Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-08-08 Thread Will Deacon
Hi Waiman, On Tue, Aug 07, 2018 at 07:29:49PM -0400, Waiman Long wrote: > On 07/24/2018 03:10 PM, Waiman Long wrote: > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > > index 3064c50..01fcb80 100644 > > --- a/kernel/locking/rwsem-xadd.c > > +++

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-08-08 Thread Will Deacon
Hi Waiman, On Tue, Aug 07, 2018 at 07:29:49PM -0400, Waiman Long wrote: > On 07/24/2018 03:10 PM, Waiman Long wrote: > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > > index 3064c50..01fcb80 100644 > > --- a/kernel/locking/rwsem-xadd.c > > +++

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-08-07 Thread Waiman Long
On 07/24/2018 03:10 PM, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-08-07 Thread Waiman Long
On 07/24/2018 03:10 PM, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-27 Thread Will Deacon
On Tue, Jul 24, 2018 at 03:10:25PM -0400, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-27 Thread Will Deacon
On Tue, Jul 24, 2018 at 03:10:25PM -0400, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-26 Thread Davidlohr Bueso
On Tue, 24 Jul 2018, Waiman Long wrote: It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering

Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-26 Thread Davidlohr Bueso
On Tue, 24 Jul 2018, Waiman Long wrote: It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering

[PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-24 Thread Waiman Long
It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will

[PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer

2018-07-24 Thread Waiman Long
It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will