Re: Prefetch the next tuple's memory during seqscans

From: Andres Freund <andres(at)anarazel(dot)de>
To: David Rowley <dgrowleyml(at)gmail(dot)com>
Cc: PostgreSQL Developers <pgsql-hackers(at)lists(dot)postgresql(dot)org>, Thomas Munro <thomas(dot)munro(at)gmail(dot)com>
Subject: Re: Prefetch the next tuple's memory during seqscans
Date: 2022-11-02 03:00:43
Views: Raw Message | Whole Thread | Download mbox | Resend email
Lists: pgsql-hackers


On 2022-10-31 16:52:52 +1300, David Rowley wrote:
> As part of the AIO work [1], Andres mentioned to me that he found that
> prefetching tuple memory during hot pruning showed significant wins.
> I'm not proposing anything to improve HOT pruning here

I did try and reproduce my old results, and it does look like we already get
most of the gains from prefetching via 18b87b201f7. I see gains from
prefetching before that patch, but see it hurt after. If I reverse the
iteration order from 18b87b201f7 prefetching helps again.

> but as a segue to get the prefetching infrastructure in so that there are
> fewer AIO patches, I'm proposing we prefetch the next tuple during sequence
> scans in while page mode.

> Time: 328.225 ms (avg ~7.7% faster)
> ...
> Time: 410.843 ms (avg ~22% faster)

That's a pretty impressive result.

I suspect that prefetching in heapgetpage() would provide gains as well, at
least for pages that aren't marked all-visible, pretty common in the real
world IME.


Andres Freund

In response to


Browse pgsql-hackers by date

  From Date Subject
Next Message Andy Fan 2022-11-02 03:02:58 A new strategy for pull-up correlated ANY_SUBLINK
Previous Message Pavel Stehule 2022-11-02 02:51:07 Re: PL/pgSQL cursors should get generated portal names by default