Re: Vectored I/O in bulk_write.c

From: Thomas Munro <thomas(dot)munro(at)gmail(dot)com>
To: Andres Freund <andres(at)anarazel(dot)de>
Cc: Heikki Linnakangas <hlinnaka(at)iki(dot)fi>, PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org>
Subject: Re: Vectored I/O in bulk_write.c
Date: 2024-04-09 04:51:52
Message-ID: CA+hUKGJRJk06OnLPV2GHmJg2vRx+4OXKr_5pFX3Dk=qMGXWtPw@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

Here's a rebase. I decided against committing this for v17 in the
end. There's not much wrong with it AFAIK, except perhaps an
unprincipled chopping up of writes with large io_combine_limit due to
simplistic flow control, and I liked the idea of having a decent user
of smgrwritev() in the tree, and it probably makes CREATE INDEX a bit
faster, but... I'd like to try something more ambitious that
streamifies this and also the "main" writeback paths. I shared some
patches for that that are counterparts to this, over at[1].

[1] https://www.postgresql.org/message-id/flat/CA%2BhUKGK1in4FiWtisXZ%2BJo-cNSbWjmBcPww3w3DBM%2BwhJTABXA%40mail.gmail.com

Attachment Content-Type Size
v7-0001-Use-smgrwritev-for-both-overwriting-and-extending.patch text/x-patch 20.7 KB
v7-0002-Use-vectored-I-O-in-CREATE-INDEX.patch text/x-patch 5.2 KB
v7-0003-Use-contiguous-memory-for-bulk_write.c.patch text/x-patch 6.4 KB

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Michael Paquier 2024-04-09 05:01:00 Re: Speed up clean meson builds by ~25%
Previous Message Erik Rijkers 2024-04-09 04:40:05 libpq.sgml: "server ejectes GSS" -> server rejects GSS