linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
To: Philippe Longepe <philippe.longepe@linux.intel.com>,
	linux-pm@vger.kernel.org
Cc: rafael@kernel.org
Subject: Re: [PATCH V5 3/4] Move the intel_pstate_calc_busy into get_target_pstate_use_performance
Date: Mon, 07 Mar 2016 13:36:41 -0800	[thread overview]
Message-ID: <1457386601.4361.9.camel@linux.intel.com> (raw)
In-Reply-To: <1457249646-23072-4-git-send-email-philippe.longepe@linux.intel.com>

On Sun, 2016-03-06 at 08:34 +0100, Philippe Longepe wrote:
> The cpu_load algorithm doesn't need to invoke
> intel_pstate_calc_busy(),
> so move that call from intel_pstate_sample() to
> get_target_pstate_use_performance().
> 
> Signed-off-by: Philippe Longepe <philippe.longepe@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>

> ---
>  drivers/cpufreq/intel_pstate.c | 5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/cpufreq/intel_pstate.c
> b/drivers/cpufreq/intel_pstate.c
> index c46d23a..903341f 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -912,8 +912,6 @@ static inline void intel_pstate_sample(struct
> cpudata *cpu, u64 time)
>  	cpu->sample.mperf -= cpu->prev_mperf;
>  	cpu->sample.tsc -= cpu->prev_tsc;
>  
> -	intel_pstate_calc_busy(cpu);
> -
>  	cpu->prev_aperf = aperf;
>  	cpu->prev_mperf = mperf;
>  	cpu->prev_tsc = tsc;
> @@ -942,7 +940,6 @@ static inline int32_t
> get_target_pstate_use_cpu_load(struct cpudata *cpu)
>  	mperf = cpu->sample.mperf + delta_iowait_mperf;
>  	cpu->prev_cummulative_iowait = cummulative_iowait;
>  
> -
>  	/*
>  	 * The load can be estimated as the ratio of the mperf
> counter
>  	 * running at a constant frequency during active periods
> @@ -960,6 +957,8 @@ static inline int32_t
> get_target_pstate_use_performance(struct cpudata *cpu)
>  	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
>  	u64 duration_ns;
>  
> +	intel_pstate_calc_busy(cpu);
> +
>  	/*
>  	 * core_busy is the ratio of actual performance to max
>  	 * max_pstate is the max non turbo pstate available

  reply	other threads:[~2016-03-07 21:39 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-06  7:34 [PATCH V5 0/4] Reduce the intel_pstate timer overhead Philippe Longepe
2016-03-06  7:34 ` [PATCH V5 1/4] Remove extra conversions in pid calculation Philippe Longepe
2016-03-07 21:30   ` Srinivas Pandruvada
2016-03-06  7:34 ` [PATCH V5 2/4] Optimize calculation for max/min_perf_adj Philippe Longepe
2016-03-07 21:35   ` Srinivas Pandruvada
2016-03-06  7:34 ` [PATCH V5 3/4] Move the intel_pstate_calc_busy into get_target_pstate_use_performance Philippe Longepe
2016-03-07 21:36   ` Srinivas Pandruvada [this message]
2016-03-06  7:34 ` [PATCH V5 4/4] intel_pstate: Remove the freq calculation from the intel_pstate_calc_busy function Philippe Longepe
2016-03-07 21:42   ` Srinivas Pandruvada

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1457386601.4361.9.camel@linux.intel.com \
    --to=srinivas.pandruvada@linux.intel.com \
    --cc=linux-pm@vger.kernel.org \
    --cc=philippe.longepe@linux.intel.com \
    --cc=rafael@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).