Date: Tue, 12 Sep 2006 23:28:35 +0930 From: "Daniel O'Connor" <doconnor@gsoft.com.au> To: freebsd-stable@freebsd.org Cc: Christian Laursen <xi@borderworlds.dk> Subject: Re: gjournal and Softupdates Message-ID: <200609122328.36605.doconnor@gsoft.com.au> In-Reply-To: <ygfirjto0z2.fsf@dominion.borderworlds.dk> References: <45066E19.2040405@kuehlbox.de> <ee5vat$fcb$1@sea.gmane.org> <ygfirjto0z2.fsf@dominion.borderworlds.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
--nextPart1273612.mW7mACUaMD Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline On Tuesday 12 September 2006 19:34, Christian Laursen wrote: > Ivan Voras <ivoras@fer.hr> writes: > > - todays desktop drives can lie about writing data. SoftUpdates relies > > on some assumptions about when the data is physically written to > > media, and those are not always valid today > > I think journaling relies on the same assumptions. You can disable write caching on your disks (most even honour it :) however= a=20 lot of people choke at the performance hit.. One big problem is that high capacity disks use track writing - if you modi= fy=20 a single sector the disk re-writes the whole track. If the power fails during the track write then you lose potentially complet= ely=20 unrelated data. This affects all file systems equally though. =2D-=20 Daniel O'Connor software and network engineer for Genesis Software - http://www.gsoft.com.au "The nice thing about standards is that there are so many of them to choose from." -- Andrew Tanenbaum GPG Fingerprint - 5596 B766 97C0 0E94 4347 295E E593 DC20 7B3F CE8C --nextPart1273612.mW7mACUaMD Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2.2 (FreeBSD) iD8DBQBFBr0M5ZPcIHs/zowRAmpJAJ9pz20mKs49Pg8L4H5rpFUXd2AA6ACdEKKe mnce7A0RRAwbLfbRPcSKCds= =gPc3 -----END PGP SIGNATURE----- --nextPart1273612.mW7mACUaMD--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200609122328.36605.doconnor>