public inbox for [email protected]  
help / color / mirror / Atom feed
From: Thomas Munro <[email protected]>
To: Andres Freund <[email protected]>
Cc: Tomas Vondra <[email protected]>
Cc: Peter Geoghegan <[email protected]>
Cc: Nazir Bilal Yavuz <[email protected]>
Cc: Robert Haas <[email protected]>
Cc: Melanie Plageman <[email protected]>
Cc: PostgreSQL Hackers <[email protected]>
Cc: Georgios <[email protected]>
Cc: Konstantin Knizhnik <[email protected]>
Cc: Dilip Kumar <[email protected]>
Subject: Re: index prefetching
Date: Fri, 29 Aug 2025 09:50:57 +1200
Message-ID: <CA+hUKGKL3MRvEftAE+kwBuL2PLg2CwUoHEMr=-KSvsWN8pHq9w@mail.gmail.com> (raw)
In-Reply-To: <5pltwb73d7cynsxo2yb54ygjk7haviatkrx43mnzihc6kkield@ahnstpgof46i>
References: <CAH2-WzkWNtCRTcUajGYrCkp9-+btteAthg21BzxbKV09AJuSrA@mail.gmail.com>
	<CAH2-WzkgkvbN_GqR+pfE7uKwhWxQ6h4jst7Rpjgrt68Vc1=FDA@mail.gmail.com>
	<5v2wuxg65l5e3s6uf373zskcqqoukmraxiucnvgn4t7b5cmeqx@5mhqsurdj6xn>
	<6butbqln6ewi5kuxz3kfv2mwomnlgtate4mb4lpa7gb2l63j4t@stlwbi2dvvev>
	<[email protected]>
	<y32ow7vfdrrcchxrwgfr5tbwg3ncm4f3rlp65svcbqorbm3tmn@cwvipbplnqyt>
	<[email protected]>
	<[email protected]>
	<onbn3rx35x6k7mfnsmejnebt4nahnii3qnjrac2jzdh3puwo6t@dzjzsx5ppaj7>
	<[email protected]>
	<5pltwb73d7cynsxo2yb54ygjk7haviatkrx43mnzihc6kkield@ahnstpgof46i>

On Fri, Aug 29, 2025 at 7:52 AM Andres Freund <[email protected]> wrote:
> On 2025-08-28 19:08:40 +0200, Tomas Vondra wrote:
> > From the 2x regression (compared to master) it might seem like that, but
> > even with the increased distance it's still slower than master (by 25%). So
> > maybe the "error" is to use AIO in these cases, instead of just switching to
> > I/O done by the backend.
>
> If it's slower at a higher distance, we're missing something.

Enough io_workers?  What kind of I/O concurrency does it want?  Does
wait_event show any backends doing synchronous IO?  How many does [1]
want to run for that test workload and does it help?

FWIW there's a very simple canned latency test in a SQL function in
the first message in that thread (0005-XXX-read_buffer_loop.patch),
just on the off-chance that it's useful as a starting point for other
ideas.  There I was interested in IPC overheads, latch collapsing and
other effects, so I was deliberately stalling on/evicting a single
block repeatedly without any readahead distance, so I wasn't letting
the stream "hide" IPC overheads.

[1] https://www.postgresql.org/message-id/flat/CA%2BhUKG%2Bm4xV0LMoH2c%3DoRAdEXuCnh%2BtGBTWa7uFeFMGgTLAw...





view thread (348+ messages)  latest in thread

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients using the --to and --cc options:
  reply via email

  To: [email protected]
  Cc: [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
  Subject: Re: index prefetching
  In-Reply-To: <CA+hUKGKL3MRvEftAE+kwBuL2PLg2CwUoHEMr=-KSvsWN8pHq9w@mail.gmail.com>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox