AF:
NF:0
PS:10
SRH:1
SFN:
DSR:
MID:<20080624115840.6bcde530@ripper.onstor.net>
CFG:
PT:0
S:andy.sharp@onstor.com
RQ:
SSV:onstor-exch02.onstor.net
NSV:
SSH:
R:<brian.montero@onstor.com>,<fay.chong@onstor.com>,<Cougar-beta@onstor.com>,<dl-qualification@onstor.com>,<bob.miller@onstor.com>
MAID:1
X-Sylpheed-Privacy-System:
X-Sylpheed-Sign:0
SCF:#mh/Mailbox/sent
RMID:#imap/andys@onstor.net@onstor-exch02.onstor.net/INBOX	0	BB375AF679D4A34E9CA8DFA650E2B04E0AA0A614@onstor-exch02.onstor.net
X-Sylpheed-End-Special-Headers: 1
Date: Tue, 24 Jun 2008 11:59:12 -0700
From: Andrew Sharp <andy.sharp@onstor.com>
To: "Brian Montero" <brian.montero@onstor.com>
Cc: "Fay Chong" <fay.chong@onstor.com>, "ext-Cougar-beta"
 <Cougar-beta@onstor.com>, "dl-qualification" <dl-qualification@onstor.com>,
 "Bob Miller" <bob.miller@onstor.com>
Subject: Re: More on XIV testing at Shopzilla, Nexsan testing at ONStor
Message-ID: <20080624115912.13025023@ripper.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E0AA0A614@onstor-exch02.onstor.net>
References: <BB375AF679D4A34E9CA8DFA650E2B04E0AA0A5C7@onstor-exch02.onstor.net>
	<BB375AF679D4A34E9CA8DFA650E2B04E0AA0A614@onstor-exch02.onstor.net>
Organization: Onstor
X-Mailer: Sylpheed-Claws 2.6.0 (GTK+ 2.8.20; x86_64-pc-linux-gnu)
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit

So what I'm hearing is that test was done by pre-heating the cache,
then running the test?  I should think in performance tests like that
we should always make two numbers available, the cold-cache number as
well as the hot-cache number.  Both are interesting and relevant,
possibly to different circumstances, but also keep misunderstandings
like this from propagating too far.

Cheers,

a


On Tue, 24 Jun 2008 11:53:26 -0700 "Brian Montero"
<brian.montero@onstor.com> wrote:

> Yes, the I/O was never hitting the array in that test.  The test file
> size was intentionally set small enough to keep the I/O in Cougar
> memory.
> 
> 
> _____________________________________________
> From: Fay Chong 
> Sent: Tuesday, June 24, 2008 11:23 AM
> To: ext-Cougar-beta; dl-qualification; Bob Miller
> Cc: dl-qualification; Fay Chong
> Subject: More on XIV testing at Shopzilla, Nexsan testing at ONStor
> 
> Apparently there was some confusion about the 406 MB/sec sequential
> read reported in Nexsan testing. This was for fp bandwidth testing
> and did not involve rotating media storage. Inclusion of this data
> was meant for engineering purposes. I have deleted this data line in
> the report.
> 
> Thanks
> Fay
> 
> Fay Chong
> Sr. Performance Engineer
> ONStor, Inc.
> fay.chong@onstor.com
> 408.376.3130 (w)
> 
> 
