Hi, Le mer. 17 nov. 2021 à 06:32, tanghy.f...@fujitsu.com < tanghy.f...@fujitsu.com> a écrit :
> Wednesday, November 17, 2021 6:29 AM, nikolai.berkoff < > nikolai.berk...@pm.me> wrote: > > > > Parallel query is explained in > > https://www.postgresql.org/docs/14/how-parallel-query-works.html and > > https://www.postgresql.org/docs/14/parallel-plans.html > > > > The docs seem clear to me that as the nodes are executed in parallel > then the > > time execution time is not 140.036*3. The 140.036 value is actual time > the Parallel > > Seq Scan nodes ran for but there were up to 2 running in parallel. > > Thanks for your reply. > I read your references but still confused about the 'loops' in parallel > query result. > > > -> Parallel Seq Scan on c (cost=0.00..8591.67 rows=416667 width=0) > (actual time=0.030..140.036 rows=333333 loops=3) > In my previous example, actual row number is 333333*3=1e6(which is > correct), so I think the actual time is 140.036*3ms. > Do your think the loops(3) has no meaning for parallel scan node when > calculate actual time? > > As far as I understand it, you have to multiply the number of rows by the number of loops, but this doesn't apply to duration at least for parallel queries. -- Guillaume.
