From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1754212AbbIBOM1 (ORCPT <rfc822;w@1wt.eu>);
	Wed, 2 Sep 2015 10:12:27 -0400
Received: from 53505047.static.ziggozakelijk.nl ([83.80.80.71]:27709 "EHLO
	ns5.tasking.nl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1753903AbbIBOM0 (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Wed, 2 Sep 2015 10:12:26 -0400
Date: Wed, 2 Sep 2015 16:12:23 +0200
From: Dick Streefland <dick.streefland@altium.nl>
To: Erik Cumps <erik.cumps@esaturnus.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Unexpected slow block device write IO performance compared to
 uncached, unsynced direct IO using stock kernels
Message-ID: <20150902141223.GA31906@altium.nl>
References: <1434462995.6161.800.camel@erik-desktop.office>
 <1434462995.6161.800.camel@erik-desktop.office>
 <CALS80vgNzNENo=mDSt2b0363UXdgnQ6GtyActdYNs=oZgunpOg@mail.gmail.com>
 <20150901091535.GA21329@altium.nl>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20150901091535.GA21329@altium.nl>
Organization: Altium BV, Amersfoort, The Netherlands
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tuesday 2015-09-01 11:15, Dick Streefland wrote:
| I'm seeing this as well here on a number of new Dell Optiplex 7020
| machines and one older Optiplex 780, all with 8GB RAM and running
| Ubuntu 14.04 in 32-bit mode.

It turned out that the dirty thresholds in /proc/vmstat became zero:

nr_dirty_threshold 0
nr_dirty_background_threshold 0

A workaround is:

# sysctl vm.highmem_is_dirtyable=1

-- 
Dick