From owner-freebsd-stable@FreeBSD.ORG Sat Nov 3 23:52:53 2012 Return-Path: Delivered-To: stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4F99C2F5 for ; Sat, 3 Nov 2012 23:52:53 +0000 (UTC) (envelope-from brett@lariat.net) Received: from lariat.net (lariat.net [66.62.230.51]) by mx1.freebsd.org (Postfix) with ESMTP id F13728FC12 for ; Sat, 3 Nov 2012 23:52:52 +0000 (UTC) Received: from Toshi.lariat.net (IDENT:ppp1000.lariat.net@lariat.net [66.119.58.2] (may be forged)) by lariat.net (8.9.3/8.9.3) with ESMTP id RAA05658; Sat, 3 Nov 2012 17:52:44 -0600 (MDT) Message-Id: <201211032352.RAA05658@lariat.net> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sat, 03 Nov 2012 17:52:42 -0600 To: Jeff Roberson , Ian Lepore From: Brett Glass Subject: Re: Why is SU+J undesirable on SSDs? In-Reply-To: References: <201211032130.PAA04484@lariat.net> <1351983269.1120.137.camel@revolution.hippie.lan> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: Adam Vande More , stable@freebsd.org X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Nov 2012 23:52:53 -0000 At 05:14 PM 11/3/2012, Jeff Roberson wrote: >The journal entries are 32 bytes per in SUJ. So the number of >extra writes is down in the noise. The journaling also gets you >asynchronous partial truncation and a few other asynchronous >operations that are sync in SU. It does cost slightly more cpu >time and more memory. I'm not saying you're making the wrong >choice. I'm just saying that it's not clear that you should or >should not use it with SSDs. This is what I would expect, and with wear leveling it is unlikely that the wear on the SSD would be significant anyway. In my case, the most important thing is not to lose logs in a crash (which could happen with just fsck), so journaling is worth it for me. The only reason I could see not to use SU+J with SSDs (or any disk, for that matter) is if there are bugs which harm stability. A look at http://www.freebsd.org/cgi/query-pr-summary.cgi?category=&severity=&priority=&class=&state=open&sort=none&text=&responsible=&multitext=&originator=&release= shows several open PRs mentioning panics, corruption, and reboots. Are they still open because problems exist? Or have the committers simply neglected to close them? --Brett Glass