From: | Bob Jolliffe <bobjolliffe(at)gmail(dot)com> |
---|---|
To: | PG-General Mailing List <pgsql-general(at)postgresql(dot)org> |
Cc: | Ron Johnson <ronljohnsonjr(at)gmail(dot)com> |
Subject: | Re: Query performance in 9.6.24 vs 14.10 |
Date: | 2024-01-29 12:08:57 |
Message-ID: | CACd=f9fEXsSgwipMfdvhhLhuYbAKK3p7vKU75UoAVYQ8E57sQQ@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-general |
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 turned jit=off we started to see improvements.
On Mon, 29 Jan 2024 at 07:55, Ron Johnson <ronljohnsonjr(at)gmail(dot)com> wrote:
> On Sun, Jan 28, 2024 at 10:44 PM David Rowley <dgrowleyml(at)gmail(dot)com>
> wrote:
>
>> On Mon, 29 Jan 2024 at 07:37, Ron Johnson <ronljohnsonjr(at)gmail(dot)com>
>> 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 think you've done "1 - sum( <14.10 numbers> ) / sum( <9.6.24 numbers>)"
>> whereas I think you should have done "sum( <9.6.24 numbers>) / sum( <14.10
>> numbers> ) - 1"
>>
>> Nonetheless, thanks for testing this out. I assume this is just a report
>> giving good feedback about progress in this area...?
>>
>
> The spreadsheet function, using the Median cells, is (PG9.6 - PG14) /
> PG9.6). That's essentially the same as what you wrote.
>
> 158.157 / 1191.081 = 0.13278
>
> 1191.081 / 158.157 = 7.53, so 9.6.24 on that query is 7.53x slower.
>
>
From | Date | Subject | |
---|---|---|---|
Next Message | Ron Johnson | 2024-01-29 14:18:37 | Re: Query performance in 9.6.24 vs 14.10 |
Previous Message | Ron Johnson | 2024-01-29 09:06:07 | Re: Scriptable way to validate a pg_dump restore ? |