Return-Path: Received: from bombadil.infradead.org ([198.137.202.133]:53640 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752022AbeDRHF4 (ORCPT ); Wed, 18 Apr 2018 03:05:56 -0400 Date: Wed, 18 Apr 2018 00:05:52 -0700 From: Christoph Hellwig To: Olga Kornievskaia Cc: Christoph Hellwig , Olga Kornievskaia , "J. Bruce Fields" , linux-nfs Subject: Re: [PATCH v8 0/9] NFSD support for async COPY Message-ID: <20180418070551.GA8764@infradead.org> References: <20180413170158.17589-1-kolga@netapp.com> <20180414072202.GA6514@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: Sender: linux-nfs-owner@vger.kernel.org List-ID: On Sat, Apr 14, 2018 at 08:32:48AM -0400, Olga Kornievskaia wrote: > On Sat, Apr 14, 2018 at 3:22 AM, Christoph Hellwig wrote: > > What is the use case for adding all these crazy complications? > > We have already provided evidence for improved performance of > asynchronous copy vs synchronous copy. This is also foundation for the > "inter" server-to-server copy which is coming later as it was decided > to add the support in parts. Well, show your evidence in the introduction of the series then. And synchronous copy is not the target - clone is.