From owner-freebsd-geom@FreeBSD.ORG Sat May 5 14:30:04 2007 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 64E5F16A403 for ; Sat, 5 May 2007 14:30:04 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: from web30309.mail.mud.yahoo.com (web30309.mail.mud.yahoo.com [209.191.69.71]) by mx1.freebsd.org (Postfix) with SMTP id 1916513C459 for ; Sat, 5 May 2007 14:30:03 +0000 (UTC) (envelope-from arne_woerner@yahoo.com) Received: (qmail 22707 invoked by uid 60001); 5 May 2007 14:30:03 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=vGSIaxyEf87fCd1PYgZPQ0JazhYem7IIq2KEOA/Xkpqf3a5yvkxbj8GsFcAhNjLOjVoNkoi9RaB7Ujcl5JAvqkU2qpln21cNzjSDJdLIioI87kUWAg1W3sTfswVgtxnWA0mVZV2FrA+l0jtATkMPpp2TxvkADm0WUH+r94ikx0o=; X-YMail-OSG: NhgNdBwVM1kF1lGrB8klX7MhqGYPf2eyfjt1_WO.QxBDPl.01hnEq69Pw4TQdzTcUZC1JD1PmnkBDy3N.3W70XKno9Qi.nJ8.bSF1i5Rg35aYWCWSnZx5c_N.oQQNA-- Received: from [213.54.47.84] by web30309.mail.mud.yahoo.com via HTTP; Sat, 05 May 2007 07:30:02 PDT Date: Sat, 5 May 2007 07:30:02 -0700 (PDT) From: Arne "Wörner" To: Ivan Voras , freebsd-geom@freebsd.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <398236.18997.qm@web30309.mail.mud.yahoo.com> Cc: Subject: Re: graid5 after-reboot problem X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 05 May 2007 14:30:04 -0000 --- Ivan Voras wrote: > Arne Wörner wrote: > > > (that disables the write cache in graid5, which slows down write requests) > > Is the write cache in graid5 aware of what happens on the VFS / UFS > layers (something like gjournal does)? Otherwise, how can you guarantee > consistency with write caching at the GEOM layer when there's a power > outage or some other system interruption? > I cant... :-) Just like many ATA disks, that just cant turn off their write cache... (but graid5 can at least turn off its write cache) But graid5 is aware of BIO_FLUSH... :-)) So somewhen UFS might send a BIO_FLUSH when it is appropriate... Or gjournal sends the BIO_FLUSH... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com