Cluster File System Manager

Z RESEARCH enables customer with little or no experience in clustering to build Clustered File Storage, HPC Clusters and Supercomputers from Commodity off the Shelf Components (COTS) using Clustered architecture and Z RESEARCH'S software stack 'Gluster'.  The goal is to truly commoditize Supercomputing, Superstorage and High Performance Computing.

• Scales to Petabytes - GlusterFS aggregates heterogeneous storage bricks(servers) over IB or TCP/IP interconnects into one large parallel network file system. GlusterFS sits “on top” of any POSIX compliant OS/file system (ext3/xfs/reiser/etc) and is simple to deploy. A 2-3 node, generic glusterfs cluster can be deployed in less than 30 minutes.
• GlusterFS is not distribution or distribution version specific –  works with almost any POSIX Compliant Operating System - Linux, FreeBSD, OS X, Open Solaris, etc.
• GlusterFS can be configured with no single point of failure, it is completely distributed and there is no centralized meta-data servers. Users can recover their files and folders even without GlusterFS.
• GlusterFS cluster capacity is seamlessly increased by simply adding another brick/server to the storage cluster configuration file, performance increases linearly with the increase in the number of storage bricks.
• GlusterFS storage bricks/servers can be made of any commodity x86-64 server with commodity hard drives and RAID controllers, hence GlusterFS based solutions cost a fraction of conventional, proprietary, SAN based clusters.
• GlusterFS is highly configurable. Features (called “translators” in gluster speak) are added/removed by editing a simple configuration file.
• GlusterFS has a very small footprint – glusterfs’ performance is achieved while running in user space, NOT kernel space. Configuration changes and updates have minimal impact on your production.