From owner-freebsd-questions Mon Aug 26 15: 8:36 2002 Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D13F637B400 for ; Mon, 26 Aug 2002 15:08:33 -0700 (PDT) Received: from apollo.sitaranetworks.com (apollo.sitaranetworks.com [199.103.141.105]) by mx1.FreeBSD.org (Postfix) with ESMTP id AB83643E77 for ; Mon, 26 Aug 2002 15:08:32 -0700 (PDT) (envelope-from cptacek@sitaranetworks.com) Received: from rios.sitaranetworks.com (rios.sitaranetworks.com [199.103.141.78]) by apollo.sitaranetworks.com (8.10.2+Sun/8.9.3) with ESMTP id g7QM43600843; Mon, 26 Aug 2002 18:04:04 -0400 (EDT) Received: by rios.sitaranetworks.com with Internet Mail Service (5.5.2653.19) id ; Mon, 26 Aug 2002 18:04:51 -0400 Message-ID: <31269226357BD211979E00A0C9866DAB02BB998C@rios.sitaranetworks.com> From: Chris Ptacek To: "'Giorgos Keramidas'" , Chris Ptacek Cc: "'David Schultz'" , Carlos Carnero , freebsd-questions@FreeBSD.ORG Subject: RE: optimization changed from TIME to SPACE ?! Date: Mon, 26 Aug 2002 18:04:42 -0400 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain; charset="iso-8859-1" Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG OK, I am still trying to get a testbed setup to reproduce the issue. Once I do I am going to try setting the block size to 4096 and the fragment size to 512 (1:8 ratio) and minsize to 10%. To do this I believe I just: umount partition newfs -b 4096 -f 512 -m 10 /dev/wd0s1e Is this correct, or do I need to go through and delete and relabel, etc? - Chris > -----Original Message----- > From: Giorgos Keramidas [mailto:keramida@ceid.upatras.gr] > Sent: Monday, August 26, 2002 2:00 PM > To: Chris Ptacek > Cc: 'David Schultz'; Carlos Carnero; freebsd-questions@FreeBSD.ORG > Subject: Re: optimization changed from TIME to SPACE ?! > > > On 2002-08-26 15:02 +0000, Chris Ptacek wrote: > > I had a few questions... What actually causes the fragmentation to > > occur? I have tried just copying a small file over and over and > > this results in no fragmentation. This leads me to believe that the > > fragmentation is a result of simultainious open files or at least > > different file sizes. > > The way that the FreeBSD filesystem organises data on disk. This > "fragmentation" is not the same as fragmentation on a DOS partition, > if this is what had you confused. > > > Also it seems that when we switch to SPACE optimizaiton is based on > > the % fragmentation based on the minfree setting. Can I change the > > minfree for the filesystem (I have a dedicated cache partition) to > > like 27% (8 is default) so that I am much less likely to hit the > > SPACE case? > > Then the SPACE optimization will start when 3 times more space is > taken by fragments. But this is going to reserve 27% of the disk > space for the superuser and block allocation routines. This is too > much disk space to reserve :/ > > A better solution is probably to format the partition with a fragment > size equal to the block size as someone mentioned. I haven't tried > this though and I can't say how much it affects performance and why. > > -- > FreeBSD: The Power to Serve <> http://www.FreeBSD.org > FreeBSD 5.0-CURRENT #0: Wed Aug 21 22:08:19 EEST 2002 > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message