Date: Sat, 22 Sep 2001 07:34:34 +1200 (NZST) From: Juha Saarinen <juha@saarinen.org> To: j mckitrick <jcm@FreeBSD-uk.eu.org> Cc: Matt Dillon <dillon@earth.backplane.com>, Mike Meyer <mwm@mired.org>, Daniel O'Connor <doconnor@gsoft.com.au>, Kevin Oberman <oberman@es.net>, "stable@freebsd.org" <stable@freebsd.org> Subject: Re: RE: hw.ata.wc && hw.ata.tags && softupdates short question Message-ID: <Pine.LNX.4.33.0109220727450.10108-100000@vimfuego.saarinen.org> In-Reply-To: <20010921185411.C81649@dogma.freebsd-uk.eu.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 21 Sep 2001, j mckitrick wrote: > We've been told write caching turned OFF causes a huge performance > hit, but ON can cause data loss. Yes, it's a big performance hit, and no, it's not write caching by itself that causes data loss. Data loss happens during system failures that prevent the drive from writing out the contents of the cache to disk. Microsoft had this problem with newer IDE drives (which have 2MB+ caches), and I think Windows 9x, during shutdown (the OS didn't wait long enough before "flipping the switch" so to speak). Think the patch issued forced a cache writeout before shutdown... It's worth querying the manufacturer of your drive to find out what (if any) mechanisms have been implemented to ensure that the cache is written out if power is suddenly removed. Some drives (IBM I believe) use large capacitors to store enough energy to write out the cache to disk. -- Regards, Juha To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.LNX.4.33.0109220727450.10108-100000>