Commit e7d85a93 authored by Thomas Renninger's avatar Thomas Renninger Committed by Dominik Brodowski
Browse files

cpupower: Add cpupower-idle-info manpage



The last missing manpage for cpupower tools.

More info about other architecture's sleep state specialities would be great.
Signed-off-by: default avatarThomas Renninger <trenn@suse.de>
Signed-off-by: default avatarDominik Brodowski <linux@dominikbrodowski.net>
parent f642089c
.TH "CPUPOWER-IDLE-INFO" "1" "0.1" "" "cpupower Manual"
.SH "NAME"
.LP
cpupower idle\-info \- Utility to retrieve cpu idle kernel information
.SH "SYNTAX"
.LP
cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP]
.SH "DESCRIPTION"
.LP
A tool which prints out per cpu idle information helpful to developers and interested users.
.SH "OPTIONS"
.LP
.TP
\fB\-f\fR \fB\-\-silent\fR
Only print a summary of all available C-states in the system.
.TP
\fB\-e\fR \fB\-\-proc\fR
deprecated.
Prints out idle information in old /proc/acpi/processor/*/power format. This
interface has been removed from the kernel for quite some time, do not let
further code depend on this option, best do not use it.
.SH IDLE\-INFO DESCRIPTIONS
CPU sleep state statistics and descriptions are retrieved from sysfs files,
exported by the cpuidle kernel subsystem. The kernel only updates these
statistics when it enters or leaves an idle state, therefore on a very idle or
a very busy system, these statistics may not be accurate. They still provide a
good overview about the usage and availability of processor sleep states on
the platform.
Be aware that the sleep states as exported by the hardware or BIOS and used by
the Linux kernel may not exactly reflect the capabilities of the
processor. This often is the case on the X86 architecture when the acpi_idle
driver is used. It is also possible that the hardware overrules the kernel
requests, due to internal activity monitors or other reasons.
On recent X86 platforms it is often possible to read out hardware registers
which monitor the duration of sleep states the processor resided in. The
cpupower monitor tool (cpupower\-monitor(1)) can be used to show real sleep
state residencies. Please refer to the architecture specific description
section below.
.SH IDLE\-INFO ARCHITECTURE SPECIFIC DESCRIPTIONS
.SS "X86"
POLL idle state
If cpuidle is active, X86 platforms have one special idle state.
The POLL idle state is not a real idle state, it does not save any
power. Instead, a busy\-loop is executed doing nothing for a short period of
time. This state is used if the kernel knows that work has to be processed
very soon and entering any real hardware idle state may result in a slight
performance penalty.
There exist two different cpuidle drivers on the X86 architecture platform:
"acpi_idle" cpuidle driver
The acpi_idle cpuidle driver retrieves available sleep states (C\-states) from
the ACPI BIOS tables (from the _CST ACPI function on recent platforms or from
the FADT BIOS table on older ones).
The C1 state is not retrieved from ACPI tables. If the C1 state is entered,
the kernel will call the hlt instruction (or mwait on Intel).
"intel_idle" cpuidle driver
In kernel 2.6.36 the intel_idle driver was introduced.
It only serves recent Intel CPUs (Nehalem, Westmere, Sandybridge, Atoms or
newer). On older Intel CPUs the acpi_idle driver is still used (if the BIOS
provides C\-state ACPI tables).
The intel_idle driver knows the sleep state capabilities of the processor and
ignores ACPI BIOS exported processor sleep states tables.
.SH "REMARKS"
.LP
By default only values of core zero are displayed. How to display settings of
other cores is described in the cpupower(1) manpage in the \-\-cpu option
section.
.SH REFERENCES
http://www.acpi.info/spec.htm
.SH "FILES"
.nf
\fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP
\fI/sys/devices/system/cpu/cpuidle/*\fP
.fi
.SH "AUTHORS"
.nf
Thomas Renninger <trenn@suse.de>
.fi
.SH "SEE ALSO"
.LP
cpupower(1), cpupower\-monitor(1), cpupower\-info(1), cpupower\-set(1)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment