All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mason <slash.tmp@free.fr>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Mans Rullgard <mans@mansr.com>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>,
	Linux PM <linux-pm@vger.kernel.org>,
	cpufreq <cpufreq@vger.kernel.org>
Subject: Re: schedule_timeout sleeps too long after dividing CPU frequency
Date: Fri, 15 May 2015 12:11:18 +0200	[thread overview]
Message-ID: <5555C646.5030504@free.fr> (raw)
In-Reply-To: <20150515041632.GG6348@linux>

On 15/05/2015 06:16, Viresh Kumar wrote:

> On 14-05-15, 16:48, Mason wrote:
>
>> How do I run the TWD in one-shot mode?
> 
> I haven't refreshed my memory for the earlier reply, but I have tried
> to go through the code again.
> 
> The logic is this:
> - Oneshot mode is only useful if we are going to support NO_HZ mode.
>   i.e. we can disable the clkevt device during CPU idle ..
> - For that to work, or in other words for the CPU to wake up from the
>   idle state, we need a broadcast timer. Which will wake up the idle
>   cpu and its clkevt device.
> 
>   You don't have this 'broadcast' timer in your case and so we aren't
>   able to switch to oneshot mode.
> 
>   Even if you do that, you will be stuck in LOW resolution mode. And
>   so you probably leave this timer as is and use a out-of-CPU-domain
>   timer for this work, which can support high resolution mode.

For the record, my kernel config contains:
(There are some BROADCAST-related options enabled.)

#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_HARDIRQS_SW_RESEND=y
CONFIG_IRQ_DOMAIN=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_KTIME_SCALAR=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
CONFIG_ARCH_HAS_TICK_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y

#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_NO_HZ_COMMON=y
# CONFIG_HZ_PERIODIC is not set
CONFIG_NO_HZ_IDLE=y
# CONFIG_NO_HZ_FULL is not set
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y

#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set
# CONFIG_IRQ_TIME_ACCOUNTING is not set
# CONFIG_BSD_PROCESS_ACCT is not set
# CONFIG_TASKSTATS is not set


Full config (and platform patch) provided in <555380F8.5050306@free.fr>
http://article.gmane.org/gmane.linux.power-management.general/60164

Regards.


WARNING: multiple messages have this Message-ID (diff)
From: slash.tmp@free.fr (Mason)
To: linux-arm-kernel@lists.infradead.org
Subject: schedule_timeout sleeps too long after dividing CPU frequency
Date: Fri, 15 May 2015 12:11:18 +0200	[thread overview]
Message-ID: <5555C646.5030504@free.fr> (raw)
In-Reply-To: <20150515041632.GG6348@linux>

On 15/05/2015 06:16, Viresh Kumar wrote:

> On 14-05-15, 16:48, Mason wrote:
>
>> How do I run the TWD in one-shot mode?
> 
> I haven't refreshed my memory for the earlier reply, but I have tried
> to go through the code again.
> 
> The logic is this:
> - Oneshot mode is only useful if we are going to support NO_HZ mode.
>   i.e. we can disable the clkevt device during CPU idle ..
> - For that to work, or in other words for the CPU to wake up from the
>   idle state, we need a broadcast timer. Which will wake up the idle
>   cpu and its clkevt device.
> 
>   You don't have this 'broadcast' timer in your case and so we aren't
>   able to switch to oneshot mode.
> 
>   Even if you do that, you will be stuck in LOW resolution mode. And
>   so you probably leave this timer as is and use a out-of-CPU-domain
>   timer for this work, which can support high resolution mode.

For the record, my kernel config contains:
(There are some BROADCAST-related options enabled.)

#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_HARDIRQS_SW_RESEND=y
CONFIG_IRQ_DOMAIN=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_KTIME_SCALAR=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
CONFIG_ARCH_HAS_TICK_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y

#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_NO_HZ_COMMON=y
# CONFIG_HZ_PERIODIC is not set
CONFIG_NO_HZ_IDLE=y
# CONFIG_NO_HZ_FULL is not set
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y

#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set
# CONFIG_IRQ_TIME_ACCOUNTING is not set
# CONFIG_BSD_PROCESS_ACCT is not set
# CONFIG_TASKSTATS is not set


Full config (and platform patch) provided in <555380F8.5050306@free.fr>
http://article.gmane.org/gmane.linux.power-management.general/60164

Regards.

  parent reply	other threads:[~2015-05-15 10:11 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-12 14:32 schedule_timeout sleeps too long after dividing CPU frequency Mason
2015-05-12 14:32 ` Mason
2015-05-12 14:46 ` Viresh Kumar
2015-05-12 14:46   ` Viresh Kumar
2015-05-12 15:14   ` Mason
2015-05-12 15:14     ` Mason
2015-05-12 15:50     ` Russell King - ARM Linux
2015-05-12 15:50       ` Russell King - ARM Linux
2015-05-12 16:14       ` Mason
2015-05-12 16:14         ` Mason
2015-05-13 16:51       ` Mason
2015-05-13 16:51         ` Mason
2015-05-14  2:13         ` Viresh Kumar
2015-05-14  2:13           ` Viresh Kumar
2015-05-14 11:22           ` Mason
2015-05-14 11:22             ` Mason
2015-05-14 11:54             ` Viresh Kumar
2015-05-14 11:54               ` Viresh Kumar
2015-05-14 13:06               ` Mason
2015-05-14 13:06                 ` Mason
2015-05-14 13:53                 ` Russell King - ARM Linux
2015-05-14 13:53                   ` Russell King - ARM Linux
2015-05-14 14:51                   ` Mason
2015-05-14 14:51                     ` Mason
2015-05-14 13:59                 ` Viresh Kumar
2015-05-14 13:59                   ` Viresh Kumar
2015-05-14 13:59                   ` Viresh Kumar
2015-05-14 14:38                   ` Viresh Kumar
2015-05-14 14:38                     ` Viresh Kumar
2015-05-14 14:42                   ` Russell King - ARM Linux
2015-05-14 14:42                     ` Russell King - ARM Linux
2015-05-15  9:29                     ` Mason
2015-05-15  9:29                       ` Mason
2015-05-15  9:51                       ` Russell King - ARM Linux
2015-05-15  9:51                         ` Russell King - ARM Linux
2015-05-15 10:01                         ` Viresh Kumar
2015-05-15 10:01                           ` Viresh Kumar
2015-05-15 10:36                         ` Mason
2015-05-15 10:36                           ` Mason
2015-05-15 11:58                           ` Russell King - ARM Linux
2015-05-15 11:58                             ` Russell King - ARM Linux
2015-05-15 12:45                             ` Mason
2015-05-15 12:45                               ` Mason
2015-05-15 13:15                               ` Russell King - ARM Linux
2015-05-15 13:15                                 ` Russell King - ARM Linux
2015-05-15 13:58                                 ` Mason
2015-05-15 18:35                                   ` Mason
2015-05-18 11:24                                     ` Mason
2015-05-18 11:54                                       ` Russell King - ARM Linux
2015-05-20 16:21                                         ` Mason
2015-05-20 18:50                                           ` Arnd Bergmann
2015-05-20 19:34                                             ` Mason
2015-05-20 20:14                                               ` Russell King - ARM Linux
2015-05-20 20:41                                                 ` Mason
2015-05-20 20:52                                                   ` Arnd Bergmann
2015-05-20 21:56                                                     ` Mason
2015-05-20 22:18                                                       ` Arnd Bergmann
2015-05-21 12:35                                                         ` Mason
2015-05-20 23:14                                                       ` Russell King - ARM Linux
2015-05-21  9:56                                                         ` Mason
2015-05-21 10:20                                                           ` Russell King - ARM Linux
2015-05-14 14:48                   ` Mason
2015-05-14 14:48                     ` Mason
2015-05-15  4:16                     ` Viresh Kumar
2015-05-15  4:16                       ` Viresh Kumar
2015-05-15  5:07                       ` Viresh Kumar
2015-05-15  5:07                         ` Viresh Kumar
2015-05-15  9:00                       ` Russell King - ARM Linux
2015-05-15  9:00                         ` Russell King - ARM Linux
2015-05-15  9:21                       ` Mason
2015-05-15  9:21                         ` Mason
2015-05-15 10:11                       ` Mason [this message]
2015-05-15 10:11                         ` Mason
2015-05-12 15:23 ` Russell King - ARM Linux
2015-05-12 15:23   ` Russell King - ARM Linux
2015-05-12 16:03   ` Mason
2015-05-12 16:03     ` Mason

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=5555C646.5030504@free.fr \
    --to=slash.tmp@free.fr \
    --cc=cpufreq@vger.kernel.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=linux@arm.linux.org.uk \
    --cc=mans@mansr.com \
    --cc=rjw@rjwysocki.net \
    --cc=viresh.kumar@linaro.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.