Re: Optimizing ResouceOwner to speed up COPY

From: Tomas Vondra <tomas(at)vondra(dot)me>
To: Heikki Linnakangas <hlinnaka(at)iki(dot)fi>
Cc: PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org>, Chao Li <li(dot)evan(dot)chao(at)gmail(dot)com>
Subject: Re: Optimizing ResouceOwner to speed up COPY
Date: 2025-10-27 15:14:38
Message-ID: f4b60fe5-5c58-4a9a-a9e0-eb6e16323422@vondra.me
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On 10/21/25 16:43, Tomas Vondra wrote:
> ...
>
> The results seem fairly stable, and the overall trend is clear. It'd be
> great if there were no regressions, but considering how narrow is this
> microbenchmark (and considering the benefits for practical COPY runs),
> I'd say it's probably OK.
>

The regression for non-pathological cases (like COPY) is bothering me,
even if it's a very narrow microbenchmark and I'd bet it would not be
measurable in practice. Still, it's annoying.

I wonder if maybe a better solution would be to invent a concept of
tuple slots for the same descriptor, and allow it to be tracked only
once in the resource owner. That'd mean no duplicates, completely
eliminating the pathological case.

regards

--
Tomas Vondra

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Sergey Prokhorenko 2025-10-27 15:33:31 Отв.: Re: Add uuid_to_base32hex() and base32hex_to_uuid() built-in functions
Previous Message shveta malik 2025-10-27 15:08:42 Re: POC: enable logical decoding when wal_level = 'replica' without a server restart