From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sm02.isp.telecom.li ([217.173.238.131]:53698 "EHLO sm02.isp.telecom.li" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751227AbaCQUlF (ORCPT ); Mon, 17 Mar 2014 16:41:05 -0400 Message-ID: <53275DCC.8050506@adon.li> Date: Mon, 17 Mar 2014 21:40:44 +0100 From: jvogt MIME-Version: 1.0 Subject: Re: correct file size to use References: <53243539.5010405@adon.li> <5327577B.8050703@adon.li> <20140317203457.GA11577@sucs.org> In-Reply-To: <20140317203457.GA11577@sucs.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: fio-owner@vger.kernel.org List-Id: fio@vger.kernel.org To: Sitsofe Wheeler Cc: Ming Lei , Matthew Eaton , fio@vger.kernel.org, Carl Zwanzig Am 17.03.2014 21:34, schrieb Sitsofe Wheeler: > On Mon, Mar 17, 2014 at 09:13:47PM +0100, jvogt wrote: >> I just wanted to make some tests before taking it all in production. >> Thank you all for your answers! > If you want raw upper maximum numbers try using direct=1 ioengine=libaio > with an appropriate iodepth against the openiscsi block device. Bear in > mind things like iodepth and whether coalescing can take place can make > a huge difference... Please explain, what do you mean with appropriate iodepth? What would you suggest?