From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx1.redhat.com (ext-mx13.extmail.prod.ext.phx2.redhat.com [10.5.110.18]) by int-mx12.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id r93JVjqG021471 for ; Thu, 3 Oct 2013 15:31:45 -0400 Received: from Ishtar.tlinx.org (ishtar.tlinx.org [173.164.175.65]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id r93JViCs029375 for ; Thu, 3 Oct 2013 15:31:44 -0400 Received: from [192.168.4.12] (Athenae [192.168.4.12]) by Ishtar.tlinx.org (8.14.7/8.14.4/SuSE Linux 0.8) with ESMTP id r93JVf3Z093062 for ; Thu, 3 Oct 2013 12:31:43 -0700 Message-ID: <524DC61D.9060704@tlinx.org> Date: Thu, 03 Oct 2013 12:31:41 -0700 From: "Linda A. Walsh" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [linux-lvm] I/O accounting by partition: "-cow" & "-real" map to base or snapshot or ??? Reply-To: LVM general discussion and development List-Id: LVM general discussion and development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , List-Id: Content-Type: text/plain; charset="us-ascii"; format="flowed" To: LVM general discussion and development I'm trying to display I/O data from /proc/diskstats for regular, non-thin partitions, by lv_name. "-cow" and "-real" bit confusing. When I look at the output of "dmsetup ls" different minor devs for: name minor Home-real 2 Home 3 Home-snapshot 5 Home-snapshot-cow 26 (snapshot=date+time snapshot was started) I regularly see I/O on 'Home' & 'Home-real'. write = "dd if=/dev/zero of=1G bs=1G count=1 oflag=direct" A 1G write to Home shows 2GB I/O on 2 partitions: Home: 1G read Home-real: 1G read Is this being double reported? (i.e. I should ignore one?) Confusing is that they don't always show the same amount of I/O. A write to the same filename again showed 4GB I/O on 3 partitions: Home: 1G read + 1G write Home-real: 1G write Home-snap-cow: 1G write Is there some read is copying off the first copy to the "cow" partition? (with a 1G duplication somewhere?). If I "overwrite" (dd if=/dev/zero of=1G bs=1G count=1 oflag=direct conv=nocreat) I see the same numbers as on the initial file creation (to both base and the "-real" partitions). Could anyone clarify what's going on in the above scenarios? (i.e. I would find each write being multiplied by 2 a bit far fetched in terms of disk-BW; Multiplied by 4... even less likely I'd think...? Thanks for any light-shed...;-)