From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | Hans Buschmann <buschmann(at)nidsa(dot)net> |
Cc: | Thomas Munro <thomas(dot)munro(at)gmail(dot)com>, "pgsql-general(at)lists(dot)postgresql(dot)org" <pgsql-general(at)lists(dot)postgresql(dot)org> |
Subject: | Re: AW: Huge performance penalty with parallel queries in Windows x64 v. Linux x64 |
Date: | 2021-05-04 16:46:58 |
Message-ID: | 3911437.1620146818@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-general |
Hans Buschmann <buschmann(at)nidsa(dot)net> writes:
> In my opinion, even for Linux the default for parallel_setup_cost is set too low (1000). It should reflect the sequential access of 1000 pages, which normally is faster from buffer cache on modern hardware.
I tend to agree with you that the default costs for parallel queries
are far too optimistic --- we've seen enough complaints about parallelism
making things slower to make that clear. However, proposing some new
numbers without gathering some hard evidence to support them is not
helpful.
regards, tom lane
From | Date | Subject | |
---|---|---|---|
Next Message | Bruce Momjian | 2021-05-04 16:52:02 | Re: PostgreSQL upgrade from 10 to 12 fails with "ERROR: column r.relhasoids does not exist at character 1616" |
Previous Message | Tom Lane | 2021-05-04 16:43:36 | Re: PostgreSQL upgrade from 10 to 12 fails with "ERROR: column r.relhasoids does not exist at character 1616" |