From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx3.redhat.com (mx3.redhat.com [172.16.48.32]) by int-mx1.corp.redhat.com (8.13.1/8.13.1) with ESMTP id kAG2t2Ru020842 for ; Wed, 15 Nov 2006 21:55:02 -0500 Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.191]) by mx3.redhat.com (8.13.1/8.13.1) with ESMTP id kAG2sYl3009837 for ; Wed, 15 Nov 2006 21:54:54 -0500 Received: by nf-out-0910.google.com with SMTP id l36so868006nfa for ; Wed, 15 Nov 2006 18:54:54 -0800 (PST) Message-ID: <170fa0d20611151854m4bc49ed6qc696e82f83417e7@mail.gmail.com> Date: Wed, 15 Nov 2006 21:54:54 -0500 From: "Mike Snitzer" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: [linux-lvm] walltime of pvs vs pvdisplay with 256 PVs 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: linux-lvm@redhat.com I have a testbed with 256 PVs. Running 'pvdisplay -c' takes .672 sec. Running 'pvs' takes 43sec! I've tried this on RHEL4U3 (lvm2-2.02.01-1.3.RHEL4) and RHEL4U4 (lvm2-2.02.06-6.0.RHEL4). lvm2 from U4 is actually slower than U3 on this issue (1m vs 43s). With RHEL4U3, pvs -vvvvv shows that a single device gets opened 264 times yet pvdisplay -c -vvvvv only opens a single device 8 times. With RHEL4U4, there are 261 opens for pvs and 5 opens for pvdisplay -c. Clearly there is something flawed in the pvs algorithm. I can dig deeper but I wanted to put this info out there in case others might have some insight. please advise, thanks. Mike