MIME-Version: 1.0
In-Reply-To: <7642C3D639A75E4284658CAA38BF60A409D529C3@US-BOS-VEX001.eu.pxl.int>
References: <CBF3A4E7.392C7%anthony.ballo@onecall.com>
 <7642C3D639A75E4284658CAA38BF60A409D529C3@US-BOS-VEX001.eu.pxl.int>
Date: Wed, 6 Jun 2012 16:41:30 +0100
Message-ID: <CABe10sbuwpNm=TrvUPpHiYUMwCd5mDHbg=cG-CxtBW_27xuUPA@mail.gmail.com>
Subject: Re: Virident FlashMAX SCM
From: Niall Litchfield <niall.litchfield@gmail.com>
To: Richard.Goulet@parexel.com
Cc: "anthony.ballo@onecall.com" <anthony.ballo@onecall.com>, 
 "oracle-l@freelists.org" <oracle-l@freelists.org>
Content-type: text/plain
Content-Transfer-Encoding: 8bit
Sender: oracle-l-bounce@freelists.org
Errors-to: oracle-l-bounce@freelists.org
Precedence: normal
Reply-To: niall.litchfield@gmail.com

Which *myth* do you mean? If you mean the idea that you can change default
block size after database creation then that is indeed untrue. If you mean
that 4k block sizes are faster than 8k block sizes, almost certainly that
will be true for this hardware (provided that the partitions are aligned
correctly as well). Flash disk most definitely benefits from doing single
4k i/os to its native 4k "blocks" where possible. an 8k block write on this
hardware is "two" writes.
I've read the white paper and it looks to me like a copy/paste error or
else an editor ensuring that all the howto sections have the same format.

On Wed, Jun 6, 2012 at 4:01 PM, Goulet, Richard
<Richard.Goulet@parexel.com>wrote:

> Darn that myth is still running around?  No you're not missing anything,
> but the author certainly is.


-- 
Niall Litchfield
Oracle DBA
http://www.orawin.info


--
http://www.freelists.org/webpage/oracle-l