Documentation, intel_pstate: Add a better description of the intel_pstate legacy mode internal governors
Subsystems (2)
PATCH 1/1 Documentation, intel_pstate: Add a better description of the intel_pstate legacy mode internal governors
This patchset was originally submitted and acked here
http://marc.info/?l=linux-kernel&m=140203008832333&w=2
but lost at some point.
P.
----8<----
The current documentation is incomplete wrt the intel_pstate legacy internal governors. The confusion comes from the general cpufreq governors which also use the names performance and powersave. This patch better differentiates between the two sets of governors and gives an explanation of how the internal P-state governors behave differently from one another.
Also fix two minor typos.
--- Documentation/cpu-freq/governors.txt | 2 +- Documentation/cpu-freq/intel-pstate.txt | 21 +++++++++++---------- 2 files changed, 12 insertions(+), 11 deletions(-)
Documentation/cpu-freq/governors.txt +1 -1
@@ -36,7 +36,7 @@ Contents: 1. What Is A CPUFreq Governor? ============================== -Most cpufreq drivers (in fact, all except one, longrun) or even most +Most cpufreq drivers (except the intel_pstate and longrun) or even most cpu frequency scaling algorithms only offer the CPU to be set to one frequency. In order to offer dynamic frequency scaling, the cpufreq core must be able to tell these drivers of a "target frequency". So
Documentation/cpu-freq/intel-pstate.txt +11 -10
@@ -3,24 +3,25 @@ Intel P-state driver This driver provides an interface to control the P state selection for SandyBridge+ Intel processors. The driver can operate two different -modes based on the processor model legacy and Hardware P state (HWP) +modes based on the processor model, legacy mode and Hardware P state (HWP) mode. -In legacy mode the driver implements a scaling driver with an internal -governor for Intel Core processors. The driver follows the same model -as the Transmeta scaling driver (longrun.c) and implements the -setpolicy() instead of target(). Scaling drivers that implement -setpolicy() are assumed to implement internal governors by the cpufreq -core. All the logic for selecting the current P state is contained -within the driver; no external governor is used by the cpufreq core. +In legacy mode, the Intel P-state implements two internal governors, +performance and powersave, that differ from the general cpufreq governors of +the same name (the general cpufreq governors implement target(), whereas the +internal Intel P-state governors implement setpolicy()). The internal +performance governor sets the max_perf_pct and min_perf_pct to 100; that is, +the governor selects the highest available P state to maximize the performance +of the core. The internal powersave governor selects the appropriate P state +based on the current load on the CPU. In HWP mode P state selection is implemented in the processor itself. The driver provides the interfaces between the cpufreq core and the processor to control P state selection based on user preferences and reporting frequency to the cpufreq core. In this mode the -internal governor code is disabled. +internal Intel P-state governor code is disabled. -In addtion to the interfaces provided by the cpufreq core for +In addition to the interfaces provided by the cpufreq core for controlling frequency the driver provides sysfs files for controlling P state selection. These files have been added to /sys/devices/system/cpu/intel_pstate/
Signature · 1 line
1.7.9.3
Quoted 9 lines · Prarit Bhargava
This patchset was originally submitted and acked here
http://marc.info/?l=linux-kernel&m=140203008832333&w=2
but lost at some point.
P.
----8<----
I don't think this is the right place to have this information, you should have added it after the three dashes below. (---).
Quoted 9 lines
The current documentation is incomplete wrt the
intel_pstatelegacy internal governors. The confusion comes from the general cpufreq governors which also use the names performance and powersave. This patch better differentiates between the two sets of governors and gives an explanation of how the internal P-state governors behave differently from one another.Also fix two minor typos.
Quoted 9 lines
Cc Jonathan Corbet <[email protected]>Cc Prarit Bhargava <[email protected]>Cc "Rafael J. Wysocki" <[email protected]>Cc Kristen Carlson Accardi <[email protected]>Cc Dirk Brandewie <[email protected]>Cc Viresh Kumar <[email protected]>Signed-off-by Prarit Bhargava <[email protected]>
You could have carried my Ack :)
Signature · 1 line
viresh
Quoted 5 lines · Viresh Kumar
Quoted 4 lines · Prarit Bhargava
This patchset was originally submitted and acked here
Quoted 8 lines
Quoted 5 lines
but lost at some point.
P.
----8<----
I don't think this is the right place to have this information, you should have added it after the three dashes below. (---).
AFAIK "scissors" works for comments not to be included in the commit.
Quoted 20 lines
Quoted 10 lines
The current documentation is incomplete wrt the
intel_pstatelegacy internal governors. The confusion comes from the general cpufreq governors which also use the names performance and powersave. This patch better differentiates between the two sets of governors and gives an explanation of how the internal P-state governors behave differently from one another.Also fix two minor typos.
Quoted 9 lines
Cc Jonathan Corbet <[email protected]>Cc Prarit Bhargava <[email protected]>Cc "Rafael J. Wysocki" <[email protected]>Cc Kristen Carlson Accardi <[email protected]>Cc Dirk Brandewie <[email protected]>Cc Viresh Kumar <[email protected]>Signed-off-by Prarit Bhargava <[email protected]>
Quoted 1 line
You could have carried my Ack :)
:) I was uncomfortable carrying it TBH because I had changed the patch.
P.
Quoted 3 lines
Acked-by Viresh Kumar <[email protected]>
Viresh Kumar
maintainerQuoted 1 line · Prarit Bhargava
AFAIK "scissors" works for comments not to be included in the commit.
Hmm, wasn't aware of git am --scissors option and am not sure if maintainers use it by default while applying patches. Also, I am not sure if this is supported by other version control systems, probably it is.
Anyway, something new for the day :)
Signature · 1 line
viresh
Jonathan Corbet
maintainerQuoted 5 lines · On Mon, 1 Jun 2015 09:36:04 -0400 Prarit Bhargava <[email protected]> wrote:
This patchset was originally submitted and acked here
http://marc.info/?l=linux-kernel&m=140203008832333&w=2
but lost at some point.
OK, I've applied it to the docs tree with Viresh's ack.
Thanks,
jon