lkml.org 
[lkml]   [2012]   [Mar]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: sched: Avoid SMT siblings in select_idle_sibling() if possible

    * Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> wrote:

    > * Peter Zijlstra <peterz@infradead.org> [2012-02-20 20:07:46]:
    >
    > > On Mon, 2012-02-20 at 19:14 +0100, Mike Galbraith wrote:

    > > > Enabling SD_BALANCE_WAKE used to be decidedly too
    > > > expensive to consider. Maybe that has changed, but I doubt
    > > > it.
    > >
    > > Right, I through I remembered somet such, you could see it
    > > on wakeup heavy things like pipe-bench and that java msg
    > > passing thing, right?
    >
    > I did some experiments with volanomark and it does turn out to
    > be sensitive to SD_BALANCE_WAKE, while the other wake-heavy
    > benchmark that I am dealing with (Trade) benefits from it.

    Does volanomark still do yield(), thereby invoking a random
    shuffle of thread scheduling and pretty much voluntarily
    ejecting itself from most scheduler performance considerations?

    If it uses a real locking primitive such as futexes then its
    performance matters more.

    Thanks,

    Ingo


    \
     
     \ /
      Last update: 2012-03-06 10:17    [W:0.021 / U:182.316 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site