Feedback-ID: i0fe9450f:Fastmail
Date: Tue, 16 May 2023 14:42:39 +0900
From: Michael Paquier <michael@paquier.xyz>
To: Andres Freund <andres@anarazel.de>
Cc: Alexander Lakhin <exclusion@gmail.com>,
	Michael Paquier <michael.paquier@gmail.com>,
	MARK CALLAGHAN <mdcallag@gmail.com>,
	pgsql-hackers@lists.postgresql.org
Subject: Re: benchmark results comparing versions 15.2 and 16
Message-ID: <ZGMXzwtcQawbkIvs@paquier.xyz>
References: <CAFbpF8N4bVFZ+eyWFj_+fZXZFSayk2kJVtZnouUVKGHudiDrSw@mail.gmail.com>
 <b32bed1b-0746-9b20-1472-4bdc9ca66d52@gmail.com>
 <20230508191117.v6475ip6hxpwukss@awork3.anarazel.de>
 <20230509164824.wtfn5aoggj4rcz67@awork3.anarazel.de>
 <ZFxu+IWkQpJhZkB3@paquier.xyz>
 <ZGHBGE45jKW8FEpe@paquier.xyz>
 <20230516001447.xrijuuqcn5s7phuz@awork3.anarazel.de>
 <ZGLRd9RRx/47BrOP@paquier.xyz>
 <20230516005453.wrsldqhhbpy5gfnd@awork3.anarazel.de>
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha512;
	protocol="application/pgp-signature"; boundary="sXYU0+mjBqt285Dw"
Content-Disposition: inline
In-Reply-To: <20230516005453.wrsldqhhbpy5gfnd@awork3.anarazel.de>
Archived-At: <https://www.postgresql.org/message-id/ZGMXzwtcQawbkIvs%40paquier.xyz>
Precedence: bulk


--sXYU0+mjBqt285Dw
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

On Mon, May 15, 2023 at 05:54:53PM -0700, Andres Freund wrote:
> Yes. numactl --physcpubind ... in my case.  Linux has an optimization where it
> does not need to send an IPI when the client and server are scheduled on the
> same core. For single threaded ping-pong tasks like pgbench -c1, that can make
> a huge difference, particularly on larger CPUs.  So you get a lot better
> performance when forcing things to be colocated.

Yes, that's not bringing the numbers higher with the simple cases I
reported previously, either.

Anyway, even if I cannot see such a high difference, I don't see how
to bring back the original numbers you are reporting without doing
more inlining and tying COERCE_SQL_SYNTAX more tightly within the
executor's portions for the FuncExprs, and there are the collation
assumptions as well.  Perhaps that's not the correct thing to do with
SQLValueFunction remaining around, but nothing can be done for v16, so
I am planning to just revert the change before beta1, and look at it
again later, from scratch.
--
Michael

--sXYU0+mjBqt285Dw
Content-Type: application/pgp-signature; name="signature.asc"

-----BEGIN PGP SIGNATURE-----
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=qX32
-----END PGP SIGNATURE-----

--sXYU0+mjBqt285Dw--