From: Eric Whitney Subject: 2.6.39 and 3.0 scalability measurement results Date: Sun, 31 Jul 2011 22:57:52 -0400 Message-ID: <4E361630.9060907@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: Ext4 Developers List Return-path: Received: from g5t0006.atlanta.hp.com ([15.192.0.43]:10058 "EHLO g5t0006.atlanta.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753297Ab1HADDI (ORCPT ); Sun, 31 Jul 2011 23:03:08 -0400 Received: from g5t0030.atlanta.hp.com (g5t0030.atlanta.hp.com [16.228.8.142]) by g5t0006.atlanta.hp.com (Postfix) with ESMTP id 11686C0FA for ; Mon, 1 Aug 2011 02:54:26 +0000 (UTC) Received: from ldl (ldl.usa.hp.com [16.125.112.222]) by g5t0030.atlanta.hp.com (Postfix) with ESMTP id DBA5F18085 for ; Mon, 1 Aug 2011 02:54:26 +0000 (UTC) Received: from localhost (ldl.fc.hp.com [127.0.0.1]) by ldl (Postfix) with ESMTP id 99459CF0008 for ; Sun, 31 Jul 2011 20:54:26 -0600 (MDT) Received: from ldl ([127.0.0.1]) by localhost (ldl.fc.hp.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id LKVEz0UaDtAA for ; Sun, 31 Jul 2011 20:54:26 -0600 (MDT) Received: from [192.168.0.12] (squirrel.fc.hp.com [15.11.146.57]) (Authenticated sender: enw@fc.hp.com) by ldl (Postfix) with ESMTPA id 4C804CF0007 for ; Sun, 31 Jul 2011 20:54:26 -0600 (MDT) Sender: linux-ext4-owner@vger.kernel.org List-ID: I've posted the results of my 2.6.38/2.6.39 and 2.6.39/3.0 ext4 scalability measurements and comparisons on a 48 core x86_64 server at: http://free.linux.hp.com/~enw/ext4/2.6.39 http://free.linux.hp.com/~enw/ext4/3.0 The results include throughput and CPU efficiency graphs for five simple workloads, the raw data for same, and lockstats as well. The data cover ext4 filesystems with and without journals. For reference, ext3, xfs, and btrfs are included as well. The 2.6.38/2.6.39 results mainly show the clear scalability benefit of making the mblk_io_submit mount option default behavior for ext4 filesystems with journals - see the large_file_creates throughput plot. In the way of more recent news, the 2.6.39/3.0 results indicate little change for ext4 either with or without journals. Thanks, Eric