The Tux3 Linux BTree-based file-system that isn't yet mainline in the Linux kernel is continuing to focus on new features and capabilities.
I'm in the process of preparing some Tux3 file-system benchmarks on Phoronix compared to Btrfs, EXT4, XFS, etc. In the process of benchmarking Tux3, I've also been looking to see what the latest activity has been for this out-of-tree project. The last time I wrote about Tux3 was last May when they claimed to be faster than Tmpfs
and previous to that was a Tux3 status update
In digging through more recent Tux3 information, this month they did publish their data compression design documentation
. Tux3 will be aiming for transparent dats compression on the file-system at both the complete file-system and per-file levels. Initial details are available on their mount option and ioctl plans along with handling of meta-data for compressed file-systems.
Also published this month were details on their psuedocode for allocation heuristics
While coming out last month was also design information on Shardmap
, the successor to HTree. "From time to time, one may fortunate enough to be blessed with a discovery in computer science that succeeds at improving all four of performance, scalability, reliability and simplicity. Of these normally conflicting goals, simplicity is usually the most elusive. It is therefore with considerable satisfaction that I present the results of our recent development work in directory indexing technology, which addresses some long-standing and vexing scalability problems exhibited by HTree, my previous contribution to the art of directory indexing. This new approach, Shardmap, will not only enhance Tux3 scalability, but provides an upgrade path for Ext4 and Lustre as well. Shardmap is also likely to be interesting for high performance database design. Best of all, Shardmap is considerably simpler than the technology we expect it to replace."
While these improvements are interesting, Tux3 remains an out-of-tree file-system with no immediate sight on being merged into the mainline Linux kernel or any time-frame for becoming a stable file-system, but it will be interesting to see how the Tux3 benchmarks perform. Additionally, while design documents have been published, the latest Tux3 commits were made one month ago per GitHub