Message-ID: <50758C1B.7010805@optionshouse.com>
Date: Wed, 10 Oct 2012 09:54:19 -0500
From: Shaun Thomas <sthomas@optionshouse.com>
Reply-To: <sthomas@optionshouse.com>
Organization: Peak6
User-Agent: Mozilla/5.0 (X11; Linux x86_64;
	rv:15.0) Gecko/20120912 Thunderbird/15.0.1
MIME-Version: 1.0
To: =?UTF-8?B?U3RyYWhpbmphIEt1c3R1ZGnEhw==?= <strahinjak@nordeus.com>
CC: <pgsql-performance@postgresql.org>
Subject: Re: shared_buffers/effective_cache_size on 96GB server
References: 
 <CADKbJJUTr9ZWkbajR-7_6qaAsWH0=09=2AMo67C_Az-raKZE4w@mail.gmail.com>
	<507573A4.1090605@optionshouse.com>
	<CADKbJJXNBLqDFwj3gnaZXdqU1sRU1qRLz=jJnyEWhUQJCC5vNQ@mail.gmail.com>
	<50758857.6030008@optionshouse.com>
	<CADKbJJW-q+swRfYPmuy1wKeUh_w9=OcuyOhNSkSeSSeowpPLfw@mail.gmail.com>
In-Reply-To: 
 <CADKbJJW-q+swRfYPmuy1wKeUh_w9=OcuyOhNSkSeSSeowpPLfw@mail.gmail.com>
Content-Type: text/plain; charset="UTF-8"; format=flowed
Content-Length: 961
Content-Transfer-Encoding: quoted-printable

On 10/10/2012 09:49 AM, Strahinja Kustudi=C4=87 wrote:

> I will change those, but I don't think this is that big of an issue if
> most of the IO is done by Postgres, since Postgres has it's own
> mechanism to tell the OS to sync the data to disk. For example when it's
> writing a wal file, or when it's writing a check point, those do not get
> cached.

You'd be surprised. Greg Smith did a bunch of work a couple years back 
that supported these changes. Most DBAs with heavily utilized systems 
could even see this in action by turning on checkpoint logging, and 
there's an occasional period where the sync time lags into the minutes 
due to a synchronous IO switch.

-- 
Shaun Thomas
OptionsHouse | 141 W. Jackson Blvd. | Suite 500 | Chicago IL, 60604
312-444-8534
sthomas@optionshouse.com

______________________________________________

See http://www.peak6.com/email_disclaimer/ for terms and conditions related to this email