[lkml]   [2011]   [Sep]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [RFC][PATCH 0/5] Signal scalability series
    On Fri, 2011-09-30 at 18:52 +0200, Oleg Nesterov wrote:
    > And, this patch adds 4 new locks:
    > sighand_struct->action_lock
    > signal_struct->ctrl_lock
    > signal_struct->shared_siglock
    > task_struct->siglock
    > Nice ;) For what? This should be justified, imho.

    Well, sighand->siglock is seriously overused. It protects so much and I
    think it's pretty confusing. It took me long enough to figure out how
    many locks were really needed. But that's beside the point, having a
    single lock doesn't scale at all, and that's what this series is about.

    > Hmm. Just out of curiosity, I blindly applied the whole series and poke
    > the _random_ function to look at, dequeue_signal(). And it looks wrong.
    > spin_lock_irqsave(&current->signal->ctrl_lock, flags);
    > current->jobctl |= JOBCTL_STOP_DEQUEUED;
    > This signal->ctrl_lock can't help. A sig_kernel_stop() should be
    > dequeued under the same lock, and we shouldn't release it unless we
    > set JOBCTL_STOP_DEQUEUED. Otherwise we race with SIGCONT.

    Hmm.. is that really a problem? Does the dequeue and setting
    JOBCTL_STOP_DEQUEUED actually need to be atomic? Does it matter if we
    have SIGCONT on the signal queue when we set JOBCTL_STOP_DEQUEUED?

    > May be do_signal_stop() does something special? At first flance it doesn't.
    > But wait, it does while_each_thread() under ->ctrl_lock, why this is safe?

    Why is it not safe? What scenario are you thinking of where that isn't

    > May be I was just lucky ;)

    I doubt luck has anything to do with it ;-)

    Thanks for the review!

    Matt Fleming, Intel Open Source Technology Center

     \ /
      Last update: 2011-09-30 22:03    [W:0.020 / U:7.672 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site