From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id C0922C05027 for ; Mon, 6 Feb 2023 15:50:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230241AbjBFPuy (ORCPT ); Mon, 6 Feb 2023 10:50:54 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59430 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229943AbjBFPux (ORCPT ); Mon, 6 Feb 2023 10:50:53 -0500 Received: from verein.lst.de (verein.lst.de [213.95.11.211]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EACC759F6 for ; Mon, 6 Feb 2023 07:50:52 -0800 (PST) Received: by verein.lst.de (Postfix, from userid 2407) id 1F16668BFE; Mon, 6 Feb 2023 16:50:49 +0100 (CET) Date: Mon, 6 Feb 2023 16:50:48 +0100 From: Christoph Hellwig To: Pankaj Raghav Cc: axboe@kernel.dk, hch@lst.de, mcgrof@kernel.org, gost.dev@samsung.com, linux-block@vger.kernel.org Subject: Re: [PATCH] brd: improve performance with blk-mq Message-ID: <20230206155048.GA13392@lst.de> References: <20230203103005.31290-1-p.raghav@samsung.com> <20230203103005.31290-2-p.raghav@samsung.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20230203103005.31290-2-p.raghav@samsung.com> User-Agent: Mutt/1.5.17 (2007-11-01) Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org On Fri, Feb 03, 2023 at 04:00:06PM +0530, Pankaj Raghav wrote: > move to blk-mq based request processing as brd is one of the few drivers > that still uses submit_bio interface. The changes are pretty trivial > to start using blk-mq. The performance increases up to 125% for direct IO > read workloads. There is a slight dip in performance for direct IO write > workload but considering the general performance gain with blk-mq > support, it is not a lot. Can you find out why writes regress, and what improves for reads? In general blk-mq is doing a lot more work for better batching, but much of that batching should not matter for a simple ramdisk. So the results look a little odd to me, and extra numbers and explanations would really help.