From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Ahern Subject: Re: Scaling 'ip addr add' (was Re: What's the right way to use a *large* number of source addresses?) Date: Thu, 29 May 2014 10:19:40 -0600 Message-ID: <53875E1C.2040708@gmail.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Jamal Hadi Salim , Eric Dumazet , =?UTF-8?B?TmllbHMgTcO2bGxlcg==?= , netdev , Jonas Bonn To: sowmini varadhan , Julian Anastasov Return-path: Received: from mail-pa0-f49.google.com ([209.85.220.49]:60927 "EHLO mail-pa0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757778AbaE2QTn (ORCPT ); Thu, 29 May 2014 12:19:43 -0400 Received: by mail-pa0-f49.google.com with SMTP id kp14so610915pab.22 for ; Thu, 29 May 2014 09:19:43 -0700 (PDT) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On 5/29/14, 10:11 AM, sowmini varadhan wrote: > I'm still not sure I understand*why* check_lifetime ends > up being expensive, though. For this particular test, all the ... > > fib_sync_up() could also use a magnifying glass - was going to > look at this later. Annotation feature of perf should help perf record -ga -- 'perf report' with a TUI and then hit 'a' for annotation mode or use 'perf annotate -k vmlinux -s ' David