Re: Monitoring number of backends - Mailing list pgsql-general

From Stephen Frost
Subject Re: Monitoring number of backends
Date
Msg-id 20131022193512.GD2706@tamriel.snowman.net
Whole thread Raw
In response to Re: Monitoring number of backends  (John R Pierce <pierce@hogranch.com>)
List pgsql-general
* John R Pierce (pierce@hogranch.com) wrote:
> On 10/22/2013 10:59 AM, Stephen Frost wrote:
> >PG is really*much*  happier if you have only one backend per CPU in your
> >system.  The way to get there is by using a connection pooler like
> >pg_bouncer and configuring it based on how many CPUs you have.
>
> Actually, I've found peak throughputs on a decent multicore server
> with lots of ram, and lots of disk IO parallelism (eg, big raid10)
> is aruond 2X the socket*hyperthread*core count... so for instance,
> on a modern 2 socket E5-2665 kind of server, thats 2 x 8 cores with
> 2 threads per core, thats 16 total cores, 32 total hardware threads,
> so about 64 database connections would be peak, given a decent
> raid10 of lots of SAS2 10k/15k disks

Sure.  As always with performance- test, test, test on gear that is as
close to identical to the prod gear (or the prod gear itself, if you can
get away with it) as possible..  Every workload is different.

    Thanks,

        Stephen

Attachment

pgsql-general by date:

Previous
From: Jeff Janes
Date:
Subject: Re: Backup Question
Next
From: Marc Mamin
Date:
Subject: Re: Error with "return query" ( "return next" working ) with custom type