All of lore.kernel.org
 help / color / mirror / Atom feed
From: Guenter Roeck <linux@roeck-us.net>
To: Borislav Petkov <bp@alien8.de>, Peter Zijlstra <peterz@infradead.org>
Cc: "Ingo Molnar" <mingo@kernel.org>, "Huang Rui" <ray.huang@amd.com>,
	"Borislav Petkov" <bp@suse.de>, "Jean Delvare" <jdelvare@suse.de>,
	"Andy Lutomirski" <luto@amacapital.net>,
	"Andreas Herrmann" <herrmann.der.user@gmail.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	"Len Brown" <lenb@kernel.org>,
	"John Stultz" <john.stultz@linaro.org>,
	"Frédéric Weisbecker" <fweisbec@gmail.com>,
	lm-sensors@lm-sensors.org, linux-kernel@vger.kernel.org,
	x86@kernel.org,
	"Andreas Herrmann" <herrmann.der.user@googlemail.com>,
	"Aravind Gopalakrishnan" <Aravind.Gopalakrishnan@amd.com>,
	"Fengguang Wu" <fengguang.wu@intel.com>,
	"Aaron Lu" <aaron.lu@intel.com>, "Tony Li" <tony.li@amd.com>
Subject: Re: [lm-sensors] [PATCH 09/15] x86, amd: add accessor for number of cores per compute unit
Date: Mon, 31 Aug 2015 16:19:20 +0000	[thread overview]
Message-ID: <55E47E88.7080202@roeck-us.net> (raw)
In-Reply-To: <20150831160622.GA29830@nazgul.tnic>

On 08/31/2015 09:06 AM, Borislav Petkov wrote:
> On Mon, Aug 31, 2015 at 10:38:21AM +0200, Peter Zijlstra wrote:
>> Looking at the BKDG Fam 15h 60h-6Fh these MSRs are per compute unit.
>> This means you can do much finer grained measurements than system wide
>
> Well, we can do finer-grained if needed. I'm all for everything which
> has a good use case. The use case we had in mind here was the physical
> processor power consumption for a time period.
>
>> -- which is all hwmon seems capable of.
>
> I guess we can do both - perf and hwmon. I don't see why not.
>
>> Not to mention the proposed code is horrible, who in their right mind
>> does two rdmsrl_safe_on_cpu() back to back.
>
> That's a good point - I missed that during previous review. Rui, please
> put the rdmsrl_safe_on_cpu() accesses in a separate function which you
> run on a particular CPU, for your next version.
>
... and maybe work with Peter to address the other hotplug related issues.

It might also be worthwhile thinking about per-CU attributes, if that
provides any value (Peter's comments suggested that this might be the case).

Thanks,
Guenter


_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

WARNING: multiple messages have this Message-ID (diff)
From: Guenter Roeck <linux@roeck-us.net>
To: Borislav Petkov <bp@alien8.de>, Peter Zijlstra <peterz@infradead.org>
Cc: "Ingo Molnar" <mingo@kernel.org>, "Huang Rui" <ray.huang@amd.com>,
	"Borislav Petkov" <bp@suse.de>, "Jean Delvare" <jdelvare@suse.de>,
	"Andy Lutomirski" <luto@amacapital.net>,
	"Andreas Herrmann" <herrmann.der.user@gmail.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	"Len Brown" <lenb@kernel.org>,
	"John Stultz" <john.stultz@linaro.org>,
	"Frédéric Weisbecker" <fweisbec@gmail.com>,
	lm-sensors@lm-sensors.org, linux-kernel@vger.kernel.org,
	x86@kernel.org,
	"Andreas Herrmann" <herrmann.der.user@googlemail.com>,
	"Aravind Gopalakrishnan" <Aravind.Gopalakrishnan@amd.com>,
	"Fengguang Wu" <fengguang.wu@intel.com>,
	"Aaron Lu" <aaron.lu@intel.com>, "Tony Li" <tony.li@amd.com>
Subject: Re: [PATCH 09/15] x86, amd: add accessor for number of cores per compute unit
Date: Mon, 31 Aug 2015 09:19:20 -0700	[thread overview]
Message-ID: <55E47E88.7080202@roeck-us.net> (raw)
In-Reply-To: <20150831160622.GA29830@nazgul.tnic>

On 08/31/2015 09:06 AM, Borislav Petkov wrote:
> On Mon, Aug 31, 2015 at 10:38:21AM +0200, Peter Zijlstra wrote:
>> Looking at the BKDG Fam 15h 60h-6Fh these MSRs are per compute unit.
>> This means you can do much finer grained measurements than system wide
>
> Well, we can do finer-grained if needed. I'm all for everything which
> has a good use case. The use case we had in mind here was the physical
> processor power consumption for a time period.
>
>> -- which is all hwmon seems capable of.
>
> I guess we can do both - perf and hwmon. I don't see why not.
>
>> Not to mention the proposed code is horrible, who in their right mind
>> does two rdmsrl_safe_on_cpu() back to back.
>
> That's a good point - I missed that during previous review. Rui, please
> put the rdmsrl_safe_on_cpu() accesses in a separate function which you
> run on a particular CPU, for your next version.
>
... and maybe work with Peter to address the other hotplug related issues.

It might also be worthwhile thinking about per-CU attributes, if that
provides any value (Peter's comments suggested that this might be the case).

Thanks,
Guenter


  reply	other threads:[~2015-08-31 16:19 UTC|newest]

Thread overview: 118+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-08-27  8:07 [lm-sensors] [PATCH 00/15] hwmon, fam15h_power: introduce an accumulated power reporting algorithm Huang Rui
2015-08-27  8:07 ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 01/15] hwmon, fam15h_power: add support for AMD Carrizo Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:35   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:35     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 02/15] hwmon, fam15h_power: rename fam15h_power_is_internal_node0 function Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:35   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:35     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 03/15] hwmon, fam15h_power: refactor attributes for dynamically added Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:46   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:46     ` Guenter Roeck
2015-08-28 10:05     ` [lm-sensors] " Huang Rui
2015-08-28 10:05       ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 04/15] hwmon, fam15h_power: update running_avg_capture bit field to 28 Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:48   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:48     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 05/15] hwmon, fam15h_power: enable power1_input on AMD Carrizo Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:50   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:50     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 06/15] hwmon, fam15h_power: add documentation for new processors support Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:51   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:51     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 07/15] hwmon, fam15h_power: add ratio of Tsample to the PTSC period Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:54   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:54     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 08/15] hwmon, fam15h_power: add max compute unit accumulated power Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 14:56   ` [lm-sensors] " Guenter Roeck
2015-08-27 14:56     ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 09/15] x86, amd: add accessor for number of cores per compute unit Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27 17:27   ` [lm-sensors] " Guenter Roeck
2015-08-27 17:27     ` Guenter Roeck
2015-08-28 10:28     ` [lm-sensors] " Huang Rui
2015-08-28 10:28       ` Huang Rui
2015-08-28  6:48   ` [lm-sensors] " Borislav Petkov
2015-08-28  6:48     ` Borislav Petkov
2015-08-28  8:00     ` [lm-sensors] " Guenter Roeck
2015-08-28  8:00       ` Guenter Roeck
2015-08-28  8:04     ` [lm-sensors] " Ingo Molnar
2015-08-28  8:04       ` Ingo Molnar
2015-08-28  8:56       ` [lm-sensors] " Borislav Petkov
2015-08-28  8:56         ` Borislav Petkov
2015-08-28 10:18       ` [lm-sensors] " Huang Rui
2015-08-28 10:18         ` Huang Rui
2015-08-29  9:19       ` [lm-sensors] " Ingo Molnar
2015-08-29  9:19         ` Ingo Molnar
2015-08-30 15:53         ` [lm-sensors] " Borislav Petkov
2015-08-30 15:53           ` Borislav Petkov
2015-08-31  8:38           ` [lm-sensors] " Peter Zijlstra
2015-08-31  8:38             ` Peter Zijlstra
2015-08-31 13:26             ` [lm-sensors] " Guenter Roeck
2015-08-31 13:26               ` Guenter Roeck
2015-08-31 13:38               ` [lm-sensors] " Peter Zijlstra
2015-08-31 13:38                 ` Peter Zijlstra
2015-08-31 13:53                 ` [lm-sensors] " Guenter Roeck
2015-08-31 13:53                   ` Guenter Roeck
2015-08-31 14:57                   ` [lm-sensors] " Peter Zijlstra
2015-08-31 14:57                     ` Peter Zijlstra
2015-08-31 15:11                     ` [lm-sensors] " Guenter Roeck
2015-08-31 15:11                       ` Guenter Roeck
2015-08-31 16:06             ` [lm-sensors] " Borislav Petkov
2015-08-31 16:06               ` Borislav Petkov
2015-08-31 16:19               ` Guenter Roeck [this message]
2015-08-31 16:19                 ` Guenter Roeck
2015-08-31 20:44                 ` [lm-sensors] " Peter Zijlstra
2015-08-31 20:44                   ` Peter Zijlstra
2015-08-31 21:24                   ` [lm-sensors] " Guenter Roeck
2015-08-31 21:24                     ` Guenter Roeck
2015-09-01 15:56                     ` [lm-sensors] " Borislav Petkov
2015-09-01 15:56                       ` Borislav Petkov
2015-09-01 16:06                       ` [lm-sensors] " Guenter Roeck
2015-09-01 16:06                         ` Guenter Roeck
2015-08-27  8:07 ` [lm-sensors] [PATCH 10/15] hwmon, fam15h_power: add compute unit accumulated power Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-28  8:03   ` [lm-sensors] " Ingo Molnar
2015-08-28  8:03     ` Ingo Molnar
2015-08-28 10:42     ` [lm-sensors] " Huang Rui
2015-08-28 10:42       ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 11/15] hwmon, fam15h_power: add ptsc counter value for " Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorith Huang Rui
2015-08-27  8:07   ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Huang Rui
2015-08-27 17:30   ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Guenter Roeck
2015-08-27 17:30     ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Guenter Roeck
2015-08-28 10:45     ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Huang Rui
2015-08-28 10:45       ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Huang Rui
2015-08-28 14:05       ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Guenter Roeck
2015-08-28 14:05         ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Guenter Roeck
2015-08-31  4:16         ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Huang Rui
2015-08-31  4:16           ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Huang Rui
2015-08-31  4:30           ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Guenter Roeck
2015-08-31  4:30             ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Guenter Roeck
2015-08-31 13:11             ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Huang Rui
2015-08-31 13:11               ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Huang Rui
2015-08-31 13:25   ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Peter Zijlstra
2015-08-31 13:25     ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Peter Zijlstra
2015-08-31 14:59     ` [lm-sensors] [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algo Peter Zijlstra
2015-08-31 14:59       ` [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm Peter Zijlstra
2015-08-27  8:07 ` [lm-sensors] [PATCH 13/15] hwmon, fam15h_power: add documentation for previous TDP reporting Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 14/15] hwmon, fam15h_power: add documentation for accumulated power algorithm Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-27  8:07 ` [lm-sensors] [PATCH 15/15] MAINTAINERS: change the maintainer of fam15h_power driver Huang Rui
2015-08-27  8:07   ` Huang Rui
2015-08-29 16:33   ` [lm-sensors] [15/15] " Guenter Roeck
2015-08-29 16:33     ` Guenter Roeck
2015-08-31  1:11     ` [lm-sensors] " Huang Rui
2015-08-31  1:11       ` Huang Rui
2015-08-31 15:19     ` [lm-sensors] " Andreas Herrmann
2015-08-31 15:19       ` Andreas Herrmann

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=55E47E88.7080202@roeck-us.net \
    --to=linux@roeck-us.net \
    --cc=Aravind.Gopalakrishnan@amd.com \
    --cc=aaron.lu@intel.com \
    --cc=bp@alien8.de \
    --cc=bp@suse.de \
    --cc=fengguang.wu@intel.com \
    --cc=fweisbec@gmail.com \
    --cc=herrmann.der.user@gmail.com \
    --cc=herrmann.der.user@googlemail.com \
    --cc=jdelvare@suse.de \
    --cc=john.stultz@linaro.org \
    --cc=lenb@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lm-sensors@lm-sensors.org \
    --cc=luto@amacapital.net \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=ray.huang@amd.com \
    --cc=rjw@rjwysocki.net \
    --cc=tglx@linutronix.de \
    --cc=tony.li@amd.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 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.