Three types of filesystem technologies are important for Linux-HA: Journalling filesystems, Cluster filesystems and Mirror filesystems. Journalling filesystems allow takeover of shared/mirrored filesystems to occur rapidly in cases of failover. Cluster filesystems allow disks to be shared read-write between all members of a cluster simultaneously - which is highly desirable for many parallel applications. Mirror file system can write the same file to two or more different systems on the network in real time, breaks through the barrier that formally confined computer system to the single standalone resources model and enables single system to be integrated into the Cloud or geographically dispersed network cluster systems.
Reiserfs[1]: A tree-structured filesystem which journals updates. It is available with most 2.4 and later kernels.
Ext3[2]: Stephen Tweedie's journalling version of the ext2 filesystem. It is available with most 2.4 and later kernels.
JFS[3]: IBM's journalled filesystem technology. It is available with many Linux distributions.
XFS[4]: SGI's journalled filesystem technology.
LinLogFS[5]: A log structured filesystem for Linux
Intermezzo[6]: A distributed file system which lets systems replicate directory trees. It is a standard part of 2.4 and later kernels. It isn't precisely what most people would call a cluster filesystem, but it's related.
Lustre[7]: Lustre is a novel storage and file system architecture and implementation which does not follow the block device paradigm. The central target in this project is the development of a next-generation cluster file system which can serve clusters with 10,000's of nodes, petabytes of storage, move 100's of GB/sec. Lustre is in trial production in several sites across the world.
GFS[8]: The Global Filesystem - fault tolerant, distributed, very cool, etc. GFS is both a cluster filesystem and a journalled filesystem.
The CODA[9] distributed, fault-tolerant filesystem
Oracle Cluster File System (OCFS)[10]: enterprise-class open-source cluster file system
MFS[11]: All conventional file systems developed until now, like ext*, ufs, gfs and NFS, are only able to write the file on a single standalone system. MFS is the only file system that can write the file on two geographically-dispersed systems simultaneously and bidirectionally. When a file is created or updated on one system, the changed portion of the file is replicated to the same copy on another remote system in real time. Both copies of the same file are live and can be used immediately. MFS is a new solution for HA, load balancing, Disaster Prevention (not just DR), online file backup and Cloud Computing that built on top of local file systems and NFS. The new technology enables many good things for the IT world and Computer Science.
| [1] | http://www.namesys.com/ |
| [2] | http://en.wikipedia.org/wiki/Ext3 |
| [3] | http://jfs.sourceforge.net/ |
| [4] | http://linux-xfs.sgi.com/projects/xfs/ |
| [5] | http://www.complang.tuwien.ac.at/czezatke/lfs.html |
| [6] | http://inter-mezzo.org/ |
| [7] | http://lustre.org/ |
| [8] | http://freshmeat.net/projects/theglobalfilesystem/ |
| [9] | http://www.coda.cs.cmu.edu/ |
| [10] | http://oss.oracle.com/projects/ocfs2/ |
| [11] | http://TwinPeakSoft.com/ |
This information provided courtesy of the Linux-HA project at http://linux-ha.org/