AF:
NF:0
PS:10
SRH:1
SFN:
DSR:
MID:<20080912114813.134bdcb7@ripper.onstor.net>
CFG:
PT:0
S:andy.sharp@onstor.com
RQ:
SSV:onstor-exch02.onstor.net
NSV:
SSH:
R:<jonathan.goldick@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	BB375AF679D4A34E9CA8DFA650E2B04E0B96947F@onstor-exch02.onstor.net
X-Sylpheed-End-Special-Headers: 1
Date: Fri, 12 Sep 2008 11:48:30 -0700
From: Andrew Sharp <andy.sharp@onstor.com>
To: "Jonathan Goldick" <jonathan.goldick@onstor.com>
Subject: Re: followup from yesterday's talk
Message-ID: <20080912114830.3fb30805@ripper.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E0B96947F@onstor-exch02.onstor.net>
References: <BB375AF679D4A34E9CA8DFA650E2B04E0B8A53DF@onstor-exch02.onstor.net>
	<20080911230805.53ef33ae@ripper.onstor.net>
	<BB375AF679D4A34E9CA8DFA650E2B04E0B96947F@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

I agree, but I'm not too worried about assigning resources at the
moment.  I have a good idea in my mind what resources are needed in the
short term, ie., to do the swagging and to research the different
approaches that might be taken.  If from that exercise, the resource
figure that comes out is some disruptive number, then perhaps some
re-thinking needs to be done.

On Fri, 12 Sep 2008 10:16:50 -0700 "Jonathan Goldick"
<jonathan.goldick@onstor.com> wrote:

> Until we can SWAG out what it would take to get anything, it's really
> going to be hard to assign resources.  My expectation is that doing
> replacing the networking core with linux on multiple cores is a much
> smaller project.  Getting a SWAG for that is step one.  Including the
> ACPU has got to be larger, if only because there is more to port.
> 
> -----Original Message-----
> From: Andy Sharp 
> Sent: Thursday, September 11, 2008 11:08 PM
> To: Jonathan Goldick
> Subject: Re: followup from yesterday's talk
> 
> On Mon, 8 Sep 2008 11:02:45 -0700 "Jonathan Goldick"
> <jonathan.goldick@onstor.com> wrote:
> 
> > Not sure if this email was also dropped
> > 
> > _____________________________________________
> > From: Jonathan Goldick 
> > Sent: Friday, September 05, 2008 5:33 PM
> > To: Andy Sharp
> > Subject: followup from yesterday's talk
> > 
> > I was thinking about your idea on Linux on the txrx.  I still think
> > it should come after the SSC work but in order to give it a fair
> > assessment can you SWAG out what the high-level tasks and effort
> > would be?  I'll be happy to work with you on that although I'm
> > traveling shortly and pegged in preparation for the Sep board
> > meeting.
> > 
> > A degrees of freedom that occurred to me is whether Linux does all
> > of the txrx or just the networking layer.  If the performance could
> > be managed we might be able to get IPv6 just by doing the networking
> > cores and not bite the cifs/nfs bullet in the same pass.  Just a
> > thought.
> 
> I got the email, but I still don't know how to respond to it.
> I've been thinking about it off and on while thinking about GUI
> and the system formerly known as Leopard.  There's just a whole lot of
> different concepts floating about here, and I'm not sure if it's
> possible to SWAG in a useful way at the moment.
> 
> The second paragraph is less clear to me. But I would respond to the
> word IPv6 by saying that would be one of the secondary but important
> goals of doing this: that other protocols could be plugged in front of
> the file protocols; and also to make user-space able to access the
> filesystem. Possibly through NFS. That would give us things like FTP
> which I believe we desire. Even HTTP. Even.
