From: Arjan van de Ven <arjan@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>,
Nicolas Pitre <nicolas.pitre@linaro.org>,
Daniel Lezcano <daniel.lezcano@linaro.org>,
Preeti U Murthy <preeti@linux.vnet.ibm.com>,
Len Brown <len.brown@intel.com>,
Preeti Murthy <preeti.lkml@gmail.com>,
"mingo@redhat.com" <mingo@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>,
LKML <linux-kernel@vger.kernel.org>,
"linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>,
Lists linaro-kernel <linaro-kernel@lists.linaro.org>
Subject: Re: [RFC PATCH 3/3] idle: store the idle state index in the struct rq
Date: Mon, 03 Feb 2014 08:17:47 -0800 [thread overview]
Message-ID: <52EFC12B.50704@linux.intel.com> (raw)
In-Reply-To: <20140203145605.GL8874@twins.programming.kicks-ass.net>
On 2/3/2014 6:56 AM, Peter Zijlstra wrote:
>
> Arjan, could you have a look at teaching your Thunderpants to wrap lines
> at ~80 chars please?
I'll try but it suffers from Apple-disease
>> 1) A latency driven one
>> 2) A performance impact on
>>
>> first one is pretty much the exit latency related time, sort of a
>> "expected time to first instruction" (currently menuidle has the
>> 99.999% worst case number, which is not useful for this, but is a
>> first approximation). This is obviously the dominating number for
>> expected-short running tasks
>>
>> second on is more of a "is there any cache/TLB left or is it flushed"
>> kind of metric. It's more tricky to compute, since what is the cost of
>> an empty cache (or even a cache migration) after all.... .... but I
>> suspect it's in part what the scheduler will care about more for
>> expected-long running tasks.
>
> Yeah, so currently we 'assume' cache hotness based on runtime; see
> task_hot(). A hint that the CPU wiped its caches might help there.
if there's a simple api like
sched_cpu_cache_wiped(int llc)
that would be very nice for this; the menuidle side knows this
for some cases and thus can just call it. This would be a very
small and minimal change
* if you don't care about llc vs core local caches then that
parameter can go away
* I assume this is also called for the local cpu... if not then we
need to add a cpu number argument
* we can also call this from architecture code when wbinvd or the
arm equivalent is called etc
next prev parent reply other threads:[~2014-02-03 16:18 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-30 14:09 [RFC PATCH 0/3] cpuidle/sched: move main idle function in the idle.c Daniel Lezcano
2014-01-30 14:09 ` [RFC PATCH 1/3] cpuidle: split cpuidle_idle_call main function into functions Daniel Lezcano
2014-01-30 15:27 ` Peter Zijlstra
2014-01-30 15:39 ` Daniel Lezcano
2014-01-30 19:39 ` Nicolas Pitre
2014-01-31 14:10 ` Daniel Lezcano
2014-01-30 14:09 ` [RFC PATCH 2/3] cpuidle: move the cpuidle_idle_call function to idle.c Daniel Lezcano
2014-01-30 19:42 ` Nicolas Pitre
2014-01-30 14:09 ` [RFC PATCH 3/3] idle: store the idle state index in the struct rq Daniel Lezcano
2014-01-30 15:31 ` Peter Zijlstra
2014-01-30 16:27 ` Daniel Lezcano
2014-01-30 16:35 ` Peter Zijlstra
2014-01-30 17:25 ` Daniel Lezcano
2014-01-30 17:50 ` Lorenzo Pieralisi
2014-01-30 21:02 ` Nicolas Pitre
2014-01-31 9:46 ` Vincent Guittot
2014-01-31 10:04 ` Lorenzo Pieralisi
2014-01-31 10:44 ` Daniel Lezcano
2014-01-31 8:45 ` Preeti Murthy
2014-01-31 9:02 ` Peter Zijlstra
2014-01-31 9:39 ` Preeti U Murthy
2014-01-31 10:24 ` Peter Zijlstra
2014-01-31 14:04 ` Daniel Lezcano
2014-01-31 14:12 ` Dietmar Eggemann
2014-01-31 15:07 ` Arjan van de Ven
2014-01-31 15:37 ` Daniel Lezcano
2014-01-31 15:50 ` Arjan van de Ven
2014-01-31 16:35 ` Daniel Lezcano
2014-01-31 16:42 ` Arjan van de Ven
2014-01-31 18:19 ` Nicolas Pitre
2014-02-01 6:00 ` Brown, Len
2014-02-01 15:31 ` Nicolas Pitre
2014-02-01 19:39 ` Brown, Len
2014-02-01 20:13 ` Nicolas Pitre
2014-02-01 15:40 ` Lorenzo Pieralisi
2014-02-03 12:54 ` Morten Rasmussen
2014-02-03 14:38 ` Arjan van de Ven
2014-02-03 14:56 ` Peter Zijlstra
2014-02-03 16:17 ` Arjan van de Ven [this message]
2014-02-11 16:41 ` Peter Zijlstra
2014-02-11 17:12 ` Arjan van de Ven
2014-02-11 19:47 ` Peter Zijlstra
2014-02-12 15:16 ` Lorenzo Pieralisi
2014-02-12 16:14 ` Arjan van de Ven
2014-02-12 17:37 ` Lorenzo Pieralisi
2014-02-12 19:05 ` Nicolas Pitre
2014-02-04 9:14 ` Ingo Molnar
2014-02-04 14:53 ` Arjan van de Ven
2014-02-04 14:56 ` Arjan van de Ven
2014-02-03 14:58 ` Nicolas Pitre
2014-01-31 10:15 ` Daniel Lezcano
2014-02-03 6:33 ` Preeti U Murthy
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=52EFC12B.50704@linux.intel.com \
--to=arjan@linux.intel.com \
--cc=daniel.lezcano@linaro.org \
--cc=len.brown@intel.com \
--cc=linaro-kernel@lists.linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=nicolas.pitre@linaro.org \
--cc=peterz@infradead.org \
--cc=preeti.lkml@gmail.com \
--cc=preeti@linux.vnet.ibm.com \
--cc=rjw@rjwysocki.net \
--cc=tglx@linutronix.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
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).