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 07D89C3064D for ; Tue, 2 Jul 2024 15:15:22 +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=ka/7u/p9ENHBdStpLxiX0zhRuapNYRxlGvy7UsI47i4=; b=m2IXV/nwOJ92vLavokEb38IXS0 qO7VNYu4YOuonk/1K2yevuLZ+UlfOnITUVXvXQ2g9yWFoMwG1f4/iezKo70S/zlMdUM6RJtOMMM4U 0CYbF7as8qfBQngtVeioQWvBpdt+aRp0Pk+lGLAHDSRt//z9VXM0rio1PSjgoLShFj8otaOf2Xxzd RJ8dwVOB8iw5KegNenTQx0+e37/jh0EuxbNmX9TBPCk8/XuaH+Sb+2p8KxwgEO8vjA52xJlv45joS RvuRZbDawUYRVACr9W4s86wDhrXoF5gWJiDI31amttOxPepdrdLTd0wzSRHUmXBOMZ+q8yyIC41Al 3d8L2Nhw==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.97.1 #2 (Red Hat Linux)) id 1sOfDw-00000007AGM-3Yn6; Tue, 02 Jul 2024 15:15:16 +0000 Received: from sin.source.kernel.org ([2604:1380:40e1:4800::1]) by bombadil.infradead.org with esmtps (Exim 4.97.1 #2 (Red Hat Linux)) id 1sOfDu-00000007AFg-0eIs for linux-nvme@lists.infradead.org; Tue, 02 Jul 2024 15:15:15 +0000 Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sin.source.kernel.org (Postfix) with ESMTP id 223E4CE122C; Tue, 2 Jul 2024 15:15:10 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id CAC10C116B1; Tue, 2 Jul 2024 15:15:08 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1719933309; bh=ka/7u/p9ENHBdStpLxiX0zhRuapNYRxlGvy7UsI47i4=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=WEnHsCd2aZp8wkpUWwJ7ja9kaewmaoLQ0se954mp+eElMX5/aQTsc4Ox2UdRhtXyW SWFnIPLs35+OnI23YyEEwjDh0sgtwuHC5r4W/3cUi3EaeVefeGoqhSbPdvFB5OfU9j 0TzgbIfd7osSi3MnGz5MpT2eiZ/iABQIInF37+WAvb89Aa0anVCUWKr/Stbs7VVVuD WDCOlgt4seOKhA0YXCreI6pTJRwJDUbuatQzdSFfm3YuKHWEbyZwtg1mx6UEWql1sD k8/2aTu/NVoV1SS2DDpdx1C6ukKL4cfTB/fmNV+Y9/7C9XkmpkxACbntmYIpPz5bAZ NKlOfiU4iaAhw== Date: Tue, 2 Jul 2024 09:15:06 -0600 From: Keith Busch To: Christoph Hellwig Cc: Kanchan Joshi , axboe@kernel.dk, martin.petersen@oracle.com, sagi@grimberg.me, linux-nvme@lists.infradead.org, bvanassche@acm.org, javier.gonz@samsung.com, gost.dev@samsung.com, Hui Qi , Nitesh Shetty Subject: Re: [PATCH v3] nvme: enable FDP support Message-ID: References: <20240702102619.164170-1-joshi.k@samsung.com> <20240702113954.GA15325@lst.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20240702113954.GA15325@lst.de> X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20240702_081514_393935_A91CDDC1 X-CRM114-Status: GOOD ( 10.77 ) 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 I like concensus on features, but I don't think we're going to get that here. It's my opinion that FDP is just arbitrary hints, and this is just one way to map it to other hints. Not a perfect match, but I don't think it needs to be. It is not realistic for protocols to target a specific operating system, and Linux's write hints are not exactly a shining example of an interface for this purpose either. My first concern for applying something like this is what kind of maintenance burdens does this create, or any potential harm to users who don't subscribe to the feature? Nothing here looks alarming to me, and there is a clear demand to be able to access these features like this. Maybe it works out for some workloads, maybe it doesn't, but I don't see a need to block this at this point.