From: | John Naylor <john(dot)naylor(at)enterprisedb(dot)com> |
---|---|
To: | David Rowley <dgrowleyml(at)gmail(dot)com> |
Cc: | PostgreSQL Developers <pgsql-hackers(at)lists(dot)postgresql(dot)org>, Thomas Munro <thomas(dot)munro(at)gmail(dot)com> |
Subject: | Re: Considering additional sort specialisation functions for PG16 |
Date: | 2023-02-16 11:46:50 |
Message-ID: | CAFBsxsFk8dv0EPQ3zxcONNTxbhpe4SWG+n-PTeUJSQvC76LW=g@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
I wrote:
> Have two memtuple arrays, one for first sortkey null and one for first
sortkey non-null:
Hacking on this has gotten only as far as the "compiles but segfaults"
stage, but I wanted to note an idea that occurred to me:
Internal qsort doesn't need the srctape member, and removing both that and
isnull1 would allow 16-byte "init-tuples" for qsort, which would save a bit
of work_mem space, binary space for qsort specializations, and work done
during swaps.
During heap sort, we already copy one entry into a stack variable to keep
from clobbering it, so it's not a big step to read a member from the init
array and form a regular sorttuple from it.
--
John Naylor
EDB: http://www.enterprisedb.com
From | Date | Subject | |
---|---|---|---|
Next Message | Jelte Fennema | 2023-02-16 11:49:38 | Re: proposal: psql: psql variable BACKEND_PID |
Previous Message | gkokolatos | 2023-02-16 11:38:00 | RE: Add LZ4 compression in pg_dump |