Re: in-memory sorting - Mailing list pgsql-performance

From Tom Lane
Subject Re: in-memory sorting
Date
Msg-id 26184.1282224579@sss.pgh.pa.us
Whole thread Raw
In response to Re: in-memory sorting  (Samuel Gendler <sgendler@ideasculptor.com>)
List pgsql-performance
Samuel Gendler <sgendler@ideasculptor.com> writes:
> Answered my own question.  Cranking work_mem up to 350MB revealed that
> the in-memory sort requires more memory than the disk sort.

Yeah.  The on-disk representation of sortable data is tighter than the
in-memory representation for various reasons, mostly that we're willing
to work at making it small.  Datums aren't necessarily properly aligned
for example, and there's also palloc overhead to consider in-memory.

            regards, tom lane

pgsql-performance by date:

Previous
From: Alexandre de Arruda Paes
Date:
Subject: Re: Fwd: Vacuum Full + Cluster + Vacuum full = non removable dead rows
Next
From: "Kevin Grittner"
Date:
Subject: Re: Fwd: Vacuum Full + Cluster + Vacuum full = non removable dead rows