Date: Tue, 30 Mar 2004 14:36:25 -0800
From: Chris Wedgwood <cw@f00f.org>
To: Jeff Garzik <jgarzik@pobox.com>
Cc: "Stephen C. Tweedie" <sct@redhat.com>, Chris Mason <mason@suse.com>,
       Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl>,
       Jens Axboe <axboe@suse.de>, Linux Kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] barrier patch set
Message-ID: <20040330223625.GA1245@dingdong.cryptoapps.com>
References: <20040319153554.GC2933@suse.de> <200403201723.11906.bzolnier@elka.pw.edu.pl> <1079800362.11062.280.camel@watt.suse.com> <200403201805.26211.bzolnier@elka.pw.edu.pl> <1080662685.1978.25.camel@sisko.scot.redhat.com> <1080674384.3548.36.camel@watt.suse.com> <1080683417.1978.53.camel@sisko.scot.redhat.com> <4069F2FC.90003@pobox.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <4069F2FC.90003@pobox.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 714
Lines: 19


> For IDE, O_DIRECT and O_SYNC can use special "FUA" commands, which
> don't return until the data is on the platter.

On modern drives how reliable is this?  At one point disk-scrubbing
software which used FUA (to ensure data was being written to the
platters) showed that some drives completely ignore this.

Has the state of things changed significantly that we can assume this
is very rare or might we need to have to kind of whitelist/blacklist
system?


    --cw
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/