Return-Path: linux-nfs-owner@vger.kernel.org Received: from mail-ob0-f170.google.com ([209.85.214.170]:48946 "EHLO mail-ob0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753026AbaBQQq4 convert rfc822-to-8bit (ORCPT ); Mon, 17 Feb 2014 11:46:56 -0500 Received: by mail-ob0-f170.google.com with SMTP id va2so17188054obc.15 for ; Mon, 17 Feb 2014 08:46:56 -0800 (PST) Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.1 \(1827\)) Subject: Re: [PATCH v3] NFSv4.1: new layout stateid can not be overwrite by one out of date From: Trond Myklebust In-Reply-To: <1392620881-26561-1-git-send-email-shaobingqing@bwstor.com.cn> Date: Mon, 17 Feb 2014 11:46:53 -0500 Cc: linuxnfs , Linux Kernel Mailing List Message-Id: References: <1392620881-26561-1-git-send-email-shaobingqing@bwstor.com.cn> To: shaobingqing Sender: linux-nfs-owner@vger.kernel.org List-ID: On Feb 17, 2014, at 2:08, shaobingqing wrote: > If initiate_file_draining returned NFS4ERR_DELAY, all the lsegs of > a file might be released before the retrying cb_layout request arriving > at the client. In this situation,the list lo->plh_segs is empty, > layoutget request of the file will use open stateid to obtain a new > layout stateid. And if the retrying cb_layout request arrived at the > client after the layoutget reply, new layout stateid would be overwrite > by one out of date. I have very serious doubts about adding layout state to represent what the server is _trying_ to do. What if the server decides not to retry the recall? What if it reboots? Let?s start with looking at the motivations: Have you ever run into the above problem in practice? If so, what was the effect on overall performance? _________________________________ Trond Myklebust Linux NFS client maintainer, PrimaryData trond.myklebust@primarydata.com