[lkml]   [2009]   [Apr]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [PATCH] mutex: have non-spinning mutexes on s390 by default
    On Thu, 2009-04-09 at 18:48 +0200, Heiko Carstens wrote:
    > Updated Patch below:
    > Subject: [PATCH] mutex: have non-spinning mutexes on s390 by default
    > From: Heiko Carstens <>
    > The adaptive spinning mutexes will not always do what one would expect on
    > virtualized architectures like s390. Especially the cpu_relax() loop in
    > mutex_spin_on_owner might hurt if the mutex holding cpu has been scheduled
    > away by the hypervisor.
    > We would end up in a cpu_relax() loop when there is no chance that the
    > state of the mutex changes until the target cpu has been scheduled again by
    > the hypervisor.
    > For that reason we should change the default behaviour to no-spin on s390.
    > We do have an instruction which allows to yield the current cpu in favour of
    > a different target cpu. Also we have an instruction which allows us to figure
    > out if the target cpu is physically backed.
    > However we need to do some performance tests until we can come up with
    > a solution that will do the right thing on s390.
    > Cc: Peter Zijlstra <>

    Acked-by: Peter Zijlstra <>

    I was looking at how an monitor-wait could be used here, but that
    appears non-trivial, there's two variables we're watching, lock->owner
    and rq->curr, either could change.

    Reducing that to 1 seems an interesting problem :-)

     \ /
      Last update: 2009-04-09 18:55    [W:0.089 / U:4.188 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site