lkml.org 
[lkml]   [1998]   [Jun]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: e2fs + large disk == slug?
    On Tue, 16 Jun 1998, Mark Lehrer wrote:
    > On Mon, 15 Jun 1998, Mark Lehrer wrote:
    >
    > > 1) removing 500 megs of files took 30 seconds.
    >
    > This will be just as slow on a 600M filesystem...
    > If there are a lot of files, it's going to take a rather
    > long time to remove them. (Just try this under Windows:)
    >
    > On my 120mhz HP-UX system this same operation on the same set of files
    > with the same model disk drive only takes a few seconds; whereas with
    > my 200MHz PPro Linux system it takes five to ten times as long...

    This is because Linux does synchronous metadata updates on
    unlink(). And even when it doesn't do that, it will still
    need to do synchronous metadata _reads_ in order to determine
    what to write out asynchronously.

    > Is it possible to optimize this?

    Well, we could recode the kernel to let bdflush or a new
    kernel daemon do the unlinks... Apart from that, there's
    not much of a solution :(
    (or you simply run 'rm -rf dir &', which will probably
    be the same thing that Solaris does internaly :-)

    Rik.
    +-------------------------------------------------------------------+
    | Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
    | Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
    +-------------------------------------------------------------------+


    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.rutgers.edu

    \
     
     \ /
      Last update: 2005-03-22 13:43    [W:0.019 / U:89.592 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site