Re: hash join hashtable size and work_mem

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: "Timothy J(dot) Kordas" <tkordas(at)greenplum(dot)com>
Cc: pgsql-hackers(at)postgresql(dot)org
Subject: Re: hash join hashtable size and work_mem
Date: 2007-03-14 16:51:01
Message-ID: 23656.1173891061@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

"Timothy J. Kordas" <tkordas(at)greenplum(dot)com> writes:
> Am I missing something about the current implementation ?

If the planner has correctly predicted the number of rows, the table
loading should be about NTUP_PER_BUCKET in either regime. Are you
sure you aren't just wishing that NTUP_PER_BUCKET were smaller?
I don't see that making the hashtable much larger than ntuples
is a good idea --- that just spreads out the live entries over more
cache lines, resulting in more cache thrashing.

regards, tom lane

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Timothy J. Kordas 2007-03-14 17:28:12 Re: hash join hashtable size and work_mem
Previous Message Joshua D. Drake 2007-03-14 16:43:38 Re: [PATCHES] Bitmapscan changes