Unified tracing buffer

[Frank Ch. Eigler]

Hi -

On Tue, Sep 23, 2008 at 11:36:26PM +0900, KOSAKI Motohiro wrote:
> > By the way, systemtap uses two modes;
> > 
> > - single-channel mode
> >  In this mode, all cpus share one buffer channel to write and read.
> >  each writer locks spinlock and write a probe-local data to buffer.
> > - per-cpu buffer mode [...]
> 
> I can't imazine a merit of the single-channel mode.
> Could you please explain it?

It could be a way of saving some memory and merging hassle for
low-throughput data.  (Remember that systemtap enables in-situ
analysis of events so that often only brief final results need be sent
along need be sent out.)  If timestampwise cross-cpu merging can be
done on demand by the hypothetical future buffer widget, then little
reason remains not to use it.

- FChE