Return-Path: linux-nfs-owner@vger.kernel.org Received: from mx142.netapp.com ([216.240.21.19]:57785 "EHLO mx142.netapp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753573AbbBEQnt (ORCPT ); Thu, 5 Feb 2015 11:43:49 -0500 Message-ID: <54D39DC2.9060808@Netapp.com> Date: Thu, 5 Feb 2015 11:43:46 -0500 From: Anna Schumaker MIME-Version: 1.0 To: Christoph Hellwig CC: , Subject: Re: [PATCH v2 2/4] NFSD: Add READ_PLUS support for data segments References: <1422477777-27933-1-git-send-email-Anna.Schumaker@Netapp.com> <1422477777-27933-3-git-send-email-Anna.Schumaker@Netapp.com> <20150205141325.GC4522@infradead.org> <54D394EC.9030902@Netapp.com> <20150205162326.GA18977@infradead.org> In-Reply-To: <20150205162326.GA18977@infradead.org> Content-Type: text/plain; charset="utf-8" Sender: linux-nfs-owner@vger.kernel.org List-ID: On 02/05/2015 11:23 AM, Christoph Hellwig wrote: > On Thu, Feb 05, 2015 at 11:06:04AM -0500, Anna Schumaker wrote: >>> If the READ_PLUS implementation can't use the splice read path it's >>> probably a loss for most workloads. >>> >> >> I'll play around with the splice path, but I don't think it was designed for encoding multiple read segments. > > The problem is that the typical case of all data won't use splice > every with your patches as the 4.2 client will always send a READ_PLUS. > > So we'll have to find a way to use it where it helps. While we might be > able to add some hacks to only use splice for the first segment I guess > we just need to make the splice support generic enough in the long run. > I should be able to use splice if I detect that we're only returning a single DATA segment easily enough.