AF:
NF:0
PS:10
SRH:1
SFN:
DSR:
MID:<20080819135010.58a2b5fc@ripper.onstor.net>
CFG:
PT:0
S:andy.sharp@onstor.com
RQ:
SSV:onstor-exch02.onstor.net
NSV:
SSH:
R:<narayan.venkat@onstor.com>,<ben.piela@onstor.com>,<dl-cstech@onstor.com>,<dl-engineering@onstor.com>,<larry.abrahams@onstor.com>,<andy.pinkard@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	BB375AF679D4A34E9CA8DFA650E2B04E0B4F381D@onstor-exch02.onstor.net
X-Sylpheed-End-Special-Headers: 1
Date: Tue, 19 Aug 2008 13:50:37 -0700
From: Andrew Sharp <andy.sharp@onstor.com>
To: "Narayan Venkat" <narayan.venkat@onstor.com>
Cc: "Ben Piela" <ben.piela@onstor.com>, "dl-cstech" <dl-cstech@onstor.com>,
 "dl-Engineering" <dl-engineering@onstor.com>, "Larry Abrahams"
 <larry.abrahams@onstor.com>, "Andy Pinkard" <andy.pinkard@onstor.com>
Subject: Re: Full Filesystem Performance
Message-ID: <20080819135037.2d8761a5@ripper.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E0B4F381D@onstor-exch02.onstor.net>
References: <BB375AF679D4A34E9CA8DFA650E2B04E08C332E7@onstor-exch02.onstor.net>
	<BB375AF679D4A34E9CA8DFA650E2B04E0B4F381D@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

On Tue, 19 Aug 2008 12:00:12 -0700 "Narayan Venkat"
<narayan.venkat@onstor.com> wrote:

> Folks,
> 
> Let's not go down that slippery slope.  The last thing that we want is
> that note to fall in the hands of a competitor and it will backfire.

Definitely.

One wonders if it was one of our competitors who talked them into
asking us for such a document.

The performance characteristics in this area would be highly dependent
on the array, the size of the filesystem, the usage footprint, ad
nauseum.  If they started with a 50TB filesystem and they filled it to
47.5TB with a series of large streaming writes, then the performance
for the remaining 2.5TB will be pretty much the same as for the first
47.5.  If they really wanted to do something like this, then they
should do their own study on their own setup with their own usage
pattern, and leave our name out of it since the results would be pretty
much the same no matter who's filer was being used.

> Moreover, we do not have a performance penalty when filesystem usage
> gets up in the high 90%.
> 
> Thanks.
> 
> Narayan Venkat
> Vice President, Marketing
> ONStor Inc. (www.onstor.com)
> Tel: (408) 963-2404
> Cell: (408) 221-4297
> -----Original Message-----
> From: Ben Piela 
> Sent: Tuesday, August 19, 2008 11:56 AM
> To: dl-cstech; dl-Engineering
> Cc: Larry Abrahams
> Subject: Full Filesystem Performance
> 
> Does performance tank as a storfs filesystem nears full capacity?  
> 
> So, IHAC that was thinking that if they had a note from an ONStor
> engineer stating that performance starts to tank at say 95% capacity,
> they could then show that to their boss and possibly make a case for
> purchasing storage from us sooner rather than later.  Sounds great to
> me.  Sign me up for some of that!
> 
> So....  Out of curiosity, does our performance tank and can I get an
> engineer to write something up on this?
> 
> Thanks,
> 
> Ben
> --------------------------
> Sent using Ben's Blackberry
