AF:
NF:0
PS:10
SRH:1
SFN:
DSR:
MID:<20061221191102.443e0f9b@ripper.onstor.net>
CFG:
PT:0
S:andy.sharp@onstor.com
RQ:
SSV:onstor-exch02.onstor.net
NSV:
SSH:
R:<dl-Cougar@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	BB375AF679D4A34E9CA8DFA650E2B04E01D4CD49@onstor-exch02.onstor.net
X-Sylpheed-End-Special-Headers: 1
Date: Thu, 21 Dec 2006 19:11:12 -0800
From: Andrew Sharp <andy.sharp@onstor.com>
To: "dl-Cougar" <dl-Cougar@onstor.com>
Subject: Re: Cougar meeting minutes
Message-ID: <20061221191112.0c6c2c98@ripper.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E01D4CD49@onstor-exch02.onstor.net>
References: <BB375AF679D4A34E9CA8DFA650E2B04E01D4CD19@onstor-exch02.onstor.net>
	<BB375AF679D4A34E9CA8DFA650E2B04E01D4CD49@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

If I might gently ask that people use standard email quoting conventions
so that replies and whatnot are actually findable and readable?
Thank you, drive through.  </sheez>


On Thu, 21 Dec 2006 18:25:43 -0800 "Tim Gardner"
<tim.gardner@onstor.com> wrote:

> Thanks for the reply Brian.
> One answer to your questions below.
>
> _____________________________________________
> From: Brian Stark
> Sent: Thursday, December 21, 2006 5:02 PM
> To: Tim Gardner; dl-Cougar
> Subject: RE: Cougar meeting minutes


> *	Why is the BCM5715 attached to the PCI-e and not the PCI-x?
> Brian?
>
>				Routing area -- PCI-X is at least 40
> signals while the PCI-e bus is 16.  Given that the cluster
> interconnect may be pushing data for GNS applications, I wanted to
> give the BCM5715 as much bandwidth as possible.  The PCI-e
> connectivity offers a lot of bandwidth, but the 32-bit PCI-X
> connectivity does not, especially since it's running at 33MHz because
> of the PCI1520.  Plus, Broadcom has indicated that PCI-X MACs will
> soon go EOL because of how pervasive PCI-e has become.

W00t, here is my opportunity to re-design the entire hardware,
including the SiByte processor nodes themselves!

OK, so tell me how stupid this is:

Well, PCIe isn't so pervasive that is was included on the SiBytes.
But if we ran the PCI-X at 64/133 rather than 32/33, we could toss the
2100 and attach the 5715 MACs and Qlogics directly to it.  Down convert
the bus just in front of the PCI1520, or use a different part or put it
on the GPIO.  If Broadcom was to be so rude as to EOL the PCI-X 5715s,
and we all know they would be, there are other GigE macs out there.
Intel, SysKonnect, SiS, RealTek....

Now if we could just get Broadcom to redesign the SiBytes with PCIe
instead, we'd be in peach city.

I only ask that you flame these suggestions in small doses rather than
one big barbequeing ... I'm applying my SPF-5000 right now.

Cheers,

a

