On Fri, May 24, 2013 at 10:36 AM, Jim Nasby <jim@nasby.net> wrote:
> Doesn't that hit the old issue of not knowing if a read came from FS cache
> or disk? I realize that the current cost_delay mechanism suffers from that
> too, but since the API is lower level that restriction is much more
> apparent.
Sure, but I think it's still useful despite that limitation.
> Instead of KB/s, could we look at how much time one process is spending
> waiting on IO vs the rest of the cluster? Is it reasonable for us to measure
> IO wait time for every request, at least on the most popular OSes?
I doubt that's going to be very meaningful. The backend that dirties
the buffer is fairly likely to be different from the backend that
writes it out.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company