From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesper Dangaard Brouer Subject: Blogpost: Explaining why I do PPS measurement with 64 bytes Date: Thu, 11 Sep 2014 11:18:07 +0200 Message-ID: <20140911111807.754b7336@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: brouer@redhat.com To: "netdev@vger.kernel.org" Return-path: Received: from mx1.redhat.com ([209.132.183.28]:38269 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753131AbaIKJSK (ORCPT ); Thu, 11 Sep 2014 05:18:10 -0400 Received: from int-mx11.intmail.prod.int.phx2.redhat.com (int-mx11.intmail.prod.int.phx2.redhat.com [10.5.11.24]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id s8B9I9Z8031048 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=FAIL) for ; Thu, 11 Sep 2014 05:18:09 -0400 Sender: netdev-owner@vger.kernel.org List-ID: People generally seem to have a hardtime understanding why I'm using 64byte packets and measuring PPS, when tuning the network stack. People keep telling me this is artificial benchmarking, which is true, but there is another reason behind these measurements. Which I have described in this blogpost: http://netoptimizer.blogspot.dk/2014/09/packet-per-sec-measurements-for.html I'm basically leveraging the PPS measurements to deduct the nanosec improvements I'm making to the code. -- Best regards, Jesper Dangaard Brouer MSc.CS, Sr. Network Kernel Developer at Red Hat Author of http://www.iptv-analyzer.org LinkedIn: http://www.linkedin.com/in/brouer