| From: | Andres Freund <andres(at)anarazel(dot)de> |
|---|---|
| To: | "Anton A(dot) Melnikov" <a(dot)melnikov(at)postgrespro(dot)ru> |
| Cc: | "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org>, David Rowley <dgrowleyml(at)gmail(dot)com>, Michael Paquier <michael(at)paquier(dot)xyz> |
| Subject: | Re: Some performance degradation in REL_16 vs REL_15 |
| Date: | 2023-10-13 02:05:22 |
| Message-ID: | 20231013020522.ljwsw7mkpf23dylq@awork3.anarazel.de |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi,
On 2023-10-12 11:00:22 +0300, Anton A. Melnikov wrote:
> Found that simple test pgbench -c20 -T20 -j8 gives approximately
> for REL_15_STABLE at 5143f76: 336+-1 TPS
> and
> for REL_16_STABLE at 4ac7635f: 324+-1 TPS
>
> The performance drop is approximately 3,5% while the corrected standard deviation is only 0.3%.
> See the raw_data.txt attached.
Could you provide a bit more details about how you ran the benchmark? The
reason I am asking is that ~330 TPS is pretty slow for -c20. Even on spinning
rust and using the default settings, I get considerably higher results.
Oh - I do get results closer to yours if I use pgbench scale 1, causing a lot
of row level contention. What scale did you use?
Greetings,
Andres Freund
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Nathan Bossart | 2023-10-13 02:25:59 | Re: Improve the log message output of basic_archive when basic_archive.archive_directory parameter is not set |
| Previous Message | Tom Lane | 2023-10-13 01:44:06 | Re: PostgreSQL domains and NOT NULL constraint |