lkml.org 
[lkml]   [2012]   [Sep]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [PATCH 4/7 V6] workqueue: fix idle worker depletion
    Hello, Lai.

    On Sun, Sep 09, 2012 at 01:12:53AM +0800, Lai Jiangshan wrote:
    > +/* does the manager need to be rebind after we just release gcwq->lock */
    > +static void maybe_rebind_manager(struct worker *manager)
    > +{
    > + struct global_cwq *gcwq = manager->pool->gcwq;
    > + bool assoc = !(gcwq->flags & GCWQ_DISASSOCIATED);
    > +
    > + if (assoc && (manager->flags & WORKER_UNBOUND)) {
    > + spin_unlock_irq(&gcwq->lock);
    > +
    > + if (worker_maybe_bind_and_lock(manager))
    > + worker_clr_flags(manager, WORKER_UNBOUND);
    > + }
    > +}

    We can reuse busy_worker_rebind_fn(), right?

    > pool->manager = worker;
    > + if (unlikely(!mutex_trylock(&pool->manager_mutex))) {
    > + /*
    > + * Ouch! rebind_workers() or gcwq_unbind_fn() beats we.
    > + * it can't return false here, otherwise it will lead to
    > + * worker depletion. So we release gcwq->lock and then
    > + * grab manager_mutex again.
    > + */
    > + spin_unlock_irq(&gcwq->lock);
    > + mutex_lock(&pool->manager_mutex);
    > + spin_lock_irq(&gcwq->lock);
    > +
    > + /* rebind_workers() can happen when we release gcwq->lock */
    > + maybe_rebind_manager(worker);

    And we can call process_scheduled_works() here and make the CPU
    hotplug check pool->manager and schedule rebind_work there.

    Thanks.

    --
    tejun


    \
     
     \ /
      Last update: 2012-09-08 20:01    [W:0.023 / U:60.888 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site