Horton

Re: Big performance slowdown from 11.2 to 13.3

Justin Pryzby <pryzby@telsasoft.com>

View thread View on postgr.es
From: Justin Pryzby <pryzby@telsasoft.com>
To: Peter Geoghegan <pg@bowt.ie>
Cc: Tom Lane <tgl@sss.pgh.pa.us>, David Rowley <dgrowleyml@gmail.com>, "ldh@laurent-hasson.com" <ldh@laurent-hasson.com>, "pgsql-performance@postgresql.org" <pgsql-performance@postgresql.org>
Date: 2021-07-22T16:41:27Z
Lists: pgsql-performance 
On Thu, Jul 22, 2021 at 09:36:02AM -0700, Peter Geoghegan wrote:
> I don't see how it's possible for get_hash_mem() to be unable to
> return a hash_mem value that could be represented by work_mem
> directly. MAX_KILOBYTES is an annoyingly low limit on Windows, where
> sizeof(long) is 4. But that's nothing new.

Oh.  So the problem seems to be that:

1) In v12, HashAgg now obeyes work_mem*hash_mem_multiplier;
2) Under windows, work_mem is limited to 2GB.

-- 
Justin

Commits

  1. Get rid of artificial restriction on hash table sizes on Windows.