From owner-freebsd-fs@FreeBSD.ORG Sat Sep 2 09:43:19 2006 Return-Path: X-Original-To: freebsd-fs@freebsd.org Delivered-To: freebsd-fs@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 53AF316A4DA for ; Sat, 2 Sep 2006 09:43:19 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30302.mail.mud.yahoo.com (web30302.mail.mud.yahoo.com [209.191.69.64]) by mx1.FreeBSD.org (Postfix) with SMTP id 957A443D62 for ; Sat, 2 Sep 2006 09:43:12 +0000 (GMT) (envelope-from arne_woerner@yahoo.com) Received: (qmail 18975 invoked by uid 60001); 2 Sep 2006 09:43:12 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=u3lOgYSVIuXhQF/ws77XrSDlbyNpiduF8Hfjr9MUvv6eQWRKf4tXyRDx8wZkW2keU715FbKMBvTBr0TosFUwqd8YYiKu1qcEDozrzmteY1/2qh9OJtNHjB9U8Md94QD+16auoOjmfpXeg1B8MDyXO2JFaGicoTVNYA3lny15YP0= ; Message-ID: <20060902094312.18973.qmail@web30302.mail.mud.yahoo.com> Received: from [62.246.209.80] by web30302.mail.mud.yahoo.com via HTTP; Sat, 02 Sep 2006 02:43:12 PDT Date: Sat, 2 Sep 2006 02:43:12 -0700 (PDT) From: "R. B. Riddick" To: hardware@ee.ccny.cuny.edu, freebsd-fs@freebsd.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: Subject: Re: ATA flush cache on sync() 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: Sat, 02 Sep 2006 09:43:19 -0000 --- hardware@ee.ccny.cuny.edu wrote: > When the sync() system call is called on an ATA drive with a UFS 2 > filesystem, is the "FLUSH CACHE" ATA command sent to the drive? > As far as I know, when sync() return u cannot even be sure, that the in-kernel buffers are flushed already... And the "FLUSH CACHE" ATA command (or BIO_FLUSH since gjournal) is disputed, since it might break (in FBSD not implemented) concepts like TCQ(?) (tagged command queuing) or so... But I think there should be a FLUSH CACHE command from time to time, so that there cannot be an arbitrary gap... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com