[ltt-dev] gettimeofday vs clock_gettime

[ltt-dev] gettimeofday vs clock_gettime

[Nils Carlson]

Is there any reason UST uses gettimeofday and not clock_gettime with the
monotonic clock?

I'm guessing this has been asked before, but the mailing list doesn't
really lend itself to searching and there is no FAQ as far as I can tell.

/Nils

[ltt-dev] gettimeofday vs clock_gettime

[Mathieu Desnoyers]

* Nils Carlson (nils.carlson at ludd.ltu.se) wrote:
> Is there any reason UST uses gettimeofday and not clock_gettime with the
> monotonic clock?

Given that clock_gettime is available as a vDSO too, I see no reason not
to use it instead of gettimeofday. It's clearly closer to the intent.

Eventually, we'd like to create a TRACE_CLOCK version of clock_gettime
that would return the same time base as LTTng.

Thanks,

Mathieu

> 
> I'm guessing this has been asked before, but the mailing list doesn't
> really lend itself to searching and there is no FAQ as far as I can tell.
> 
> /Nils
> 
> 
> 
> _______________________________________________
> ltt-dev mailing list
> ltt-dev at lists.casi.polymtl.ca
> http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev
> 

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com

[ltt-dev] gettimeofday vs clock_gettime

[Pierre-Marc Fournier]

Nils Carlson wrote:
> Is there any reason UST uses gettimeofday and not clock_gettime with the
> monotonic clock?

The only reason is braindeadness. ;-) Can you provide a patch to fix this?

pmf