From owner-freebsd-stable Thu May 9 18:14:34 2002 Delivered-To: freebsd-stable@freebsd.org Received: from luna.affordablehost.com (ns7.affordablehost.com [206.104.238.125]) by hub.freebsd.org (Postfix) with SMTP id 96DE137B40D for ; Thu, 9 May 2002 18:14:25 -0700 (PDT) Received: (qmail 9189 invoked from network); 10 May 2002 01:18:02 -0000 Received: from 174.113.sn.ct.dsl.thebiz.net (HELO winbloat) (216.238.113.174) by 0 with SMTP; 10 May 2002 01:18:02 -0000 Message-ID: <200205092114190775.00FC1737@luna.affordablehost.com> In-Reply-To: <200205100004.g4A04Q2n029553@apollo.backplane.com> References: <20020509143427.GA28486@student.uu.se> <20020509164709.GA29822@student.uu.se> <200205100004.g4A04Q2n029553@apollo.backplane.com> X-Mailer: Calypso Version 3.20.01.01 (4) Date: Thu, 09 May 2002 21:14:19 -0400 Reply-To: myraq@mgm51.com From: "MikeM" To: freebsd-stable@FreeBSD.ORG Subject: Re: Steadily increasing memory usage on a lightly loaded server Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On 5/9/2002 at 5:04 PM Matthew Dillon wrote: |: |: What this means is that FreeBSD will not try very hard to separate |: out dirty pages (inactive queue) from clean pages (cache queue) when |: the system is not being stressed, nor will it try to deactivate |: pages (active queue -> inactive queue) when the system is not being |: stressed, even if they are not being used. |: |: |:My interpretation is that the inactive queue does not really hold pages |:that are "dirty but not recently referenced" but rather pages that are |:"possibly dirty and not recently referenced", while the cache queue |:holds pages that are known not to be dirty. |:This probably means that under a normal load most of the pages in the |:inactive queue are not in fact dirty. |: |: |:Erik Trulsson |:ertr1013@student.uu.se | | You are correct. If the system is not being stressed you can wind | up with a large number of pages marked 'active' which are really | inactive, and a large number of pages marked 'inactive' which are | really cache. The original posting had this: | | Mem: 23M Active, 618M Inact, 69M Wired, 40M Cache, 86M Buf, 1328K Free | | This looks like a fairly unstressed system to me. The actual | definitions for the page queues are: | [snip] =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D Correct, the system is very lighted loaded. The second part of my original question, which has been overlooked in these= most excellent discussions, is why am I seeing this only recently. Let me= explain the series of events that led up to my decision to post my= original message. I colo'd this server around the end of February 2002 with version 4.5 of= the OS. On March 1 I installed the phpSysInfo page (example:= http://phpsysinfo.sourceforge.net/phpsysinfo). Each morning since= February, I have checked the logs and the phpSysInfo page. Each morning,= the Physical Memory bar graph was low and green. Then, after applying the= recent two security patches, the bar all of a sudden turned red and hung= out around 95% utilization. I now understand that the current memory= utilization is A Good Thing. And I have actually been keeping up with= the discussions regarding *why* it is a good thing. But I remain curious why why I am seeing this behavior after the recent= patches, and why I didn't see this behavior from the first day I colo'd= the server. In my cvsup file, I am following the RELENG_4_5 tag. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message