lkml.org 
[lkml]   [2005]   [Oct]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2
    On Tue, Oct 04, 2005 at 02:02:39PM -0600, Christopher Friesen wrote:
    > Dipankar Sarma wrote:
    >
    > >Since then, I have done some testing myself, but I can't reproduce
    > >this problem in two of my systems - x86 and x86_64. I ran rename14
    > >in a loop too, but after exhausting a lot of free memory, dcache
    > >does get shrunk and I don't see dentries stuck in RCU queues at all.
    > >I tried UP kernel too.
    >
    > I've only managed to reproduce it on a UP system with HIGHMEM.
    >
    > >So, there must be something else in your system that I
    > >am missing in my setup. Could you please mail me your .config ?
    >
    > Sent privately.

    Chris pointed out privately that the LTP rename14 test always
    creates a directory in /tmp and runs from there (hidden
    in an ltp library call tst_tmpdir()), not from the current
    working directory. So, my tests weren't really running on
    tmpfs. So, I commented out the tst_tmpdir() call in the test
    forcing it to run on tmpfs and immediately I got the following
    errors -

    llm22:/test # ./rename14
    Bad page state at prep_new_page (in process 'rename14', page ffff810008000000)
    flags:0x4000000000000090 mapping:0000000000000000 mapcount:0 count:0
    Backtrace:
    Trying to fix it up, but a reboot is needed
    Bad page state at prep_new_page (in process 'syslogd', page ffff8100080002a0)
    flags:0x4000000000000000 mapping:0000000000000000 mapcount:0 count:-26471
    Backtrace:
    Trying to fix it up, but a reboot is needed

    Bad page state at prep_new_page (in process 'rename14', page ffff810008001538)

    llm22 kernel: Bflags:0x4000000000000000 mapping:0000005500005555 mapcount:0 count:0
    ad page state atBacktrace:
    prep_new_page (Trying to fix it up, but a reboot is needed
    in process 'renaBad page state at prep_new_page (in process 'rename14', page ffff810008002aa8)
    me14', page ffffflags:0x4000000000000090 mapping:0000000000000000 mapcount:0 count:0
    810008000000)
    Backtrace:
    Trying to fix it up, but a reboot is needed

    Message from syslogd@llm22 at Tue Oct 4 19:41:42 2005 ...
    llm22 kernel: fBad page state at prep_new_page (in process 'rename14', page ffff810008005550)
    lags:0x400000000flags:0x4000005500009090 mapping:0000000000000000 mapcount:0 count:0
    0000090 mapping:Backtrace:
    0000000000000000Trying to fix it up, but a reboot is needed
    mapcount:0 count:0

    Andi, does this look any familiar ? This is on a 2-CPU x86_64 system
    running 2.6.14-rc3 (UP kernel though).

    Thanks
    Dipankar
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2005-10-05 06:08    [W:0.031 / U:30.932 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site