From: Alex Shi <alex.shi@intel.com>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linux PM list <linux-pm@vger.kernel.org>,
"Brown, Len" <len.brown@intel.com>,
"Wysocki, Rafael J" <rafael.j.wysocki@intel.com>,
Arjan van de Ven <arjan@linux.intel.com>,
LKP ML <lkp@linux.intel.com>
Subject: Re: bltk-game regressions on snb laptop
Date: Thu, 18 Apr 2013 14:16:41 +0800 [thread overview]
Message-ID: <516F8FC9.8010005@intel.com> (raw)
In-Reply-To: <CAKohponG+F6ikVb2iY_Qg5E6NoCkPVj5VC12JqwXfamzsKLrXA@mail.gmail.com>
On 04/18/2013 01:37 PM, Viresh Kumar wrote:
>>> >> About your system: Can you give output of cpufreq-info for v3.8 and
>>> >> v3.9-latestrc?
>>> >> Your cpus share a clock line or not?
>> >
>> > Yes our cpu shares a clock line. So the cpufreq-info is same. SNB CPU
>> > p-state is per cpu package, and hardware will coordinate the software
>> > asking, then decide which cpufreq should be.
> Can you paste cpufreq-info output, that will give us a better picture of your
> system.
will give you turbostat info later.
>
>> > That's sth I am also confused. Yes, that cpu share a clock line. But
>> > Arjan and Len both said affected_cpus should only include the cpu self,
>> > because cpu will do hardware coordination for them.
> Why? we need a reason for that.... Do they mean Linux shouldn't be aware
> of any requirement of freq sync? But why?
Nope.
acpi_processor_preregister_performance() will read ACPI table and get the
p-state coordinate type. I think that is the agreement between kernel and hardware.
Maybe the ondemand governor doesn't fit well with the laptop's p-state internal logical.
So, there is intel p-state driver for SNB, and it use different internal governor.
acpi_processor_preregister_performance():
715 if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
716 pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ALL;
717 else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
718 pr->performance->shared_type = CPUFREQ_SHARED_TYPE_HW;
719 else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
720 pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ANY;
721
--
Thanks Alex
next prev parent reply other threads:[~2013-04-18 6:17 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-16 7:14 bltk-game regressions on snb laptop Alex Shi
2013-04-17 16:34 ` Rafael J. Wysocki
2013-04-18 0:23 ` Alex Shi
2013-04-17 16:46 ` Viresh Kumar
2013-04-18 0:48 ` Alex Shi
2013-04-18 4:26 ` Viresh Kumar
2013-04-18 4:36 ` Viresh Kumar
2013-04-18 5:24 ` Alex Shi
2013-04-18 5:16 ` Alex Shi
2013-04-18 5:37 ` Viresh Kumar
2013-04-18 6:16 ` Alex Shi [this message]
2013-04-18 8:54 ` Alex Shi
2013-04-18 10:01 ` Viresh Kumar
2013-04-19 10:00 ` Alex Shi
2013-04-19 12:23 ` Viresh Kumar
2013-04-19 14:43 ` Alex Shi
2013-04-19 15:44 ` Arjan van de Ven
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=516F8FC9.8010005@intel.com \
--to=alex.shi@intel.com \
--cc=arjan@linux.intel.com \
--cc=len.brown@intel.com \
--cc=linux-pm@vger.kernel.org \
--cc=lkp@linux.intel.com \
--cc=rafael.j.wysocki@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: 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.