Page 5 of 7 FirstFirst ... 34567 LastLast
Results 41 to 50 of 68

Thread: With Linux 2.6.32, Btrfs Gains As EXT4 Recedes

  1. #41

    Default

    for instance benches where OpenSolaris used gcc v3.2 in 32bit mode vs Linux gcc 4.3 in 64bit mode, but such is life. If Solaris people could tailor the compiler, vs Linux people it would be more fair. But not many people has that expertise.
    What we saw at Phoronix were 64 bit OpenSolaris benchmarked against 32 bit Ubuntu and Freebsd. Even running in 64 bit Solaris was slow.

    Btw. Kebabbert is a troll who's trolling not only at Phoronix and who's cross-posting (he wrote similar or even exactly the same things at Phoronix):

    http://forums.theregister.co.uk/user/34256/
    http://www.osnews.com/thread?373085
    http://forums.theregister.co.uk/user/34256/

    What a performance monster slowlaris is (by Kebabbert):

    http://forums.sun.com/thread.jspa?th...756061#9756061


    http://forums.theregister.co.uk/foru...7_z11_rollout/
    http://forums.theregister.co.uk/foru...sparc64_crank/
    Last edited by kraftman; 12-21-2009 at 07:28 AM.

  2. #42
    Join Date
    Apr 2008
    Location
    Saskatchewan, Canada
    Posts
    460

    Default

    Quote Originally Posted by kebabbert View Post
    But the point of a file system is that your data is safe.
    Is it?

    I believe my netbook puts /tmp into RAM, which means that the data in there is completely lost if the machine reboots. That's trading performance for a complete lack of reliabile storage over system restarts.

    I think you'll find that people's needs vary from 'data absolutely must get to the disk and stay there' (e.g. online sales order database) to 'I want performance and if I lose the file on a reboot I don't care' (e.g. said temporary files). Different filesystems serve different needs.

    That said, I agree that a filesystem for general uses (e.g. extN) should put reliability above performance.
    Last edited by movieman; 12-21-2009 at 11:58 AM.

  3. #43
    Join Date
    Jul 2008
    Posts
    1,720

    Default

    Quote Originally Posted by movieman View Post
    Is it?

    I believe my netbook puts /tmp into RAM, which means that the data in there is completely lost if the machine reboots. That's trading performance for a complete lack of reliabile storage over system restarts.

    I think you'll find that people's needs vary from 'data absolutely must get to the disk and stay there' (e.g. online sales order database) to 'I want performance and if I lose the file on a reboot I don't care' (e.g. said temporary files). Different filesystems serve different needs.

    That said, I agree that a filesystem for general uses (e.g. extN) should put reliability above performance.
    which is supposed to be so. Data in /tmp is supposed to be gone after a reboot. So it is save and even smart to put /tmp into ram. If you have temp data that must survive a reboot use /var/tmp.

    So -your example is completely and utterly pointless.

  4. #44
    Join Date
    Apr 2008
    Location
    Saskatchewan, Canada
    Posts
    460

    Default

    Quote Originally Posted by energyman View Post
    So -your example is completely and utterly pointless.
    I was responding to someone who said, and I quote:

    But the point of a file system is that your data is safe.
    Clearly you agree with me that a file system which doesn't provide safe storage of data -- even to the extent of never writing it to disk at all -- can be useful, yet you claim my post is pointless?

    Here's another example for you: I use XFS on MythTV for off-air recordings, because while it has worse behaviour on a power failure than ext3, it also has better performance. I don't much care if I lose the TV show that was recording when the power goes out, because it's pretty much useless if it only recorded 2/3 of the show... I do care if it can't write the file to disk because the file system is busy deleting a large file so writes can't be processed.

  5. #45
    Join Date
    Jul 2008
    Posts
    1,720

    Default

    and you use what for /tmp in ram? tmpfs. A filesystem made for this kind of stuff. You are comapring a 'forget everything' filesystem with a filesystem class that should never ever risk the safety of your data.

    You can not comapre /tmp and /home. Or tmpfs with any disk based filesystem.

    That extX devs think that data is without value and speed everything is not a mindset you should copy.

  6. #46
    Join Date
    Aug 2006
    Posts
    158

    Default

    Quote Originally Posted by energyman View Post
    and you use what for /tmp in ram? tmpfs. A filesystem made for this kind of stuff. You are comapring a 'forget everything' filesystem with a filesystem class that should never ever risk the safety of your data.

    You can not comapre /tmp and /home. Or tmpfs with any disk based filesystem.

    That extX devs think that data is without value and speed everything is not a mindset you should copy.
    Actually, the ext4 devs seem to be so concerned about safety that they are sacrificing speed by turning on by default options like barrier and data=ordered. Phoronix articles keep mentioning the recent performance regression caused by yet another safety enhancement (see here).

    I'm surprised you would say they think data has no value, when the opposite appears to be true: they're prepared to drop everything for data integrity. Perhaps this is a reaction to complaints from Ubuntu users, but still.

    Personally I wish they would try harder to make sure their safety fixes hurt performance less. I also wish reiser4 had less bugs. Reiser4 is my favorite filesystem - fast (especially with transparent compression enabled) and never loses my data. But it has scared me away with weird bugs (like rm -Rf leaving an undeletable folder). So for now I'm using ext4, and I really don't see what's wrong with it. It seems to be a decent filesystem and has served me well.
    Last edited by StringCheesian; 12-21-2009 at 06:39 PM.

  7. #47
    Join Date
    Dec 2009
    Posts
    18

    Default

    For what it's worth, multi-threaded ReiserFS performance should improve significantly in kernel 2.6.33 because that version eliminates the Big Kernel Lock from ReiserFS code.

  8. #48
    Join Date
    Jul 2008
    Posts
    1,720

    Default

    they turn it on NOW. How many versions after ext4 was declared 'stable' - a bad joke that cost a lot of people a lot of data?

    They did not learn from ext3. Nope. They tuned for speed to wow the masses and now that there is a 'omg ext4 is fast' seed planted, they do some sensible stuff.

    That is nothing but manipulation.

  9. #49
    Join Date
    Jul 2008
    Posts
    1,720

    Default

    if you have an undeletable folder, you have a corruption.

    For what it is worth, I am using reiser4 for a long time now, and since many kernel releases it is very very well behaving. It even goes into sync mode when it detects that barriers are not present. I love that. Data is important.

  10. #50
    Join Date
    Apr 2008
    Location
    /dev/random
    Posts
    218

    Default

    This is why XFS rules.
    Just Kidding

    I use ext4 for /, ext3 for /home and /boot, xfs for some other data, and tmpfs for /tmp.

    IMO, XFS is still the best 'stable' filesystem. (Never tried ZFS)

    The only problem with XFS is that it is impossible to shrink filesystems.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •