From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay3.corp.sgi.com [198.149.34.15]) by oss.sgi.com (Postfix) with ESMTP id 23EC77F50 for ; Tue, 25 Feb 2014 02:11:16 -0600 (CST) Received: from cuda.sgi.com (cuda2.sgi.com [192.48.176.25]) by relay3.corp.sgi.com (Postfix) with ESMTP id 93F56AC30F for ; Tue, 25 Feb 2014 00:11:15 -0800 (PST) Received: from mail.zbfmail.de (mail.zbfmail.de [176.9.84.12]) by cuda.sgi.com with ESMTP id PTTXahVrpIWU4Y25 (version=TLSv1 cipher=AES256-SHA bits=256 verify=NO) for ; Tue, 25 Feb 2014 00:10:39 -0800 (PST) Received: from [10.28.238.236] (tmo-100-212.customers.d1-online.com [80.187.100.212]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) (Authenticated sender: weber@zbfmail.de) by mail.zbfmail.de (Postfix) with ESMTPSA id 83F7010C147 for ; Tue, 25 Feb 2014 09:10:37 +0100 (CET) In-Reply-To: <530A71E3.9060107@hardwarefreak.com> References: <9963a76fbd006355c9ffd79f341c9971@zbfmail.de> <530A71E3.9060107@hardwarefreak.com> MIME-Version: 1.0 Subject: Re: gentoo linux, kernel 3.10.31 mount options bug? From: Marko Weber|8000 Date: Tue, 25 Feb 2014 09:10:35 +0100 Message-ID: List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: multipart/mixed; boundary="===============3440864160526654730==" Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Xfs --===============3440864160526654730== Content-Type: multipart/alternative; boundary="----ZAN00CQ4Q8W1GTNO7HICO0VWUPOA80" Content-Transfer-Encoding: 8bit ------ZAN00CQ4Q8W1GTNO7HICO0VWUPOA80 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Thanks for the short and clear answer stan. Marko On 23. Februar 2014 23:10:43 MEZ, Stan Hoeppner wrote: >On 2/23/2014 3:37 AM, Marko Weber|8000 wrote: >... >> linux /bzImage-3.10.31 root=/dev/md2 elevator=cfq clocksource=hpet > ^^^^^^^^^^^^ > >cfq tends to defeat much of the parallelism in XFS, decreasing >throughput substantially. This is documented in the XFS FAQ and has >been discussed here many times in the past. It has been recommended >for >a few years now that XFS not be used with the cfq elevator. Use >deadline with md arrays on plain HBAs and noop on SSDs or any device >with [F|B]BWC, i.e. RAID HBA or SAN controller. > >If you're using cfq to allow shaping of per process IO with control >groups, simply using cfq alone may slow down XFS throughput to the >point >that you don't need to bother with control group optimizations. > >-- >Stan -- Diese Nachricht wurde von meinem Android-Mobiltelefon mit K-9 Mail gesendet. ------ZAN00CQ4Q8W1GTNO7HICO0VWUPOA80 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: 8bit Thanks for the short and clear answer stan.

Marko

On 23. Februar 2014 23:10:43 MEZ, Stan Hoeppner <stan@hardwarefreak.com> wrote:
On 2/23/2014 3:37 AM, Marko Weber|8000 wrote:
...
 linux /bzImage-3.10.31 root=/dev/md2 elevator=cfq clocksource=hpet
                                       ^^^^^^^^^^^^

cfq tends to defeat much of the parallelism in XFS, decreasing
throughput substantially.  This is documented in the XFS FAQ and has
been discussed here many times in the past.  It has been recommended for
a few years now that XFS not be used with the cfq elevator.  Use
deadline with md arrays on plain HBAs and noop on SSDs or any device
with [F|B]BWC, i.e. RAID HBA or SAN controller.

If you're using cfq to allow shaping of per process IO with control
groups, simply using cfq alone may slow down XFS throughput to the point
that you don't need to bother with control group optimizations.

--
Diese Nachricht wurde von meinem Android-Mobiltelefon mit K-9 Mail gesendet. ------ZAN00CQ4Q8W1GTNO7HICO0VWUPOA80-- --===============3440864160526654730== 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 --===============3440864160526654730==--