Messages in this thread | | | Date | Thu, 6 Mar 2003 23:03:07 +0100 | From | Martin Waitz <> | Subject | Re: [patch] "HT scheduler", sched-2.5.63-B3 |
| |
hi :)
On Wed, Mar 05, 2003 at 07:20:34PM -0800, Linus Torvalds wrote: > How about something more like this (yeah, untested, but you get the idea): > the person who wakes up an interactive task gets the interactivity bonus > if the interactive task is already maxed out. I dunno how well this plays > with the X server, but assuming most clients use UNIX domain sockets, the > wake-ups _should_ be synchronous, so it should work well to say "waker > gets bonus".
i used a similar method to correctly account resource usage (cpu,energy,..) of processes in my diploma thesis: work done by a sever (e.g. X) is accounted to the current client, giving more resources to the server http://admingilde.org/~martin/papers/
implementation is working but far from being mergeable...
RE: the patch, i think using sleep_avg is a wrong metric from the beginning.
in addition, timeslices should be shortest for high priority processes (depending on dynamic prio, not static)
but these are of course just simple statements and i don't have a patch that makes a really good scheduler :(
-- CU, / Friedrich-Alexander University Erlangen, Germany Martin Waitz // [Tali on IRCnet] [tali.home.pages.de] _________ ______________/// - - - - - - - - - - - - - - - - - - - - /// dies ist eine manuell generierte mail, sie beinhaltet // tippfehler und ist auch ohne grossbuchstaben gueltig. / - Wer bereit ist, grundlegende Freiheiten aufzugeben, um sich kurzfristige Sicherheit zu verschaffen, der hat weder Freiheit noch Sicherheit verdient. Benjamin Franklin (1706 - 1790) [unhandled content-type:application/pgp-signature] | |