Return-Path: Received: from bombadil.infradead.org ([198.137.202.9]:50097 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932951AbcFOOxb (ORCPT ); Wed, 15 Jun 2016 10:53:31 -0400 Date: Wed, 15 Jun 2016 07:53:30 -0700 From: Christoph Hellwig To: Trond Myklebust Cc: Christoph Hellwig , "linux-nfs@vger.kernel.org" Subject: Re: [PATCH 11/12] NFS: Don't count O_DIRECT reads in the inode->i_dio_count Message-ID: <20160615145330.GA5297@infradead.org> References: <1465931115-30784-6-git-send-email-trond.myklebust@primarydata.com> <1465931115-30784-7-git-send-email-trond.myklebust@primarydata.com> <1465931115-30784-8-git-send-email-trond.myklebust@primarydata.com> <1465931115-30784-9-git-send-email-trond.myklebust@primarydata.com> <1465931115-30784-10-git-send-email-trond.myklebust@primarydata.com> <1465931115-30784-11-git-send-email-trond.myklebust@primarydata.com> <20160615071605.GD4318@infradead.org> <20160615144150.GA18524@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 Wed, Jun 15, 2016 at 02:50:07PM +0000, Trond Myklebust wrote: > Fair enough. So it sounds as if you are suggesting we can just drop using inode_dio_*() altogether? Maybe. The big question is how a direct write vs truncate race is handled. Either way I think a patch like this deserves a detailed analysis documented in the changelog and/or comments in the code.