[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87397035dn.fsf@sejong.aot.lge.com>
Date: Wed, 16 May 2012 17:19:16 +0900
From: Namhyung Kim <namhyung.kim@....com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...nel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Arnaldo Carvalho de Melo <acme@...radead.org>,
linux-kernel@...r.kernel.org,
Arjan van de Ven <arjan@...radead.org>,
David Ahern <dsahern@...il.com>,
Frederic Weisbecker <fweisbec@...il.com>,
Mike Galbraith <efault@....de>,
Paul Mackerras <paulus@...ba.org>,
Stephane Eranian <eranian@...gle.com>, arnaldo.melo@...il.com,
Arnaldo Carvalho de Melo <acme@...hat.com>
Subject: Re: [GIT PULL 0/8] Annotation weekly ponies delivery
Hi,
On Wed, 16 May 2012 14:57:49 +0900, Namhyung Kim wrote:
> Hmm.. but it seems this breaks my 'perf stat -g' - it doesn't
> respond any more (even for ^C):
>
I've found that it's a problem of whole perf stat, not only for -g
option. It's because the perf stat should use per-task events for some
reason as it's not use mmap on the events.
The commit 77a6f014e9ae ("perf stat: Use perf_evlist__create_maps")
introduced the issue and it seems following patch works well for me:
---[ cut here ]---
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d19058a7b84c..185e59a4715d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -754,6 +754,9 @@ static struct perf_record record = {
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 1000,
+ .target = {
+ .need_mmap = true,
+ },
},
.write_mode = WRITE_FORCE,
.file_new = true,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 553560a8b1be..ebcd15883ab8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1162,6 +1162,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
.freq = 1000, /* 1 KHz */
.mmap_pages = 128,
.sym_pcnt_filter = 5,
+ .target = {
+ .need_mmap = true,
+ },
};
char callchain_default_opt[] = "fractal,0.5,callee";
const struct option options[] = {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 87889f325678..ba43c3a4046c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -611,6 +611,8 @@ int perf_evlist__create_maps(struct perf_evlist *evlist,
if (perf_target__has_task(target))
evlist->cpus = cpu_map__dummy_new();
+ else if (!perf_target__has_cpu(target) && !target->need_mmap)
+ evlist->cpus = cpu_map__dummy_new();
else
evlist->cpus = cpu_map__new(target->cpu_list);
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index c43f632955fa..ffa247d3ede3 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -11,6 +11,7 @@ struct perf_target {
const char *uid_str;
uid_t uid;
bool system_wide;
+ bool need_mmap;
};
enum perf_target_errno {
--
Thanks,
Namhyung
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists