Slashdot Mirror

← Back to Stories (view on slashdot.org)

Kernel Hackers On Ext3/4 After 2.6.29 Release

Posted by timothy on from the good-things-come-from-certain-clashes dept.

microbee writes "Following the Linux kernel 2.6.29 release, several famous kernel hackers have raised complaints upon what seems to be a long-time performance problem related to ext3. Alan Cox, Ingo Molnar, Andrew Morton, Andi Keen, Theodore Ts'o, and of course Linus Torvalds have all participated. It may shed some light on the status of Linux filesystems. For example, Linus Torvalds commented on the corruption caused by writeback mode, calling it 'idiotic.'"

2 of 316 comments (clear)

  1. Linus Torvalds...sponsored by "Girl World Live" by Anonymous Coward · · Score: -1, Troll

    ???!

  2. Performance problems of 2.6 kernel by Anonymous Coward · · Score: -1, Troll

    Hey, Linus is starting to realize what's going on: the whole 2.6 kernel series has serious performance problems. 2.2 kernel is still much better, especially on IO-heavy applications. The only reason to use 2.6 over 2.2 is hardware drivers.

    2.6 is so slow, it's a pain. The only way to ignore this is to have very expensive 4- or 8-core CPUs with Gigs of RAM, idleing with the four xterms running vi. KDE sucks, Firefox sucks, OpenOffice and Gnome have always sucked... (sorry, I have to say this)

    BTW, Linuses meta-data problem is something that I have seen before in reiserfs. I used to believe that the advantage of ext3 over ext2 was that it will leave a consistent fs when it crashes. Well, aparantly, nobody has told the kiddies who are coding ext4 or btrfs or whatever.