Re: scheduler interactivity: timeslice calculation seem wrong

From: Con Kolivas (kernel_at_kolivas.org)
Date: 08/19/03

  • Next message: Eric St-Laurent: "Re: scheduler interactivity: timeslice calculation seem wrong" 
    To: Eric St-Laurent <ericstl34@sympatico.ca>, linux-kernel@vger.kernel.org
Date:	Tue, 19 Aug 2003 14:13:00 +1000

    On Tue, 19 Aug 2003 12:54, Eric St-Laurent wrote:
    > currently, nicer tasks (nice value toward -20) get larger timeslices,
    > and less nice tasks (nice value toward 19) get small timeslices.

    You mean this the other way round, no? +nice means more nice.

    For the most part, most tasks start at nice 0 so they pretty much all get the
    same size timslices unless they get preempted. The rest of the discussion
    you can debate to the end of the earth, but application counts once you've
    implemented theory. Changing it up and down by dynamic priority one way and
    then the other wasn't helpful when I've tried it previously.

    Con

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Eric St-Laurent: "Re: scheduler interactivity: timeslice calculation seem wrong"

    Relevant Pages

    • Re: Linux 2.6 nanosecond time stamp weirdness breaks GCC build
      ... >> However, I'd say that this should probably be fixed in the kernel, ... > The solution from back then I actually liked best was to just round ... if the .c file is flushed from the cache before the ... To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ ...
      (Linux-Kernel)
    • Re: Kernel 2.6.6 & 2.6.7 sometime hang after much I/O
      ... At the same round as the former ... Real Programmers consider "what you see is what you get" to be just as ... bad a concept in Text Editors as it is in women. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [PATCH] Load balancing problem in 2.6.2-mm1
      ... >>Hopefully just tending to round down more would damp it better. ... >I'd side with just removing the addition alltogether ... ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: sched domains kernbench improvements
      ... It will as far as balancing between physical CPUs, ... if one sibling goes idle than if one CPU goes idle). ... But if you could do a round with SCHED_SMT enabled it would be very ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [pm] fix time after suspend-to-*
      ... >>round and round about how a tick on one should be a tick on the other. ... but then is there some sort of house cleaning that happens to clean up the ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)