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 2A79BC77B7A for ; Wed, 17 May 2023 12:39:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230472AbjEQMj1 (ORCPT ); Wed, 17 May 2023 08:39:27 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:51110 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229983AbjEQMj0 (ORCPT ); Wed, 17 May 2023 08:39:26 -0400 Received: from verein.lst.de (verein.lst.de [213.95.11.211]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 808EC1BFC; Wed, 17 May 2023 05:39:25 -0700 (PDT) Received: by verein.lst.de (Postfix, from userid 2407) id E2BDC68BEB; Wed, 17 May 2023 14:39:21 +0200 (CEST) Date: Wed, 17 May 2023 14:39:21 +0200 From: Christoph Hellwig To: Pavel Begunkov Cc: Christoph Hellwig , linux-nvme@lists.infradead.org, linux-block@vger.kernel.org, io-uring@vger.kernel.org, axboe@kernel.dk, kbusch@kernel.org, sagi@grimberg.me, joshi.k@samsung.com Subject: Re: [PATCH for-next 2/2] nvme: optimise io_uring passthrough completion Message-ID: <20230517123921.GA19835@lst.de> References: <20230517072314.GC27026@lst.de> <9367cc09-c8b4-a56c-a61a-d2c776c05a1c@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <9367cc09-c8b4-a56c-a61a-d2c776c05a1c@gmail.com> User-Agent: Mutt/1.5.17 (2007-11-01) Precedence: bulk List-ID: X-Mailing-List: io-uring@vger.kernel.org On Wed, May 17, 2023 at 01:32:53PM +0100, Pavel Begunkov wrote: > 1) ublk does secondary batching and so may produce multiple cqes, > that's not supported. I believe Ming sent patches removing it, > but I'd rather not deal with conflicts for now. > > 2) Some users may have dependencies b/w requests, i.e. a request > will only complete when another request's task_work is executed. > > 3) There might be use cases when you don't wont it to be delayed, > IO retries would be a good example. I wouldn't also use it for > control paths like ublk_ctrl_uring_cmd. You speak a lot of some users and some cases when the only users are ublk and nvme, both of which would obviously benefit. If you don't want conflicts wait for Ming to finish his work and then we can do this cleanly and without leaving dead code around.