From: Frederic Weisbecker <fweisbec@gmail.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: LKML <linux-kernel@vger.kernel.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Paul Mackerras <paulus@samba.org>,
Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>,
Ingo Molnar <mingo@elte.hu>,
Masami Hiramatsu <mhiramat@redhat.com>,
Tom Zanussi <tzanussi@gmail.com>
Subject: [PATCH 8/9] perf: Add a perf trace option to check samples ordering reliability
Date: Sat, 24 Apr 2010 04:05:41 +0200 [thread overview]
Message-ID: <1272074742-3654-9-git-send-regression-fweisbec@gmail.com> (raw)
In-Reply-To: <1272074742-3654-1-git-send-regression-fweisbec@gmail.com>
To ensure sample events time reordering is reliable, add a -d option
to perf trace to check that automatically.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
---
tools/perf/builtin-trace.c | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1d034f6..77f556f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -11,6 +11,8 @@
static char const *script_name;
static char const *generate_script_lang;
+static bool debug_ordering;
+static u64 last_timestamp;
static int default_start_script(const char *script __unused,
int argc __unused,
@@ -87,6 +89,14 @@ static int process_sample_event(event_t *event, struct perf_session *session)
}
if (session->sample_type & PERF_SAMPLE_RAW) {
+ if (debug_ordering) {
+ if (data.time < last_timestamp) {
+ pr_err("Samples misordered, previous: %llu "
+ "this: %llu\n", last_timestamp,
+ data.time);
+ }
+ last_timestamp = data.time;
+ }
/*
* FIXME: better resolve from pid from the struct trace_entry
* field, although it should be the same than this perf
@@ -532,6 +542,8 @@ static const struct option options[] = {
"generate perf-trace.xx script in specified language"),
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
+ OPT_BOOLEAN('d', "debug-ordering", &debug_ordering,
+ "check that samples time ordering is monotonic"),
OPT_END()
};
--
1.6.2.3
next prev parent reply other threads:[~2010-04-24 2:06 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-24 2:05 [GIT PULL] perf tools updates Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 1/9] perf lock: Fix state machine to recognize lock sequence Frederic Weisbecker
2010-04-24 10:43 ` [PATCH] perf lock: add "info" subcommand for dumping misc information Hitoshi Mitake
2010-04-24 10:46 ` Hitoshi Mitake
2010-04-24 10:46 ` [PATCH v2] " Hitoshi Mitake
2010-04-24 13:41 ` Frederic Weisbecker
2010-04-30 18:49 ` Frederic Weisbecker
2010-05-03 5:11 ` Hitoshi Mitake
2010-05-03 5:12 ` [PATCH v3] " Hitoshi Mitake
2010-05-05 21:10 ` Frederic Weisbecker
2010-05-06 9:31 ` Hitoshi Mitake
2010-05-06 9:32 ` [PATCH] perf lock: track only specified threads Hitoshi Mitake
2010-05-07 0:49 ` Frederic Weisbecker
2010-05-08 8:02 ` Hitoshi Mitake
2010-05-08 8:10 ` [PATCH] perf lock: Drop "-a" option from set of default arguments to cmd_record() Hitoshi Mitake
2010-05-08 16:14 ` Frederic Weisbecker
2010-05-09 14:53 ` Hitoshi Mitake
2010-05-11 6:48 ` Frederic Weisbecker
2010-05-12 10:23 ` Hitoshi Mitake
2010-05-12 15:51 ` Frederic Weisbecker
2010-05-15 8:54 ` Hitoshi Mitake
2010-05-10 7:19 ` [tip:perf/core] perf lock: Add "info" subcommand for dumping misc information tip-bot for Hitoshi Mitake
2010-04-24 2:05 ` [PATCH 2/9] perf: Fix initialization bug in parse_single_tracepoint_event() Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 3/9] perf: Generalize perf lock's sample event reordering to the session layer Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 4/9] perf: Use generic sample reordering in perf sched Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 5/9] perf: Use generic sample reordering in perf kmem Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 6/9] perf: Use generic sample reordering in perf trace Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 7/9] perf: Use generic sample reordering in perf timechart Frederic Weisbecker
2010-04-24 2:05 ` Frederic Weisbecker [this message]
2010-04-24 16:13 ` [PATCH 8/9] perf: Add a perf trace option to check samples ordering reliability Masami Hiramatsu
2010-04-25 18:08 ` Frederic Weisbecker
2010-04-24 2:05 ` [PATCH 9/9] perf: Some perf-kvm documentation edits Frederic Weisbecker
2010-04-24 2:27 ` [GIT PULL] perf tools updates Frederic Weisbecker
2010-04-27 9:15 ` 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=1272074742-3654-9-git-send-regression-fweisbec@gmail.com \
--to=fweisbec@gmail.com \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mhiramat@redhat.com \
--cc=mingo@elte.hu \
--cc=mitake@dcl.info.waseda.ac.jp \
--cc=paulus@samba.org \
--cc=tzanussi@gmail.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;
as well as URLs for NNTP newsgroup(s).