Re: Monitoring number of backends

From: Stephen Frost <sfrost(at)snowman(dot)net>
To: John R Pierce <pierce(at)hogranch(dot)com>
Cc: pgsql-general(at)postgresql(dot)org
Subject: Re: Monitoring number of backends
Date: 2013-10-22 19:35:13
Message-ID: 20131022193512.GD2706@tamriel.snowman.net
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-general

* John R Pierce (pierce(at)hogranch(dot)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

In response to

Browse pgsql-general by date

  From Date Subject
Next Message Marc Mamin 2013-10-22 19:54:23 Re: Error with "return query" ( "return next" working ) with custom type
Previous Message Jeff Janes 2013-10-22 19:27:23 Re: Backup Question