From owner-freebsd-arch Thu Dec 14 4:16:24 2000 From owner-freebsd-arch@FreeBSD.ORG Thu Dec 14 04:16:21 2000 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mail-relay.eunet.no (mail-relay.eunet.no [193.71.71.242]) by hub.freebsd.org (Postfix) with ESMTP id D11A337B404 for ; Thu, 14 Dec 2000 04:16:14 -0800 (PST) Received: from login-1.eunet.no (login-1.eunet.no [193.75.110.2]) by mail-relay.eunet.no (8.9.3/8.9.3/GN) with ESMTP id NAA14576; Thu, 14 Dec 2000 13:16:12 +0100 (CET) (envelope-from mbendiks@eunet.no) Received: from localhost (mbendiks@localhost) by login-1.eunet.no (8.9.3/8.8.8) with ESMTP id NAA43785; Thu, 14 Dec 2000 13:16:12 +0100 (CET) (envelope-from mbendiks@eunet.no) X-Authentication-Warning: login-1.eunet.no: mbendiks owned process doing -bs Date: Thu, 14 Dec 2000 13:16:09 +0100 (CET) From: Marius Bendiksen To: Matt Dillon Cc: Julian Elischer , Seigo Tanimura , arch@FreeBSD.ORG Subject: Re: Even 1GB KVA is not enough, but we have no more space In-Reply-To: <200012140655.eBE6tmP92001@earth.backplane.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-arch@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > We're probably not going to ever do anything like this, because > manipulating page directory entries or the whole VM space on a > user->supervisor or supervisor->user transition flushes > the TLB and seriously degrades performance. Hence my reference to doing this on-demand. If the kernel could be taught about virtual/physical paging issues (ie. could be aware of whether objects are currently in the KV space), then you could avoid this except in the few cases where you hit the 1G limit. Marius To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message