Return-Path: Received: from natasha.panasas.com ([67.152.220.90]:60820 "EHLO natasha.panasas.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752506Ab1IUKi2 (ORCPT ); Wed, 21 Sep 2011 06:38:28 -0400 Message-ID: <4E79BE96.1070905@panasas.com> Date: Wed, 21 Sep 2011 13:38:14 +0300 From: Boaz Harrosh To: CC: , , , , Subject: Re: [PATCH 2/3] pnfs: introduce pnfs private workqueue References: <1316488728-24912-1-git-send-email-rees@umich.edu> <1316488728-24912-3-git-send-email-rees@umich.edu> <1316558461.15093.4.camel@lade.trondhjem.org> <20110921002917.GA30770@merit.edu> <2E1EB2CF9ED1CB4AA966F0EB76EAB4430B480226@SACMVEXC2-PRD.hq.netapp.com> <4E798C93.40409@tonian.com> In-Reply-To: Content-Type: text/plain; charset="UTF-8" Sender: linux-nfs-owner@vger.kernel.org List-ID: MIME-Version: 1.0 On 09/21/2011 01:23 PM, tao.peng@emc.com wrote: > > Unless we do following: > 1. preallocate memory for extent state convertion > 2. use nfsiod/rpciod to handle bl_write_cleanup > 3. for pnfs error case, create a kthread to recollapse and resend to MDS > > not sure if it worth the complexity though... > > Cheers, > Tao > Please forgive my ignorance but what is the big difference between a kthread and a workqueue? I thought a workqueue is just a kthread and some memory structures (list). I agree with "keep things simple" But what do I know ;-) Thanks Boaz