Re: [PATCH 2/3] perf events: Introduce realtime clock event

[Ingo Molnar <mingo@elte.hu>]

* Peter Zijlstra <peterz@infradead.org> wrote:

> > Programs that generate time-of-day output are using gettimeofday which is tied 
> > to CLOCK_REALTIME. We want to be able to correlate a perf sample to an entry in 
> > an applications log file.
> 
> Well, you can argue those programs are broken :-), [...]

Then 99% of the world is broken as daylight saving time jumps are part of our lives.

> [...] Imagine the joys of trying to figure out wth happens when DST jumps the 
> clock back an hour and you have an hour of duplicate data.

DST means twice a year the clock jumps back and forth by exactly one hour, on a 
given Saturday night. People debugging logs on Saturday nights and not realizing 
that there's a (always highly publicized) DST switch going on *deserve* to be 
surprised twice a year! :-)

Really, i dont think it's a big issue - and timestamping in *real* time has very 
obvious advantages as its name already suggests.

Thanks,

	Ingo