All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Jones <davej@redhat.com>
To: Erik Mouw <erik@harddisk-recovery.com>
Cc: Andrew Morton <akpm@osdl.org>, Andi Kleen <ak@suse.de>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Lee Revell <rlrevell@joe-job.com>,
	cpufreq <cpufreq@www.linux.org.uk>
Subject: Re: [PATCH] CPU frequency display in /proc/cpuinfo
Date: Tue, 6 Dec 2005 11:56:07 -0500	[thread overview]
Message-ID: <20051206165607.GA440@redhat.com> (raw)
In-Reply-To: <20051206111349.GB32737@harddisk-recovery.com>

On Tue, Dec 06, 2005 at 12:13:49PM +0100, Erik Mouw wrote:
 > On Mon, Dec 05, 2005 at 12:25:13PM -0500, Dave Jones wrote:
 > > On Mon, Dec 05, 2005 at 02:02:24PM +0100, Erik Mouw wrote:
 > >  > If you want a userspace governor to change the CPU speed, you need to
 > >  > export the value to userland. 
 > > 
 > > We have sysfs files for that.
 > 
 > Earlier in this thread you said (I should have quoted that, my fault):
 > 
 >   Adding any other interface to obtain this value is equally as broken.
 > 
 > So I'm confused, sysfs one of the "any other interfaces"...

userspace governors need to know the available frequencies to scale to, 
which they obtain from sysfs. In addition, we maintain an index as to
which of those is currently chosen.  However, programs should not rely
on this to be a "how fast is my CPU" status, as it's totally meaningless.
It's there purely for humans to see "Yes, X < Y, so I'm going at the
lower of the frequencies my CPU can do", not for programs to calculate
delays loops and such.

		Dave

WARNING: multiple messages have this Message-ID (diff)
From: Dave Jones <davej@redhat.com>
To: Erik Mouw <erik@harddisk-recovery.com>
Cc: Lee Revell <rlrevell@joe-job.com>, Andi Kleen <ak@suse.de>,
	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>,
	Andrew Morton <akpm@osdl.org>, cpufreq <cpufreq@www.linux.org.uk>,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] CPU frequency display in /proc/cpuinfo
Date: Tue, 6 Dec 2005 11:56:07 -0500	[thread overview]
Message-ID: <20051206165607.GA440@redhat.com> (raw)
In-Reply-To: <20051206111349.GB32737@harddisk-recovery.com>

On Tue, Dec 06, 2005 at 12:13:49PM +0100, Erik Mouw wrote:
 > On Mon, Dec 05, 2005 at 12:25:13PM -0500, Dave Jones wrote:
 > > On Mon, Dec 05, 2005 at 02:02:24PM +0100, Erik Mouw wrote:
 > >  > If you want a userspace governor to change the CPU speed, you need to
 > >  > export the value to userland. 
 > > 
 > > We have sysfs files for that.
 > 
 > Earlier in this thread you said (I should have quoted that, my fault):
 > 
 >   Adding any other interface to obtain this value is equally as broken.
 > 
 > So I'm confused, sysfs one of the "any other interfaces"...

userspace governors need to know the available frequencies to scale to, 
which they obtain from sysfs. In addition, we maintain an index as to
which of those is currently chosen.  However, programs should not rely
on this to be a "how fast is my CPU" status, as it's totally meaningless.
It's there purely for humans to see "Yes, X < Y, so I'm going at the
lower of the frequencies my CPU can do", not for programs to calculate
delays loops and such.

		Dave



  reply	other threads:[~2005-12-06 16:56 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-12-02 18:13 [PATCH] CPU frequency display in /proc/cpuinfo Venkatesh Pallipadi
2005-12-02 18:19 ` Andi Kleen
2005-12-02 18:43   ` Venkatesh Pallipadi
2005-12-04 16:43     ` Dominik Brodowski
2005-12-04 18:32       ` Andi Kleen
2005-12-04 19:49         ` Lee Revell
2005-12-04 19:49           ` Lee Revell
2005-12-04 20:13           ` Andi Kleen
2005-12-04 20:13             ` Andi Kleen
2005-12-04 21:01           ` Horst von Brand
2005-12-05  1:16           ` Dave Jones
2005-12-05  1:16             ` Dave Jones
2005-12-05 13:02             ` Erik Mouw
2005-12-05 17:25               ` Dave Jones
2005-12-05 17:25                 ` Dave Jones
2005-12-05 17:27                 ` Lee Revell
2005-12-05 17:27                   ` Lee Revell
2005-12-06 11:13                 ` Erik Mouw
2005-12-06 16:56                   ` Dave Jones [this message]
2005-12-06 16:56                     ` Dave Jones
2005-12-06 17:35                     ` Erik Mouw
2005-12-05 15:32             ` Lee Revell
2005-12-05 15:32               ` Lee Revell
2005-12-05 18:36               ` Andi Kleen
2005-12-05 15:59             ` Mark Lord
2005-12-05 17:26               ` Dave Jones
2005-12-05 17:26                 ` Dave Jones
2005-12-05 16:29             ` Avi Kivity
2005-12-05 16:29               ` Avi Kivity
2005-12-05 16:46               ` linux-os (Dick Johnson)
2005-12-05 16:46                 ` linux-os (Dick Johnson)
2005-12-05 17:27               ` Dave Jones
2005-12-05 17:27                 ` Dave Jones

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=20051206165607.GA440@redhat.com \
    --to=davej@redhat.com \
    --cc=ak@suse.de \
    --cc=akpm@osdl.org \
    --cc=cpufreq@www.linux.org.uk \
    --cc=erik@harddisk-recovery.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rlrevell@joe-job.com \
    /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.