The Red Hat Storage team would like to congratulate the Gluster Community on the beta release of GlusterFS 3.4. With new features and enhancements in cloud, virtualization, and performance, the beta version of GlusterFS 3.4 brings high reliability, scalability, and data mobility to users and application developers.

GlusterFS is an open source, distributed file system capable of scaling to several petabytes (actually, 72 brontobytes!) while handling thousands of clients. GlusterFS functions as a distributed data overlay, pooling together storage building blocks over TCP/IP, aggregating disk resources and managing data in a single global namespace. GlusterFS is based on a stackable user space design and can deliver linear scale-out performance for diverse workloads.

We hope you’ll be as excited as we are about the new features and capabilities in the GlusterFS 3.4 beta.

VM Image Handling and QEMU Integration

• QEMU integration with libgfapi
• New Block Device translator
• Support for FUSE bypass using libgfapi
• Performance improvements for VM image storage for KVM

Virtualization Management User Interface

• oVirt 3.2 includes GlusterFS management GUI
• RESTful API gateway via oVirt for integration with management tools

Server Quorum, Security, and Glusterd

• Quorum for split-brain resolution now supports replica 2 configurations
• Support for SSL-based encryption of ‘in-flight’ data
• Multi-threaded glusterd for better performance
• Duplicate Request Cache (DRC) for GlusterNFS to prevent data loss from RPC failures
• Operating version support for glusterd, enabling easier upgrades and using multiple versions of GlusterFS
• NFSv3 ACL support

The Gluster community is extremely appreciative to the key GlusterFS contributors, such as Bharata B. Rao, M. Mohan Kumar and Deepak C. Shetty from IBM. GlusterFS is only successful through input and feedback from the community, so we welcome your comments. To give these new features and enhancements a test drive, download the GlusterFS 3.4 beta at the Gluster Community site.