Date: Tue, 26 Jan 1999 15:06:54 -0500 (EST) From: Robert Watson <robert@cyrus.watson.org> To: "Russell L. Carter" <rcarter@pinyon.org> Cc: hackers@FreeBSD.ORG Subject: Re: Error in vm_fault change Message-ID: <Pine.BSF.3.96.990126150352.27963B-100000@fledge.watson.org> In-Reply-To: <199901230616.XAA21124@psf.Pinyon.ORG>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 22 Jan 1999, Russell L. Carter wrote: > A single parameter like "priority" won't do it. Application > domains need scheduling partitions too. And there is no "GOD" algorithm > that fits all. I would suggest that if the scheduler needs to be reworked, > to fit at a minimum the kinds of work John lists, that people > think about how to provide a framework to plug in various scheduling > (process|memory) implementations. uhhhh, ye olde "strategy pattern". In Fall, 1997 someone here at CMU stuck a lottery algorithm scheduler into FreeBSD, and wrote a paper describing where they had to make changes to FreeBSD to allow for more pluggable schedulers. They didn't attempt to handle either real-time issues (and hence preemption for in-kernel processes) or SMP, but it might be a useful read. I'll see if I can dig up a reference. Allowing a pluggable scheduler via a kernel module would be pretty cool. I.e., today it's a realtime machine, tomorrow it's a single-user workstation, the next day a heavily loaded timesharing machine with CPU time partitioning. Robert N Watson robert@fledge.watson.org http://www.watson.org/~robert/ PGP key fingerprint: 03 01 DD 8E 15 67 48 73 25 6D 10 FC EC 68 C1 1C Carnegie Mellon University http://www.cmu.edu/ TIS Labs at Network Associates, Inc. http://www.tis.com/ SafePort Network Services http://www.safeport.com/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.990126150352.27963B-100000>