From: Peter Zijlstra <peterz@infradead.org>
To: "Luck, Tony" <tony.luck@intel.com>
Cc: "Yu, Fenghua" <fenghua.yu@intel.com>,
Rusty Russell <rusty@rustcorp.com.au>,
Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
H Peter Anvin <hpa@zytor.com>,
"Siddha, Suresh B" <suresh.b.siddha@intel.com>,
"Mallick, Asit K" <asit.k.mallick@intel.com>,
Arjan Dan De Ven <arjan@linux.intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>, x86 <x86@kernel.org>,
linux-pm <linux-pm@vger.kernel.org>,
"Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Subject: RE: [PATCH 0/6] x86/cpu hotplug: Wake up offline CPU via mwait or nmi
Date: Tue, 05 Jun 2012 19:50:25 +0200 [thread overview]
Message-ID: <1338918625.2749.29.camel@twins> (raw)
In-Reply-To: <3908561D78D1C84285E8C5FCA982C28F19300965@ORSMSX104.amr.corp.intel.com>
On Tue, 2012-06-05 at 17:44 +0000, Luck, Tony wrote:
> > Like what? Offline is nothing more than a C state on x86.
>
> Offline is a bigger hammer than idle.
>
> When a core is idle it may take an interrupt which wakes it up to use power.
> The scheduler may assign a process to run on it, which will wake it up to use power.
>
> When a core is offline we take extra steps (re-routing interrupts, telling the
> scheduler it is not available for work) to make sure it STAYS in that low
> power state.
You also wreck cpusets, cpu affinity and you need some userspace crap to
poll state trying to figure out when to wake up again.
(And yes, I've heard stories about userspace hotplug daemons that cause
machine wakeups themselves and were a main source of power usage at some
point).
All the timer/interrupt nonsense needs to be fixed anyhow, the HPC and
RT people want isolation anyway.
So shouldn't we all start by fixing the entire
load-balancer/timer/interrupt madness before we start swinging stupid
big hammers around that break half the interfaces we have?
next prev parent reply other threads:[~2012-06-05 17:50 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-04 18:17 [PATCH 0/6] x86/cpu hotplug: Wake up offline CPU via mwait or nmi Fenghua Yu
2012-06-04 18:17 ` [PATCH 1/6] x86/Documentation/kernel-parameters.txt: Add wakeup_cpu_via_init kernel parameter help Fenghua Yu
2012-06-04 18:17 ` [PATCH 2/6] x86/head_32.S/head_64.S: Kernel entry code after waking up offline CPU via mwait or nmi Fenghua Yu
2012-06-04 18:17 ` [PATCH 3/6] x86/smpboot.c: Wake " Fenghua Yu
2012-06-04 18:58 ` Suresh Siddha
2012-06-04 19:35 ` Yu, Fenghua
2012-06-04 18:17 ` [PATCH 4/6] x86/apic_flat_64.c: Wakeup function in apic calls mwait or nmi method Fenghua Yu
2012-06-04 18:17 ` [PATCH 5/6] x86/x2apic_cluster.c: Wakeup function in x2apic_cluster " Fenghua Yu
2012-06-04 18:17 ` [PATCH 6/6] x86/x2apic_phys.c: Wakeup function in x2apic_phys " Fenghua Yu
2012-06-04 18:17 ` Fenghua Yu
2012-06-04 20:11 ` [PATCH 0/6] x86/cpu hotplug: Wake up offline CPU via mwait or nmi Thomas Gleixner
2012-06-04 20:18 ` Luck, Tony
2012-06-04 22:52 ` Thomas Gleixner
2012-06-04 20:33 ` Peter Zijlstra
2012-06-05 0:40 ` Rusty Russell
2012-06-05 1:23 ` Arjan van de Ven
2012-06-05 7:38 ` Peter Zijlstra
2012-06-05 14:17 ` Alan Stern
2012-06-05 15:27 ` Arjan van de Ven
2012-06-05 7:39 ` Peter Zijlstra
2012-06-05 16:02 ` Yu, Fenghua
2012-06-05 16:09 ` Peter Zijlstra
2012-06-05 16:18 ` Yu, Fenghua
2012-06-05 16:19 ` Peter Zijlstra
2012-06-05 17:44 ` Luck, Tony
2012-06-05 17:50 ` Peter Zijlstra [this message]
2012-06-05 19:43 ` Thomas Gleixner
2012-06-05 19:45 ` Peter Zijlstra
2012-06-05 19:49 ` Peter Zijlstra
2012-06-05 19:51 ` Arjan van de Ven
2012-06-05 19:52 ` Peter Zijlstra
2012-06-05 20:47 ` Thomas Gleixner
2012-06-05 21:30 ` Peter Zijlstra
2012-06-05 22:09 ` Thomas Gleixner
2012-06-06 8:23 ` Peter Zijlstra
2012-06-06 8:30 ` Peter Zijlstra
2012-06-06 8:40 ` Peter Zijlstra
2012-06-05 22:12 ` Paul E. McKenney
2012-06-06 8:40 ` Peter Zijlstra
2012-06-06 8:42 ` Peter Zijlstra
2012-06-06 14:44 ` Paul E. McKenney
2012-06-06 15:46 ` Peter Zijlstra
2012-06-06 23:20 ` Paul E. McKenney
2012-06-08 9:20 ` Peter Zijlstra
2012-06-06 8:43 ` Peter Zijlstra
2012-06-06 14:41 ` Paul E. McKenney
2012-06-06 15:23 ` Arjan van de Ven
2012-06-06 15:48 ` Peter Zijlstra
2012-06-06 15:49 ` Paul E. McKenney
2012-06-06 16:59 ` Arjan van de Ven
2012-06-05 21:29 ` Paul E. McKenney
2012-06-05 21:37 ` Peter Zijlstra
2012-06-05 22:00 ` Paul E. McKenney
2012-06-06 12:17 ` Peter Zijlstra
2012-06-06 14:43 ` Paul E. McKenney
2012-06-05 19:51 ` Peter Zijlstra
2012-06-05 20:58 ` Andi Kleen
2012-06-05 21:15 ` Thomas Gleixner
2012-06-05 21:33 ` Thomas Gleixner
2012-06-05 23:13 ` Andi Kleen
2012-06-06 1:52 ` Arjan van de Ven
2012-06-05 18:07 ` Peter Zijlstra
2012-06-05 19:54 ` Luck, Tony
2012-06-05 19:56 ` Peter Zijlstra
2012-06-05 9:36 ` Thomas Gleixner
2012-06-05 13:41 ` [PATCH] kthread: Implement park/unpark facility Thomas Gleixner
2012-06-05 14:01 ` Peter Zijlstra
2012-06-05 14:05 ` Peter Zijlstra
2012-06-07 0:04 ` H. Peter Anvin
2012-06-10 5:40 ` Rusty Russell
2012-06-11 9:26 ` Thomas Gleixner
2012-06-12 0:23 ` Rusty Russell
2012-06-05 15:35 ` [PATCH 0/6] x86/cpu hotplug: Wake up offline CPU via mwait or nmi Jiang Liu
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=1338918625.2749.29.camel@twins \
--to=peterz@infradead.org \
--cc=arjan@linux.intel.com \
--cc=asit.k.mallick@intel.com \
--cc=fenghua.yu@intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rusty@rustcorp.com.au \
--cc=srivatsa.bhat@linux.vnet.ibm.com \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=x86@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