results are similar to what parallel file systems achieved in the same environment and we have a solid roadmap to continued performance improvements in future Swarm releases.“

The infrastructure for JASMIN is designed, deployed and managed by the SCD  team at STFC Rutherford Appleton Laboratory. STFC is a multi-disciplinary science organization with the goal to deliver economic, societal, scientific and international benefits to the UK and its people-and more broadly, to the world.

The first phase of JASMIN was funded in 2011 and deployed in 2012. Since then, hundreds of petabytes of data have been processed and thousands of researchers have accessed the platform.