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 9945F7F37 for ; Mon, 21 Dec 2015 12:25:43 -0600 (CST) Received: from cuda.sgi.com (cuda2.sgi.com [192.48.176.25]) by relay1.corp.sgi.com (Postfix) with ESMTP id 89F278F8039 for ; Mon, 21 Dec 2015 10:25:40 -0800 (PST) Received: from sandeen.net (sandeen.net [63.231.237.45]) by cuda.sgi.com with ESMTP id 0zq3bFPjXPTGyLJw for ; Mon, 21 Dec 2015 10:25:34 -0800 (PST) Received: from liberator.sandeen.net (liberator.sandeen.net [10.0.0.4]) (using TLSv1.2 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (No client certificate requested) by sandeen.net (Postfix) with ESMTPSA id 0762363C5A9F for ; Mon, 21 Dec 2015 12:25:34 -0600 (CST) Subject: Re: xfs within one hour after power-on reset , nginx performance is poor and do not have this phenomenon on ext4 References: <11FA37A582DFC847A21131D4B69D8B495AA49849@szxema505-mbs.china.huawei.com> From: Eric Sandeen Message-ID: <5678441D.5090103@sandeen.net> Date: Mon, 21 Dec 2015 12:25:33 -0600 MIME-Version: 1.0 In-Reply-To: <11FA37A582DFC847A21131D4B69D8B495AA49849@szxema505-mbs.china.huawei.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com There is not enough information here to begin considering your problem report. http://xfs.org/index.php/XFS_FAQ#Q:_What_information_should_I_include_when_reporting_a_problem.3F I'm not even sure I understand what you have stated so far; you see the RPS (requests per second) increase after the system has been up for one hour, is that correct? In any case, we aren't nginx experts here; you will need to do more investigation to find out what is actually happening at the filesystem level before we can be of much help, I think. -Eric On 12/21/15 1:09 AM, Linpeimin wrote: > Hello , we use xfs file system to test nginx , I found the power-on > reset , within the first one hour nginx relatively poor performance, > and after one hour , re- test , performance result( RPS) of dynamic > pages has improved.If we change the file system into ext4, you do not > have this phenomenon , after the start,RPS performance has remained > stable. _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs