mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>, Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Stephane Eranian <eranian@google.com>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>
Subject: [PATCH 7/7] perf inject: Remove stale build-id processing
Date: Wed, 23 Sep 2020 17:05:37 +0900	[thread overview]
Message-ID: <20200923080537.155264-8-namhyung@kernel.org> (raw)
In-Reply-To: <20200923080537.155264-1-namhyung@kernel.org>

I think we don't need to call build_id__mark_dso_hit() in the
perf_event__repipe_sample() as it's not used by -b option.  In case of
the -b option is used, it uses perf_event__inject_buildid() instead.
This can remove unnecessary overhead of finding thread/map for each
sample event.

Also I suspect HEADER_BUILD_ID feature bit setting since we already
generated/injected BUILD_ID event into the output stream.  So this
header information seems redundant.  I'm not 100% sure about the
auxtrace usage, but it looks like not related to this directly.

And we now have --buildid-all so users can get the same behavior if
they want.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-inject.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 500428aaa576..0191d72be7c4 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -277,8 +277,6 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 		return f(tool, event, sample, evsel, machine);
 	}
 
-	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
-
 	if (inject->itrace_synth_opts.set && sample->aux_sample.size)
 		event = perf_inject__cut_auxtrace_sample(inject, event, sample);
 
@@ -767,16 +765,6 @@ static int __cmd_inject(struct perf_inject *inject)
 		return ret;
 
 	if (!data_out->is_pipe) {
-		if (inject->build_ids)
-			perf_header__set_feat(&session->header,
-					      HEADER_BUILD_ID);
-		/*
-		 * Keep all buildids when there is unprocessed AUX data because
-		 * it is not known which ones the AUX trace hits.
-		 */
-		if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
-		    inject->have_auxtrace && !inject->itrace_synth_opts.set)
-			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag and
-- 
2.28.0.681.g6f77f65b4e-goog


  parent reply	other threads:[~2020-09-23  8:06 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-23  8:05 [PATCHSET v2 0/7] perf inject: Speed build-id injection Namhyung Kim
2020-09-23  8:05 ` [PATCH 1/7] perf bench: Add build-id injection benchmark Namhyung Kim
2020-09-23 22:13   ` Ian Rogers
2020-09-24  6:23     ` Namhyung Kim
2020-09-23  8:05 ` [PATCH 2/7] perf inject: Add missing callbacks in perf_tool Namhyung Kim
2020-09-23  8:05 ` [PATCH 3/7] perf inject: Enter namespace when reading build-id Namhyung Kim
2020-09-23  8:05 ` [PATCH 4/7] perf inject: Do not load map/dso when injecting build-id Namhyung Kim
2020-09-24 13:09   ` Jiri Olsa
2020-09-24 13:20     ` Namhyung Kim
2020-09-24 13:44       ` Jiri Olsa
2020-09-24 14:46         ` Namhyung Kim
2020-09-25 14:26           ` Jiri Olsa
2020-09-28 12:31             ` Arnaldo Carvalho de Melo
2020-09-23  8:05 ` [PATCH 5/7] perf inject: Add --buildid-all option Namhyung Kim
2020-09-23 22:16   ` Ian Rogers
2020-09-23  8:05 ` [PATCH 6/7] perf bench: Run inject-build-id with --buildid-all option too Namhyung Kim
2020-09-23 22:17   ` Ian Rogers
2020-09-23  8:05 ` Namhyung Kim [this message]
2020-09-23 14:36   ` [PATCH 7/7] perf inject: Remove stale build-id processing Adrian Hunter
2020-09-24  3:51     ` Namhyung Kim
2020-09-24 13:33   ` Jiri Olsa
2020-09-24 14:23     ` Namhyung Kim
2020-09-24 13:35 ` [PATCHSET v2 0/7] perf inject: Speed build-id injection Jiri Olsa

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=20200923080537.155264-8-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@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

all inboxes | Powered by JetHome®