From owner-freebsd-current@FreeBSD.ORG Fri May 16 23:17:32 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 C404B37B401 for ; Fri, 16 May 2003 23:17:32 -0700 (PDT) Received: from HAL9000.homeunix.com (12-233-57-131.client.attbi.com [12.233.57.131]) by mx1.FreeBSD.org (Postfix) with ESMTP id 38C2743FCB for ; Fri, 16 May 2003 23:17:32 -0700 (PDT) (envelope-from das@FreeBSD.ORG) Received: from HAL9000.homeunix.com (localhost [127.0.0.1]) by HAL9000.homeunix.com (8.12.9/8.12.5) with ESMTP id h4H6HShO022074; Fri, 16 May 2003 23:17:28 -0700 (PDT) (envelope-from das@FreeBSD.ORG) Received: (from das@localhost) by HAL9000.homeunix.com (8.12.9/8.12.5/Submit) id h4H6HRul022073; Fri, 16 May 2003 23:17:27 -0700 (PDT) (envelope-from das@FreeBSD.ORG) Date: Fri, 16 May 2003 23:17:27 -0700 From: David Schultz To: Peter Edwards Message-ID: <20030517061727.GC21878@HAL9000.homeunix.com> Mail-Followup-To: Peter Edwards , current@freebsd.org References: <20030515073237.879E243FA3@mx1.FreeBSD.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20030515073237.879E243FA3@mx1.FreeBSD.org> cc: current@FreeBSD.ORG Subject: Re: vm_page_max_wired and gpg... 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: Sat, 17 May 2003 06:17:33 -0000 On Thu, May 15, 2003, Peter Edwards wrote: > The kernel has a "max wired pages" limit, that's set when the swapper > starts up to be one third of physical memory. You can see this in > src/sys/vm_pageout.c, on about line 1414: > > > if (vm_page_max_wired == 0) > > vm_page_max_wired = cnt.v_free_count / 3; > > This is pretty much a third of what you see at boot time (and in > /var/log/messages or dmesg) for "avail memory = " [...] > For your purpose, making vm_page_max_wired a sysctl would probably > fix the problem in the short term. It could be made a tunable, but that's mostly just a footshooting opportunity. If you wire too much memory, the system will thrash and possibly deadlock. On the other hand, I suppose it could be useful in systems with very little memory...