Re: Patch: add timing of buffer I/O requests

Greg Stark <stark(at)mit(dot)edu> writes:
> On Sun, Apr 29, 2012 at 12:26 AM, Robert Haas <robertmhaas(at)gmail(dot)com> wrote:
>> As for track_iotiming -> track_io_timing, I'm fine with that as well.

> I'm still grumpy about the idea of a GUC changing the explain analyze
> output. How would people feel about adding an explain option that
> explicitly requests io timing for this explain analyze and then having
> the io timing be enabled if either it's requested by explain analyze
> or if it's set on globally? That would make it more consistent with
> the other explain analyze options?

I think it's going to be hard to decouple that altogether. For
instance, if track_io_timing were not on but you did EXPLAIN (TIMING),
you'd end up with timing info getting sent to the stats collector for
just that one statement. That seems a bit weird too.

I see where you're coming from but I don't think it's a good idea to
add an EXPLAIN option unless you can make the two behaviors (EXPLAIN
reporting and stats collection) truly independent.

regards, tom lane