* fairsched for o(1)-scheduler
@ 2003-07-27 21:35 Antonio Vargas
0 siblings, 0 replies; only message in thread
From: Antonio Vargas @ 2003-07-27 21:35 UTC (permalink / raw)
To: linux-kernel, user-mode-linux-devel; +Cc: mingo, kernel, riel, wind
Given I've got spare time now, I'm trying to revive and finally
have a working implementation for the 2.6 fairsched patch.
Since my early attempts crashed, I would appreciate peer review
and advise on how to do a first implementation.
I was told that printk should not be used inside the scheduler,
is this true?
Also, in order to park tasks aside, I created another prio_array
besides the active and expired ones, queuing expired tasks there
until the used could afford to move them to the active one. Does
the scheduler assume, in implicit form, that a task is either on
the active or expired array?
The proposed design is described at this page:
http://wind.cocodriloo.com/~wind/fairsched/
And also by Hubertus Franke on his OLS 2003 paper:
http://archive.linuxsymposium.org/ols2003/Proceedings/All-Reprints/Reprint-Franke-OLS2003.pdf
Greets, Antonio.
--
1. Dado un programa, siempre tiene al menos un fallo.
2. Dadas varias lineas de codigo, siempre se pueden acortar a menos lineas.
3. Por induccion, todos los programas se pueden
reducir a una linea que no funciona.
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2003-07-27 23:22 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2003-07-27 21:35 fairsched for o(1)-scheduler Antonio Vargas
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®