DragonFlyBSD: Designing a Highly Available Clustering Filesystem

ふらふらっと Kernel Trap の記事 に辿り着きました。なんだかすごいファイルシステムを作ろうとしているようです > Matt さん。

Matt Dillon posted the design synopsis of a new highly available clustered filesystem he will soon begin writing for DragonFlyBSD. The feature summary at the beginning of his document included, "on-demand filesystem check and recovery; infinite snapshots; multi-master operation, including the ability to self-heal a corrupted filesystem by accessing replicated data; infinite logless replication, meaning that replication targets can be offline for 'days' without effecting performance or operation; 64 bit file space, 64 bit filesystem space, no space restrictions whatsoever; reliably handles data storage for huge multi-hundred-terrabyte filesystems without fear of unrecoverable corruption; cluster operation, provides the ability to commit data to locally replicated store independantly of other replication nodes, with access governed by cache coherency protocols; independant index, data is laid out in a highly recoverable fashion, independant of index generation, and indexes can be regenerated from scratch and thus indexes can be updated asynchronously." He then goes into detail on each of these points and many more, explaining how he intends to implement the new filesystem.


Sun MicrosystemsZFS のイメージが浮かんだんですが、全然違うんでしょうか?