Re: How to solve my slow disk i/o throughput during index scan - Mailing list pgsql-performance

From Andrei Lepikhov
Subject Re: How to solve my slow disk i/o throughput during index scan
Date
Msg-id 671f72cc-ef05-426a-b697-7041880e5f28@gmail.com
Whole thread Raw
In response to RE: How to solve my slow disk i/o throughput during index scan  ("FREYBURGER Simon (SNCF VOYAGEURS / DIRECTION GENERALE TGV / DM RMP YIELD MANAGEMENT)" <simon.freyburger@sncf.fr>)
List pgsql-performance
On 11/7/2024 21:59, FREYBURGER Simon (SNCF VOYAGEURS / DIRECTION 
GENERALE TGV / DM RMP YIELD MANAGEMENT) wrote:
> 
> Hello, and thank you again for your example !
> 
> Sorry for my late answer, I was working on a patch for our requests. I 
> am though not completely understanding what is happening. Here is a plan 
> of a query where I splitted the calls with OR as you suggested, what 
> seemed to have enabled parallel scans.
Thanks for the feedback!
Generally, I don't understand why you needed to transform ANY -> OR at 
all to get BitmapScan. Can you just disable IndexScan and possibly 
SeqScan to see is it a hard transformation limit or mistake in cost 
estimation?

-- 
regards, Andrei Lepikhov




pgsql-performance by date:

Previous
From: Andrei Lepikhov
Date:
Subject: Re: How to solve my slow disk i/o throughput during index scan
Next
From: Paul George
Date:
Subject: inequality predicate not pushed down in JOIN?