From owner-freebsd-fs@FreeBSD.ORG Thu Aug 30 21:00:52 2007 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1F1A316A419 for ; Thu, 30 Aug 2007 21:00:52 +0000 (UTC) (envelope-from juri_mian@yahoo.com) Received: from web45607.mail.sp1.yahoo.com (web45607.mail.sp1.yahoo.com [68.180.197.108]) by mx1.freebsd.org (Postfix) with SMTP id 062B113C45B for ; Thu, 30 Aug 2007 21:00:51 +0000 (UTC) (envelope-from juri_mian@yahoo.com) Received: (qmail 63722 invoked by uid 60001); 30 Aug 2007 20:11:37 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=ir1QEw40NJNJUAnR8iQ7WKX9ijcIm+eY9yF+hC/hyIHrhtQtonfZhAdO+AjxO0tmU08A3BauxDzCn7fJSgyMc+NeaGFr5BuH2fZyYPugJiwbAOTP8nBVfo93/1l8fjfB2sjto0yxBabnt3WT0eTW4ZfOzwTeG/OGrwSyAT5matU=; X-YMail-OSG: pTYwYgYVM1kKDLkzaZ0fW9LccqiHyf5IBlERPzjcou0EWgAcTGTTtbJjvBfiFOIzV3i7VpEVU8f_MX8WaEIlxy1HaYJMGsxuqjIn Received: from [71.63.232.32] by web45607.mail.sp1.yahoo.com via HTTP; Thu, 30 Aug 2007 13:11:37 PDT Date: Thu, 30 Aug 2007 13:11:37 -0700 (PDT) From: Juri Mianovich To: Dag-Erling "Sm�rgrav" In-Reply-To: <868x7tys87.fsf@ds4.des.no> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <588014.62881.qm@web45607.mail.sp1.yahoo.com> Cc: freebsd-fs@freebsd.org Subject: Re: forcing a permanent "time" optimization with tunefs ? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 30 Aug 2007 21:00:52 -0000 --- Dag-Erling Sm�rgrav wrote: > BTW, explain this: if you don't care about > conserving space, why did you > lower minfree in the first place? As per the original thread, I _did_ care about conserving space, and in fact would _very much like_ to optimize for space. However, it turns out that the 6.2-RELEASE version of aac combined with a adaptec 2820sa is overwhelmed by the combination of: - 0% minfree - quotas - a few rsync processes So I _immediately_ tuned it right back to 1% minfree where it had been for 200+ days. Oops - it turns out that going downwards in minfree is a one-way operation, in some aspects - and going back to 1% did not reduce the stress on the controller. So what I needed very desperately was to find a way to force it to optimize for time, and not for space, even though I had not yet freed up enough bytes to move all the way to 6% minfree. Days later, I was able to move to 6% minfree, and my immediate problems are over. So there's your answer. It turns out that I _did_ have a reason to quickly force a filesystem into "time" optimized, even though its not the best thing overall. ____________________________________________________________________________________ Need a vacation? Get great deals to amazing places on Yahoo! Travel. http://travel.yahoo.com/