Tux3

Tux3
Developer(s) Daniel Phillips, Ogawa Hirofumi
Full name Tux3
Introduced 23 Jul 2008 with Linux 2.6.x
Partition identifier

0x83 (MBR)

Superblock magic: "tux3" {0x74, 0x75, 0x78, 0x33}
Structures
Directory contents B-tree
File allocation B-tree
Limits
Max. volume size 2^60 bytes (1 EiB)
Max. file size 2^60 bytes (1 EiB)
Max. number of files 2^48
Max. filename length 255 bytes
Allowed characters in filenames All bytes except NUL and '/'
Features
Dates recorded attribute modification (ctime), modification (mtime), access time (atime), version create
Date range 40 bits
Date resolution 1/256 second
File system permissions POSIX
Other
Supported operating systems Linux

Tux3 is an open-source versioning filesystem created by Daniel Phillips. He introduced the filesystem as a public replacement for his Tux2 filesystem which had encountered licensing issues due to the filing of several patents.[1] Phillips had previously created the Htree directory indexing system which eventually became an official feature of ext3.[2] The technical details of Tux3 were first publicized in an email on 23 July 2008.[3]

Design

In broad outline, Tux3 follows a conventional Unix-style inode/file/directory design. A Tux3 inode table is a B-tree with versioned attributes at the leaves. A file is an inode attribute that is a B-tree with versioned extents at the leaves. Directory indexes are mapped into directory file blocks as with Htree. Free space is mapped by a B-tree with extents at the leaves. It attempts to avoid traditional journaling by introducing a recovery logic which allows it to recover upon remounting.[4]

A Tux3 inode is a variable sized object consisting of a list of attributes, each labeled by the version at which the attribute was added, changed or removed. The B-tree index by which inodes are referenced is not versioned. The B-tree index of a large file is also not versioned, except for the leaves of the index, which contain lists of extents, each labeled by the version at which the referenced file data was added or changed. This style of versioning is essentially the inverse of tree versioning methods used by Write Anywhere File Layout (WAFL), ZFS and Btrfs, where multiple tree roots of an entire filesystem are created in order to express differences between versions of the filesystem.

A claimed advantage of Tux3 style versioned entities is that only a few bytes need to be added to represent single changes to inode attributes or to index new versions of file data blocks, compared to some number of index blocks needing to be allocated and written for tree-versioned filesystems.

Development history

As of August 2008, Tux3 was only capable of performing basic file I/O on files. By the end of 2008, Tux3 was capable of running within the kernel and able to sustain repeated runs of the file system exerciser fsx-linux, a big accomplishment.[5]

On 17 February 2009, Linux booted from a Tux3 root filesystem for the first time.[6]

On 18 January 2013, initial fsck support was added.[7] So far it just checks physical referential integrity, but the developers are confident that they can make a fully functional e2fsck-quality fsck soon.

On 17 May 2014, Daniel Phillips made a plea[8] to the kernel maintainer, to review the code and implement it into the kernel. The goal is to stabilize the code in the kernel and finally get stable[9]

See also

References

This article is issued from Wikipedia - version of the 9/17/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.