| From: | Arne Roland <A(dot)Roland(at)index(dot)de> |
|---|---|
| To: | "reid(dot)thompson(at)crunchydata(dot)com" <reid(dot)thompson(at)crunchydata(dot)com>, Andres Freund <andres(at)anarazel(dot)de> |
| Cc: | vignesh C <vignesh21(at)gmail(dot)com>, "pgsql-hackers(at)lists(dot)postgresql(dot)org" <pgsql-hackers(at)lists(dot)postgresql(dot)org>, Justin Pryzby <pryzby(at)telsasoft(dot)com>, Ibrar Ahmed <ibrar(dot)ahmad(at)gmail(dot)com>, stephen(dot)frost <stephen(dot)frost(at)crunchydata(dot)com> |
| Subject: | Re: Add the ability to limit the amount of memory that can be allocated to backends. |
| Date: | 2023-04-19 23:28:36 |
| Message-ID: | BE1P281MB313901E262719C4CF69B224BFE9C9@BE1P281MB3139.DEUP281.PROD.OUTLOOK.COM |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Thank you! I just tried our benchmark and got a performance degration of around 28 %, which is way better than the last patch.
The simple query select * from generate_series(0, 10000000) shows roughly 18.9 % degradation on my test server.
By raising initial_allocation_allowance and allocation_allowance_refill_qty I can get it to 16 % degradation. So most of the degradation seems to be independent from raising the allowance.
I think we probably should investigate this further.
Regards
Arne
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Peter Geoghegan | 2023-04-19 23:46:11 | Re: Should we put command options in alphabetical order in the doc? |
| Previous Message | David Rowley | 2023-04-19 22:37:49 | Re: Incremental sort for access method with ordered scan support (amcanorderbyop) |