Designed to meet the demands of the world's largest high-performance compute clusters, the Lustre file system redefines scalability and provides groundbreaking I/O and metadata throughput. An object-based cluster file system, Lustre currently supports tens of thousands of nodes, petabytes of data, and billions of files — and development is underway to support one million nodes, trillions of files, and zetta to yotta bytes.
At a Glance
Production-quality stability and failover
No single point of failure
Scales to meet high performance computing demands
Supports unprecedented metadata and I/O performance rates
Aggregates petabytes into a group or enterprise-wide file system
