mirror of
https://github.com/torvalds/linux.git
synced 2024-11-11 06:31:49 +00:00
8e7fbcbc22
It's been broken forever (i.e. it's not scheduling in a power
aware fashion), as reported by Suresh and others sending
patches, and nobody cares enough to fix it properly ...
so remove it to make space free for something better.
There's various problems with the code as it stands today, first
and foremost the user interface which is bound to topology
levels and has multiple values per level. This results in a
state explosion which the administrator or distro needs to
master and almost nobody does.
Furthermore large configuration state spaces aren't good, it
means the thing doesn't just work right because it's either
under so many impossibe to meet constraints, or even if
there's an achievable state workloads have to be aware of
it precisely and can never meet it for dynamic workloads.
So pushing this kind of decision to user-space was a bad idea
even with a single knob - it's exponentially worse with knobs
on every node of the topology.
There is a proposal to replace the user interface with a single
3 state knob:
sched_balance_policy := { performance, power, auto }
where 'auto' would be the preferred default which looks at things
like Battery/AC mode and possible cpufreq state or whatever the hw
exposes to show us power use expectations - but there's been no
progress on it in the past many months.
Aside from that, the actual implementation of the various knobs
is known to be broken. There have been sporadic attempts at
fixing things but these always stop short of reaching a mergable
state.
Therefore this wholesale removal with the hopes of spurring
people who care to come forward once again and work on a
coherent replacement.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1326104915.2442.53.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
||
|---|---|---|
| .. | ||
| bench | ||
| debug | ||
| lib | ||
| man | ||
| po | ||
| utils | ||
| .gitignore | ||
| Makefile | ||
| README | ||
| ToDo | ||
The cpufrequtils package (homepage:
http://www.kernel.org/pub/linux/utils/kernel/cpufreq/cpufrequtils.html )
consists of the following elements:
requirements
------------
On x86 pciutils is needed at runtime (-lpci).
For compilation pciutils-devel (pci/pci.h) and a gcc version
providing cpuid.h is needed.
For both it's not explicitly checked for (yet).
libcpufreq
----------
"libcpufreq" is a library which offers a unified access method for userspace
tools and programs to the cpufreq core and drivers in the Linux kernel. This
allows for code reduction in userspace tools, a clean implementation of
the interaction to the cpufreq core, and support for both the sysfs and proc
interfaces [depending on configuration, see below].
compilation and installation
----------------------------
make
su
make install
should suffice on most systems. It builds default libcpufreq,
cpufreq-set and cpufreq-info files and installs them in /usr/lib and
/usr/bin, respectively. If you want to set up the paths differently and/or
want to configure the package to your specific needs, you need to open
"Makefile" with an editor of your choice and edit the block marked
CONFIGURATION.
THANKS
------
Many thanks to Mattia Dongili who wrote the autotoolization and
libtoolization, the manpages and the italian language file for cpufrequtils;
to Dave Jones for his feedback and his dump_psb tool; to Bruno Ducrot for his
powernow-k8-decode and intel_gsic tools as well as the french language file;
and to various others commenting on the previous (pre-)releases of
cpufrequtils.
Dominik Brodowski