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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 20FE9C77B75 for ; Mon, 15 May 2023 15:47:26 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:In-Reply-To:Content-Type: MIME-Version:References:Message-ID:Subject:Cc:To:From:Date:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=w4/WZO73pOyG5F0QBp13bMti6iuUdNn5K9d8kRWxy68=; b=tePXbVZi5mWsfzjhg1ZTzswrHl LDFB8Vrfs78JT6Bx/EoFw+IZ4/hQI2Ys/5BheK8w+/920V4vjdDH1uYEGh0WXok8R1eT/luKmz2XB WKjRqbSgy/D4OskxOSRFiYdef8TVT3tHB0GoTN4HTxmICEsPwcaJKOj+IFI1V5rkON4zBjrSVVSkw gjWBRkBO/gmVcbjhNZaPqJBkn50Ige3dg0ZI8wNtMY4uZstiSnwWQPn9RNqXnZYaxuVtWk6/bElZB DBwbEXxmEsQgRF8O92rq9giY1aeI/NTzuiS/ENixn+rBxGqGu2Li8Bdw78o9HE3Vksd5dw24J1Hk3 GgqbqW+g==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1pyaPw-002clj-2h; Mon, 15 May 2023 15:47:20 +0000 Received: from dfw.source.kernel.org ([2604:1380:4641:c500::1]) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1pyaPu-002ckn-1h for linux-nvme@lists.infradead.org; Mon, 15 May 2023 15:47:19 +0000 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 6F07861FAD; Mon, 15 May 2023 15:47:16 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 5AE2FC433EF; Mon, 15 May 2023 15:47:15 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1684165635; bh=W4NQWF7lda7qu8vNpd5FlZvTG+e654oz8MJ2TScQyzM=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=us7fP7ymd5R5YpdWXlafSi10vkSaePrpgJtaigLDxdOoxeDzp0mpXrIMbk6gxa8Yl MaNFKWJeA5fj1o4u3cGCTjeCeMdryNJ1EuLOsBQhGql47fBpGU59B1cjTLENqv3KUz TrXRvKpHGomAOc9BYu8gQtm/Lxedc3ySkpM0SdY9PB91FUKY+qs/L4Y/oCwUxzgipy YzGSC/3W8h1TNW9+1nLl17PnYJzreTvjRgReFiiz3dgXeOCIG1nMipjNral4ciXOXC x2XZVgsLlOVcxGCGLuGj76+sP5Y+kj06SdNmK2tewowFzti3AP6dQTYN8hpwE0XGj3 7+6Z6JlK1JwTg== Date: Mon, 15 May 2023 09:47:12 -0600 From: Keith Busch To: Christoph Hellwig Cc: Keith Busch , linux-nvme@lists.infradead.org, linux-block@vger.kernel.org, joshi.k@samsung.com, axboe@kernel.dk, xiaoguang.wang@linux.alibaba.com Subject: Re: [RFC 1/3] nvme: skip block cgroups for passthrough commands Message-ID: References: <20230501153306.537124-1-kbusch@meta.com> <20230501153306.537124-2-kbusch@meta.com> <20230503050414.GA19301@lst.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20230515_084718_633285_D1AC9B58 X-CRM114-Status: GOOD ( 19.62 ) X-BeenThere: linux-nvme@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Linux-nvme" Errors-To: linux-nvme-bounces+linux-nvme=archiver.kernel.org@lists.infradead.org On Wed, May 03, 2023 at 09:25:21AM -0600, Keith Busch wrote: > On Wed, May 03, 2023 at 07:04:14AM +0200, Christoph Hellwig wrote: > > On Mon, May 01, 2023 at 08:33:04AM -0700, Keith Busch wrote: > > > From: Keith Busch > > > > > > Passthrough requests don't go through the submit_bio() path, so all the > > > overhead of setting up the bio's cgroup is wasted cycles. Provide a path > > > to skip this setup. > > > > These days we should not need to set bi_bdev at all for passthrough, > > so I think we can just drop the assingment. > > We can't really skip it for polling since that needs a bio with a > bdev. I'll take another shot at detandling that requirement. I've got a new version ready to go that removes the bio and bi_dev requirement for polling uring commands, but passthrough still needs to set bi_bdev for metadata since it's used in bio_integrity_add_page(). I suppose we could have that just take the queue limits directly instead of extracting them from an assumed bi_dev.