From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rob Ross Subject: Re: NFSv4/pNFS possible POSIX I/O API standards Date: Tue, 05 Dec 2006 15:55:12 -0600 Message-ID: <4575EAC0.5070408@mcs.anl.gov> References: <20061128055428.GA29891@infradead.org> <20061129090450.GA16296@infradead.org> <20061129122313.GG14315@parisc-linux.org> <20061129123913.GA15994@infradead.org> <4570ACD1.7060800@mcs.anl.gov> <4574BF52.6090600@mcs.anl.gov> <20061205170109.GP3013@parisc-linux.org> <20061205173953.GQ3013@parisc-linux.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Latchesar Ionkov , linux-fsdevel@vger.kernel.org Return-path: Received: from mailgw.mcs.anl.gov ([140.221.9.4]:36054 "EHLO mailgw.mcs.anl.gov" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759874AbWLEVzO (ORCPT ); Tue, 5 Dec 2006 16:55:14 -0500 To: Matthew Wilcox In-Reply-To: <20061205173953.GQ3013@parisc-linux.org> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Matthew Wilcox wrote: > On Tue, Dec 05, 2006 at 06:09:03PM +0100, Latchesar Ionkov wrote: >> It could be wasteful, but it could (most likely) also be useful. Name >> resolution is not that expensive on either side of the network. The >> latency introduced by the single-name lookups is :) > > *is* latency the problem here? Last I heard, it was the intolerable > load placed on the DLM by having clients bounce the read locks for each > directory element all over the cluster. I think you're both right: it's either the time spent on all the actual lookups or the time involved in all the lock traffic, depending on FS and network of course. Rob