On 01/27/2014 08:48 AM, Mitsumasa KONDO wrote:
>
>
> The issue of concern is not the performance of pg_stat_statements,
> AUIU. The issue is whether this patch affects performance
> generally, i.e. is there a significant cost in collecting these
> extra stats. To test this you would compare two general pgbench
> runs, one with the patch applied and one without.
>
> I showed first test result which is compared with without
> pg_stat_statements and without patch last day. They ran in same server
> and same benchmark settings(clients and scale factor) as today's
> result. When you merge and see the results, you can confirm not to
> affect of performance in my patch.
>
>
Yeah, sorry, I misread your message. I think this is good to go from a
performance point of view, although I'm still a bit worried about the
validity of the method (accumulating a sum of squares). OTOH, Welford's
method probably requires slightly more per statement overhead, and
certainly requires one more accumulator per statement. I guess if we
find ill conditioned results it wouldn't be terribly hard to change.
cheers
andrew