Welcome, Please Sign In

Get in touch with your rep, view past orders, save configurations and more. Don't have an account? Create one in seconds below.

login

Lustre RA High Performance Storage Solution

High-Speed, Scratch-Based Storage for HPC

Lustre is an open source, high-performance parallel file system widely used in HPC environments to manage large-scale storage and I/O operations efficiently. It is primarily designed as a high-speed storage solution to ensure quick file access, preventing file access from becoming a bottleneck in HPC compute jobs.

Key Features:

We can assist you whether you need to integrate your new storage solution into an existing network or set up something completely new.

  • 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 due to the size of their machines and I/O requirements.

Use Cases and Applications


Scientific Research



Machine Learning/AI



Government & Defense



Seismic Processing



Oil & Gas



Lustre storage is best known for powering 7 of the 10 largest HPC clusters in the world, with many of these systems supporting:

  • 10,000+ clients
  • 100s of PB of storage
  • 100s of GB/sec of I/O throughput

Custom Storage Solutions

At Silicon Mechanics, we specialize in designing and implementing Lustre storage systems tailored to your unique requirements. Our collaborative process ensures that your storage solution is co-designed with your specific needs in mind, from initial planning to deployment. You can rely on us for expert answers and guidance on how to get started, including:
  • Designing a robust hardware and software architecture
  • OS support options
  • Integrating with existing systems, interfaces, and applications
  • Tuning and optimizing system performance

Support and Services

Silicon Mechanics offers comprehensive support and maintenance services, providing you with peace of mind and ensuring that your Lustre storage system operates efficiently and reliably over time.

Expert Included

Our engineers are not only experts in traditional HPC and AI technologies, we also routinely build complex rack-scale solutions with today's newest innovations so that we can design and build the best solution for your unique needs.

Talk to an engineer and see how we can help solve your computing challenges today.