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|
|Operating Systems||Mac OS X POSIX Solaris Linux FreeBSD NetBSD OpenSolaris|
Release Notes: The most important changes include limiting of chunkserver disconnections, a fix for network connection timeouts, a progress percentage in metarestore, and an improved algorithm for choosing servers for write new chunks.
Release Notes: The most important changes include fixed signal handling in multithreaded modules, goal and trashtime limits in mfsexport.cfg, and a simple check for downloaded metadata files.
Release Notes: The most important changes include retention of previous copies of metadata, applying new settings on "reload" (SIGHUP), and better handling of full disks on the master.
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.
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.