From owner-freebsd-xen@FreeBSD.ORG Thu Jan 30 14:10:46 2014 Return-Path: Delivered-To: freebsd-xen@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2A027C68 for ; Thu, 30 Jan 2014 14:10:46 +0000 (UTC) Received: from mail.tdx.com (mail.tdx.com [62.13.128.18]) by mx1.freebsd.org (Postfix) with ESMTP id E6337104D for ; Thu, 30 Jan 2014 14:10:45 +0000 (UTC) Received: from Mail-PC.tdx.co.uk (storm.tdx.co.uk [62.13.130.251]) (authenticated bits=0) by mail.tdx.com (8.14.3/8.14.3/) with ESMTP id s0UEAh32094977 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Thu, 30 Jan 2014 14:10:44 GMT Date: Thu, 30 Jan 2014 14:10:43 +0000 From: Karl Pielorz To: freebsd-xen@freebsd.org Subject: FreeBSD 10 under XenServer 6.2(SP1) - Higher load average? Message-ID: X-Mailer: Mulberry/4.0.8 (Win32) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-BeenThere: freebsd-xen@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: Discussion of the freebsd port to xen - implementation and usage List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 30 Jan 2014 14:10:46 -0000 I've just installed a couple of FreeBSD 10-R instances on our Xen pool. The load averages on these machines seems to run higher for an idle box, than FreeBSD 9.x did e.g. 10.0-R (amd64 GENERIC): last pid: 4219; load averages: 0.31, 0.23, 0.12 up 0+00:07:45 14:04:08 15 processes: 1 running, 14 sleeping CPU: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 100% idle Mem: 16M Active, 15M Inact, 44M Wired, 20M Buf, 1893M Free Swap: 2046M Total, 2046M Free A 9.2-STABLE (amd64 XENHVM) instance on the same XenServer: last pid: 76440; load averages: 0.00, 0.00, 0.00 up 2+15:07:27 14:05:10 22 processes: 1 running, 21 sleeping CPU: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 100% idle Mem: 13M Active, 128M Inact, 91M Wired, 59M Buf, 237M Free Swap: 494M Total, 494M Free Both have xe-guest-utilities installed. The second box is actually technically busier than the first (as it's routing traffic between it's interfaces - admittedly, not much). But the load average on 10.0-R never settles to zero (like it did for 9.x) Just a bit confused as to if the user, nice, system and interrupt times are zero - how can the LA be >0? Anyone else noticed this? - I know an LA of 0.31 isn't the end of the world - but it's a bit of a jump on 0.00... -Karl