----- Original Message -----
> From: "Steven Rostedt" <rostedt@xxxxxxxxxxx>
> To: "tip-bot for Thomas Gleixner" <tipbot@xxxxxxxxx>
> Cc: linux-tip-commits@xxxxxxxxxxxxxxx, "john stultz" <john.stultz@xxxxxxxxxx>, hpa@xxxxxxxxx, mingo@xxxxxxxxxx,
> "mathieu desnoyers" <mathieu.desnoyers@xxxxxxxxxxxx>, peterz@xxxxxxxxxxxxx, tglx@xxxxxxxxxxxxx
> Sent: Wednesday, July 23, 2014 7:41:46 PM
> Subject: Re: [tip:timers/core] ftrace: Provide trace clocks monotonic
>
> On Wed, 23 Jul 2014 15:48:03 -0700
> tip-bot for Thomas Gleixner <tipbot@xxxxxxxxx> wrote:
>
> > Commit-ID: 1b3e5c0936046e7e023149ddc8946d21c2ea20eb
> > Gitweb:
> > http://git.kernel.org/tip/1b3e5c0936046e7e023149ddc8946d21c2ea20eb
> > Author: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> > AuthorDate: Wed, 16 Jul 2014 21:05:25 +0000
> > Committer: John Stultz <john.stultz@xxxxxxxxxx>
> > CommitDate: Wed, 23 Jul 2014 15:01:55 -0700
> >
> > ftrace: Provide trace clocks monotonic
> >
> > Expose the new NMI safe accessor to clock monotonic to the tracer.
> >
> > Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> > Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> > Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> > Signed-off-by: John Stultz <john.stultz@xxxxxxxxxx>
> > ---
> > kernel/trace/trace.c | 11 ++++++-----
> > 1 file changed, 6 insertions(+), 5 deletions(-)
> >
> > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> > index f243444..84e2b45 100644
> > --- a/kernel/trace/trace.c
> > +++ b/kernel/trace/trace.c
> > @@ -806,11 +806,12 @@ static struct {
> > const char *name;
> > int in_ns; /* is this clock in nanoseconds? */
> > } trace_clocks[] = {
> > - { trace_clock_local, "local", 1 },
> > - { trace_clock_global, "global", 1 },
> > - { trace_clock_counter, "counter", 0 },
> > - { trace_clock_jiffies, "uptime", 1 },
> > - { trace_clock, "perf", 1 },
> > + { trace_clock_local, "local", 1 },
> > + { trace_clock_global, "global", 1 },
> > + { trace_clock_counter, "counter", 0 },
> > + { trace_clock_jiffies, "uptime", 1 },
> > + { trace_clock, "perf", 1 },
> > + { ktime_get_mono_fast_ns, "mono", 1 },
>
> Thomas,
>
> Can we please call this something else. "mono" is rather ambiguous as
> all the clocks are monotonic. In fact, the only real monotonic one is
> "global" as it synchronizes to keep true order. Oh, "counter" is
> another one, but it's not actually a clock. If I understand correctly,
> this new "mono" clock may not actually be monotonic between CPUs.
>
> I rather call it "user", as that's the purpose of this clock. To allow
> userspace to use the same clock as the kernel, isn't it?
How do you envision that a user would know what clock this "monotonic nmi-safe
fast clock" correlates with in userspace if it's called "user" clock ? There are
many kinds of user clocks: CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_MONOTONIC_RAW,
and so on....
Therefore, calling it with the same name as the specific user-visible clock
it can correlate with (CLOCK_MONOTONIC) seems like a sane choice to me.
Thanks,
Mathieu
>
> -- Steve
>
> > ARCH_TRACE_CLOCKS
> > };
> >
>
>
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|