From owner-freebsd-amd64@FreeBSD.ORG Mon Oct 9 22:15:54 2006 Return-Path: X-Original-To: freebsd-amd64@freebsd.org Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A559116A47B; Mon, 9 Oct 2006 22:15:54 +0000 (UTC) (envelope-from linimon@lonesome.com) Received: from mail.soaustin.net (mail.soaustin.net [207.200.4.66]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5F36843D58; Mon, 9 Oct 2006 22:15:54 +0000 (GMT) (envelope-from linimon@lonesome.com) Received: by mail.soaustin.net (Postfix, from userid 502) id C42F52EC4; Mon, 9 Oct 2006 17:15:53 -0500 (CDT) Date: Mon, 9 Oct 2006 17:15:53 -0500 To: "O. Hartmann" Message-ID: <20061009221553.GC6561@soaustin.net> References: <200610081720.k98HKkQx058984@freefall.freebsd.org> <20061008215308.W89071@mp2.macomnet.net> <20061008180120.GX21333@submonkey.net> <452AB103.8030305@mail.uni-mainz.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <452AB103.8030305@mail.uni-mainz.de> User-Agent: Mutt/1.5.9i From: linimon@lonesome.com (Mark Linimon) Cc: maho@freebsd.org, Maxim Konovalov , freebsd-bugs@freebsd.org, freebsd-amd64@freebsd.org Subject: Re: kern/85820: 1.5 times slower performance with SCHED_ULE than SCHED_4BSD X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 09 Oct 2006 22:15:54 -0000 On Mon, Oct 09, 2006 at 10:28:51PM +0200, O. Hartmann wrote: > I never realized, that SCHED_ULE has been discarded from being the > default scheduler in FreeBSD 6.X, as I can remember, SCHED_ULE has been > promoted to be the default scheduler due to its improvements to SMP. Yes, it was, but as time went on, more work was being done on the kernel in performance improvements in areas other than the scheduler. Whether or not these affected ULE's performance is not clear to me. However, this is a good example of the type of thing that you have to follow discussions on the -current mailing list to keep up with. > Well, I may be wrong, but it would be much more convenient having those > important informations being released more public There hasn't been any effort to keep this information confidential. It's just that individuals' efforts have been going on in areas other than ULE, and it is possible that ULE just hasn't kept up with those changes. These things aren't as cut-and-dried as you seem to think that they are. mcl