public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ian Rogers <irogers@google.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>,
	Mike Leach <mike.leach@linaro.org>,
	James Clark <james.clark@linaro.org>,
	John Garry <john.g.garry@oracle.com>,
	Will Deacon <will@kernel.org>, Leo Yan <leo.yan@linux.dev>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Charlie Jenkins <charlie@rivosinc.com>,
	Thomas Falcon <thomas.falcon@intel.com>,
	Yicong Yang <yangyicong@hisilicon.com>,
	Thomas Richter <tmricht@linux.ibm.com>,
	Athira Rajeev <atrajeev@linux.ibm.com>,
	Howard Chu <howardchu95@gmail.com>, Song Liu <song@kernel.org>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>,
	Levi Yun <yeoreum.yun@arm.com>,
	Zhongqiu Han <quic_zhonhan@quicinc.com>,
	Blake Jones <blakejones@google.com>,
	Anubhav Shelat <ashelat@redhat.com>,
	Chun-Tse Shao <ctshao@google.com>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	Jean-Philippe Romain <jean-philippe.romain@foss.st.com>,
	Gautam Menghani <gautam@linux.ibm.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	Yang Li <yang.lee@linux.alibaba.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Andi Kleen <ak@linux.intel.com>,
	Weilin Wang <weilin.wang@intel.com>
Subject: Re: [RFC PATCH v1 12/15] perf evlist: Add reference count
Date: Wed, 29 Oct 2025 13:25:14 -0300	[thread overview]
Message-ID: <aQI_6vZUbjhnl4ZJ@x1> (raw)
In-Reply-To: <aQI_OJziRPMRqzM9@x1>

On Wed, Oct 29, 2025 at 01:22:21PM -0300, Arnaldo Carvalho de Melo wrote:
> On Tue, Oct 28, 2025 at 10:34:10PM -0700, Ian Rogers wrote:
> > This a no-op for most of the perf tool. The reference count is set to
> > 1 at allocation, the put will see the 1, decrement it and perform the
> > delete. The purpose for adding the reference count is for the python
> > code. Prior to this change the python code would clone evlists, but
> > this has issues if events are opened, etc. This change adds a
> > reference count for the evlists and a later change will add it to
> > evsels. The combination is needed for the python code to operate
> > correctly (not hit asserts in the evsel clone), but the changes are
> > broken apart for the sake of smaller patches.
 
> Looks ok, noisy for all the s/delete/put/ but that is ok, but then you
> are not using the RC_CHK_ACCESS stuff from the get go, why not?
 
> All the prep patches looks ok, assuming they build in succession.

Also I tried to run the test case before the patches on a 9950x3d, AMD,
with ibs and couldn't, some perf.data format error, then on Intel I had
to hit control+c and got a deprecation warning, both, of course
completely unrelated to your work, so just FYI:

root@five:~# perf mem record -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 2.247 MB perf.data (12814 samples) ]
root@five:~# time perf script mem-phys-addr
/home/acme/libexec/perf-core/scripts/python/mem-phys-addr.py:49: DeprecationWarning: 'maxsplit' is passed as positional argument
  m = re.split('-|:', line, 2)
^CWarning:
929 out of order events recorded.
Event: cpu_core/mem_inst_retired.all_loads/P
Memory type                                    count  percentage
----------------------------------------  ----------  ----------
100000000-8bfbfffff : System RAM              149050        87.4
  2ac600000-2ad75cfff : Kernel rodata           1567         0.9
  2ad800000-2adc6a47f : Kernel data              517         0.3
  2ae7e8000-2aedfffff : Kernel bss               282         0.2
  2ab000000-2ac54d27e : Kernel code               21         0.0
0-fff : Reserved                               18990        11.1
100000-30093fff : System RAM                    2566         1.5

real	11m46.282s
user	0m1.317s
sys	0m0.344s
root@five:~# grep -m1 'model name' /proc/cpuinfo
model name	: Intel(R) Core(TM) i7-14700K
root@five:~# cat /etc/redhat-release
Fedora release 42 (Adams)
root@five:~# uname -a
Linux five 6.16.9-200.fc42.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Sep 25 18:05:50 UTC 2025 x86_64 GNU/Linux
root@five:~#

- Arnaldo

  reply	other threads:[~2025-10-29 16:25 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-29  5:33 [RFC PATCH v1 00/15] Addition of session API to python module Ian Rogers
2025-10-29  5:33 ` [RFC PATCH v1 01/15] perf arch arm: Sort includes and add missed explicit dependencies Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 02/15] perf arch x86: " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 03/15] perf tests: " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 04/15] perf script: " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 05/15] perf util: " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 06/15] perf python: Add " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 07/15] perf evsel/evlist: Avoid unnecessary #includes Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 08/15] perf maps: Move getting debug_file to verbose path Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 09/15] perf data: Clean up use_stdio and structures Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 10/15] perf python: Add wrapper for perf_data file abstraction Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 11/15] perf python: Add python session abstraction wrapping perf's session Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 12/15] perf evlist: Add reference count Ian Rogers
2025-10-29 16:22   ` Arnaldo Carvalho de Melo
2025-10-29 16:25     ` Arnaldo Carvalho de Melo [this message]
2025-10-29 16:56     ` Ian Rogers
2025-10-29 18:33       ` Arnaldo Carvalho de Melo
2025-10-29 21:12         ` Ian Rogers
2025-10-30 13:09           ` Arnaldo Carvalho de Melo
2025-10-29  5:34 ` [RFC PATCH v1 13/15] perf evsel: " Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 14/15] perf python: Add access to evsel and phys_addr in event Ian Rogers
2025-10-29  5:34 ` [RFC PATCH v1 15/15] perf mem-phys-addr.py: Port to standalone application from perf script Ian Rogers

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=aQI_6vZUbjhnl4ZJ@x1 \
    --to=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=ashelat@redhat.com \
    --cc=atrajeev@linux.ibm.com \
    --cc=blakejones@google.com \
    --cc=charlie@rivosinc.com \
    --cc=christophe.leroy@csgroup.eu \
    --cc=ctshao@google.com \
    --cc=dapeng1.mi@linux.intel.com \
    --cc=dvyukov@google.com \
    --cc=gautam@linux.ibm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=howardchu95@gmail.com \
    --cc=irogers@google.com \
    --cc=james.clark@linaro.org \
    --cc=jean-philippe.romain@foss.st.com \
    --cc=john.g.garry@oracle.com \
    --cc=jolsa@kernel.org \
    --cc=leo.yan@linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mike.leach@linaro.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=quic_zhonhan@quicinc.com \
    --cc=song@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=thomas.falcon@intel.com \
    --cc=tmricht@linux.ibm.com \
    --cc=weilin.wang@intel.com \
    --cc=will@kernel.org \
    --cc=yang.lee@linux.alibaba.com \
    --cc=yangyicong@hisilicon.com \
    --cc=yeoreum.yun@arm.com \
    /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