Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-08 Thread Waiman Long
On 04/07/2016 08:13 PM, Andy Lutomirski wrote: On Thu, Apr 7, 2016 at 8:07 AM, Waiman Long wrote: On 04/07/2016 12:58 AM, Andy Lutomirski wrote: Reading the HPET is so slow that all the atomic ops in the world won't make a dent. Why not just turn this optimization on

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-08 Thread Waiman Long
On 04/07/2016 08:13 PM, Andy Lutomirski wrote: On Thu, Apr 7, 2016 at 8:07 AM, Waiman Long wrote: On 04/07/2016 12:58 AM, Andy Lutomirski wrote: Reading the HPET is so slow that all the atomic ops in the world won't make a dent. Why not just turn this optimization on unconditionally? --Andy

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-07 Thread Andy Lutomirski
On Thu, Apr 7, 2016 at 8:07 AM, Waiman Long wrote: > On 04/07/2016 12:58 AM, Andy Lutomirski wrote: >> Reading the HPET is so slow that all the atomic ops in the world won't >> make a dent. Why not just turn this optimization on unconditionally? >> >> --Andy > > > I am

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-07 Thread Andy Lutomirski
On Thu, Apr 7, 2016 at 8:07 AM, Waiman Long wrote: > On 04/07/2016 12:58 AM, Andy Lutomirski wrote: >> Reading the HPET is so slow that all the atomic ops in the world won't >> make a dent. Why not just turn this optimization on unconditionally? >> >> --Andy > > > I am constantly on the alert

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-07 Thread Waiman Long
On 04/07/2016 12:58 AM, Andy Lutomirski wrote: On Wed, Apr 6, 2016 at 7:02 AM, Waiman Long wrote: On a large system with many CPUs, using HPET as the clock source can have a significant impact on the overall system performance because of the following reasons: 1) There

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-07 Thread Waiman Long
On 04/07/2016 12:58 AM, Andy Lutomirski wrote: On Wed, Apr 6, 2016 at 7:02 AM, Waiman Long wrote: On a large system with many CPUs, using HPET as the clock source can have a significant impact on the overall system performance because of the following reasons: 1) There is a single HPET

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-06 Thread Andy Lutomirski
On Wed, Apr 6, 2016 at 7:02 AM, Waiman Long wrote: > On a large system with many CPUs, using HPET as the clock source can > have a significant impact on the overall system performance because > of the following reasons: > 1) There is a single HPET counter shared by all the

Re: [PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-06 Thread Andy Lutomirski
On Wed, Apr 6, 2016 at 7:02 AM, Waiman Long wrote: > On a large system with many CPUs, using HPET as the clock source can > have a significant impact on the overall system performance because > of the following reasons: > 1) There is a single HPET counter shared by all the CPUs. > 2) HPET

[PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-06 Thread Waiman Long
On a large system with many CPUs, using HPET as the clock source can have a significant impact on the overall system performance because of the following reasons: 1) There is a single HPET counter shared by all the CPUs. 2) HPET counter reading is a very slow operation. Using HPET as the

[PATCH] x86/hpet: Reduce HPET counter read contention

2016-04-06 Thread Waiman Long
On a large system with many CPUs, using HPET as the clock source can have a significant impact on the overall system performance because of the following reasons: 1) There is a single HPET counter shared by all the CPUs. 2) HPET counter reading is a very slow operation. Using HPET as the