Postgres Pro
Downloads
Home   >   mailing lists

Re: Allow a per-tablespace effective_io_concurrency setting - Mailing list pgsql-hackers

From Josh Berkus
Subject Re: Allow a per-tablespace effective_io_concurrency setting
Date
Msg-id 55E76AB7.4030306@agliodbs.com
Whole thread Raw
In response to Re: [PERFORM] intel s3500 -- hot stuff  (Julien Rouhaud <julien.rouhaud@dalibo.com>)
Responses Re: Allow a per-tablespace effective_io_concurrency setting  (Merlin Moncure <mmoncure@gmail.com>)
Re: Allow a per-tablespace effective_io_concurrency setting  (Jeff Janes <jeff.janes@gmail.com>)
Re: Allow a per-tablespace effective_io_concurrency setting  (Andres Freund <andres@anarazel.de>)
List pgsql-hackers
Tree view 
On 09/02/2015 02:25 PM, Tomas Vondra wrote:
> 
> As I explained, spindles have very little to do with it - you need
> multiple I/O requests per device, to get the benefit. Sure, the DBAs
> should know how many spindles they have and should be able to determine
> optimal IO depth. But we actually say this in the docs:

My experience with performance tuning is that values above 3 have no
real effect on how queries are executed.

-- 
Josh Berkus
PostgreSQL Experts Inc.
http://pgexperts.com

pgsql-hackers by date:

Previous
From: Joe Conway
Date:
Subject: Re: exposing pg_controldata and pg_config as functions
Next
From: Alvaro Herrera
Date:
Subject: Re: exposing pg_controldata and pg_config as functions