Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754871AbdC3UaQ (ORCPT ); Thu, 30 Mar 2017 16:30:16 -0400 Received: from lang.hm ([66.167.227.134]:53315 "EHLO bifrost.lang.hm" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750766AbdC3UaP (ORCPT ); Thu, 30 Mar 2017 16:30:15 -0400 X-Greylist: delayed 814 seconds by postgrey-1.27 at vger.kernel.org; Thu, 30 Mar 2017 16:30:15 EDT Date: Thu, 30 Mar 2017 13:16:24 -0700 (PDT) From: David Lang X-X-Sender: dlang@dlang-laptop To: David Howells cc: Linus Torvalds , Thomas Gleixner , John Stultz , Linux Kernel Mailing List , linux-fsdevel Subject: Re: Apparent backward time travel in timestamps on file creation In-Reply-To: <23902.1490904827@warthog.procyon.org.uk> Message-ID: References: <22214.1490895007@warthog.procyon.org.uk> <23410.1490902528@warthog.procyon.org.uk> <23902.1490904827@warthog.procyon.org.uk> User-Agent: Alpine 2.21.1 (DEB 209 2017-03-23) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 714 Lines: 18 On Thu, 30 Mar 2017, David Howells wrote: > Linus Torvalds wrote: > >> The error bar can be huge, for the simple reason that the filesystem >> you are testing may not be sharing a clock with the CPU at _all_. >> >> IOW, think network filesystems. > > Can't I just not do the tests when the filesystem is a network fs? I don't > think it should be a problem for disk filesystems on network-attached storage. it's not trivial to detect if a filesystem is local or network (you would have to do calls to figure out what filesystem you are on, then have a list to define what's local and what's remote, that list would become out of date as new filesystems are added) David Lang