Re: track_planning causing performance regression

On Mon, Apr 19, 2021 at 11:44:05PM +0900, Fujii Masao wrote:
> On 2021/04/19 8:36, Justin Pryzby wrote:
> > Reviewing this change which was committed last year as
> > 321fa6a4a26c9b649a0fbec9fc8b019f19e62289
> >
> > On Fri, Jul 03, 2020 at 03:57:38PM +0900, Fujii Masao wrote:
> > > On 2020/07/03 13:05, Pavel Stehule wrote:
> > > > pá 3. 7. 2020 v 4:39 odesílatel Fujii Masao <masao(dot)fujii(at)oss(dot)nttdata(dot)com> napsal:
> > > >
> > > > Maybe there can be documented so enabling this option can have a negative impact on performance.
> > >
> > > Yes. What about adding either of the followings into the doc?
> > >
> > > Enabling this parameter may incur a noticeable performance penalty.
> > >
> > > or
> > >
> > > Enabling this parameter may incur a noticeable performance penalty,
> > > especially when a fewer kinds of queries are executed on many
> > > concurrent connections.
> >
> > Something seems is wrong with this sentence, and I'm not sure what it's trying
> > to say. Is this right ?
>
> pg_stat_statements users different spinlock for each kind of query.
> So fewer kinds of queries many sessions execute, fewer spinlocks
> they try to acquire. This may lead to spinlock contention and
> significant performance degration. This is what the statement is
> trying to say.

What does "kind" mean ? I think it means a "normalized" query or a "query
structure".

"a fewer kinds" is wrong, so I think the docs should say "a small number of
queries" or maybe:

> > > Enabling this parameter may incur a noticeable performance penalty,
> > > especially similar queries are run by many concurrent connections and
> > > compete to update the same pg_stat_statements entry

--
Justin