Re: significant slowdown of HashAggregate between 9.6 and 10

From: Andres Freund <andres(at)anarazel(dot)de>
To: Tomas Vondra <tomas(dot)vondra(at)2ndquadrant(dot)com>
Cc: Pavel Stehule <pavel(dot)stehule(at)gmail(dot)com>, PostgreSQL Hackers <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: significant slowdown of HashAggregate between 9.6 and 10
Date: 2020-06-03 20:26:43
Message-ID: 20200603202643.heyk452fqbgksqzy@alap3.anarazel.de
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

Hi,

On 2020-06-03 21:31:01 +0200, Tomas Vondra wrote:
> So there seems to be +40% between 9.6 and 10, and further +25% between
> 10 and master. However, plain hashagg, measured e.g. like this:

Ugh.

Since I am a likely culprit, I'm taking a look.

> Not sure what to think about this. Seems slot_deform_tuple got way more
> expensive between 9.6 and 10, for some reason.

Might indicate too many calls instead. Or it could just be the fact that
we have expressions deform all columns once, instead of deforming
columns one-by-one now.

Greetings,

Andres Freund

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Bruce Momjian 2020-06-03 20:34:20 Re: what can go in root.crt ?
Previous Message Andres Freund 2020-06-03 20:12:42 libpq copy error handling busted