Re: [RFC] Avoid mutex starvation when optimistic spinning is disabled

From	Jason Low <jason.low2@hpe.com>
Newsgroups	linux.kernel
Subject	Re: [RFC] Avoid mutex starvation when optimistic spinning is disabled
Date	2016-07-21 23:00 +0200
Message-ID	<rXtex-4cZ-11@gated-at.bofh.it> (permalink)
References	(2 earlier) <rWkQ1-PW-1@gated-at.bofh.it> <rWGxc-6sA-5@gated-at.bofh.it> <rWMsV-1T0-5@gated-at.bofh.it> <rWRCh-58W-3@gated-at.bofh.it> <rWZTc-21W-15@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, 2016-07-20 at 16:29 +0300, Imre Deak wrote:
> On ti, 2016-07-19 at 21:39 -0700, Jason Low wrote:
> > On Tue, 2016-07-19 at 16:04 -0700, Jason Low wrote:
> > > Hi Imre,
> > > 
> > > Here is a patch which prevents a thread from spending too much "time"
> > > waiting for a mutex in the !CONFIG_MUTEX_SPIN_ON_OWNER case.
> > > 
> > > Would you like to try this out and see if this addresses the mutex
> > > starvation issue you are seeing in your workload when optimistic
> > > spinning is disabled?
> > 
> > Although it looks like it didn't take care of the 'lock stealing' case
> > in the slowpath. Here is the updated fixed version:
> 
> This also got rid of the problem, I only needed to change the ww
> functions accordingly. Also, imo mutex_trylock() needs the same
> handling

Good point. I supposed mutex_trylock() may not be causing starvation
issues, but I agree that it makes sense if mutex_trylock() fails too if
threads are supposed to yield to a waiter. I'll make the update.

Thanks,
Jason

Thread

[RFC] locking/mutex: Fix starvation of sleeping waiters Imre Deak <imre.deak@intel.com> - 2016-07-18 18:20 +0200
  Re: [RFC] locking/mutex: Fix starvation of sleeping waiters Peter Zijlstra <peterz@infradead.org> - 2016-07-18 19:20 +0200
    Re: [RFC] locking/mutex: Fix starvation of sleeping waiters Jason Low <jason.low2@hpe.com> - 2016-07-18 19:50 +0200
      Re: [RFC] locking/mutex: Fix starvation of sleeping waiters Imre Deak <imre.deak@intel.com> - 2016-07-19 19:00 +0200
        Re: [RFC] locking/mutex: Fix starvation of sleeping waiters Jason Low <jason.low2@hpe.com> - 2016-07-20 01:10 +0200
        [RFC] Avoid mutex starvation when optimistic spinning is disabled Jason Low <jason.low2@hpe.com> - 2016-07-20 01:20 +0200
          Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Jason Low <jason.low2@hpe.com> - 2016-07-20 06:50 +0200
            Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Imre Deak <imre.deak@intel.com> - 2016-07-20 15:40 +0200
              Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Jason Low <jason.low2@hpe.com> - 2016-07-21 23:00 +0200
                Re: [RFC] Avoid mutex starvation when optimistic spinning is disabled Davidlohr Bueso <dave@stgolabs.net> - 2016-07-22 20:10 +0200
                Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Imre Deak <imre.deak@intel.com> - 2016-07-22 20:40 +0200
                Re: [RFC] Avoid mutex starvation when optimistic spinning is disabled Davidlohr Bueso <dave@stgolabs.net> - 2016-07-22 21:30 +0200
                Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Imre Deak <imre.deak@intel.com> - 2016-07-22 22:00 +0200
            Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Jason Low <jason.low2@hpe.com> - 2016-07-22 00:40 +0200
              Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Imre Deak <imre.deak@intel.com> - 2016-07-22 11:40 +0200
                Re: [RFC] Avoid mutex starvation when optimistic spinning is  disabled Jason Low <jason.low2@hpe.com> - 2016-07-22 20:50 +0200

csiph-web