From owner-freebsd-fs@FreeBSD.ORG Mon Nov 28 15:04:27 2011 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 D8D9A1065673; Mon, 28 Nov 2011 15:04:27 +0000 (UTC) (envelope-from pawel@dawidek.net) Received: from mail.dawidek.net (60.wheelsystems.com [83.12.187.60]) by mx1.freebsd.org (Postfix) with ESMTP id 8D3E68FC13; Mon, 28 Nov 2011 15:04:27 +0000 (UTC) Received: from localhost (58.wheelsystems.com [83.12.187.58]) by mail.dawidek.net (Postfix) with ESMTPSA id CFEE6EEB; Fri, 25 Nov 2011 12:03:40 +0100 (CET) Date: Fri, 25 Nov 2011 12:02:35 +0100 From: Pawel Jakub Dawidek To: Kostik Belousov Message-ID: <20111125110235.GB1642@garage.freebsd.pl> References: <1957615267.20111123230026@serebryakov.spb.ru> <20111123194444.GE50300@deviant.kiev.zoral.com.ua> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="OwLcNYc0lM97+oe1" Content-Disposition: inline In-Reply-To: <20111123194444.GE50300@deviant.kiev.zoral.com.ua> X-OS: FreeBSD 9.0-CURRENT amd64 User-Agent: Mutt/1.5.21 (2010-09-15) Cc: freebsd-fs@freebsd.org Subject: Re: Does UFS2 send BIO_FLUSH to GEOM when update metadata (with softupdates)? 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: Mon, 28 Nov 2011 15:04:27 -0000 --OwLcNYc0lM97+oe1 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Nov 23, 2011 at 09:44:44PM +0200, Kostik Belousov wrote: > On Wed, Nov 23, 2011 at 11:00:26PM +0400, Lev Serebryakov wrote: > > Hello, Freebsd-fs. > >=20 > > Does UFS2 with softupdates (without journal) issues BIO_FLUSH to > > GEOM layer when it need to ensure consistency on on-disk metadata? > No. Softupdates do not need flushes. Well, they do for two reasons: 1. To properly handle sync operations (fsync(2), O_SYNC). 2. To maintain consistent on-disk structures. The second point is there, because BIO_FLUSH is the only way to avoid reordering (apart from turning off disk write cache). SU assumes no I/O reordering will happen, which is very weak assumption. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com FreeBSD committer http://www.FreeBSD.org Am I Evil? Yes, I Am! http://yomoli.com --OwLcNYc0lM97+oe1 Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.14 (FreeBSD) iEYEARECAAYFAk7PdcsACgkQForvXbEpPzR8WgCffIE47sDfnjN+O411ELBT/hAV NRcAoKzWvT5wiAqg6reIdvqJqtAq5/30 =kLyd -----END PGP SIGNATURE----- --OwLcNYc0lM97+oe1--