Thanks for the update.
On Mon, Jan 29, 2024, 16:53 Ron Johnson wrote:
> According to my tests, sometimes JIT is a little faster, and sometimes
> it's a little slower. Mostly within the realm of statistical noise
> (especially with each query having a sample size of only 13, on a VM that
> lives
According to my tests, sometimes JIT is a little faster, and sometimes it's
a little slower. Mostly within the realm of statistical noise (especially
with each query having a sample size of only 13, on a VM that lives on a
probably-busy host).
On Mon, Jan 29, 2024 at 9:18 AM Ron Johnson wrote:
>
Yes, jit=on.
I'll test them with jit=off, to see the difference. (The application is
3rd party, so will change it at the system level.)
On Mon, Jan 29, 2024 at 7:09 AM Bob Jolliffe wrote:
> Out of curiosity, is the pg14 running with the default jit=on setting?
>
> This is obviously entirely du
Out of curiosity, is the pg14 running with the default jit=on setting?
This is obviously entirely due to the nature of the particular queries
themselves, but we found that for our workloads that pg versions
greater than 11 were exacting a huge cost due to the jit compiler. Once we
explicitly turn
On Sun, Jan 28, 2024 at 10:44 PM David Rowley wrote:
> On Mon, 29 Jan 2024 at 07:37, Ron Johnson wrote:
>
>> 08 9.6.24 1,142.164 1,160.801 1,103.716 1,249.852 1,191.081
>> 14.10 159.354 155.111 155.111 162.797 158.157 86.72%
>>
>
> Your speedup per cent calculation undersells PG14 by quite a bit
On Mon, 29 Jan 2024 at 07:37, Ron Johnson wrote:
> 08 9.6.24 1,142.164 1,160.801 1,103.716 1,249.852 1,191.081
> 14.10 159.354 155.111 155.111 162.797 158.157 86.72%
>
Your speedup per cent calculation undersells PG14 by quite a bit. I'd call
that an increase of ~639% rather than 86.72%.
I thi
(I don't know how this will look in text mode. Hopefully it will be
comprehensible in the archives.)
This is the summary of EXPLAIN (ANALYZE) on eight frequently-run complex
queries from our application, extracted from the Postgresql log because
either the BIND or SELECT takes longer than 3000 ms
