public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	lkml <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Michael Petlan <mpetlan@redhat.com>,
	Joe Mario <jmario@redhat.com>, Kajol Jain <kjain@linux.ibm.com>
Subject: Re: [RFC 0/3] perf tools: Add support for used defined metric
Date: Thu, 12 Dec 2019 10:37:00 +0100	[thread overview]
Message-ID: <20191212093700.GD22550@krava> (raw)
In-Reply-To: <20191211230126.GC862919@tassilo.jf.intel.com>

On Wed, Dec 11, 2019 at 03:01:26PM -0800, Andi Kleen wrote:
> On Wed, Dec 11, 2019 at 11:47:57PM +0100, Jiri Olsa wrote:
> > hi,
> > Joe asked for possibility to add user defined metrics. Given that
> > we already have metrics support, I added --metric option that allows
> > to specify metric on the command line, like:
> > 
> >   # perf stat  --metric 'DECODED_ICACHE_UOPS% = 100 * (idq.dsb_uops / \
> >     (idq.ms_uops + idq.mite_uops + idq.dsb_uops + lsd.uops))' ...
> > 
> > The code facilitates the current metric code, and I was surprised
> > how easy it was, so I'm not sure I omitted something ;-)
> 
> There are some asserts you can hit, like for too many events.
> 
> Also some of the syntax (e.g. using @ instead of / and escapes) are
> not super user friendly.
> 
> Other than that it should be ok.
> 
> Of course it would be better to put it into a file,
> and then support comments etc.

should be also reasonable easy, redirecting the input for lex

> 
> I've been considering some extensions to perf to support @file
> reading with comment support.
> 
> Right now there are some very odd bugs when you do that, lie
> 
> -e 'event,<newline>
> event,<newline>
> event...'
> 
> adds the newline to the event name, which breaks the output formats.

should be possible to ignore new lines at some point no?

jirka


      reply	other threads:[~2019-12-12  9:37 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-11 22:47 [RFC 0/3] perf tools: Add support for used defined metric Jiri Olsa
2019-12-11 22:47 ` [PATCH 1/3] perf tools: Factor metric addition into add_metric function Jiri Olsa
2019-12-11 22:47 ` [PATCH 2/3] perf tools: Factor metric setup code into metricgroup__setup function Jiri Olsa
2019-12-11 22:48 ` [PATCH 3/3] perf stat: Add --metric option Jiri Olsa
2019-12-11 23:02   ` Andi Kleen
2019-12-12  9:41     ` Jiri Olsa
2019-12-11 23:01 ` [RFC 0/3] perf tools: Add support for used defined metric Andi Kleen
2019-12-12  9:37   ` Jiri Olsa [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191212093700.GD22550@krava \
    --to=jolsa@redhat.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=jmario@redhat.com \
    --cc=jolsa@kernel.org \
    --cc=kjain@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=mpetlan@redhat.com \
    --cc=namhyung@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox