Return-Path: Received: from fieldses.org ([173.255.197.46]:34002 "EHLO fieldses.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2389692AbeHARGt (ORCPT ); Wed, 1 Aug 2018 13:06:49 -0400 Date: Wed, 1 Aug 2018 11:20:38 -0400 From: Bruce Fields To: Chuck Lever Cc: linux-rdma@vger.kernel.org, Linux NFS Mailing List Subject: Re: [PATCH v1 0/4] NFS/RDMA server patches for v4.19 Message-ID: <20180801152038.GB18338@fieldses.org> References: <20180727142007.21878.77494.stgit@klimt.1015granger.net> <20180801143622.GF16651@fieldses.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 Wed, Aug 01, 2018 at 11:14:14AM -0400, Chuck Lever wrote: > > On Aug 1, 2018, at 10:36 AM, J. Bruce Fields wrote: > > But I'd rather not invest a lot of time trying to make NFSv2/v3 better, > > the priority for older protocols is just to avoid regressions. > > Fair 'nuf. > > I'm not clear where NFSv4.0 fits here. I realize most of us would > consider NFSv4.0 to be a "legacy protocol". Does the Linux server > utilize the DRC for NFSv4.0 ? If I remember correctly, it uses the DRC and decides whether to cache particular compounds based on the mix of operation numbers making up the compound. (I wrote that code but haven't looked at it recently.)--b.