Lustre RA High Performance Storage Solution

• High Performance: Designed for maximum I/O throughput, achieving several terabytes per second of sustained I/O bandwidth.
• Scalability:Effortlessly scale to support thousands of clients and handle hundreds of petabytes of storage without any need for modifications.
• Open source:Benefit from continuous community-driven development, ensuring rapid innovation, wide compatibility, and cost savings on licensing fees​.
• Tunability: Lustre offers extensive configuration options, allowing the allocation of files across the system based on different workload types and specifying which servers or groups of disks files should be allocated to.
• Configurable Networking:Lustre includes built-in features to control network utilization and allows servers to act as “gateway routers” for communication across different network types, such as Ethernet and InfiniBand.
• Migration:With a skilled admin team, phasing out old hardware and storage, and migrating data to new storage, becomes a seamless process.
• Ease of Integration:Easily integrates into existing Lustre installations. Because Lustre supports a limited number of operating systems and versions, its specialized focus ensures optimized performance and reliability within the Lustre platform.

Lustre requires a skilled administrative staff for proper maintenance. Organizations such as the Department of Energy National Laboratories including Lawrence Livermore, Sandia, Oak Ridge as well as Los Alamos’ Cielo supercomputer is supported by the Lustre file system.