From: Pawel Moll <pawel.moll@arm.com>
To: Stephane Eranian <eranian@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
John Stultz <john.stultz@linaro.org>,
Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>,
"mingo@elte.hu" <mingo@elte.hu>,
Paul Mackerras <paulus@samba.org>,
Anton Blanchard <anton@samba.org>,
Will Deacon <Will.Deacon@arm.com>,
"ak@linux.intel.com" <ak@linux.intel.com>,
Pekka Enberg <penberg@gmail.com>,
Steven Rostedt <rostedt@goodmis.org>,
Robert Richter <robert.richter@amd.com>
Subject: Re: [RFC] perf: need to expose sched_clock to correlate user samples with kernel samples
Date: Thu, 14 Mar 2013 19:57:01 +0000 [thread overview]
Message-ID: <1363291021.3100.144.camel@hornet> (raw)
In-Reply-To: <CABPqkBS4TELhoUGrO+moca2fPUoqGjiYCdHJc=H8CjLomPWWDQ@mail.gmail.com>
On Thu, 2013-03-14 at 15:34 +0000, Stephane Eranian wrote:
> > Well, the timestamps themselves are already exposed to userspace
> > through the ftrace and perf data logs. All people want is to add
> > secondary data stream in the same time-line.
> >
> I agree with Peter on this. The timestamps are already visible.
> All we need is the ability to generate them for another user-level
> level data stream.
Ok, how about the code below? I must say I have some doubts about the
resolution, as there seem to be no generic way of figuring it out for
the sched_clock (the arch/arm/kernel/sched_clock.c is actually
calculating it, but than just prints it out and nothing more).
And, to summarize, we went through 3 ideas:
1. ioctl() - http://article.gmane.org/gmane.linux.kernel/1433933
2. syscall - http://article.gmane.org/gmane.linux.kernel/1437057
3. POSIX clock - below
John also suggested that maybe the perf could use CLOCK_MONOTONIC_RAW
instead of local/sched_clock().
How about a final decision?
Regards
Pawel
8<--------------------
>From c986492d38156f1fc25ab3182f0a494bb13389ce Mon Sep 17 00:00:00 2001
From: Pawel Moll <pawel.moll@arm.com>
Date: Thu, 14 Mar 2013 19:49:09 +0000
Subject: [PATCH] perf: POSIX CLOCK_PERF to report current time value
To co-relate user space events with the perf events stream
a current (as in: "what time(stamp) is it now?") time value
must be made available.
This patch adds a POSIX clock returning the perf_clock()
value and accesible from userspace:
#include <time.h>
struct timespec ts;
clock_gettime(CLOCK_PERF, &ts);
Signed-off-by: Pawel Moll <pawel.moll@arm.com>
---
include/uapi/linux/time.h | 1 +
kernel/events/core.c | 20 ++++++++++++++++++++
2 files changed, 21 insertions(+)
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index 0d3c0ed..cea16b0 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -54,6 +54,7 @@ struct itimerval {
#define CLOCK_BOOTTIME 7
#define CLOCK_REALTIME_ALARM 8
#define CLOCK_BOOTTIME_ALARM 9
+#define CLOCK_PERF 10
/*
* The IDs of various hardware clocks:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0cd865..81ca459 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -37,6 +37,7 @@
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
+#include <linux/posix-timers.h>
#include "internal.h"
@@ -209,6 +210,19 @@ static inline u64 perf_clock(void)
return local_clock();
}
+static int perf_posix_clock_getres(const clockid_t which_clock,
+ struct timespec *tp)
+{
+ *tp = ns_to_timespec(TICK_NSEC);
+ return 0;
+}
+
+static int perf_posix_clock_get(clockid_t which_clock, struct timespec *tp)
+{
+ *tp = ns_to_timespec(perf_clock());
+ return 0;
+}
+
static inline struct perf_cpu_context *
__get_cpu_context(struct perf_event_context *ctx)
{
@@ -7391,6 +7405,10 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
void __init perf_event_init(void)
{
+ struct k_clock perf_posix_clock = {
+ .clock_getres = perf_posix_clock_getres,
+ .clock_get = perf_posix_clock_get,
+ };
int ret;
idr_init(&pmu_idr);
@@ -7407,6 +7425,8 @@ void __init perf_event_init(void)
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
+ posix_timers_register_clock(CLOCK_PERF, &perf_posix_clock);
+
/* do not patch jump label more than once per second */
jump_label_rate_limit(&perf_sched_events, HZ);
--
1.7.10.4
next prev parent reply other threads:[~2013-03-14 19:57 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-16 10:13 [RFC] perf: need to expose sched_clock to correlate user samples with kernel samples Stephane Eranian
2012-10-16 17:23 ` Peter Zijlstra
2012-10-18 19:33 ` Stephane Eranian
2012-11-10 2:04 ` John Stultz
2012-11-11 20:32 ` Stephane Eranian
2012-11-12 18:53 ` John Stultz
2012-11-12 20:54 ` Stephane Eranian
2012-11-12 22:39 ` John Stultz
2012-11-13 20:58 ` Steven Rostedt
2012-11-14 22:26 ` John Stultz
2012-11-14 23:30 ` Steven Rostedt
2013-02-01 14:18 ` Pawel Moll
2013-02-05 21:18 ` David Ahern
2013-02-05 22:13 ` Stephane Eranian
2013-02-05 22:28 ` John Stultz
2013-02-06 1:19 ` Steven Rostedt
2013-02-06 18:17 ` Pawel Moll
2013-02-13 20:00 ` Stephane Eranian
2013-02-14 10:33 ` Pawel Moll
2013-02-18 15:16 ` Stephane Eranian
2013-02-18 18:59 ` David Ahern
2013-02-18 20:35 ` Thomas Gleixner
2013-02-19 18:25 ` John Stultz
2013-02-19 19:55 ` Thomas Gleixner
2013-02-19 20:15 ` Thomas Gleixner
2013-02-19 20:35 ` John Stultz
2013-02-19 21:50 ` Thomas Gleixner
2013-02-19 22:20 ` John Stultz
2013-02-20 10:06 ` Thomas Gleixner
2013-02-20 10:29 ` Peter Zijlstra
2013-02-23 6:04 ` John Stultz
2013-02-25 14:10 ` Peter Zijlstra
2013-03-14 15:34 ` Stephane Eranian
2013-03-14 19:57 ` Pawel Moll [this message]
2013-03-31 16:23 ` David Ahern
2013-04-01 18:29 ` John Stultz
2013-04-01 22:29 ` David Ahern
2013-04-01 23:12 ` John Stultz
2013-04-03 9:17 ` Stephane Eranian
2013-04-03 13:55 ` David Ahern
2013-04-03 14:00 ` Stephane Eranian
2013-04-03 14:14 ` David Ahern
2013-04-03 14:22 ` Stephane Eranian
2013-04-03 17:57 ` John Stultz
2013-04-04 8:12 ` Stephane Eranian
2013-04-04 22:26 ` John Stultz
2013-04-02 7:54 ` Peter Zijlstra
2013-04-02 16:05 ` Pawel Moll
2013-04-02 16:19 ` John Stultz
2013-04-02 16:34 ` Pawel Moll
2013-04-03 17:19 ` Pawel Moll
2013-04-03 17:29 ` John Stultz
2013-04-03 17:35 ` Pawel Moll
2013-04-03 17:50 ` John Stultz
2013-04-04 7:37 ` Richard Cochran
2013-04-04 16:33 ` Pawel Moll
2013-04-04 16:29 ` Pawel Moll
2013-04-05 18:16 ` Pawel Moll
2013-04-06 11:05 ` Richard Cochran
2013-04-08 17:58 ` Pawel Moll
2013-04-08 19:05 ` John Stultz
2013-04-09 5:02 ` Richard Cochran
2013-02-06 18:17 ` Pawel Moll
2013-06-26 16:49 ` David Ahern
2013-07-15 10:44 ` Pawel Moll
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=1363291021.3100.144.camel@hornet \
--to=pawel.moll@arm.com \
--cc=Will.Deacon@arm.com \
--cc=ak@linux.intel.com \
--cc=anton@samba.org \
--cc=eranian@google.com \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=penberg@gmail.com \
--cc=peterz@infradead.org \
--cc=robert.richter@amd.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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