Re: Yet another fast GiST build (typo) - Mailing list pgsql-hackers

From Heikki Linnakangas
Subject Re: Yet another fast GiST build (typo)
Date
Msg-id 7945a3c2-b947-d0f8-167d-d43c44808caf@iki.fi
Whole thread Raw
In response to Re: Yet another fast GiST build (typo)  ("Andrey M. Borodin" <x4mmm@yandex-team.ru>)
Responses Re: Yet another fast GiST build (typo)  ("Andrey M. Borodin" <x4mmm@yandex-team.ru>)
Re: Yet another fast GiST build (typo)  ("Andrey M. Borodin" <x4mmm@yandex-team.ru>)
List pgsql-hackers
On 05/09/2020 14:53, Andrey M. Borodin wrote:
> Thanks for ideas, Heikki. Please see v13 with proposed changes.

Thanks, that was quick!

> But I've found out that logging page-by-page slows down GiST build by
> approximately 15% (when CPU constrained). Though In think that this
> is IO-wise.
Hmm, any ideas why that is? log_newpage_range() writes one WAL record 
for 32 pages, while now you're writing one record per page, so you'll 
have a little bit more overhead from that. But 15% seems like a lot.

- Heikki



pgsql-hackers by date:

Previous
From: David Rowley
Date:
Subject: Re: Optimising compactify_tuples()
Next
From: Heikki Linnakangas
Date:
Subject: Re: Dubious code in pg_rewind's process_target_file()