From: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
To: Andrey Wagin <avagin@gmail.com>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@redhat.com>
Subject: Re: [PATCH 2/3] perf: teach perf inject to merge sched_stat_* and sched_switch events
Date: Mon, 6 Aug 2012 19:00:00 -0300 [thread overview]
Message-ID: <20120806220000.GH21441@infradead.org> (raw)
In-Reply-To: <CANaxB-xq_wDGZQ16nTD6agwc_JiE4dQe1fXmvmPZckAX0EVr9w@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 885 bytes --]
Em Mon, Aug 06, 2012 at 11:43:04PM +0400, Andrey Wagin escreveu:
> 2012/8/6 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>:
> >> +struct perf_session *session;
>
> perf_event__sched_stat (perf_inject.sample) uses "session" for getting
> an event name. I don't know how to get it by another way
Can you try with the attached patch? We already lookup the event_format
entries when we read the perf.data header so that we can cache
evsel->name, we might as well cache the event_format in
evsel->tp_format, so that tools don't have to relookup this for each
sample.
It would look like:
static int perf_event__sched_stat(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
int type;
struct event_format *e = evsel->tp_format;
const char *evname = e->name;
- Arnaldo
[-- Attachment #2: a.patch --]
[-- Type: text/plain, Size: 660 bytes --]
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b559929..a56c457 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -56,6 +56,7 @@ struct perf_evsel {
int ids;
struct hists hists;
char *name;
+ struct event_format *tp_format;
union {
void *priv;
off_t id_offset;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 24c489b..5b328a4 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2126,6 +2126,7 @@ static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel,
if (event->name == NULL)
return -1;
+ evsel->tp_format = event;
return 0;
}
next prev parent reply other threads:[~2012-08-06 22:00 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-06 10:01 [PATCH 0/3] perf: Teach perf tool to profile sleep times Andrew Vagin
2012-08-06 10:01 ` [PATCH 1/3] perf: teach "perf inject" to work with files Andrew Vagin
2012-08-06 18:12 ` Arnaldo Carvalho de Melo
2012-08-06 10:01 ` [PATCH 2/3] perf: teach perf inject to merge sched_stat_* and sched_switch events Andrew Vagin
2012-08-06 18:19 ` Arnaldo Carvalho de Melo
2012-08-06 19:43 ` Andrey Wagin
2012-08-06 22:00 ` Arnaldo Carvalho de Melo [this message]
2012-08-06 23:31 ` Arnaldo Carvalho de Melo
2012-08-13 9:17 ` Ingo Molnar
2012-08-06 10:01 ` [PATCH 3/3] perf: mark a dso if it's used Andrew Vagin
2012-08-06 18:14 ` Arnaldo Carvalho de Melo
2012-08-06 19:50 ` Andrey Wagin
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=20120806220000.GH21441@infradead.org \
--to=acme@ghostprotocols.net \
--cc=a.p.zijlstra@chello.nl \
--cc=avagin@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=paulus@samba.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®