From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751035AbdIKGmj (ORCPT ); Mon, 11 Sep 2017 02:42:39 -0400 Received: from bombadil.infradead.org ([65.50.211.133]:51543 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750991AbdIKGmh (ORCPT ); Mon, 11 Sep 2017 02:42:37 -0400 Date: Sun, 10 Sep 2017 23:42:37 -0700 From: Christoph Hellwig To: Hao Chen Cc: "Lu, Qian" , "linux-xfs@vger.kernel.org" , "darrick.wong@oracle.com" , "linux-kernel@vger.kernel.org" , amazon-linux-kernel Subject: Re: XFS mounted with 'discard' option - deleting fio test files slow Message-ID: <20170911064237.GA15161@infradead.org> References: <42228B9C-D2D3-4B9C-BFCF-BC9AED4A9678@amazon.com> <506FE85F-21F5-444C-876D-8C25DBB442EE@amazon.com> <20170908232152.GA44231@amazon.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170908232152.GA44231@amazon.com> User-Agent: Mutt/1.8.3 (2017-05-23) X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org. See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Sep 08, 2017 at 04:21:52PM -0700, Hao Chen wrote: > This is expected. To get a better performance of XFS on NVMe drive, it > is advised not use use the realtime discard option. > > https://www.intel.com/content/dam/support/us/en/documents/ssdc/data-center-ssds/Intel_Linux_NVMe_Guide_330602-002.pdf Again, this will depend on your device. Intel in particular was the example in my presentation for horrible performance of the NVMe discard support - other vendors implement much better discard support, so you'll see much better results.