LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Peter Zijlstra <peterz@infradead.org>,
	Linux PM <linux-pm@vger.kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Paul McKenney <paulmck@linux.vnet.ibm.com>,
	Thomas Ilsche <thomas.ilsche@tu-dresden.de>,
	Doug Smythies <dsmythies@telus.net>,
	Rik van Riel <riel@surriel.com>,
	Aubrey Li <aubrey.li@linux.intel.com>,
	Mike Galbraith <mgalbraith@suse.de>,
	LKML <linux-kernel@vger.kernel.org>
Subject: [RFT][PATCH v7 8/8] cpuidle: menu: Avoid selecting shallow states with stopped tick
Date: Tue, 20 Mar 2018 16:47:09 +0100
Message-ID: <2317533.DCFkBeZAbT@aspire.rjw.lan> (raw)
In-Reply-To: <2390019.oHdSGtR3EE@aspire.rjw.lan>

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

If the scheduler tick has been stopped already and the governor
selects a shallow idle state, the CPU can spend a long time in that
state if the selection is based on an inaccurate prediction of idle
time.  That effect turns out to be relevant, so it needs to be
mitigated.

To that end, modify the menu governor to discard the result of the
idle time prediction if the tick is stopped and the predicted idle
time is less than the tick period length, unless the tick timer is
going to expire soon.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---

v5 -> v7:
  * Rebase on top of the new [5-7/8].

Note that the problem tackled here may be addressed in a couple of other
ways in principle.

---
 drivers/cpuidle/governors/menu.c |   29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

Index: linux-pm/drivers/cpuidle/governors/menu.c
===================================================================
--- linux-pm.orig/drivers/cpuidle/governors/menu.c
+++ linux-pm/drivers/cpuidle/governors/menu.c
@@ -352,13 +352,28 @@ static int menu_select(struct cpuidle_dr
 	 */
 	data->predicted_us = min(data->predicted_us, expected_interval);
 
-	/*
-	 * Use the performance multiplier and the user-configurable
-	 * latency_req to determine the maximum exit latency.
-	 */
-	interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
-	if (latency_req > interactivity_req)
-		latency_req = interactivity_req;
+	if (tick_nohz_tick_stopped()) {
+		/*
+		 * If the tick is already stopped, the cost of possible short
+		 * idle duration misprediction is much higher, because the CPU
+		 * may be stuck in a shallow idle state for a long time as a
+		 * result of it.  In that case say we might mispredict and try
+		 * to force the CPU into a state for which we would have stopped
+		 * the tick, unless the tick timer is going to expire really
+		 * soon anyway.
+		 */
+		if (data->predicted_us < TICK_USEC)
+			data->predicted_us = min_t(unsigned int, TICK_USEC,
+						   ktime_to_us(delta_next));
+	} else {
+		/*
+		 * Use the performance multiplier and the user-configurable
+		 * latency_req to determine the maximum exit latency.
+		 */
+		interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
+		if (latency_req > interactivity_req)
+			latency_req = interactivity_req;
+	}
 
 	expected_interval = data->predicted_us;
 	/*

  parent reply index

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-20 15:12 [RFT][PATCH v7 0/8] sched/cpuidle: Idle loop rework Rafael J. Wysocki
2018-03-20 15:13 ` [RFT][PATCH v7 1/8] time: tick-sched: Reorganize idle tick management code Rafael J. Wysocki
2018-03-20 15:15 ` [RFT][PATCH v7 2/8] sched: idle: Do not stop the tick upfront in the idle loop Rafael J. Wysocki
2018-03-20 15:15 ` [RFT][PATCH v7 3/8] " Rafael J. Wysocki
2018-03-20 18:00   ` [Correction][RFT][PATCH v7 3/8] sched: idle: Do not stop the tick before cpuidle_idle_call() Rafael J. Wysocki
2018-03-20 15:16 ` [RFT][PATCH v7 4/8] jiffies: Introduce USER_TICK_USEC and redefine TICK_USEC Rafael J. Wysocki
2018-03-20 15:45 ` [RFT][PATCH v7 5/8] cpuidle: Return nohz hint from cpuidle_select() Rafael J. Wysocki
2018-03-21  6:48   ` [RFT][PATCH v7.1 " Rafael J. Wysocki
2018-03-21 11:52     ` Rafael J. Wysocki
2018-03-21 13:03   ` [RFT][PATCH v7.2 " Rafael J. Wysocki
2018-03-21 14:36   ` [RFT][PATCH v7 " Rafael J. Wysocki
2018-03-21 17:59     ` Thomas Ilsche
2018-03-21 22:15       ` Rafael J. Wysocki
2018-03-22 13:18         ` Thomas Ilsche
2018-03-22 17:23           ` Rafael J. Wysocki
2018-03-22  6:24       ` Doug Smythies
2018-03-22 15:41       ` Doug Smythies
2018-03-22 17:21         ` Rafael J. Wysocki
2018-03-21 18:23     ` Doug Smythies
2018-03-22 17:40   ` [RFT][PATCH v7.3 " Rafael J. Wysocki
2018-03-28  9:14     ` Thomas Ilsche
2018-03-30  9:39       ` Rafael J. Wysocki
2018-04-10 15:22         ` Thomas Ilsche
2018-03-22 20:46   ` Doug Smythies
2018-03-20 15:45 ` [RFT][PATCH v7 6/8] sched: idle: Select idle state before stopping the tick Rafael J. Wysocki
2018-03-27 21:50   ` Thomas Ilsche
2018-03-27 22:10     ` Rafael J. Wysocki
2018-03-28  8:13       ` Rafael J. Wysocki
2018-03-28  8:38         ` Thomas Ilsche
2018-03-28 10:37           ` Rafael J. Wysocki
2018-03-28 10:56             ` Rafael J. Wysocki
2018-03-28 15:15               ` Thomas Ilsche
2018-03-28 20:41               ` Doug Smythies
2018-03-28 23:11                 ` Rafael J. Wysocki
2018-03-20 15:46 ` [RFT][PATCH v7 7/8] cpuidle: menu: Refine idle state selection for running tick Rafael J. Wysocki
2018-03-20 15:47 ` Rafael J. Wysocki [this message]
2018-03-20 17:52 ` [RFT][PATCH v7 3/8] sched: idle: Do not stop the tick upfront in the idle loop Doug Smythies
2018-03-20 18:01   ` Rafael J. Wysocki
2018-03-21 12:31 ` [RFT][PATCH v7 0/8] sched/cpuidle: Idle loop rework Rik van Riel
2018-03-21 13:55   ` Rafael J. Wysocki
2018-03-21 14:53     ` Rik van Riel

Reply instructions:

You may reply publically 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=2317533.DCFkBeZAbT@aspire.rjw.lan \
    --to=rjw@rjwysocki.net \
    --cc=aubrey.li@linux.intel.com \
    --cc=dsmythies@telus.net \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mgalbraith@suse.de \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.ilsche@tu-dresden.de \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox