From: Thomas Gleixner <tglx@linutronix.de> To: Jacob Pan <jacob.jun.pan@linux.intel.com> Cc: "Pan, Jacob jun" <jacob.jun.pan@intel.com>, Preeti U Murthy <preeti@linux.vnet.ibm.com>, Peter Zijlstra <peterz@infradead.org>, Viresh Kumar <viresh.kumar@linaro.org>, LKP <lkp@01.org>, LKML <linux-kernel@vger.kernel.org>, "Zhang, Rui" <rui.zhang@intel.com>, Frederic Weisbecker <frederic@kernel.org>, Eduardo Valentin <edubezval@gmail.com> Subject: Re: [PATCH] tick/powerclamp: Remove tick_nohz_idle abuse Date: Thu, 18 Dec 2014 22:12:57 +0100 (CET) [thread overview] Message-ID: <alpine.DEB.2.11.1412182209010.17382@nanos> (raw) In-Reply-To: <20141218115239.53d17e39@jacob-VirtualBox> On Thu, 18 Dec 2014, Jacob Pan wrote: > OK I agree, also as I mentioned earlier, Peter already has a patch for > consolidated idle loop and remove tick_nohz_idle_enter/exit call from > powerclamp driver. I have been working on a few tweaks to maintain the > functionality and efficiency with the consolidated idle loop. > We can apply the patches on top of yours. No. This is equally wrong as I pointed out before. The 'unified' idle loop is still fake and just pretending to be idle. If simple standard interfaces like cpu_idle() are not working from idle code anymore then this simply stinks. And that's what any fake idle thread will do. The whole approach is wrong. Implement a sched fair throttler and you can avoid the whoile trainwreck. > > 1. Queue a deferable periodic timer whose handler checks if idle > > needs to be injected. If so, it sets rq->need_throttle for the cpu. > > If its already in the fake idle period, it clears rq->need_throttle > > and sets need_resched. > > > The key to powerclamp driver is to achieve package level idle > states, which implies synchronized idle injection. From > power/performance standpoint, only package level idle states is worth > injection. Then use a synchronized non deferrable timer on all cpus. It's simple enough. Thanks, tglx
WARNING: multiple messages have this Message-ID (diff)
From: Thomas Gleixner <tglx@linutronix.de> To: lkp@lists.01.org Subject: Re: [PATCH] tick/powerclamp: Remove tick_nohz_idle abuse Date: Thu, 18 Dec 2014 22:12:57 +0100 [thread overview] Message-ID: <alpine.DEB.2.11.1412182209010.17382@nanos> (raw) In-Reply-To: <20141218115239.53d17e39@jacob-VirtualBox> [-- Attachment #1: Type: text/plain, Size: 1330 bytes --] On Thu, 18 Dec 2014, Jacob Pan wrote: > OK I agree, also as I mentioned earlier, Peter already has a patch for > consolidated idle loop and remove tick_nohz_idle_enter/exit call from > powerclamp driver. I have been working on a few tweaks to maintain the > functionality and efficiency with the consolidated idle loop. > We can apply the patches on top of yours. No. This is equally wrong as I pointed out before. The 'unified' idle loop is still fake and just pretending to be idle. If simple standard interfaces like cpu_idle() are not working from idle code anymore then this simply stinks. And that's what any fake idle thread will do. The whole approach is wrong. Implement a sched fair throttler and you can avoid the whoile trainwreck. > > 1. Queue a deferable periodic timer whose handler checks if idle > > needs to be injected. If so, it sets rq->need_throttle for the cpu. > > If its already in the fake idle period, it clears rq->need_throttle > > and sets need_resched. > > > The key to powerclamp driver is to achieve package level idle > states, which implies synchronized idle injection. From > power/performance standpoint, only package level idle states is worth > injection. Then use a synchronized non deferrable timer on all cpus. It's simple enough. Thanks, tglx
next prev parent reply other threads:[~2014-12-18 21:13 UTC|newest] Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top 2014-12-18 10:51 [PATCH] tick/powerclamp: Remove tick_nohz_idle abuse Thomas Gleixner 2014-12-18 10:51 ` Thomas Gleixner 2014-12-18 14:01 ` Eduardo Valentin 2014-12-18 14:01 ` Eduardo Valentin 2014-12-18 14:43 ` Thomas Gleixner 2014-12-18 14:43 ` Thomas Gleixner 2014-12-18 17:28 ` Preeti U Murthy 2014-12-18 17:28 ` Preeti U Murthy [not found] ` <DD415AA12F8FF042BF4EA69DF123C1478AF91730@ORSMSX101.amr.corp.intel.com> 2014-12-18 19:52 ` Jacob Pan 2014-12-18 19:52 ` Jacob Pan 2014-12-18 21:12 ` Thomas Gleixner [this message] 2014-12-18 21:12 ` Thomas Gleixner 2014-12-19 18:39 ` Jacob Pan 2014-12-19 18:39 ` Jacob Pan 2014-12-19 19:56 ` Thomas Gleixner 2014-12-19 19:56 ` Thomas Gleixner 2014-12-20 1:31 ` Preeti U Murthy 2014-12-20 1:31 ` Preeti U Murthy 2014-12-23 2:57 ` Jacob Pan 2014-12-23 2:57 ` Jacob Pan 2014-12-31 5:04 ` Preeti U Murthy 2014-12-31 5:04 ` Preeti U Murthy 2014-12-19 13:09 ` [tip:timers/urgent] " tip-bot for Thomas Gleixner 2014-12-19 13:09 ` tip-bot for Thomas Gleixner
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=alpine.DEB.2.11.1412182209010.17382@nanos \ --to=tglx@linutronix.de \ --cc=edubezval@gmail.com \ --cc=frederic@kernel.org \ --cc=jacob.jun.pan@intel.com \ --cc=jacob.jun.pan@linux.intel.com \ --cc=linux-kernel@vger.kernel.org \ --cc=lkp@01.org \ --cc=peterz@infradead.org \ --cc=preeti@linux.vnet.ibm.com \ --cc=rui.zhang@intel.com \ --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: linkBe 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.