[lkml]   [2007]   [Dec]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [feature] automatically detect hung TASK_UNINTERRUPTIBLE tasks

    * Radoslaw Szkodzinski <> wrote:

    > > iirc TASK_KILLABLE fixed NFS only. While that's a good thing there
    > > are unfortunately a lot more subsystems that would need the same
    > > treatment.
    > Yes, that's exactly why the patch is needed - to find the bugs and fix
    > them. Otherwise you'll have problems finding some places to convert to
    > CIFS and similar have to be fixed - it tends to lock the app using it,
    > in unkillable state.

    Amen. I still have to see a single rational argument against this
    debugging feature - and tons of arguments were listed in favor of it. So
    let's just try and see what happens.

    > > Yes let's break things first instead of looking at the implications
    > > closely.
    > Throwing _rare_ stack traces is not breakage. 120s
    > task_uninterruptible in the usual case (no errors) is already broken -
    > there are no sane loads that can invoke that IMO.
    > A stack trace on x subsystem error is not that bad, especially as
    > these are limited to 10 per session.

    we could lower that limit to 1 per bootup - if they become annoying.
    There's lots of flexibility in the code. Really, we should have done
    this 10 years ago - it would have literally saved me many days of
    debugging time combined, and i really have experience in identifying
    such bad tasks. (and it would have sped up debugging in countless number
    of instances when users were met with an uninterruptible task.)


     \ /
      Last update: 2007-12-03 11:27    [W:0.025 / U:92.692 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site