From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay1.corp.sgi.com [137.38.102.111]) by oss.sgi.com (Postfix) with ESMTP id A22E87CA0 for ; Mon, 8 Aug 2016 23:03:54 -0500 (CDT) Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by relay1.corp.sgi.com (Postfix) with ESMTP id 366558F8037 for ; Mon, 8 Aug 2016 21:03:50 -0700 (PDT) Received: from nm32.bullet.mail.sg3.yahoo.com (nm32.bullet.mail.sg3.yahoo.com [106.10.151.27]) by cuda.sgi.com with ESMTP id u4e6GFScQ8o436x8 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NO) for ; Mon, 08 Aug 2016 21:03:45 -0700 (PDT) Date: Tue, 9 Aug 2016 04:02:55 +0000 (UTC) From: Gim Leong Chin Message-ID: <592673683.10446004.1470715375850.JavaMail.yahoo@mail.yahoo.com> In-Reply-To: <20160808174427.24d8272c@harpe.intellique.com> References: <5787852A.7030900@st-andrews.ac.uk> <20160808161132.1d76eb5c@harpe.intellique.com> <1470670691.8958.11.camel@filmlight.ltd.uk> <20160808174427.24d8272c@harpe.intellique.com> Subject: Re: Advice needed with file system corruption MIME-Version: 1.0 Reply-To: Gim Leong Chin List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: multipart/mixed; boundary="===============2786244616168090254==" Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Emmanuel Florac , Roger Willcocks Cc: Steve Brooks , "xfs@oss.sgi.com" --===============2786244616168090254== Content-Type: multipart/alternative; boundary="----=_Part_10446003_2107006600.1470715375844" ------=_Part_10446003_2107006600.1470715375844 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable From: Emmanuel Florac To: Roger Willcocks =20 Cc: Steve Brooks ; xfs@oss.sgi.com Sent: Monday, 8 August 2016, 23:44 Subject: Re: Advice needed with file system corruption =20 Le Mon, 08 Aug 2016 16:38:11 +0100 Roger Willcocks =C3=A9crivait: > >=20 > > Late to the game, I just wanted to remark that I've unfortunately > > verified many times that write activity during rebuilds on Adaptec > > RAID controllers often creates corruption. I've reported that to > > Adaptec, but they don't seem to care much... > >=C2=A0=20 >=20 > It seems like explicitly disabling individual disk drives write-back > cache somewhat mitigates the effect.=20 Drives connected to RAID controllers with battery backed cache should have = their caches "disabled" (they are really set to write through mode instead)= .=C2=A0 By the way, I found out in lab testing that 7200 RPM SATA drives su= ffer a big performance loss when doing sequential writes in cache write thr= ough mode. ------=_Part_10446003_2107006600.1470715375844 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
<= /div>


From: Emmanuel Florac <eflorac= @intellique.com>
To: Roger Willcocks <roger@filmlight.ltd.uk>
Cc: Steve Brooks <sjb14@st-andrews.ac.uk>;= xfs@oss.sgi.com
Sent:= Monday, 8 August 2016, 23:44
Sub= ject: Re: Advice needed with file system corruption
 =

Le Mon, 08 Aug 2016 16:38:11 +0100
Roger Will= cocks <roger@filmlight.ltd.uk> =C3=A9cri= vait:

> >
>= ; > Late to the game, I just wanted to remark that I've unfortunately> > verified many times that write activity during re= builds on Adaptec
> > RAID controllers often create= s corruption. I've reported that to
> > Adaptec, bu= t they don't seem to care much...
> > 
>

> It seems like = explicitly disabling individual disk drives write-back
&g= t; cache somewhat mitigates the effect.

Drives connected to RAID controllers w= ith battery backed cache should have their caches "disabled" (they are real= ly set to write through mode instead).  By the way, I found out in lab= testing that 7200 RPM SATA drives suffer a big performance loss when doing= sequential writes in cache write through mode.


------=_Part_10446003_2107006600.1470715375844-- --===============2786244616168090254== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs --===============2786244616168090254==--