Mailing List Archive

1 2  View All
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
On Nov 13, 2009, at 4:14 AM, Matthew Walster wrote:

> 2009/11/12 David Coulson <david@davidcoulson.net>
>
>> You could route /32s within your L3 environment, or maybe even
>> leverage
>> something like VPLS - Not sure of any TOR-level switches that MPLS
>> pseudowire a port into a VPLS cloud though.
>>
>
> Just to let you know - the Juniper EX4200 series only support a
> single label
> stack, and RSVP not LDP - plus they have a restricted BGP table
> size, so
> VPLS is out of the question.

If you wanted something to do this, it's called an MX series. The ex
is a switch... l3, but still a switch.
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
Disagree, the EX is a very capable L3 router for LANs.


On Nov 13, 2009, at 1:17 PM, Cord MacLeod wrote:

> On Nov 13, 2009, at 4:14 AM, Matthew Walster wrote:
>
>> 2009/11/12 David Coulson <david@davidcoulson.net>
>>
>>> You could route /32s within your L3 environment, or maybe even leverage
>>> something like VPLS - Not sure of any TOR-level switches that MPLS
>>> pseudowire a port into a VPLS cloud though.
>>>
>>
>> Just to let you know - the Juniper EX4200 series only support a single label
>> stack, and RSVP not LDP - plus they have a restricted BGP table size, so
>> VPLS is out of the question.
>
> If you wanted something to do this, it's called an MX series. The ex is a switch... l3, but still a switch.
>
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
On Fri, 2009-11-13 at 09:44 +0100, Tore Anderson wrote:
> * Jonathan Lassoff
>
> > Are there any applications that absolutely *have* to sit on the same
> > LAN/broadcast domain and can't be configured to use unicast or multicast
> > IP?
>
> FCoE comes to mind.
>

....and in a similar vein, ATAoE ; either Coraid stuff or the the free
one in the Linux kernel. Its heavily used in some shops that use virtual
farms with SANS as it's cheap/free and works over existing hardware but
only at layer 2.

I even run it at home (!) - and it's a surprisingly easy way to have a
shelf of storage hanging off the back of a server, with 4GB of cache for
each set of 4 disks per box. Stand too close can feel the wind from it,
especially if RAIDed.

Depends if there's much call for VM-ing in your shop in the future?

Gord
--
NNNN
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
Tore Anderson writes:
> * Jonathan Lassoff
>> Are there any applications that absolutely *have* to sit on the same
>> LAN/broadcast domain and can't be configured to use unicast or multicast
>> IP?

> FCoE comes to mind.

Doesn't FCoE need even more than that, i.e. "lossless" Ethernet with
end-to-end flow control, such as IEEE DCB? As far as I understand,
traditional switched Ethernets don't fit the bill anyway.

On the other hand iSCSI should be fine with routed IP paths; though
Malte's mail suggests that there are (broken?) implementations that aren't.
--
Simon.
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
On Thu, Nov 12, 2009 at 9:40 PM, Bulger, Tim <Tim_Bulger@polk.com> wrote:
> If you use stackable switches, you can stack across cabinets (up to 3 with 1 meter Cisco 3750 Stackwise), and uplink on the ends.  It's a pretty solid layout if you plan your port needs properly based on NIC density and cabinet size, plus you can cable cleanly to an adjacent cabinet's switch if necessary.



Juniper claims their switches can do clustering using ethernet
cabling, yet a cluster behaves as a single-system-image
configuration-wise. Should allow for very flexible cabling and
operations-wise for TOR switches. I have never tried it however.

/Kinkie
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
On Wed, Nov 18, 2009 at 4:04 PM, Kinkie <gkinkie@gmail.com> wrote:
> On Thu, Nov 12, 2009 at 9:40 PM, Bulger, Tim <Tim_Bulger@polk.com> wrote:
>> If you use stackable switches, you can stack across cabinets (up to 3 with 1 meter Cisco 3750 Stackwise), and uplink on the ends.  It's a pretty solid layout if you plan your port needs properly based on NIC density and cabinet size, plus you can cable cleanly to an adjacent cabinet's switch if necessary.
>
>
>
> Juniper claims their switches can do clustering using ethernet
> cabling, yet a cluster behaves as a single-system-image
> configuration-wise. Should allow for very flexible cabling and
> operations-wise for TOR switches. I have never tried it however.
>

The Ex4200 can be stacked by the ethernet expansion ports, either 4 x
1G or 2 x 10G.
And yes, it behaves as single switch with multiple line cards.
Re: Layer 2 vs. Layer 3 to TOR [ In reply to ]
On Wed, Nov 18, 2009 at 04:34:11PM +0200, Eugeniu Patrascu wrote:
> On Wed, Nov 18, 2009 at 4:04 PM, Kinkie <gkinkie@gmail.com> wrote:
> > On Thu, Nov 12, 2009 at 9:40 PM, Bulger, Tim <Tim_Bulger@polk.com> wrote:
> >> If you use stackable switches, you can stack across cabinets (up to 3 with 1 meter Cisco 3750 Stackwise), and uplink on the ends.  It's a pretty solid layout if you plan your port needs properly based on NIC density and cabinet size, plus you can cable cleanly to an adjacent cabinet's switch if necessary.
> >
> >
> >
> > Juniper claims their switches can do clustering using ethernet
> > cabling, yet a cluster behaves as a single-system-image
> > configuration-wise. Should allow for very flexible cabling and
> > operations-wise for TOR switches. I have never tried it however.
> >
>
> The Ex4200 can be stacked by the ethernet expansion ports, either 4 x
> 1G or 2 x 10G.
> And yes, it behaves as single switch with multiple line cards.

Yes, up to 10 EX4200 switches can be interconnected into a "Virtual
Chassis" using either the rear Virtual Chassis Ports (32 Gbps ingress
+ 32 Gbps egress for each of the 2 ports) with up to 5-meter VCP
cables, or using SFP, XFP or SFP+ fiber links (not sure if it works
with copper SFP, but might). You can mix/match each type of
interconnection within the same VC.

1 2  View All