Re: [PATCH 04/15] ftrace: pack event structures.

[Steven Rostedt]

On Thu, 2011-03-10 at 15:21 -0800, David Sharp wrote:

> Yes, I think that should have the same effect. Of course the next time
> we come along and remove other useless fields like 'flags' and
> 'preempt_count', a similar condition could arise.
> 
> (Note I don't necessarily think that 'flags' and 'preempt_count' are
> useless; although I don't know what they're used for, or why they need
> to be in every entry. fwiw, we've taken trace_entry down to 4 bytes of
> {unsigned short type; unsigned short pid;}, and we even have plans to
> completely remove pid.)

The flags and preempt count are legacy from the latency-tracer. But they
do come in quite handy when debugging -rt code. I've gotten trace data
from customers that knowing if preemption is enabled or disable and
whether or not something happened in interrupt context was detrimental.

That said, I would love to figure out a nice way to make these optional.

-- Steve


--
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/