The Panasas ActiveScale File System (PanFS) integrates an object-based clustered architecture to orchestrate file activity across the Storage Cluster and manage system performance. The file system virtualizes data across all StorageBlade modules, and presents a single, cache coherent unified namespace.

PanFS simultaneously supports two high-performance data access modes: the DirectFLOW data path and the NFS/CIFS data path.

• DirectFLOW - A powerful "out-of-band" solution, DirectFLOW enables direct and highly parallel data access between StorageBlade modules and Linux cluster nodes. Cluster nodes are able to directly access data on StorageBlade modules in parallel.
• NFS/CIFS – The file system also operates "in-band" supporting both NFS and CIFS file access protocols. Here, DirectorBlade modules serve as a gateway between NFS and CIFS clients and StorageBlade modules. Performance can be scaled by simply adding DirectorBlade modules.

The PanFS file system is designed to dynamically link DirectorBlade modules and StorageBlade modules together into a single clustered storage network. Unlike traditional network storage systems that require expensive file server upgrades, the performance of a Panasas system can be easily increased by adding DirectorBlade modules and StorageBlade modules to provide a single, scalable Storage Cluster. Each new DirectorBlade module adds a data path and boosts overall system performance.

PanFS has the ability to support all three data access protocols – DirectFlow, NFS and CIFS – simultaneously. Multiple clients (server nodes or workstations) can access the Panasas storage cluster using the protocol required by that client. This delivers an unprecedented level of flexibility to optimize the utilization of the storage system.