Re: [PATCH 3/3] perf events: add timehist option to record and report

[David Ahern]

On 02/18/11 11:39, Peter Zijlstra wrote:
> On Fri, 2011-02-18 at 11:07 -0700, David Ahern wrote:
>> We want not only context-switch events, but the stack trace at the
>> switch. 
> 
> Both ftrace and perf can do that:
> 
>  perf record -ge sched:sched_switch -c 1

Yes, exactly. And that is what I am using -- well, -e cs -c 1.

> 
> or
> 
> echo 1 > /debug/tracing/options/stacktrace

> 
>> That data along with the gettimeofday timestamp has allowed us to
>> resolve performance issues such as a system call taking longer than
>> expected during a specific sequence of events or a process getting
>> preempted and not scheduled for N seconds. etc., etc.
> 
> Non of that seems to require GTOD stamps.

On 01/23/11 at 03:45:67 a syslog event noted an application restart.
Checking the applications logs it went silent. Why? What does perf say?

Oh, 2 days have gone by before said event is reported to engineering,
and the server was been rebooted to 'clear' the problem - hence
resetting monotonic clock.

Multiply that by 100's of processes.

David

> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-perf-users" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/