From owner-freebsd-current@FreeBSD.ORG Wed Jun 25 22:03:49 2003 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5098337B405 for ; Wed, 25 Jun 2003 22:03:49 -0700 (PDT) Received: from puffin.mail.pas.earthlink.net (puffin.mail.pas.earthlink.net [207.217.120.139]) by mx1.FreeBSD.org (Postfix) with ESMTP id 87D2944029 for ; Wed, 25 Jun 2003 22:03:48 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from user-2ivfirs.dialup.mindspring.com ([165.247.203.124] helo=mindspring.com) by puffin.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19VOvB-0002WR-00; Wed, 25 Jun 2003 22:03:47 -0700 Message-ID: <3EFA7E71.75919A7E@mindspring.com> Date: Wed, 25 Jun 2003 22:02:41 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: "Cagle, John (ISS-Houston)" References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a44cebcdc796d9f298272eb6e938b5fc68350badd9bab72f9c350badd9bab72f9c350badd9bab72f9c cc: Mike Silbersack cc: current@freebsd.org Subject: Re: Best way to get max KVA setting? X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 Jun 2003 05:03:49 -0000 "Cagle, John (ISS-Houston)" wrote: > Terry Lambert [mailto:tlambert2@mindspring.com] > > Mike Silbersack wrote: > > > I could probably grep for this, but what's the best way to get a hold > > > of the # of pages (or MB of ram) that max KVA is set to? I'm adding > > > another autosize option, and I want to base it on min (KVA, ram) so > > > that it doesn't balloon on boxes where ram >> KVA. > > > > I posted a patch about a month ago that did exactly this. > > > > It was for a guy who was was running with PAE enabled on an > > 8G machine, and the autotuning was shooting him in the foot when it > > tried to grab enough memory to create kmem_map entries for the 8G of RAM > > in his 2G KVA space, and its head exploded. > > I'm that guy who was running PAE on an 8GB machine... > > BTW, it turns out the problem was _not_ the autotuning, it was simply an > overflow of a 32-bit variable in the kernel. It's been fixed in > -current, checked in 2 weeks ago. I still expect that there are issues with the autotuning not taking KVA << RAM into account, without something like my patch, even if it's not biting you specifically at 8G. I'd like to see what happens at 64G RAM, for example... In any case, the patch I posted is still probably what Mike wanted. 8-). -- Terry