From: Thomas Renninger <trenn@suse.de>
To: lenb@kernel.org
Cc: linux-acpi@vger.kernel.org, cpufreq@vger.kernel.org,
venkatesh.pallipadi@intel.com, Thomas Renninger <trenn@suse.de>
Subject: [PATCH 8/8] CPUFREQ: Add documentation for new average_freq cpufreq_stats sysfs file
Date: Fri, 17 Apr 2009 16:22:12 +0200 [thread overview]
Message-ID: <1239978132-6261-9-git-send-email-trenn@suse.de> (raw)
In-Reply-To: <1239978132-6261-1-git-send-email-trenn@suse.de>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Cc: <linux-acpi@vger.kernel.org>
Cc: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>
Cc: <cpufreq@vger.kernel.org>
---
Documentation/cpu-freq/cpufreq-stats.txt | 17 +++++++++++++++++
1 files changed, 17 insertions(+), 0 deletions(-)
diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt
index fc64749..aa05b65 100644
--- a/Documentation/cpu-freq/cpufreq-stats.txt
+++ b/Documentation/cpu-freq/cpufreq-stats.txt
@@ -44,11 +44,28 @@ the stats driver insertion.
total 0
drwxr-xr-x 2 root root 0 May 14 16:06 .
drwxr-xr-x 3 root root 0 May 14 15:58 ..
+-r--r--r-- 1 root root 4096 May 14 16:06 average_freq
-r--r--r-- 1 root root 4096 May 14 16:06 time_in_state
-r--r--r-- 1 root root 4096 May 14 16:06 total_trans
-r--r--r-- 1 root root 4096 May 14 16:06 trans_table
--------------------------------------------------------------------------------
+- average_freq
+Shows the average frequency the processor stayed in since the file was read
+the last time. Zero is shown if it is read the first time or "not supported".
+
+CONFIG_X86_AVERAGE_FREQUENCY=y config needs to be set and the processor must
+support overclocking of single cores (ida flag in /proc/cpuinfo).
+This is the only way to detect, monitor and optimze for the feature that the
+BIOS can overclock single CPU cores behind the kernel's back if thermal
+requirements are met (e.g. other cores of the socket run at low frequency or
+sleep).
+
+Also on multi-core processors the shown current CPU frequency the machine is
+running on in cpufreq/cpufreq_scaling_cur and /proc/cpuinfo can be wrong with
+current kernels if the frequency of several cores must be the same because of
+HW restritions. average_freq should show the real frequency.
+
- time_in_state
This gives the amount of time spent in each of the frequencies supported by
this CPU. The cat output will have "<frequency> <time>" pair in each line, which
--
1.6.0.2
prev parent reply other threads:[~2009-04-17 14:22 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-17 14:22 acpi-cpufreq: Move average performance code and make it available to userspace and several cleanups in this area Thomas Renninger
2009-04-17 14:22 ` [PATCH 1/8] Fix for a regression that was introduced by earlier commit Thomas Renninger
2009-04-18 5:30 ` Len Brown
2009-04-17 14:22 ` [PATCH 2/8] acpi-cpufreq: Cleanup: Use printk_once Thomas Renninger
2009-04-18 5:31 ` Len Brown
2009-04-17 14:22 ` [PATCH 3/8] acpi-cpufreq: First multiply then divide to avoid zero results Thomas Renninger
2009-04-17 17:10 ` Pallipadi, Venkatesh
2009-04-18 5:37 ` Len Brown
2009-04-17 14:22 ` [PATCH 4/8] acpi-cpufreq: Do not let get_measured perf depend on internal variable Thomas Renninger
2009-04-17 17:24 ` Pallipadi, Venkatesh
2009-04-18 9:49 ` Thomas Renninger
2009-04-17 14:22 ` [PATCH 5/8] acpi-cpufreq: Move average performance funtions into separate file and KConfig Thomas Renninger
2009-04-17 17:32 ` Pallipadi, Venkatesh
2009-04-20 11:41 ` Thomas Renninger
2009-04-20 17:04 ` Pallipadi, Venkatesh
2009-04-17 14:22 ` [PATCH 6/8] CPUFREQ: Add average frequency to sysfs exported files of cpufreq_stats Thomas Renninger
2009-04-17 14:22 ` [PATCH 7/8] acpi-cpufreq: Use already defined IDA feature flag instead of checking cpuid Thomas Renninger
2009-04-17 17:35 ` Pallipadi, Venkatesh
2009-04-17 14:22 ` Thomas Renninger [this message]
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=1239978132-6261-9-git-send-email-trenn@suse.de \
--to=trenn@suse.de \
--cc=cpufreq@vger.kernel.org \
--cc=lenb@kernel.org \
--cc=linux-acpi@vger.kernel.org \
--cc=venkatesh.pallipadi@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox