Date: Mon, 04 Oct 2004 14:08:11 +0200 From: =?ISO-8859-1?Q?S=F8ren_Schmidt?= <sos@DeepCore.dk> To: Jason DiCioccio <jd@ods.org> Cc: freebsd-current@freebsd.org Subject: Re: Serial ATA, Write Caching and Soft-Updates Message-ID: <41613D2B.6030609@DeepCore.dk> In-Reply-To: <B35CE5F261C0CAB86D0B0D48@[10.102.0.67]> References: <B35CE5F261C0CAB86D0B0D48@[10.102.0.67]>
next in thread | previous in thread | raw e-mail | index | archive | help
Jason DiCioccio wrote: > Greetings! > I'm just asking this question mainly out of curiosity. However, I kno= w=20 > that Serial ATA drives can support 'native command queuing' (an improve= d=20 > version of tagged command queuing apparently). As a result, are serial= =20 > ATA drives safe to use in a soft-updates+write caching enabled setup? = > Do they suffer from the same write caching issues that the PATA drives = > suffered from? First off we (or rather I) need to grow support for NCQ, and in most=20 cases you will need a controller that supports it as well. As to the suffering, no idea yet, havn't had any NCQ capable HW in the=20 lab yet. --=20 -S=F8ren
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?41613D2B.6030609>