linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
To: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	linux-kernel@vger.kernel.org,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Jiri Olsa <jolsa@redhat.com>, Mike Galbraith <efault@gmx.de>,
	Namhyung Kim <namhyung@gmail.com>,
	Paul Mackerras <paulus@samba.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Stephane Eranian <eranian@google.com>
Subject: Re: [PATCH 02/25] perf top: Delete maps on exit
Date: Thu, 31 Jan 2013 16:05:58 -0300	[thread overview]
Message-ID: <20130131190558.GJ7651@ghostprotocols.net> (raw)
In-Reply-To: <510AB468.8020904@gmail.com>

Em Thu, Jan 31, 2013 at 11:14:00AM -0700, David Ahern escreveu:
> On 1/31/13 10:25 AM, Arnaldo Carvalho de Melo wrote:
> >Removing one more memory leak found with valgrind.

> If you are spending time one memory consumption by perf-top one thing

Those are the low hanging fruits :-)

> to look at is handling of terminated threads. Currently, terminated
> threads are stuck onto the dead_threads list and only cleaned up when
> perf terminates (perf_session__delete_dead_threads).

We need to have a refcount to know how many hist_entry instances point
to threads, once that refcount hits zero, because all symbols for such
thread have been decayed to zero samples and thus will be deleted and
removed from its hists struct, then we can remove it from dead_threads
list and delete it for good.

Ditto for dsos, etc.
 
> Since the thread entries can still be referenced in hists perhaps a
> refcnt is needed that indicates when the threads can be deleted.

Yeah, wrote the above before reading this 8-)

> From there regular calls to perf_session__delete_dead_threads can be
> made. I needed to add a regular call to that function in my perf
> daemon to keep memory usage stable - but then I don't have lingering
> references.
> 
> A lot of work yes but will be needed if there is to be an official
> libperf.so that apps can leverage.

Right, I just added this to the TODO list in the perf wiki at:

https://perf.wiki.kernel.org/index.php/Todo

Thanks,

- Arnaldo

  reply	other threads:[~2013-01-31 19:06 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-01-31 17:25 [GIT PULL 00/25] perf/core improvements and fixes Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 01/25] perf top: Stop using exit() Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 02/25] perf top: Delete maps on exit Arnaldo Carvalho de Melo
2013-01-31 18:14   ` David Ahern
2013-01-31 19:05     ` Arnaldo Carvalho de Melo [this message]
2013-01-31 17:25 ` [PATCH 03/25] perf tools: Keep group information Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 04/25] perf tests: Add group test conditions Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 05/25] perf header: Add HEADER_GROUP_DESC feature Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 06/25] perf report: Make another loop for linking group hists Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 07/25] perf hists: Resort hist entries using group members for output Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 08/25] perf ui/hist: Consolidate hpp helpers Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 09/25] perf hists browser: Convert hpp helpers to a function Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 10/25] perf gtk/browser: " Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 11/25] perf ui/hist: Add support for event group view Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 12/25] perf hists browser: Move coloring logic to hpp functions Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 13/25] perf hists browser: Add suppport for event group view Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 14/25] perf gtk/browser: Add support " Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 15/25] perf gtk/browser: Trim column header string when event group enabled Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 16/25] perf report: Bypass non-leader events when event group is enabled Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 17/25] perf report: Show group description " Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 18/25] perf report: Add --group option Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 19/25] perf report: Add report.group config option Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 20/25] perf evlist: Add --group option Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 21/25] perf/Power7: Use macros to identify perf events Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 22/25] perf: Make EVENT_ATTR global Arnaldo Carvalho de Melo
2013-02-01 10:26   ` Ingo Molnar
2013-01-31 17:25 ` [PATCH 23/25] perf/POWER7: Make generic event translations available in sysfs Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 24/25] perf/POWER7: Make some POWER7 events " Arnaldo Carvalho de Melo
2013-01-31 17:25 ` [PATCH 25/25] perf: Document the ABI of perf sysfs entries Arnaldo Carvalho de Melo
2013-02-01 10:18 ` [GIT PULL 00/25] perf/core improvements and fixes Ingo Molnar

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=20130131190558.GJ7651@ghostprotocols.net \
    --to=acme@ghostprotocols.net \
    --cc=dsahern@gmail.com \
    --cc=efault@gmx.de \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@gmail.com \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.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;
as well as URLs for NNTP newsgroup(s).