| From: | Michael Paquier <michael(at)paquier(dot)xyz> |
|---|---|
| To: | Heikki Linnakangas <hlinnaka(at)iki(dot)fi> |
| Cc: | Nathan Bossart <nathandbossart(at)gmail(dot)com>, Xiang Gao <Xiang(dot)Gao(at)arm(dot)com>, "pgsql-hackers(at)lists(dot)postgresql(dot)org" <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: CRC32C Parallel Computation Optimization on ARM |
| Date: | 2023-10-24 22:17:55 |
| Message-ID: | ZThCk2O8ST2zbKAE@paquier.xyz |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Wed, Oct 25, 2023 at 12:37:45AM +0300, Heikki Linnakangas wrote:
> On 25/10/2023 00:18, Nathan Bossart wrote:
>> Actually, since the pg_waldump benchmark likely only involves very small
>> WAL records, it would make sense that there isn't much difference.
>> *facepalm*
>
> No need to guess, pg_waldump -z will tell you what the record size is. And
> you can vary it by changing the checkpoint interval and/or pgbench scale
> factor: if you checkpoint frequently or if the database is larger, you get
> more full-page images which makes the records larger on average, and vice
> versa.
If you are looking at computing the CRC of records with arbitrary
sizes, why not just generating a series with
pg_logical_emit_message() before doing a comparison with pg_waldump or
a custom replay loop to go through the records? At least it would
make the results more predictible.
--
Michael
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andres Freund | 2023-10-24 23:09:29 | walwriter interacts quite badly with synchronous_commit=off |
| Previous Message | Heikki Linnakangas | 2023-10-24 21:37:45 | Re: CRC32C Parallel Computation Optimization on ARM |