Date: Thu, 26 Mar 2026 16:23:48 -0500
From: Nathan Bossart <nathandbossart@gmail.com>
To: KAZAR Ayoub <ma_kazar@esi.dz>
Cc: Andres Freund <andres@anarazel.de>,
	Pg Hackers <pgsql-hackers@postgresql.org>,
	Neil Conway <neil.conway@gmail.com>,
	Manni Wood <manni.wood@enterprisedb.com>,
	Andrew Dunstan <andrew@dunslane.net>,
	Shinya Kato <shinya11.kato@gmail.com>,
	Mark Wong <markwkm@gmail.com>,
	Nazir Bilal Yavuz <byavuz81@gmail.com>
Subject: Re: Speed up COPY TO text/CSV parsing using SIMD
Message-ID: <acWj5FntidHJ9nVP@nathan>
References: 
 <CA+K2Runi_H2CBL0yMm3De2KqcR9RMA0HK5cLJjEhoNszC7myeg@mail.gmail.com>
 <aY5C6Xa5im72NF_Y@alap3.anarazel.de>
 <CA+K2Rum_QTZqTUrdMOL5hr-OOpCwGR_9Nj1z15BFObjktMOY6A@mail.gmail.com>
 <abBuKalOno33MQFw@nathan>
 <CA+K2Rum7+Jm2rm65K5msxaiAM8QTkhSNAYarPBP9O7nBXYo12Q@mail.gmail.com>
 <abmiNPQOqBrRlf_m@nathan>
 <CA+K2Rum-TB_iNzDWoXOJspf=jq0gd-wees8+9tBTJNyhy9cK5g@mail.gmail.com>
 <CA+K2Ru=PdZuXQbcfvqKysTkebTyXNd9j7dp+mTFQEYpLdGw1eA@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: 
 <CA+K2Ru=PdZuXQbcfvqKysTkebTyXNd9j7dp+mTFQEYpLdGw1eA@mail.gmail.com>
Archived-At: <https://www.postgresql.org/message-id/acWj5FntidHJ9nVP%40nathan>
Precedence: bulk

On Wed, Mar 18, 2026 at 03:29:32AM +0100, KAZAR Ayoub wrote:
> If we have some json(b) column like : {"key1":"val1","key2":"val2"}, for
> CSV format this would immediately exit the SIMD path because of quote
> character, for json(b) this is going to be always the case.
> I measured the overhead of exiting the SIMD path a lot (8 million times for
> one COPY TO command), i only found 3% regression for this case, sometimes
> 2%.

I'm a little worried that we might be dismissing small-yet-measurable
regressions for extremely common workloads.  Unlike the COPY FROM work,
this operates on a per-attribute level, meaning we only use SIMD when an
attribute is at least 16 bytes.  The extra branching for each attribute
might not be something we can just ignore.

> For cases where we do a false commitment on SIMD because we read a binary
> size >= sizeof(Vector8), which i found very niche too, the short circuit to
> scalar each time is even more negligible (the above CSV JSON case is the
> absolute worst case).

That's good to hear.

-- 
nathan