Re: Improving btree performance through specializing by key shape, take 2

From: Matthias van de Meent <boekewurm+postgres(at)gmail(dot)com>
To: David Christensen <david(at)pgguru(dot)net>
Cc: Peter Geoghegan <pg(at)bowt(dot)ie>, pgsql-hackers(at)lists(dot)postgresql(dot)org
Subject: Re: Improving btree performance through specializing by key shape, take 2
Date: 2023-01-23 13:54:01
Message-ID: CAEze2WgNojtsBw82hqZXLAO_UCEtBufav7vhMYVNEzfCi1MciQ@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Fri, 20 Jan 2023 at 20:37, Matthias van de Meent
<boekewurm+postgres(at)gmail(dot)com> wrote:
> On Thu, 12 Jan 2023 at 16:11, David Christensen <david(at)pgguru(dot)net> wrote:
> >
> > Hi Matthias,
> >
> > I'm going to look at this patch series if you're still interested. What was the status of your final performance testing for the 0008 patch alone vs the specialization series? Last I saw on the thread you were going to see if the specialization was required or not.
>
> Thank you for your interest, and sorry for the delayed response. I've
> been working on rebasing and polishing the patches, and hit some
> issues benchmarking the set. Attached in Perf_results.xlsx are the
> results of my benchmarks, and a new rebased patchset.

Attached v9 which rebases the patchset on b90f0b57 to deal with
compilation errors after d952373a. It also cleans up 0001 which
previously added an unrelated file, but is otherwise unchanged.

Kind regards,

Matthias van de Meent

Attachment Content-Type Size
v9-0005-Add-an-attcacheoff-populating-function.patch application/octet-stream 4.7 KB
v9-0004-Optimize-nbts_attiter-for-nkeyatts-1-btrees.patch application/octet-stream 6.2 KB
v9-0003-Use-specialized-attribute-iterators-in-the-specia.patch application/octet-stream 13.3 KB
v9-0001-Implement-dynamic-prefix-compression-in-nbtree.patch application/octet-stream 22.8 KB
v9-0002-Specialize-nbtree-functions-on-btree-key-shape.patch application/octet-stream 247.2 KB
v9-0006-btree-specialization-for-variable-length-multi-at.patch application/octet-stream 11.8 KB

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message James Coleman 2023-01-23 14:00:31 Re: Parallelize correlated subqueries that execute within each worker
Previous Message Andrew Dunstan 2023-01-23 13:45:01 Re: Add a test to ldapbindpasswd