Re: index prefetching - Mailing list pgsql-hackers

From Andres Freund
Subject Re: index prefetching
Date
Msg-id xw56ywdes77rfiyyy5cpxml5rirj3lthrqx6hezi2rqofz6oj7@lmxwnmcjayjt
Whole thread Raw
In response to Re: index prefetching  (Peter Geoghegan <pg@bowt.ie>)
Responses Re: index prefetching
List pgsql-hackers
Hi,

On 2025-08-15 15:42:10 -0400, Peter Geoghegan wrote:
> On Fri, Aug 15, 2025 at 3:38 PM Andres Freund <andres@anarazel.de> wrote:
> > I see absolutely no effect of the patch with shared_buffers=1GB and a
> > read-only scale 200 pgbench at 40 clients. What data sizes, shared buffers
> > etc. were you testing?
> 
> Just to be clear: you are testing with both the index prefetching
> patch and your patch together, right? Not just your own patch?

Correct.


> My shared_buffers is 16GB, with pgbench scale 300.

So there's actually no IO, given that a scale 300 is something like 4.7GB? In
that case my patch could really not make a difference, neither of the changed
branches would ever be reached?

Or were you testing the warmup phase, rather than the steady state?

Greetings,

Andres Freund



pgsql-hackers by date:

Previous
From: Peter Geoghegan
Date:
Subject: Re: index prefetching
Next
From: Andres Freund
Date:
Subject: Re: Remove Instruction Synchronization Barrier in spin_delay() for ARM64 architecture