From owner-freebsd-hackers Thu Dec 11 18:53:28 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id SAA07972 for hackers-outgoing; Thu, 11 Dec 1997 18:53:28 -0800 (PST) (envelope-from owner-freebsd-hackers) Received: from smtp02.primenet.com (smtp02.primenet.com [206.165.6.132]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id SAA07960 for ; Thu, 11 Dec 1997 18:53:19 -0800 (PST) (envelope-from tlambert@usr02.primenet.com) Received: (from daemon@localhost) by smtp02.primenet.com (8.8.8/8.8.8) id TAA24699; Thu, 11 Dec 1997 19:59:36 -0700 (MST) Received: from usr02.primenet.com(206.165.6.202) via SMTP by smtp02.primenet.com, id smtpd024609; Thu Dec 11 19:59:14 1997 Received: (from tlambert@localhost) by usr02.primenet.com (8.8.5/8.8.5) id TAA07810; Thu, 11 Dec 1997 19:52:18 -0700 (MST) From: Terry Lambert Message-Id: <199712120252.TAA07810@usr02.primenet.com> Subject: Re: Process scheduling: nice does not work ??? To: jonny@coppe.ufrj.br (Joao Carlos Mendes Luis) Date: Fri, 12 Dec 1997 02:52:18 +0000 (GMT) Cc: tlambert@primenet.com, chuckr@glue.umd.edu, jonny@coppe.ufrj.br, freebsd-hackers@freebsd.org In-Reply-To: <199712112013.SAA00694@gaia.coppe.ufrj.br> from "Joao Carlos Mendes Luis" at Dec 11, 97 06:13:19 pm X-Mailer: ELM [version 2.4 PL23] Content-Type: text Sender: owner-freebsd-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > // If he wanted to "lock" priorities, he need to use rtprio. Otherwise, > // the scheduler will drift them as it sees fit. > > I don't want to lock priorities. I want both processes to run, one > with more time ticks than the other. The way you do this in Solaris/SVR4 is to used "fixed" as your scheduling class when you prioctl the thing... > // IMO, Linux is implementing a "fairness" algorithm based on the NI value; > > Isn't it what NI for ? If not, what is it for ? It's for setting your priority to less than the default of 0 so that you don't bother interactive users with your compute intensive tasks (in fact, there used to be code in the BSD scheduler to whomp your priority way down when it determined that your process was non-interactive; I have no idea when it went away, but it did). > // I think Linux is wrong, FWIW. > > And Solaris also, by peeking at my measures on the first post. I didn't gather that from the Solaris numbers. The thing is that the process percentages are instantaneous. The only thing that means anything, really, is the PRI at the next time the thing is in the ready-to-run-queue with other processes. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers.