GPN16:Proposing a Replacement for FreeBSD's powerd (Preview): Unterschied zwischen den Versionen

aus dem Wiki des Entropia e.V., CCC Karlsruhe
(Fahrplanbot tut Dinge)
 
(→‎Links: Add slides)
 
(6 dazwischenliegende Versionen von 3 Benutzern werden nicht angezeigt)
Zeile 1: Zeile 1:
{{#css:GPN15:Stylesheet}}
==== ''Or, how I tamed the fan of my notebook'' ====


Ein Vortrag von kamikaze (Dominic Fandrey) auf der [[GPN15]].
----
 
Ein Vortrag von kamikaze (Dominic Fandrey) auf der [[GPN16]].
 
 
FreeBSD's powerd CPU frequency daemon provides userland P-State (power state) switching since 2005. Multi Core Processing has come a long way since 2005 and the increasing number of cores and pipelines in modern CPUs have exposed flaws in powerd's design that were not obvious at the time of its conception.
 
The talk proposes three design changes addressing these flaws. A daemon named powerd++ implements this improved design.


The talk will present:
The talk will present:
Zeile 14: Zeile 21:
== Links ==
== Links ==


* [https://people.freebsd.org/~kami/2016-GPN16/2016%20GPN16%20Replacing%20powerd.pdf Slides]
* [http://angryswarm.blogspot.com/2016/04/powerd-better-cpu-clock-control-for.html powerd++ in my blog]
* [http://angryswarm.blogspot.com/2016/04/powerd-better-cpu-clock-control-for.html powerd++ in my blog]
* [https://github.com/lonkamikaze/powerdxx powerd++ on GitHub]
* [https://github.com/lonkamikaze/powerdxx powerd++ on GitHub]




{{Navigationsleiste GPN15}}
{{Navigationsleiste GPN16:Vorträge}}
[[Kategorie:GPN15:Events]]

Aktuelle Version vom 28. Mai 2016, 18:20 Uhr

Or, how I tamed the fan of my notebook


Ein Vortrag von kamikaze (Dominic Fandrey) auf der GPN16.


FreeBSD's powerd CPU frequency daemon provides userland P-State (power state) switching since 2005. Multi Core Processing has come a long way since 2005 and the increasing number of cores and pipelines in modern CPUs have exposed flaws in powerd's design that were not obvious at the time of its conception.

The talk proposes three design changes addressing these flaws. A daemon named powerd++ implements this improved design.

The talk will present:

  • Challenging load characteristics
  • The three core design differences between powerd and powerd++

This is a short version of a talk I want to present at the EuroBSDCon 2016 later this year. The complete talk should contain benchmarks for the performance of the tools. I hope to collect some ideas about how these benchmarks should be designed from the audience.

Links