[go: up one dir, main page]

RozoFS is a free software distributed file system. It comes as a free software, licensed under the GNU GPL v2. RozoFS uses erasure coding for redundancy.[1][improper synthesis?]

RozoFS
Developer(s)Rozo Systems, SAS.
Stable release
2.5.1 / 26 February 2018 (2018-02-26)
Written inC and Python
Operating systemLinux, Mac OS X, NetBSD, FreeBSD, OpenSolaris
TypeDistributed file system
LicenseGNU General Public License v2
Websitewww.rozosystems.com

Design

edit

Rozo provides an open source POSIX filesystem, built on top of distributed file system architecture similar to Google File System, Lustre or Ceph. The Rozo specificity lies in the way data is stored. The data to be stored is translated into several chunks using Mojette Transform[2] and distributed across storage devices in such a way that it can be retrieved even if several pieces are unavailable. On the other hand, chunks are meaningless alone.[3] Redundancy schemes based on coding techniques like the one used by RozoFS allow to achieve significant storage savings as compared to simple replication.[4][5]

The file system comprises three components:

  • Exports server — (Meta Data Server) manages the location (layout) of chunks (managing capacity load balancing with respect to high availability), file access and namespace (hierarchy). Multiple replicated metadata servers are used to provide failover. The Exports server is a user-space daemon; the metadata are stored synchronously to a usual file system (the underlying file system must support extended attributes).
  • Storage servers — (Chunk Server) store the chunks. The Chunk server is also a user-space daemon that relies on the underlying local file system to manage the actual storage.
  • Clients — talk to both the exports server and chunk servers and are responsible for data transformation. Clients mount the file system into user-space via FUSE.

See also

edit

References

edit
  1. ^ ZHANG, Z.; DESHPANDE, A.; MA, X.; THERESKA, E. & NARAYANAN (May 2010). "Does erasure coding have a role to play in my data center?" (PDF). Tech. Rep. MSR-TR-2010-52. Microsoft Research.
  2. ^ Jeanpierre, Guédon (2009). The Mojette Transform theory and applications. ISTE-WILEY. ISBN 9781848210806.
  3. ^ J. P. Guédon; B. Parrein; N. Normand (August 2001). "Secure Distributed Storage based on the Mojette transform". Integrated Computer-Aided Engineering V.8 N.3: 205–214. doi:10.3233/ICA-2001-8303.
  4. ^ Weatherspoon, Hakim & Kubiatowicz, John (2002). "Erasure Coding Vs. Replication: A Quantitative Comparison". Revised Papers from the First International Workshop on Peer-to-Peer Systems. IPTPS '01. Springer-Verlag: 328–338.
  5. ^ Rodrigues, Rodrigo & Liskov, Barbara (2005). "High Availability in DHTS: Erasure Coding vs. Replication". Peer-to-Peer Systems IV. IPTPS'05. Vol. 3640. Springer-Verlag. pp. 226–239. CiteSeerX 10.1.1.59.6053. doi:10.1007/11558989_21. ISBN 978-3-540-29068-1. {{cite book}}: |journal= ignored (help)

Press articles

edit
edit