Date: Fri, 25 May 2001 12:39:11 -0400 From: Shannon Hendrix <shannon@widomaker.com> To: Doug Barton <DougB@DougBarton.net> Cc: Ed Hudson <elh_fbsd@spnet.com>, hackers@FreeBSD.ORG Subject: Re: general speed differences between 4.1.1-RELEASE and 4.3-RELEASE Message-ID: <20010525123906.B26445@widomaker.com> In-Reply-To: <3B0DF980.EDA844F7@DougBarton.net>; from DougB@DougBarton.net on Thu, May 24, 2001 at 11:19:44PM -0700 References: <200105250025.f4P0Pu905553@m44.spnet.com> <3B0DF980.EDA844F7@DougBarton.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, May 24, 2001 at 11:19:44PM -0700, Doug Barton wrote: > The current mood (which I agree with) is to make softupdates the default > after installation. The problem with the combo of write caching and > softupdates is that if the power actually goes off the meta-data writes > that softupdates postpones and are further postponed by the write cache > will never happen, therefore leaving the file system in a potentially > unrecoverable state. If drives could be counted on to have a synchronous write command, and the driver interface let you send a flag (cache/no-cache) with each write, would that be acceptable? In the XFS miling list at SGI, some were saying that that is what they wanted for metadata and log writes. -- "Whatever..." -- Kenny Gatdula To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010525123906.B26445>