Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-23 Thread Thomas Gleixner
On Thu, 22 Sep 2016, Waiman Long wrote: > On 09/22/2016 09:32 AM, Thomas Gleixner wrote: > > > + WARN_ON(!pi_state->owner); > > > + if (pi_state->owner) > > > + wake_up_process(pi_state->owner); > > And what handles or sanity checks the

Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-23 Thread Thomas Gleixner
On Thu, 22 Sep 2016, Waiman Long wrote: > On 09/22/2016 09:32 AM, Thomas Gleixner wrote: > > > + WARN_ON(!pi_state->owner); > > > + if (pi_state->owner) > > > + wake_up_process(pi_state->owner); > > And what handles or sanity checks the

Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-22 Thread Waiman Long
On 09/22/2016 09:32 AM, Thomas Gleixner wrote: On Tue, 6 Sep 2016, Waiman Long wrote: +enum futex_type { + TYPE_PI = 0, + TYPE_TO, +}; Please introduce the futex_type magic and the related changes to the pi code in a seperate patch so it can be verified independently. It's sad

Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-22 Thread Waiman Long
On 09/22/2016 09:32 AM, Thomas Gleixner wrote: On Tue, 6 Sep 2016, Waiman Long wrote: +enum futex_type { + TYPE_PI = 0, + TYPE_TO, +}; Please introduce the futex_type magic and the related changes to the pi code in a seperate patch so it can be verified independently. It's sad

Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-22 Thread Thomas Gleixner
On Tue, 6 Sep 2016, Waiman Long wrote: > +enum futex_type { > + TYPE_PI = 0, > + TYPE_TO, > +}; Please introduce the futex_type magic and the related changes to the pi code in a seperate patch so it can be verified independently. It's sad that one has to explain that to you over and over

Re: [RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-22 Thread Thomas Gleixner
On Tue, 6 Sep 2016, Waiman Long wrote: > +enum futex_type { > + TYPE_PI = 0, > + TYPE_TO, > +}; Please introduce the futex_type magic and the related changes to the pi code in a seperate patch so it can be verified independently. It's sad that one has to explain that to you over and over

[RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-06 Thread Waiman Long
This patch introduces a new futex implementation called throughput-optimized (TO) futexes. The goal of this new futex type is to provide locking throughput that is higher than wait-wake futexes especially on systems with a large number of CPUs and the lock owners are unlikely to sleep. The

[RFC PATCH 3/4] futex: Throughput-optimized (TO) futexes

2016-09-06 Thread Waiman Long
This patch introduces a new futex implementation called throughput-optimized (TO) futexes. The goal of this new futex type is to provide locking throughput that is higher than wait-wake futexes especially on systems with a large number of CPUs and the lock owners are unlikely to sleep. The