Reiser5 File-System Working On New Features Like Data Tiering, Burst Buffers

Reiser5 was announced back on New Year's Eve with support for local volumes and supporting parallel scaling out and other improvements over the long-in-development but never mainlined Reiser4. While Reiser5 was not met with enthusiasm, Edward Shishkin has continued working on this next-generation file-system and today announced the latest round of improvements.

Shishkin announced today with support for dumping peaks of I/O load to a proxy device with Reiser5, "Now you can add a small high-performance block device to your large logical volume composed of relatively slow commodity disks and get an impression that the whole your volume has throughput which is as high, as the one of that "proxy" device!"

The former Namesys developer that previously worked alongside Hans Reiser also announced work on speed-ups of atomic updates in user space, work-in-progress speeding up of all synchronous modifications, meta-data migration, and related work.

Those interested in some of the latest file-system innovation work happening as part of Reiser5 can read this mailing list thread posted minutes ago by Edward Shishkin. In going along with the latest work, Shishkin posted updated Reiser5 patches for the kernel driver and user-space programs.