Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932641Ab0HDMGh (ORCPT ); Wed, 4 Aug 2010 08:06:37 -0400 Received: from alpha.arachsys.com ([91.203.57.7]:35514 "EHLO alpha.arachsys.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932192Ab0HDMGg (ORCPT ); Wed, 4 Aug 2010 08:06:36 -0400 Date: Wed, 4 Aug 2010 13:04:32 +0100 From: Chris Webb To: Wu Fengguang Cc: Minchan Kim , "linux-mm@kvack.org" , "linux-kernel@vger.kernel.org" , KOSAKI Motohiro , Pekka Enberg Subject: Re: Over-eager swapping Message-ID: <20100804120430.GB23551@arachsys.com> References: <20100803033108.GA23117@arachsys.com> <20100803042835.GA17377@localhost> <20100803214945.GA2326@arachsys.com> <20100804022148.GA5922@localhost> <20100804032400.GA14141@localhost> <20100804095811.GC2326@arachsys.com> <20100804114933.GA13527@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100804114933.GA13527@localhost> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1539 Lines: 36 Wu Fengguang writes: > Maybe turn off KSM? It helps to isolate problems. It's a relative new > and complex feature after all. Good idea! I'll give that a go on one of the machines without swap at the moment, re-add the swap with ksm turned off, and see what happens. > > However, your suggestion is right that the CPU loads on these machines are > > typically quite high. The large number of kvm virtual machines they run mean > > thatl oads of eight or even sixteen in /proc/loadavg are not unusual, and > > these are higher when there's swap than after it has been removed. I assume > > this is mostly because of increased IO wait, as this number increases > > significantly in top. > > iowait = CPU (idle) waiting for disk IO > > So iowait means not CPU load, but somehow disk load :) Sorry, yes, I wrote very unclearly here. What I should have written is that the load numbers are fairly high even without swap, when the IO wait figure is pretty small. This is presumably normal CPU load from the guests. The load average rises significantly when swap is added, but I think that rise is due to an increase in processes waiting for IO (io wait %age increases considerably) rather than extra CPU work. Presumably this is the IO from swapping. Cheers, Chris. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/