From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail138.messagelabs.com (mail138.messagelabs.com [216.82.249.35]) by kanga.kvack.org (Postfix) with SMTP id 8EB3D6B02B0 for ; Fri, 30 Jul 2010 10:15:51 -0400 (EDT) Received: by wyg36 with SMTP id 36so1363038wyg.14 for ; Fri, 30 Jul 2010 07:15:46 -0700 (PDT) Date: Fri, 30 Jul 2010 16:15:53 +0200 From: Frederic Weisbecker Subject: Re: [PATCH 1/6] vmscan: tracing: Roll up of patches currently in mmotm Message-ID: <20100730141552.GC5269@nowhere> References: <1280497020-22816-1-git-send-email-mel@csn.ul.ie> <1280497020-22816-2-git-send-email-mel@csn.ul.ie> <20100730140441.GB5269@nowhere> <20100730141217.GG3571@csn.ul.ie> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100730141217.GG3571@csn.ul.ie> Sender: owner-linux-mm@kvack.org To: Mel Gorman Cc: Andrew Morton , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, Dave Chinner , Chris Mason , Nick Piggin , Rik van Riel , Johannes Weiner , Christoph Hellwig , Wu Fengguang , KAMEZAWA Hiroyuki , KOSAKI Motohiro , Andrea Arcangeli List-ID: On Fri, Jul 30, 2010 at 03:12:18PM +0100, Mel Gorman wrote: > On Fri, Jul 30, 2010 at 04:04:42PM +0200, Frederic Weisbecker wrote: > > On Fri, Jul 30, 2010 at 02:36:55PM +0100, Mel Gorman wrote: > > > This is a roll-up of patches currently in mmotm related to stack reduction and > > > tracing reclaim. It is based on 2.6.35-rc6 and included for the convenience > > > of testing. > > > > > > No signed off required. > > > --- > > > .../trace/postprocess/trace-vmscan-postprocess.pl | 654 ++++++++++++++++++++ > > > > I have the feeling you've made an ad-hoc post processing script that seems > > to rewrite all the format parsing, debugfs, stream handling, etc... we > > have that in perf tools already. > > > > It's an hoc adaption of trace-pagealloc-postprocess.pl which was developed > before the perf scripting report. It's a bit klunky. > > > May be you weren't aware of what we have in perf in terms of scripting support. > > > > I'm aware, I just haven't gotten around to adapting what the script does > to the perf scripting support. The existance of the script I have means > people can reproduce my results without having to wait for me to rewrite > the post-processing scripts for perf. > > > First, launch perf list and spot the events you're interested in, let's > > say you're interested in irqs: > > > > $ perf list > > [...] > > irq:irq_handler_entry [Tracepoint event] > > irq:irq_handler_exit [Tracepoint event] > > irq:softirq_entry [Tracepoint event] > > irq:softirq_exit [Tracepoint event] > > [...] > > > > Now do a trace record: > > > > # perf record -e irq:irq_handler_entry -e irq:irq_handler_exit -e irq:softirq_entry -e irq:softirq_exit cmd > > > > or more simple: > > > > # perf record -e irq:* cmd > > > > You can use -a instead of cmd for wide tracing. > > > > Now generate a perf parsing script on top of these traces: > > > > # perf trace -g perl > > generated Perl script: perf-trace.pl > > > > Fill up the trace handlers inside perf-trace.pl and just run it: > > > > # perf trace -s perf-trace.pl > > > > Once ready, you can place your script in the script directory. > > > > Ultimately, the post-processing scripts should be adapted to perf but it > could be a while before I get around to it. Ok, I thought it was a brand new thing. No problem then. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org