Red Hat announced it's paying $136 million to acquire Gluster, a startup founded in 2005 with the goal of simplifying storage using open source software and commodity hardware. The company appropriately gets its name from a combination of the words "GNU" and "cluster."
This acquisition marks an exciting new area of potential growth for Red Hat as industry analysts estimate the total addressable market for unstructured data storage at approximately $4 billion and growing.
[ Also on InfoWorld.com: Ascending Open Virtualization Alliance aims to bolster KVM usage. | Read about how Big Switch Networks lured away VMware virtual networking veteran. | Keep up on virtualization by signing up for InfoWorld's Virtualization newsletter. ]
At the heart of the startup company is its technology called GlusterFS, a software-only, scale-out storage system that allows enterprises to combine large numbers of commodity storage and compute resources into a high-performance, centrally managed, and globally accessible storage pool. It is capable of scaling to several petabytes of data, and clusters storage building blocks over Infiniband RDMA (Remote Direct Memory Access) or a TCP/IP interconnect. GlusterFS was built upon an open source model that makes for a good fit with Red Hat's operation.
Currently, GlusterFS supports Apache Hadoop for Big Data applications and can be installed across a host of file systems such as ext3, ext4, XFS -- exposing the file system as a global namespace that spans the storage server nodes as a CIFS, NFS, or Gluster Native mount point. It also sends data to Linux, Unix, and Windows servers, and it has multitenant capabilities that give it added value for use in a private or public cloud.
Gluster's ability to advance Red Hat's storage capabilities offers a unique opportunity for Red Hat and its customers.
"Our customers are looking for software-based storage solutions that manage their file-based data on-premise, in the cloud and bridging between the two," said Brian Stevens, CTO and vice president, Worldwide Engineering at Red Hat. "With unstructured data growth (such as log files, virtual machines, email, audio, video and documents), the '90s paradigm of forcing everything into expensive, single-system DBMS residing on an internal corporate SAN has become unwieldy and impractical."
