Received-SPF: pass (caiguna.hst.terra.com.br: domain of terra.com.br
	designates 200.176.10.4 as permitted sender)
	client-ip=200.176.10.4; envelope-from=carlosreimer@terra.com.br;
	helo=reimer;
Reply-To: <carlosreimer@terra.com.br>
From: <carlosreimer@terra.com.br>
To: "Mark Lewis" <mark.lewis@mir3.com>
Cc: "Tom Lane" <tgl@sss.pgh.pa.us>,
	<pgsql-performance@postgresql.org>
Subject: RES: RES: Initial database loading and IDE x SCSI
Date: Fri, 2 Jun 2006 17:37:01 -0300
Message-ID: <PEEPKDFEHHEMKBBFPOOKMEHHCPAA.carlosreimer@terra.com.br>
MIME-Version: 1.0
Content-Type: text/plain;
	charset="utf-8"
Content-Transfer-Encoding: quoted-printable
In-Reply-To: <1149279209.20798.108.camel@archimedes>
Importance: Normal

Many thanks Mark,

I will consider fsync=3Doff only to do an initial load, not for a =
database normal operation.

I was just thinking about this hipotetical scenario:=20
a) a restore database operation
b) fsync off
c) write-back on (IDE)

As I could understand, in this sceneraio, it=C2=B4s normal the IDE drive =
be faster than the SCSI, ok?

Of course, the database is exposed because of the fsync=3Doff, but if =
you consider only the system performance, then it is true. Isn=C2=B4t =
it?

Thanks,

Reimer