RE: sched_4bsd.c Quantum change

From: Smith III, Edward Mr. CAA/ISC (ed.smithiii_at_us.army.mil)
Date: 02/25/05

  • Next message: Peter C. Lai: "sandisk cruzer mini quirks [failure] on RELENG_4" 
    Date: Fri, 25 Feb 2005 09:12:12 -0500
To: "Ashwin Chandra" <ashcs@ucla.edu>, <freebsd-hackers@freebsd.org>

    just use the "nice" call with a negative value for the process. the time quantum will be the same but it will get more run time.

    man nice

    -----Original Message-----
    From: owner-freebsd-hackers@freebsd.org
    [mailto:owner-freebsd-hackers@freebsd.org]On Behalf Of Ashwin Chandra
    Sent: Thursday, February 24, 2005 7:50 PM
    To: freebsd-hackers@freebsd.org
    Subject: sched_4bsd.c Quantum change

    Quick question for you hackers!

    If i wanted to change the scheduler to have a certain marked bad process have a higher time quantum than everyone elses (because it is behaving bad, high mem usage and context switching) to let it run longer to finish faster and avoid context switches and swapping, is this possible in the current scheduler without major changes to it? Right now the scheduler works by having a uniform quantum for all processes, am i correct?

    Thanks
    Ash
    _______________________________________________
    freebsd-hackers@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
    To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org"
    _______________________________________________
    freebsd-hackers@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
    To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org"

  • Next message: Peter C. Lai: "sandisk cruzer mini quirks [failure] on RELENG_4"