Projects / Moose File System

Moose File System

Moose File System (MooseFS / MFS) is a fault tolerant, network distributed file system. It spreads data over several physical servers, which are visible to the user as one resource. For standard file operations MooseFS mounted with FUSE acts like other Unix-alike file systems: it has a hierarchical structure; it stores POSIX file attributes; and it supports special files, symbolic links, and hard links. Access to the file system can be limited based on IP address and/or password. It offers high reliability, since several copies of the data can be stored across separate computers. Capacity is dynamically expandable by attaching new computers or disks. Deleted files are retained for a configurable period of time (with a file system level "trash bin"). MooseFS supports coherent snapshots of files, even while the file is being written or accessed.

Tags	filesystem distributed file system fault tolerant high availability
Licenses	GPLv3
Operating Systems	Mac OS X POSIX Solaris Linux FreeBSD NetBSD OpenSolaris
Implementation	C

Website

Download

Release tags

All releases

Recent releases

1.6.20

17 Jan 2011 10:44

Release Notes: Chunkserver packet registration has been improved (one big packet is divided into several small ones). Also, minimum socket timeout has been set to ten seconds so that the system has time to register and the master doesn't hang up.

1.6.19

22 Dec 2010 10:21

Release Notes: Substantial changes were introduced to the metalogger machine and metarestore tool for better integrity of the metadata. A scanning progress bar in CS was added. The master name is now resolved when a connection fails. A new session is created when the previous one is lost. Lots of other bug fixes and improvements were made.

1.6.17

28 Jul 2010 20:32

Release Notes: Automatic data cache management and a new flag "nodatacache" were added.

1.6.16

22 Jul 2010 08:55

Release Notes: This release added clearing of SUID/SGID bits and a check for the "sticky" flag during rename and unlink operations, fixed POSIX compatibility with removing empty directories on rename and proper changing of ctime, fixed some constants to provide better support for larger systems with millions of files and chunks, fixed error logging, fixed some OpenSolaris compilation issues (mainly by adding -D__EXTENSIONS__ to the compile flags), fixed an OpenSolaris pthreads issue, and fixed an overflow on negative time differences in hdd stats. A man page was added for mfscgiserv and "BIND" option descriptions were added to the man pages.

1.6.15

21 Apr 2010 08:29

Release Notes: This is a maintenance release. A "double free" error was fixed for the daemons. Bugs were fixed in the "REPAIR" and "SNAPSHOT" entries for metarestore. A bug in the master "snapshot" command was fixed, in which "mfsmakesnapshot dir dir/" caused master to hang-up. Atime and mtime are preserved during the master "snapshot" operation, which makes "snapshot" work more like "cp -Rp" than "cp -R". "Marked for removal" disks are omitted by cs during chunk test loo.