Message-ID: <d8bb1295-6392-4cba-917d-de7da2b8c8bd@vondra.me>
Date: Wed, 25 Mar 2026 23:10:25 +0100
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: Change default of jit to off
To: Andres Freund <andres@anarazel.de>, Pierre Ducroquet <p.psql@pinaraf.info>
Cc: Tom Lane <tgl@sss.pgh.pa.us>, Jelte Fennema-Nio <postgres@jeltef.nl>,
 Greg Sabino Mullane <htamfids@gmail.com>,
 Adrien Nayrat <adrien.nayrat@anayrat.info>, Christoph Berg
 <myon@debian.org>, Euler Taveira <euler@eulerto.com>,
 =?UTF-8?Q?=C3=81lvaro_Herrera?= <alvherre@kurilemu.de>,
 PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>,
 Andreas Karlsson <andreas@proxel.se>,
 Anthonin Bonnefoy <anthonin.bonnefoy@datadoghq.com>,
 pgsql-hackers <pgsql-hackers@postgresql.org>, Michael Banck <mbanck@gmx.net>
References: <aYHN-fxswaIgfI-B@msg.df7cb.de>
 <49490d8d-e8b9-497b-9a58-712daadb9ca9@anayrat.info>
 <CAKAnmmKZ_Yg2CEt9Wa-QZWZ7UePfWB9qnk=qDiXZcqNS5MdrGQ@mail.gmail.com>
 <zavalseit5sbjf5gx352ioobtlqtycrs5yczynwzckacdwqh23@mjuvibp2z44t>
 <CAGECzQQdO5OGnxe7bpN1usp+ku+tLBW=SwgLbrULVcFAjH5_yA@mail.gmail.com>
 <5b5d04c3-e34e-4ae9-8b39-12b52e63154a@vondra.me>
 <1629115.1774023867@sss.pgh.pa.us>
 <gPNlX1QTDtJW2Cyi3fA2OGFvoIybkehUYKCHCe2r3Ujm_0y9V1T13CPI2MA6RyPhLi8zNwNczq1DNrbh1l47eVn6tOwz-qzG2yXw_XtptTQ=@pinaraf.info>
 <vhiu76rnwynmtmm3jbkettfelj5l2jtnbkwm7szpiyjbyrmd44@3gdapm3mnu3m>
Content-Language: en-US
From: Tomas Vondra <tomas@vondra.me>
In-Reply-To: <vhiu76rnwynmtmm3jbkettfelj5l2jtnbkwm7szpiyjbyrmd44@3gdapm3mnu3m>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Archived-At: 
 <https://www.postgresql.org/message-id/d8bb1295-6392-4cba-917d-de7da2b8c8bd%40vondra.me>
Precedence: bulk


On 3/24/26 22:56, Andres Freund wrote:
> Hi,
> 
> On 2026-03-23 06:33:33 +0000, Pierre Ducroquet wrote:
>> Le vendredi 20 mars 2026 à 5:25 PM, Tom Lane <tgl@sss.pgh.pa.us> a écrit :
>>
>>> Tomas Vondra <tomas@vondra.me> writes:
>>>> ISTM there's a clear consensus to get this committed for PG19, so
>>>> barring objections I'll take care of that in the next couple days.
>>>> Unless someone else wants to ...
>>>
>>> +1
>>>
>>>> Another option would be to leave that for mid-beta, which is where we
>>>> tweaked the io_method GUCs last year. But we did that to get some
>>>> testing for 'worker' (in case we revert to 'sync'), and we don't need
>>>> that for jit.
>>>
>>> Doesn't seem like something to change mid-beta.  If it makes anyone
>>> unhappy, we'd best find out sooner not later.
>>
>> I've not seen any feedback on my "counter"-proposal: switch
>> jit_tuple_deforming to off by default. Sure, for the perfect llvmjit use
>> cases this will reduce the performance benefits, but it will remove most if
>> not all the problematic queries (for instance queries running on many
>> partitions, adding/moving columns leading to explosions in compilation
>> time...)  Of course if there are other troublesome situations, I would love
>> being proven wrong.
> 
> I doubt that that addresses the problem in any meaningful way. In nearly all
> the cases I've looked at expression compilation completely dominates the cost,
> due to being instantiated for every partition etc. So I'm rather surprised to
> see this claim?
> 

That's my understanding too. I did search in the archives for
performance issues related to JIT, and those are the first two I found:

1)
https://www.postgresql.org/message-id/6191e1ee-d548-2a8c-d87d-dab63c05ad2e@code-sourcery.de

2)
https://www.postgresql.org/message-id/flat/LEXPR01MB09897821BA2CDDB70225EF7BE79C0%40LEXPR01MB0989.DEUPRD01.PROD.OUTLOOK.DE

Both have all the JIT stuff enabled, and the timings are dominated by
Optimization:

* Timing: Generation 15.707 ms, Inlining 4.688 ms, Optimization
652.021 ms, Emission 939.556 ms, Total 1611.973 ms

* Timing: Generation 27.833 ms, Inlining 117.093 ms, Optimization
3917.001 ms, Emission 2027.251 ms, Total 6089.177 ms

Or am I mistaken and it could still be due to deforming? It'd be a bit
silly to disable jit_tuple_deforming=off, only to find it's not enough
and have to disable more stuff for PG20.

Furthermore, jit_tuple_deforming is marked as DEVELOPER_OPTIONS, and is
not in the sample. Wouldn't that be a bit confusing/surprising, if we
disable just that, as it's not in the sample?


regards

-- 
Tomas Vondra