Re: [RFC][PATCH] ftrace interface for blktrace

[Ingo Molnar]

* Arnaldo Carvalho de Melo <acme@xxxxxxxxxx> wrote:

> I hope that by dropping the requirement to a userspace bit (be it big or 
> small) we can set a record for such kind of tracing infrastructure now 
> that tracepoints are being proposed left and right.
> 
> After all, somebody said that userspace is just a test case for the 
> kernel, and for things like developer assists...

Exactly.

Also, for certain tracing modes where we just do the run to gather 
statistics (but do not plan to capture any trace), it is more efficient to 
have an in-kernel histogram than to export gobs of data to user-space at 
great expense, just to throw away most of it there ;-)

	Ingo
--
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/