From owner-cvs-src@FreeBSD.ORG Wed Oct 3 01:58:12 2007 Return-Path: Delivered-To: cvs-src@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C491C16A417; Wed, 3 Oct 2007 01:58:12 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from mail35.syd.optusnet.com.au (mail35.syd.optusnet.com.au [211.29.133.51]) by mx1.freebsd.org (Postfix) with ESMTP id 4A16D13C458; Wed, 3 Oct 2007 01:58:12 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from c220-239-235-248.carlnfd3.nsw.optusnet.com.au (c220-239-235-248.carlnfd3.nsw.optusnet.com.au [220.239.235.248]) by mail35.syd.optusnet.com.au (8.13.1/8.13.1) with ESMTP id l931vqI4021798 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 3 Oct 2007 11:57:54 +1000 Date: Wed, 3 Oct 2007 11:57:52 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: John Baldwin In-Reply-To: <200710021443.40264.jhb@freebsd.org> Message-ID: <20071003115323.Q14348@delplex.bde.org> References: <20071001145257.EC9FC4500F@ptavv.es.net> <20071001232743.Q539@10.0.0.1> <20071002213829.F12287@delplex.bde.org> <200710021443.40264.jhb@freebsd.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Wed, 03 Oct 2007 02:11:42 +0000 Cc: cvs-all@FreeBSD.org, src-committers@FreeBSD.org, Kevin Oberman , cvs-src@FreeBSD.org, Jeff Roberson , Garance A Drosehn , Ben Kaduk , Bruce Evans , Jeff Roberson Subject: Re: cvs commit: src/sys/kern sched_ule.c X-BeenThere: cvs-src@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: CVS commit messages for the src tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 03 Oct 2007 01:58:12 -0000 On Tue, 2 Oct 2007, John Baldwin wrote: > On Tuesday 02 October 2007 09:49:34 am Bruce Evans wrote: >> Apparently, there is a scaling bug for hz or extra interrupts for >> the larger hz help, and the default preempt_thresh is not best. > > -current on i386 and amd64 does a very poor job of scaling stathz and profhz > with hz, so this may explain problems at hz=100. I have an attempt to make > stathz and profhz more sane while also trying to not always drive the lapic > timer at hz * 2. I used to have a test program that would display all the > frequencies for different 'hz' values but have misplaced it. :( I fixed that about a year ago in my version of -current, and may have sent you the patch, and mentioned the need to fix it before using hz = 100 in a previous reply to this thread. Neverthless, most things including schedulers barely noticed when stahz is completely broken -- stathz needs to be about 100 to work as intended, but most things didn't notice when old bugs made it 1024 and most things don't notice when current bugs make it 13. [Patch deleted]. [My patch sent in private mail]. Bruce