From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753702AbcAIK51 (ORCPT ); Sat, 9 Jan 2016 05:57:27 -0500 Received: from mail-wm0-f53.google.com ([74.125.82.53]:35305 "EHLO mail-wm0-f53.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752398AbcAIK5Z (ORCPT ); Sat, 9 Jan 2016 05:57:25 -0500 Date: Sat, 9 Jan 2016 11:57:21 +0100 From: "Steinar H. Gunderson" To: Lingzhu Xiang Cc: Greg Kroah-Hartman , linux-usb@vger.kernel.org, linux-kernel@vger.kernel.org, Alan Stern Subject: Re: [PATCH v2] Add support for usbfs zerocopy. Message-ID: <20160109105717.GB23584@imap.gmail.com> References: <20160106001143.GA1171@kroah.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jan 08, 2016 at 11:00:54PM -0500, Lingzhu Xiang wrote: > Extended testing over one hour shows significant improved CPU usage > and stability: > The old CPU usage is about 12% +/- 5%. The new CPU usage is 4% +/- 1%. > > The setup is an i7-4600U laptop running Kinect v2 with 260MB/s > isochronous and 20MB/s bulk transfers. > > The improvement in reducing jitter is particularly preferable to > Kinect v2 driver because the isochronous data is structured and one > packet lost means discarding a lot of data. Thanks for testing this! It's not unexpected, but it's good to see others are also seeing performance improvements. /* Steinar */ -- Software Engineer, Google Switzerland