| From: | "tsunakawa(dot)takay(at)fujitsu(dot)com" <tsunakawa(dot)takay(at)fujitsu(dot)com> |
|---|---|
| To: | "tanghy(dot)fnst(at)cn(dot)fujitsu(dot)com" <tanghy(dot)fnst(at)cn(dot)fujitsu(dot)com> |
| Cc: | 'Amit Kapila' <amit(dot)kapila16(at)gmail(dot)com>, Greg Nancarrow <gregn4422(at)gmail(dot)com>, Dilip Kumar <dilipbalaut(at)gmail(dot)com>, vignesh C <vignesh21(at)gmail(dot)com>, Bharath Rupireddy <bharath(dot)rupireddyforpostgres(at)gmail(dot)com>, Andres Freund <andres(at)anarazel(dot)de>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>, Antonin Houska <ah(at)cybertec(dot)at> |
| Subject: | RE: Parallel INSERT (INTO ... SELECT ...) |
| Date: | 2021-01-18 08:23:29 |
| Message-ID: | OSBPR01MB29826C3FB3CB38FD5C5CE667FEA40@OSBPR01MB2982.jpnprd01.prod.outlook.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
From: Tang, Haiying <tanghy(dot)fnst(at)cn(dot)fujitsu(dot)com>
> (does this patch make some optimizes in serial insert? I'm a little confused
> here, Because the patched execution time is less than unpatched, but I didn't
> find information in commit messages about it. If I missed something, please
> kindly let me know.)
I haven't thought of anything yet. Could you show us the output of EXPLAIN (ANALYZE, BUFFERS, VERBOSE) of 1,000 partitions case for the patched and unpatched? If it doesn't show any difference, the output of perf may be necessary next.
(BTW, were all the 1,000 rows stored in the target table?)
> I did another test which made check overhead obvious. this case is not fitting
> for partition purpose, but I put it here as an extreme case too.
> Select table total rows are 1,000, # of partitions is 2000. So only the first 1000
> partitions have 1 row per partition, the last 1000 partitions have no data
> inserted.
Thank you, that's a good test.
Regards
Takayuki Tsunakawa
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Amit Kapila | 2021-01-18 08:28:03 | Re: Parallel INSERT (INTO ... SELECT ...) |
| Previous Message | Tatsuo Ishii | 2021-01-18 08:17:05 | Re: Code of Conduct plan,Re: Code of Conduct plan |