From owner-freebsd-questions@FreeBSD.ORG Thu Feb 26 03:58:34 2009 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F2D14106564A for ; Thu, 26 Feb 2009 03:58:34 +0000 (UTC) (envelope-from fbsd.questions@rachie.is-a-geek.net) Received: from mail.rachie.is-a-geek.net (rachie.is-a-geek.net [66.230.99.27]) by mx1.freebsd.org (Postfix) with ESMTP id C1F8F8FC22 for ; Thu, 26 Feb 2009 03:58:34 +0000 (UTC) (envelope-from fbsd.questions@rachie.is-a-geek.net) Received: from localhost (mail.lan.rachie.is-a-geek.net [192.168.2.101]) by mail.rachie.is-a-geek.net (Postfix) with ESMTP id 3934CAFC1FF; Wed, 25 Feb 2009 18:58:34 -0900 (AKST) From: Mel To: freebsd-questions@freebsd.org Date: Wed, 25 Feb 2009 18:58:33 -0900 User-Agent: KMail/1.9.10 References: <49A5CFA2.2090509@risei.net> <200902251620.08629.fbsd.questions@rachie.is-a-geek.net> <49A5F227.7070003@risei.net> In-Reply-To: <49A5F227.7070003@risei.net> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200902251858.33652.fbsd.questions@rachie.is-a-geek.net> Cc: Scott Seekamp Subject: Re: Tuning Question X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 Feb 2009 03:58:35 -0000 On Wednesday 25 February 2009 16:36:39 Scott Seekamp wrote: > I did search and it did not return any results. They should really kill the htdig project already ;) > That is helpful, but I was hoping to get an indication of what the > effects of changing this setting and what is the maximum before looking > elsewhere for changes? Your system might be wanting more then the system can offer. It's further explained here: Quoting Mark Tinguely: > Sometimes pv_entry allocation can fail even below the pv_entry_high_water > if there is no more free pages available to allocate for a pv_entry chunk. > Operations (such temp mappings, copies) will not occur if the > pv_entry_high_water (90% if pv_entry_max) has been reached OR a > page is not immediately available for allocation. I don't know what the max is. If you have to increase it a lot, f.e. >500%, then either the default is porely chosen, you demand a lot or your system is doing things it's not supposed to do. I would slowly increase it to insane ammounts. If it never goes away and load of the machine isn't shocking, then this might be a bug. Either way, there aren't too many tools to diagnose this problem. Maybe procstat(8) -v should give some insight. -- Mel Problem with today's modular software: they start with the modules and never get to the software part.