From owner-freebsd-arch Wed Jan 31 12: 4:46 2001 Delivered-To: freebsd-arch@freebsd.org Received: from dan.emsphone.com (dan.emsphone.com [199.67.51.101]) by hub.freebsd.org (Postfix) with ESMTP id BA70F37B65D for ; Wed, 31 Jan 2001 12:04:27 -0800 (PST) Received: (from dan@localhost) by dan.emsphone.com (8.11.1/8.11.1) id f0VK4Hv23602; Wed, 31 Jan 2001 14:04:17 -0600 (CST) (envelope-from dan) Date: Wed, 31 Jan 2001 14:04:17 -0600 From: Dan Nelson To: Seigo Tanimura Cc: arch@FreeBSD.ORG Subject: Bumping up {MAX,DFLT}*PHYS (was Re: Bumping up {MAX,DFL}*SIZ in i386) Message-ID: <20010131140416.C21193@dan.emsphone.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.3.14i In-Reply-To: ; from "Seigo Tanimura" on Wed Jan 31 14:33:04 GMT 2001 X-OS: FreeBSD 5.0-CURRENT Sender: owner-freebsd-arch@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In the last episode (Jan 31), Seigo Tanimura said: > Now that even an entry-model workstation can equip memory up to 1GB > or more, MAXDSIZ and DFLDSIZ should be increased so that a process > can make use of large memory. On the other hand, MAXDSIZ is also > likely to hit VM_MAXUSER_ADDRESS, which is generally 3GB and may be > 2GB if the size of KVM is expanded to the maximum. MAXDSIZ should > thus not exceed 2GB. On a similar note, is there any reason for us to have DFLTPHYS at 64k anymore? With the insane interface speeds of SCSI and ATA devices nowadays, you can easily hit 600 I/Os per second on sequential reads (40MB/sec, 64K per I/O). Would anything break if MAXPHYS/DFLTPHYS was bumped to say, 1mb? -- Dan Nelson dnelson@emsphone.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message