Re: Query is over 2x slower with jit=on - Mailing list pgsql-hackers

From Andres Freund
Subject Re: Query is over 2x slower with jit=on
Date
Msg-id 20180418155055.gawfkerzvy5rxpxe@alap3.anarazel.de
Whole thread Raw
In response to Query is over 2x slower with jit=on  (Andreas Joseph Krogh <andreas@visena.com>)
Responses Sv: Re: Query is over 2x slower with jit=on
Re: Query is over 2x slower with jit=on
Re: Query is over 2x slower with jit=on
List pgsql-hackers
On 2018-04-18 17:35:31 +0200, Andreas Joseph Krogh wrote:
> With jit=on:
> https://explain.depesz.com/s/vYB
> Planning Time: 0.336 ms 
>  JIT:
>   Functions: 716
>   Generation Time: 78.404 ms
>   Inlining: false
>   Inlining Time: 0.000 ms
>   Optimization: false
>   Optimization Time: 43.916 ms
>   Emission Time: 600.031 ms

Any chance this is a debug LLVM build?


> What's the deal with jit making it slower?

JIT has cost, and sometimes it's not beneficial. Here our heuristics
when to JIT appear to be a bit off. In the parallel world it's worse
because the JITing is duplicated for parallel workers atm.

Greetings,

Andres Freund


pgsql-hackers by date:

Previous
From: Julian Markwort
Date:
Subject: Re: [FEATURE PATCH] pg_stat_statements with plans (v02)
Next
From: Yuriy Zhuravlev
Date:
Subject: Re: Setting rpath on llvmjit.so?