Return-Path: linux-nfs-owner@vger.kernel.org Received: from mx12.netapp.com ([216.240.18.77]:51115 "EHLO mx12.netapp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752508Ab3J2Mow convert rfc822-to-8bit (ORCPT ); Tue, 29 Oct 2013 08:44:52 -0400 From: "Myklebust, Trond" To: Hellwig Christoph CC: "Schumaker, Bryan" , Mailing List Linux NFS Subject: Re: [PATCH 2/3] NFS: Allow for asynchronous WRITE_PLUS calls Date: Tue, 29 Oct 2013 12:44:50 +0000 Message-ID: References: <1382972418-2249-1-git-send-email-bjschuma@netapp.com> <1382972418-2249-3-git-send-email-bjschuma@netapp.com> <20131029073943.GD10889@infradead.org> In-Reply-To: <20131029073943.GD10889@infradead.org> Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Sender: linux-nfs-owner@vger.kernel.org List-ID: On Oct 29, 2013, at 3:39 AM, Christoph Hellwig wrote: > On Mon, Oct 28, 2013 at 11:00:17AM -0400, Anna Schumaker wrote: >> Clients are required to support CB_OFFLOAD for the NFS4_CONTENT_HOLE arm >> of the WRITE_PLUS union. > > This sounds pretty stupid. Just curious, who got this braindamage into > the standard? > It exists because the server vendors were worried that operations such as preallocation and/or hole punching can take a more or less unbounded amount of time due to the 64-bit size. By using an (optional) callback method, the server can free up the RPC slot that would otherwise be kept waiting in the synchronous case. Cheers Trond