Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-17 Thread Peter Zijlstra
On Wed, May 16, 2018 at 10:55:13AM -0700, Srinivas Pandruvada wrote: > On Wed, 2018-05-16 at 09:37 +0200, Peter Zijlstra wrote: > > On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: > > Hurmph, this looks like you're starting to duplicate the schedutil > > iowait logic. Why

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-17 Thread Peter Zijlstra
On Wed, May 16, 2018 at 10:55:13AM -0700, Srinivas Pandruvada wrote: > On Wed, 2018-05-16 at 09:37 +0200, Peter Zijlstra wrote: > > On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: > > Hurmph, this looks like you're starting to duplicate the schedutil > > iowait logic. Why

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Srinivas Pandruvada
On Wed, 2018-05-16 at 11:45 +0200, Rafael J. Wysocki wrote: [...] > > > + if (time_before64(time, cpu->last_io_update + 2 * > > TICK_NSEC) && > > + intel_pstate_check_boost_threhold(cpu)) > > + cpu->iowait_boost = true; > > + > > +

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Srinivas Pandruvada
On Wed, 2018-05-16 at 11:45 +0200, Rafael J. Wysocki wrote: [...] > > > + if (time_before64(time, cpu->last_io_update + 2 * > > TICK_NSEC) && > > + intel_pstate_check_boost_threhold(cpu)) > > + cpu->iowait_boost = true; > > + > > +

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Srinivas Pandruvada
On Wed, 2018-05-16 at 09:37 +0200, Peter Zijlstra wrote: > On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: [...] > > @@ -258,6 +261,8 @@ struct cpudata { > > s16 epp_saved; > > u64 hwp_req_cached; > > call_single_data_t csd; > > + bool hwp_boost_active; > > +

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Srinivas Pandruvada
On Wed, 2018-05-16 at 09:37 +0200, Peter Zijlstra wrote: > On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: [...] > > @@ -258,6 +261,8 @@ struct cpudata { > > s16 epp_saved; > > u64 hwp_req_cached; > > call_single_data_t csd; > > + bool hwp_boost_active; > > +

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Rafael J. Wysocki
On Wed, May 16, 2018 at 6:49 AM, Srinivas Pandruvada wrote: > When a task is woken up from IO wait, boost HWP prformance to max. This > helps IO workloads on servers with per core P-states. But changing limits > has extra over head of issuing new HWP Request

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Rafael J. Wysocki
On Wed, May 16, 2018 at 6:49 AM, Srinivas Pandruvada wrote: > When a task is woken up from IO wait, boost HWP prformance to max. This > helps IO workloads on servers with per core P-states. But changing limits > has extra over head of issuing new HWP Request MSR, which takes 1000+ > cycles. So

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Peter Zijlstra
On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: > When a task is woken up from IO wait, boost HWP prformance to max. This > helps IO workloads on servers with per core P-states. But changing limits > has extra over head of issuing new HWP Request MSR, which takes 1000+ >

Re: [RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-16 Thread Peter Zijlstra
On Tue, May 15, 2018 at 09:49:06PM -0700, Srinivas Pandruvada wrote: > When a task is woken up from IO wait, boost HWP prformance to max. This > helps IO workloads on servers with per core P-states. But changing limits > has extra over head of issuing new HWP Request MSR, which takes 1000+ >

[RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-15 Thread Srinivas Pandruvada
When a task is woken up from IO wait, boost HWP prformance to max. This helps IO workloads on servers with per core P-states. But changing limits has extra over head of issuing new HWP Request MSR, which takes 1000+ cycles. So this change limits setting HWP Request MSR. Also request can be for a

[RFC/RFT] [PATCH 05/10] cpufreq: intel_pstate: HWP boost performance on IO Wake

2018-05-15 Thread Srinivas Pandruvada
When a task is woken up from IO wait, boost HWP prformance to max. This helps IO workloads on servers with per core P-states. But changing limits has extra over head of issuing new HWP Request MSR, which takes 1000+ cycles. So this change limits setting HWP Request MSR. Also request can be for a