From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dmitry Ivanov Subject: IO monitoring of dm devices with iostat Date: Mon, 11 Jan 2010 13:50:11 +0300 Message-ID: <4B4B0263.4030308@vtsystems.com> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: device-mapper development List-Id: dm-devel.ids Hello! Can you help me with iostat monitoring of /dev/dm-* and /dev/sd* devices. Main question is about understanding of tps value. For example /dev/dm-5 is a dm-mapper-device based on /dev/sde and /dev/sdc. tps value of dm-5 is 30% bigger than sde+sdf. According to stats from storage, right TPS io value is sde+sdf. Why /dev/dm* values differ while other columns are the same? How to treat this numbers? Thank you! avg-cpu: %user %nice %system %iowait %steal %idle 0.16 0.00 0.08 0.02 0.00 99.73 Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn sda 0.50 0.00 0.01 0 0 sda1 0.00 0.00 0.00 0 0 sda2 0.50 0.00 0.01 0 0 sdb 0.00 0.00 0.00 0 0 sdb1 0.00 0.00 0.00 0 0 sdc 0.43 0.00 0.01 0 0 sdc1 0.00 0.00 0.00 0 0 sdc2 0.43 0.00 0.01 0 0 sdd 0.00 0.00 0.00 0 0 sdd1 0.00 0.00 0.00 0 0 sde 38.00 0.00 0.25 0 7 sde1 38.00 0.00 0.25 0 7 sdf 38.50 0.00 0.25 0 7 sdf1 38.50 0.00 0.25 0 7 dm-0 3.70 0.00 0.01 0 0 dm-1 0.00 0.00 0.00 0 0 dm-2 3.70 0.00 0.01 0 0 dm-3 3.70 0.00 0.01 0 0 dm-4 0.00 0.00 0.00 0 0 dm-5 126.43 0.00 0.49 0 14 dm-6 126.43 0.00 0.49 0 14 dm-7 0.00 0.00 0.00 0 0 dm-8 0.00 0.00 0.00 0 0 --