linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Philippe Longepe <philippe.longepe@linux.intel.com>
To: linux-pm@vger.kernel.org
Cc: srinivas.pandruvada@linux.intel.com,
	Stephane Gasparini <stephane.gasparini@intel.com>,
	Philippe Longepe <philippe.longepe@intel.com>
Subject: [PATCH V5 3/3] cpufreq: intel_pstate: Account for IO wait time
Date: Thu,  3 Dec 2015 18:55:58 +0100	[thread overview]
Message-ID: <1449165359-25832-7-git-send-email-philippe.longepe@linux.intel.com> (raw)
In-Reply-To: <1449165359-25832-1-git-send-email-philippe.longepe@linux.intel.com>

From: Stephane Gasparini <stephane.gasparini@intel.com>

To improve IO bound work, account IO wait time in calculating
CPU busy. This change gets IO wait time using get_cpu_iowait_time_us,
and converts time into number of IO cycles spent at max non turbo
frequency. This IO cycle count is added to mperf value to account
for IO wait time.

Signed-off-by: Philippe Longepe <philippe.longepe@intel.com>
Signed-off-by: Stephane Gasparini <stephane.gasparini@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2cf8bb6..fb92402 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -114,6 +114,7 @@ struct cpudata {
 	u64	prev_mperf;
 	u64	prev_tsc;
 	struct sample sample;
+	u64 prev_cummulative_iowait;
 };
 
 static struct cpudata **all_cpu_data;
@@ -934,16 +935,28 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
+	u64 cummulative_iowait, delta_iowait_us;
+	u64 delta_iowait_mperf;
+	u64 mperf, now;
 	int32_t cpu_load;
 
+	cummulative_iowait = get_cpu_iowait_time_us(cpu->cpu, &now);
+
+	/* Convert iowait time into number of IO cycles spent at max_freq */
+	delta_iowait_us = cummulative_iowait - cpu->prev_cummulative_iowait;
+	delta_iowait_mperf = div64_u64(delta_iowait_us * cpu->pstate.scaling *
+		cpu->pstate.max_pstate, 1000);
+
+	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
 	 * (C0) and the time stamp counter running at the same frequency
 	 * also during C-states.
 	 */
-	cpu_load = div64_u64(100 * sample->mperf, sample->tsc);
-
+	cpu_load = div64_u64(100 * mperf, sample->tsc);
 	cpu->sample.busy_scaled = int_tofp(cpu_load);
 
 	return (cpu->pstate.current_pstate - pid_calc(&cpu->pid,
-- 
1.9.1


  parent reply	other threads:[~2015-12-03 17:55 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-03 17:55 [PATCH V5 0/3] cpufreq: intel_pstate: account non C0 time Philippe Longepe
2015-12-03 17:55 ` Philippe Longepe
2015-12-03 17:55 ` [PATCH V5 1/3] cpufreq: intel_pstate: configurable algorithm to get target pstate Philippe Longepe
2015-12-04  1:41   ` Rafael J. Wysocki
2015-12-03 17:55 ` Philippe Longepe
2015-12-03 17:55 ` [PATCH V5 2/3] cpufreq: intel_pstate: account for non C0 time Philippe Longepe
2015-12-04  2:12   ` Rafael J. Wysocki
2015-12-04 14:33     ` Philippe Longepe
2015-12-04 17:39       ` Srinivas Pandruvada
2015-12-04 23:01         ` Rafael J. Wysocki
2015-12-04 22:48           ` Srinivas Pandruvada
2015-12-04 23:16             ` Rafael J. Wysocki
2015-12-03 17:55 ` Philippe Longepe
2015-12-03 17:55 ` Philippe Longepe [this message]
2015-12-04  2:27   ` [PATCH V5 3/3] cpufreq: intel_pstate: Account for IO wait time Rafael J. Wysocki
2015-12-03 17:55 ` Philippe Longepe

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=1449165359-25832-7-git-send-email-philippe.longepe@linux.intel.com \
    --to=philippe.longepe@linux.intel.com \
    --cc=linux-pm@vger.kernel.org \
    --cc=philippe.longepe@intel.com \
    --cc=srinivas.pandruvada@linux.intel.com \
    --cc=stephane.gasparini@intel.com \
    /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).