Horton

Re: A qsort template

Peter Geoghegan <pg@bowt.ie>

View thread View on postgr.es
From: Peter Geoghegan <pg@bowt.ie>
To: Thomas Munro <thomas.munro@gmail.com>
Cc: John Naylor <john.naylor@enterprisedb.com>, pgsql-hackers <pgsql-hackers@postgresql.org>
Date: 2021-08-05T23:18:41Z
Lists: pgsql-hackers 
On Sun, Aug 1, 2021 at 5:41 PM Thomas Munro <thomas.munro@gmail.com> wrote:
> On Fri, Jul 30, 2021 at 12:34 PM John Naylor
> <john.naylor@enterprisedb.com> wrote:
> > I got around to getting a benchmark together to serve as a starting point. I based it off something I got from the archives, but don't remember where (I seem to remember Tomas Vondra wrote the original, but not sure). To start I just used types that were there already -- int, text, numeric. The latter two won't be helped by this patch, but I wanted to keep something like that so we can see what kind of noise variation there is. I'll probably cut text out in the future and just keep numeric for that purpose.
>
> Thanks, that's very useful.

If somebody wants to get a sense of what the size hit is from all of
these specializations, I can recommend the diff feature of bloaty:

https://github.com/google/bloaty/blob/master/doc/using.md#size-diffs

Obviously you'd approach this by building postgres without the patch,
and diffing that baseline to postgres with the patch. And possibly
variations of the patch, with less or more sort specializations.

-- 
Peter Geoghegan

Commits

  1. Remove debug messages from tuplesort_sort_memtuples()

  2. Fix performance regression in tuplesort specializations

  3. Fix tuplesort optimization for CLUSTER-on-expression.

  4. Initial pgindent and pgperltidy run for v14.

  5. Specialize checkpointer sort functions.

  6. Use sort_template.h for qsort() and qsort_arg().

  7. Use sort_template.h for qsort_tuple() and qsort_ssup().

  8. Add sort_template.h for making sort functions.

  9. Use abbreviated keys for faster sorting of text datums.