From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay2.corp.sgi.com [137.38.102.29]) by oss.sgi.com (Postfix) with ESMTP id BD6FA7D17 for ; Wed, 6 Jul 2016 18:06:25 -0500 (CDT) Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by relay2.corp.sgi.com (Postfix) with ESMTP id 6B6DD30408C for ; Wed, 6 Jul 2016 16:06:22 -0700 (PDT) Received: from ipmail06.adl2.internode.on.net (ipmail06.adl2.internode.on.net [150.101.137.129]) by cuda.sgi.com with ESMTP id 8I7AdCH38wgvKRNf for ; Wed, 06 Jul 2016 16:06:20 -0700 (PDT) Date: Thu, 7 Jul 2016 09:05:35 +1000 From: Dave Chinner Subject: Re: Bad Metadata performances for XFS? Message-ID: <20160706230535.GF12670@dastard> References: <3ED34739A4E85E4F894367D57617CDEF9ED9518B@LAX-EX-MB2.datadirect.datadirectnet.com> <20160704225226.GD27480@dastard> <20160705001854.GY12670@dastard> <3ED34739A4E85E4F894367D57617CDEF9ED955AB@LAX-EX-MB2.datadirect.datadirectnet.com> <1467805769.7631.249.camel@filmlight.ltd.uk> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <1467805769.7631.249.camel@filmlight.ltd.uk> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Roger Willcocks Cc: "linux-xfs@vger.kernel.org" , Chris Murphy , Wang Shilong , "xfs@oss.sgi.com" On Wed, Jul 06, 2016 at 12:49:29PM +0100, Roger Willcocks wrote: > On Tue, 2016-07-05 at 14:34 -0600, Chris Murphy wrote: > > On Mon, Jul 4, 2016 at 7:43 PM, Wang Shilong wrote: > > > > > > > > > I understand that this is single thread Limit, but I guess there are some > > > other Limit here, because even single thread creating 50W files speed > > > is twice than 200W files. > > > > Watts or Wolframs (tungsten)? > > > > 50W!=50000. You could write it as 50k and 200k. It's unlikely to get > > confused with 50K and 200K, which are temperatures, because of > > context. But W makes no sense. > > > > > > > > I suspect it's an abbreviation for the (Chinese) unit 'wan' > > https://www.quora.com/Why-do-Chinese-people-count-in-units-of-10-000 > > so it makes perfect sense but it's not an SI unit. Thanks, Roger - it does make sense now the unit being used has been explained. This is a canonical example of how being explicit about units being used and what they mean is of prime importance to understanding what each other are saying. Cheers, Dave. -- Dave Chinner david@fromorbit.com _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs