From mleber at he.net  Fri Nov  7 01:03:07 2008
From: mleber at he.net (Mike Leber)
Date: Thu, 06 Nov 2008 16:03:07 -0800
Subject: fixed configuration 48 port layer 3 routers
Message-ID: <491385BB.1060301@he.net>


Hi, I'd like to hear what solutions people are using as a fixed 
configuration 48 port layer 3 router (for customer aggregation) that 
supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough 
price that it cost.

We've been evaluating (and using) various boxes over the years and so 
far all the solutions have the same high per port cost as a core router.

I'm looking for something the is the same or close to the cost we'd see 
for fixed configuration IPv4 routers, so that we have a good answer for 
what to tell people to use (other than core routers or quagga and switches).

Considerations are:

layer 3 wirespeed IPv6 and IPv4 routing
OSPFv3
at least 8000 ARP entries *with* IPv6 enabled
48 ports
10/100/1000 copper
optional 10GE uplink
BGP a plus, but not required.

Mike.

-- 
+---------------- H U R R I C A N E - E L E C T R I C ----------------+
| Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580 4100 |
| Hurricane Electric                                           AS6939 |
| mleber at he.net     Internet Backbone & Colocation      http://he.net |
+---------------------------------------------------------------------+

From mloftis at wgops.com  Fri Nov  7 01:14:03 2008
From: mloftis at wgops.com (Michael Loftis)
Date: Thu, 06 Nov 2008 17:14:03 -0700
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <491385BB.1060301@he.net>
References: <491385BB.1060301@he.net>
Message-ID: <F720791F907039CDAD0200DE@ZOP-MACTEL.local>

Not an endorsement, but it seems the HP Procurve 3500yl-48G-PWR (copy paste 
model number from their site) might be.  I'm deploying a 5406zl, which is 
essentially the modular version of that switch.  So far it's going well. 
We're actively working on an issue with engineering though, but it seems to 
be isolated to AAA (802.1x or mac-based auth).  Too early to tell there.

As for v6, I've not really started to push/test v6 on the switch yet.

--On November 6, 2008 4:03:07 PM -0800 Mike Leber <mleber at he.net> wrote:

>
> Hi, I'd like to hear what solutions people are using as a fixed
> configuration 48 port layer 3 router (for customer aggregation) that
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough price
> that it cost.
>
> We've been evaluating (and using) various boxes over the years and so far
> all the solutions have the same high per port cost as a core router.
>
> I'm looking for something the is the same or close to the cost we'd see
> for fixed configuration IPv4 routers, so that we have a good answer for
> what to tell people to use (other than core routers or quagga and
> switches).
>
> Considerations are:
>
> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3
> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports
> 10/100/1000 copper
> optional 10GE uplink
> BGP a plus, but not required.
>
> Mike.
>
> --
> +---------------- H U R R I C A N E - E L E C T R I C ----------------+
>| Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580 4100 |
>| Hurricane Electric                                           AS6939 |
>| mleber at he.net     Internet Backbone & Colocation      http://he.net |
> +---------------------------------------------------------------------+



-- 
"Genius might be described as a supreme capacity for getting its possessors
into trouble of all kinds."
-- Samuel Butler

From truman at suspicious.org  Fri Nov  7 01:26:29 2008
From: truman at suspicious.org (Truman Boyes)
Date: Thu, 6 Nov 2008 19:26:29 -0500
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <491385BB.1060301@he.net>
References: <491385BB.1060301@he.net>
Message-ID: <12FDA860-0FCC-4623-BBC1-F3DF565B1914@suspicious.org>

Hi Mike,

Juniper MX 240s support:

* IPv6 (RA, DHCPv6)
* OSPFv3
* CoS, L2/L3 aggregation
* L2VPN/ VPLS/ Internet / L3VPN
* 4 slot chassis, 5RU high
* Each DPC (line card) can have 40GE ports.
* Hierarchical shaping (on inner and outer vlans)
* 240Gbps switching fabric, wirespeed forwarding, etc ,etc.
* yes it supports BGP
* Runs standard JUNOS

Truman


On 6/11/2008, at 7:03 PM, Mike Leber wrote:

>
> Hi, I'd like to hear what solutions people are using as a fixed  
> configuration 48 port layer 3 router (for customer aggregation) that  
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough  
> price that it cost.
>
> We've been evaluating (and using) various boxes over the years and  
> so far all the solutions have the same high per port cost as a core  
> router.
>
> I'm looking for something the is the same or close to the cost we'd  
> see for fixed configuration IPv4 routers, so that we have a good  
> answer for what to tell people to use (other than core routers or  
> quagga and switches).
>
> Considerations are:
>
> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3
> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports
> 10/100/1000 copper
> optional 10GE uplink
> BGP a plus, but not required.
>
> Mike.
>
> -- 
> +---------------- H U R R I C A N E - E L E C T R I C  
> ----------------+
> | Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580  
> 4100 |
> | Hurricane Electric                                            
> AS6939 |
> | mleber at he.net     Internet Backbone & Colocation      http:// 
> he.net |
> + 
> ---------------------------------------------------------------------+
>


From berni at birkenwald.de  Fri Nov  7 01:33:33 2008
From: berni at birkenwald.de (Bernhard Schmidt)
Date: Fri, 07 Nov 2008 01:33:33 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <F720791F907039CDAD0200DE@ZOP-MACTEL.local>
References: <491385BB.1060301@he.net>
	<F720791F907039CDAD0200DE@ZOP-MACTEL.local>
Message-ID: <49138CDD.70603@birkenwald.de>

Hi,

> Not an endorsement, but it seems the HP Procurve 3500yl-48G-PWR (copy 
> paste model number from their site) might be.  I'm deploying a 5406zl, 
> which is essentially the modular version of that switch.  So far it's 
> going well. We're actively working on an issue with engineering though, 
> but it seems to be isolated to AAA (802.1x or mac-based auth).  Too 
> early to tell there.
> 
> As for v6, I've not really started to push/test v6 on the switch yet.

Do you have a beta firmware? The publically available software can only 
be an IPv6 host so far (for management, just like e.g. the Cisco 2960 
L2-Switches) and possibly to MLD snooping, but cannot route it.

Mike, have a look at Cisco 3560G/3750G (ME6500 for more features, but 
that only has 24 copper + 8 SFP and is more expensive) or Foundry FESX(E).

Bernhard

From david.freedman at uk.clara.net  Fri Nov  7 01:43:29 2008
From: david.freedman at uk.clara.net (David Freedman)
Date: Fri, 7 Nov 2008 00:43:29 -0000
Subject: fixed configuration 48 port layer 3 routers
References: <491385BB.1060301@he.net>
	<12FDA860-0FCC-4623-BBC1-F3DF565B1914@suspicious.org>
Message-ID: <FFBEC1DE79841C4C965378BBDA5913FC4CDD9C@EXVS01.claranet.local>


>
> Hi, I'd like to hear what solutions people are using as a fixed  
> configuration 48 port layer 3 router (for customer aggregation) that  
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough  
> price that it cost.
>

for the price, you can use Cisco Catalyst 4900M, if you believe the marketing figures

http://www.cisco.com/en/US/prod/collateral/switches/ps5718/ps6021/product_data_sheet0900aecd8017a72e.html

http://www.cisco.com/en/US/prod/collateral/switches/ps5718/ps6021/ps9310/Data_Sheet_Cat_4900M.html

> layer 3 wirespeed IPv6 and IPv4 routing

250 mpps ipv4
125 mpps ipv6
(/me imagines fixed 64B packets and not imix)

> OSPFv3
yup

> at least 8000 ARP entries *with* IPv6 enabled
TCAM can hold 64K Entries. 

> 48 ports
Check, modular on 4900M

> 10/100/1000 copper
Yup

> optional 10GE uplink
if you buy the modules, you can have lots

> BGP a plus, but not required.
most certainly 

------------------------------------------------
David Freedman
Group Network Engineering 
Claranet Limited
http://www.clara.net



-----Original Message-----
From: ipv6-ops-bounces+david.freedman=uk.clara.net at lists.cluenet.de on behalf of Truman Boyes
Sent: Fri 11/7/2008 00:26
To: Mike Leber
Cc: ipv6-ops at lists.cluenet.de
Subject: Re: fixed configuration 48 port layer 3 routers
 
Hi Mike,

Juniper MX 240s support:

* IPv6 (RA, DHCPv6)
* OSPFv3
* CoS, L2/L3 aggregation
* L2VPN/ VPLS/ Internet / L3VPN
* 4 slot chassis, 5RU high
* Each DPC (line card) can have 40GE ports.
* Hierarchical shaping (on inner and outer vlans)
* 240Gbps switching fabric, wirespeed forwarding, etc ,etc.
* yes it supports BGP
* Runs standard JUNOS

Truman


On 6/11/2008, at 7:03 PM, Mike Leber wrote:

>
> Hi, I'd like to hear what solutions people are using as a fixed  
> configuration 48 port layer 3 router (for customer aggregation) that  
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough  
> price that it cost.
>
> We've been evaluating (and using) various boxes over the years and  
> so far all the solutions have the same high per port cost as a core  
> router.
>
> I'm looking for something the is the same or close to the cost we'd  
> see for fixed configuration IPv4 routers, so that we have a good  
> answer for what to tell people to use (other than core routers or  
> quagga and switches).
>
> Considerations are:
>
> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3
> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports
> 10/100/1000 copper
> optional 10GE uplink
> BGP a plus, but not required.
>
> Mike.
>
> -- 
> +---------------- H U R R I C A N E - E L E C T R I C  
> ----------------+
> | Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580  
> 4100 |
> | Hurricane Electric                                            
> AS6939 |
> | mleber at he.net     Internet Backbone & Colocation      http:// 
> he.net |
> + 
> ---------------------------------------------------------------------+
>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.cluenet.de/pipermail/ipv6-ops/attachments/20081107/01153d74/attachment.html 

From david.freedman at uk.clara.net  Fri Nov  7 01:44:18 2008
From: david.freedman at uk.clara.net (David Freedman)
Date: Fri, 7 Nov 2008 00:44:18 -0000
Subject: fixed configuration 48 port layer 3 routers
References: <491385BB.1060301@he.net><12FDA860-0FCC-4623-BBC1-F3DF565B1914@suspicious.org>
	<FFBEC1DE79841C4C965378BBDA5913FC4CDD9C@EXVS01.claranet.local>
Message-ID: <FFBEC1DE79841C4C965378BBDA5913FC4CDD9D@EXVS01.claranet.local>

oh, and the reason this isn't fixed configuration is that I was looking at the 4948 (which unfortunately only does in s/w) and went off on a complete tangent :)


------------------------------------------------
David Freedman
Group Network Engineering 
Claranet Limited
http://www.clara.net



-----Original Message-----
From: ipv6-ops-bounces+david.freedman=uk.clara.net at lists.cluenet.de on behalf of David Freedman
Sent: Fri 11/7/2008 00:43
To: Truman Boyes; Mike Leber
Cc: ipv6-ops at lists.cluenet.de
Subject: RE: fixed configuration 48 port layer 3 routers
 

>
> Hi, I'd like to hear what solutions people are using as a fixed  
> configuration 48 port layer 3 router (for customer aggregation) that  
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough  
> price that it cost.
>

for the price, you can use Cisco Catalyst 4900M, if you believe the marketing figures

http://www.cisco.com/en/US/prod/collateral/switches/ps5718/ps6021/product_data_sheet0900aecd8017a72e.html

http://www.cisco.com/en/US/prod/collateral/switches/ps5718/ps6021/ps9310/Data_Sheet_Cat_4900M.html

> layer 3 wirespeed IPv6 and IPv4 routing

250 mpps ipv4
125 mpps ipv6
(/me imagines fixed 64B packets and not imix)

> OSPFv3
yup

> at least 8000 ARP entries *with* IPv6 enabled
TCAM can hold 64K Entries. 

> 48 ports
Check, modular on 4900M

> 10/100/1000 copper
Yup

> optional 10GE uplink
if you buy the modules, you can have lots

> BGP a plus, but not required.
most certainly 

------------------------------------------------
David Freedman
Group Network Engineering 
Claranet Limited
http://www.clara.net



-----Original Message-----
From: ipv6-ops-bounces+david.freedman=uk.clara.net at lists.cluenet.de on behalf of Truman Boyes
Sent: Fri 11/7/2008 00:26
To: Mike Leber
Cc: ipv6-ops at lists.cluenet.de
Subject: Re: fixed configuration 48 port layer 3 routers
 
Hi Mike,

Juniper MX 240s support:

* IPv6 (RA, DHCPv6)
* OSPFv3
* CoS, L2/L3 aggregation
* L2VPN/ VPLS/ Internet / L3VPN
* 4 slot chassis, 5RU high
* Each DPC (line card) can have 40GE ports.
* Hierarchical shaping (on inner and outer vlans)
* 240Gbps switching fabric, wirespeed forwarding, etc ,etc.
* yes it supports BGP
* Runs standard JUNOS

Truman


On 6/11/2008, at 7:03 PM, Mike Leber wrote:

>
> Hi, I'd like to hear what solutions people are using as a fixed  
> configuration 48 port layer 3 router (for customer aggregation) that  
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough  
> price that it cost.
>
> We've been evaluating (and using) various boxes over the years and  
> so far all the solutions have the same high per port cost as a core  
> router.
>
> I'm looking for something the is the same or close to the cost we'd  
> see for fixed configuration IPv4 routers, so that we have a good  
> answer for what to tell people to use (other than core routers or  
> quagga and switches).
>
> Considerations are:
>
> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3
> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports
> 10/100/1000 copper
> optional 10GE uplink
> BGP a plus, but not required.
>
> Mike.
>
> -- 
> +---------------- H U R R I C A N E - E L E C T R I C  
> ----------------+
> | Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580  
> 4100 |
> | Hurricane Electric                                            
> AS6939 |
> | mleber at he.net     Internet Backbone & Colocation      http:// 
> he.net |
> + 
> ---------------------------------------------------------------------+
>



-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.cluenet.de/pipermail/ipv6-ops/attachments/20081107/5921604d/attachment-0001.html 

From mloftis at wgops.com  Fri Nov  7 07:28:57 2008
From: mloftis at wgops.com (Michael Loftis)
Date: Thu, 06 Nov 2008 23:28:57 -0700
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <49138CDD.70603@birkenwald.de>
References: <491385BB.1060301@he.net>
	<F720791F907039CDAD0200DE@ZOP-MACTEL.local>
	<49138CDD.70603@birkenwald.de>
Message-ID: <26780D8F7E13933A0ADDC310@ZOP-MACTEL.local>

K.13.25 on a 5406zl has the features.  And the yl and zl run the same 
firmware...

vlan <n>
ipv6 enable
ipv6 address <>

...

--On November 7, 2008 1:33:33 AM +0100 Bernhard Schmidt 
<berni at birkenwald.de> wrote:

> Hi,
>
>> Not an endorsement, but it seems the HP Procurve 3500yl-48G-PWR (copy
>> paste model number from their site) might be.  I'm deploying a 5406zl,
>> which is essentially the modular version of that switch.  So far it's
>> going well. We're actively working on an issue with engineering though,
>> but it seems to be isolated to AAA (802.1x or mac-based auth).  Too
>> early to tell there.
>>
>> As for v6, I've not really started to push/test v6 on the switch yet.
>
> Do you have a beta firmware? The publically available software can only
> be an IPv6 host so far (for management, just like e.g. the Cisco 2960
> L2-Switches) and possibly to MLD snooping, but cannot route it.
>
> Mike, have a look at Cisco 3560G/3750G (ME6500 for more features, but
> that only has 24 copper + 8 SFP and is more expensive) or Foundry FESX(E).
>
> Bernhard



-- 
"Genius might be described as a supreme capacity for getting its possessors
into trouble of all kinds."
-- Samuel Butler

From matthias.cramer at interway.ch  Fri Nov  7 07:45:48 2008
From: matthias.cramer at interway.ch (Matthias Cramer)
Date: Fri, 07 Nov 2008 07:45:48 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <491385BB.1060301@he.net>
References: <491385BB.1060301@he.net>
Message-ID: <4913E41C.4000809@interway.ch>

Mike Leber wrote:
> 
> Hi, I'd like to hear what solutions people are using as a fixed
> configuration 48 port layer 3 router (for customer aggregation) that
> supports OSPFv3 and IPv6 (BGP a plus but not required), and a rough
> price that it cost.

> Considerations are:
> 
> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3
> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports
> 10/100/1000 copper
> optional 10GE uplink
> BGP a plus, but not required.

We use Foundry FESX Switches for that, depending on how many routes you need a standard or
 X version would be what you need. But for IPv6 you need the PREM6 image.

Regards

  Matthias

-- 
Matthias Cramer / mc322-ripe   System & Network Manager
Interway Communication GmbH    Phone +41 43 500 1111
Josefstrasse 225               Fax   +41 44 271 3535
CH-8005 Z?rich                 http://www.interway.ch/
GnuPG 1024D/2D208250 = DBC6 65B6 7083 1029 781E  3959 B62F DF1C 2D20 8250

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 252 bytes
Desc: OpenPGP digital signature
Url : http://lists.cluenet.de/pipermail/ipv6-ops/attachments/20081107/9b47a446/attachment.bin 

From udo at stueberl.de  Fri Nov  7 09:06:00 2008
From: udo at stueberl.de (Udo Steinegger)
Date: Fri, 7 Nov 2008 09:06:00 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <491385BB.1060301@he.net>
References: <491385BB.1060301@he.net>
Message-ID: <2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>


On 07.11.2008, at 01:03, Mike Leber wrote:

Good morning,

I have seen answers with the Juniper MX240, but i wonder if you have  
considered the Juniper EX-Series 4200 switches?

http://www.juniper.net/products/exseries/dsheet/100215.pdf

> layer 3 wirespeed IPv6 and IPv4 routing
> OSPFv3

Yep - (i would like to test the wirespeed, but the other
features are there)

> at least 8000 ARP entries *with* IPv6 enabled
> 48 ports

yep

> 10/100/1000 copper

yep

> optional 10GE uplink

yep, actually a 2-port 10GE uplink port.

> BGP a plus, but not required.

BGP is there, up to 18000 routes, which doesnt deliver a
full BGP feed but serves well for internal puposes.

hope that helps.

cheers

Udo

From pekkas at netcore.fi  Fri Nov  7 09:09:06 2008
From: pekkas at netcore.fi (Pekka Savola)
Date: Fri, 7 Nov 2008 10:09:06 +0200 (EET)
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
Message-ID: <alpine.LRH.2.00.0811071007140.7052@netcore.fi>

On Fri, 7 Nov 2008, Udo Steinegger wrote:
> I have seen answers with the Juniper MX240, but i wonder if you have 
> considered the Juniper EX-Series 4200 switches?

This allows me to climb on a soapbox.

Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by 
default. DUH!

Let's see how many "v6 is broken" messages this will generate over the 
years.

-- 
Pekka Savola                 "You each name yourselves king, yet the
Netcore Oy                    kingdom bleeds."
Systems. Networks. Security. -- George R.R. Martin: A Clash of Kings

From udo at stueberl.de  Fri Nov  7 09:14:47 2008
From: udo at stueberl.de (Udo Steinegger)
Date: Fri, 7 Nov 2008 09:14:47 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <alpine.LRH.2.00.0811071007140.7052@netcore.fi>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
Message-ID: <B4FE507D-ECC7-45A2-901F-882F3979FD0D@stueberl.de>


On 07.11.2008, at 09:09, Pekka Savola wrote:

Good Morning Pekka,

> This allows me to climb on a soapbox.
>
> Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by  
> default. DUH!

Well, Mike wanted a fixed port L3 solution :) we were not
talking about L2 :P

But putting this key fact aside, thanks for bringing this
up, as I will test this with the new SW for the box next
week together with other tests.



> Let's see how many "v6 is broken" messages this will generate over  
> the years.

If that above is really the case, then I dont consider it
a problem for years.

cheers

Udo



From berni at birkenwald.de  Fri Nov  7 09:59:38 2008
From: berni at birkenwald.de (Bernhard Schmidt)
Date: Fri, 7 Nov 2008 09:59:38 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <26780D8F7E13933A0ADDC310@ZOP-MACTEL.local>
References: <491385BB.1060301@he.net>
	<F720791F907039CDAD0200DE@ZOP-MACTEL.local>
	<49138CDD.70603@birkenwald.de>
	<26780D8F7E13933A0ADDC310@ZOP-MACTEL.local>
Message-ID: <20081107085938.GA6319@schleppi.birkenwald.de>

On Thu, Nov 06, 2008 at 11:28:57PM -0700, Michael Loftis wrote:

> K.13.25 on a 5406zl has the features.  And the yl and zl run the same  
> firmware...
>
> vlan <n>
> ipv6 enable
> ipv6 address <>
>
> ...

I'm well aware of that

bschmidt at lxbsc01:~$ telnet 2001:4ca0:0:800:.....
Trying 2001:4ca0:0:800:........                         
Connected to 2001:4ca0:0:800:.......
Escape character is '^]'.                                            
ProCurve J8697A Switch 5406zl
Software revision K.13.23

but at the moment they can only be IPv6 host (for management), not IPv6
router. See page 2-6 in the IPv6 configuration guide
(http://cdn.procurve.com/training/Manuals/2900-3500-5400-6200-8200-IPv6-Jan08-K-13_01.pdf):

| Supported IPv6 Operation in Release K.13.01
| Software release K.13.01 provides IPv6 protocol and addressing to
| support host-mode (endpoint) IPv6 operation, including basic layer-2
| functionality.  IPv6 routing features are not available in this release.
| However, using a dual- stack (IPv4/IPv6-capable) router, IPv6 traffic
| can be routed between VLANs and sent across an IPv4 network to another
| IPv6 device.  (For general information on sending IPv6 traffic across an
| IPv4 network, refer to ?Connecting to Devices Supporting IPv6 Over IPv4
| Tunneling? on page 2-5.) The IPv6 features available in release K.13.01
| belong to these general categories:
| * switch configuration and management
| * security
| * IPv6 multicast traffic
| * diagnostic and troubleshooting

There is nothing in the release notes to suggest there have been
improvements in that area between K.13.01 and the current K.13.25

Regards,
Bernhard

From cfriacas at fccn.pt  Fri Nov  7 10:09:20 2008
From: cfriacas at fccn.pt (Carlos Friacas)
Date: Fri, 7 Nov 2008 09:09:20 +0000 (WET)
Subject: Some leaks in China/Hongkong
In-Reply-To: <20081029080814.GB21072@Space.Net>
References: <20081026131752.GA7741@pest> <490493EA.4050009@he.net>
	<20081027051754.GO21072@Space.Net> <490739B1.3040500@dfn.de>
	<20081029080814.GB21072@Space.Net>
Message-ID: <Pine.LNX.4.64.0811070900450.6846@gauntlet.fccn.pt>

On Wed, 29 Oct 2008, Gert Doering wrote:

> To be a bit more constructive: you could maintain a list of AS numbers
> that belong to known research networks and should be reached via Geant2,
> and local-pref these.  Anything else coming in via Geant2 should not be
> local-prefed (don't necessarily *drop*, even if that might be prudent given
> some of the crap I2 is leaking, but at least do not *force*) - which would
> avoid routing Google traffic to Hongkong, instead of Amsterdam.

Hello,

I can say that from my small corner, something has really improved.

In Abril, when ipv6.google.com was launched, the avg latency from my 
network was about 140% higher when comparing to www.google.com.

*Now* it's about 10% *lower*! (about ~5ms in absolute values). So, someone 
tweaked something, somewhere regarding v6 routing :-)

IMHO, this also may indicate that there is still something along the 
path in the v4 side which may need some tunning... ;-)


Best Regards,
Carlos
(Portuguese NREN)

From nuno.vieira at nfsi.pt  Fri Nov  7 10:37:22 2008
From: nuno.vieira at nfsi.pt (Nuno Vieira - nfsi telecom)
Date: Fri, 7 Nov 2008 09:37:22 +0000 (WET)
Subject: Some leaks in China/Hongkong
In-Reply-To: <Pine.LNX.4.64.0811070900450.6846@gauntlet.fccn.pt>
Message-ID: <2046639469.28451226050642462.JavaMail.root@zimbra.nfsi.pt>

Hi Carlos, Hi All,

Speaking of commercial isp's, I see a huge difference from here... (40% +/-)

is this GeoIP / DNS thingie, or something really nasty on v4 ?

# ping www.google.com
PING www.l.google.com (64.233.183.103) 56(84) bytes of data.
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=1 ttl=244 time=59.6 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=2 ttl=244 time=56.8 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=3 ttl=244 time=57.1 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=4 ttl=244 time=58.9 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=5 ttl=244 time=58.7 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=6 ttl=244 time=58.1 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=7 ttl=244 time=57.3 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=8 ttl=244 time=57.7 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=9 ttl=244 time=59.6 ms
64 bytes from nf-in-f103.google.com (64.233.183.103): icmp_seq=10 ttl=244 time=60.2 ms

--- www.l.google.com ping statistics ---
10 packets transmitted, 10 received, 0% packet loss, time 8999ms
rtt min/avg/max/mdev = 56.822/58.447/60.252/1.161 ms

# ping6 ipv6.google.com
PING ipv6.google.com(2001:4860:0:1001::68) 56 data bytes
64 bytes from 2001:4860:0:1001::68: icmp_seq=1 ttl=56 time=38.7 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=2 ttl=56 time=36.6 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=3 ttl=56 time=36.8 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=4 ttl=56 time=36.3 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=5 ttl=56 time=36.2 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=6 ttl=56 time=36.5 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=7 ttl=56 time=36.2 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=8 ttl=56 time=36.8 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=9 ttl=56 time=36.9 ms
64 bytes from 2001:4860:0:1001::68: icmp_seq=10 ttl=56 time=36.7 ms

--- ipv6.google.com ping statistics ---
10 packets transmitted, 10 received, 0% packet loss, time 9033ms
rtt min/avg/max/mdev = 36.261/36.829/38.737/0.685 ms


# traceroute www.google.com
traceroute: Warning: www.google.com has multiple addresses; using 64.233.183.103
traceroute to www.l.google.com (64.233.183.103), 30 hops max, 40 byte packets
 1  ge130-1000m.cr2.lisboa.nfsi.pt (81.92.200.126)  0.139 ms  0.199 ms  0.113 ms
 2  xe12-10GE.xmr1.as25137.net (81.92.201.10)  1.359 ms  0.348 ms  0.365 ms
 3  if-1-2-151.core1.PV9-Lisbon.as6453.net (195.219.186.9)  0.487 ms  0.346 ms  0.240 ms
 4  if-12-0-0.mcore3.L78-London.as6453.net (195.219.144.5)  27.349 ms  27.073 ms  26.976 ms
 5  if-5-0-0.mcore3.LDN-London.as6453.net (195.219.195.9)  32.463 ms  32.324 ms  32.613 ms
 6  ldn-b4-link.telia.net (213.248.74.1)  32.446 ms  34.502 ms  32.539 ms
 7  ldn-bb1-link.telia.net (80.91.249.77)  32.622 ms ldn-bb1-link.telia.net (80.91.250.234)  32.700 ms  32.452 ms
 8  adm-bb2-pos6-0-0.telia.net (213.248.65.158)  39.836 ms adm-bb1-pos6-0-0.telia.net (213.248.65.150)  43.489 ms  43.314 ms
 9  adm-b4-link.telia.net (80.91.250.66)  43.338 ms adm-b4-link.telia.net (80.91.253.86)  39.976 ms adm-b4-link.telia.net (80.91.253.82)  39.699 ms
10  google-118151-adm-b4.c.telia.net (213.248.72.14)  54.257 ms google-ic-127680-adm-bb2.c.telia.net (213.248.91.54)  48.193 ms google-ic-126116-adm-b4.c.telia.net (80.239.193.182)  45.820 ms
11  209.85.251.12 (209.85.251.12)  52.971 ms 209.85.251.14 (209.85.251.14)  56.089 ms  53.862 ms
12  64.233.175.246 (64.233.175.246)  51.057 ms 72.14.233.114 (72.14.233.114)  49.855 ms 64.233.175.246 (64.233.175.246)  48.394 ms
13  209.85.255.23 (209.85.255.23)  58.856 ms 216.239.46.51 (216.239.46.51)  49.990 ms 72.14.233.79 (72.14.233.79)  48.822 ms
14  209.85.249.133 (209.85.249.133)  57.250 ms 216.239.43.30 (216.239.43.30)  61.987 ms  65.345 ms
15  nf-in-f103.google.com (64.233.183.103)  61.596 ms  61.217 ms  60.348 ms

# traceroute6 ipv6.google.com
traceroute to ipv6.l.google.com (2001:4860:0:1001::68) from 2001:b18::211:43ff:fefd:90f6, 30 hops max, 16 byte packets
 1  ge-1.Edge1.ip6.Lisbon.NFSi.pt (2001:b18::ffff)  0.346 ms  0.31 ms  0.234 ms
 2  2001:5a0:1500::1 (2001:5a0:1500::1)  0.729 ms  0.456 ms  0.358 ms
 3  2001:5a0:1500::e (2001:5a0:1500::e)  27.217 ms  27.205 ms  27.213 ms
 4  2001:5a0:c00:100::e (2001:5a0:c00:100::e)  32.949 ms  36.937 ms  32.967 ms
 5  2001:5a0:200::5 (2001:5a0:200::5)  68.051 ms  37.071 ms  37.088 ms
 6  pr61.ams04.net.google.com (2001:7f8:1::a501:5169:1)  33.581 ms  36.939 ms  33.709 ms
 7  * * *
 8  * * *
 9  * * *
10  * * *
11  * 2001:4860:0:1001::68 (2001:4860:0:1001::68)  39.995 ms  36.551 ms

Regards,
---
Nuno Vieira
nfsi telecom, lda.

nuno.vieira at nfsi.pt
Tel. (+351) 21 949 2300 - Fax (+351) 21 949 2301
http://www.nfsi.pt/



----- "Carlos Friacas" <cfriacas at fccn.pt> wrote:

> On Wed, 29 Oct 2008, Gert Doering wrote:
> 
> > To be a bit more constructive: you could maintain a list of AS
> numbers
> > that belong to known research networks and should be reached via
> Geant2,
> > and local-pref these.  Anything else coming in via Geant2 should not
> be
> > local-prefed (don't necessarily *drop*, even if that might be
> prudent given
> > some of the crap I2 is leaking, but at least do not *force*) - which
> would
> > avoid routing Google traffic to Hongkong, instead of Amsterdam.
> 
> Hello,
> 
> I can say that from my small corner, something has really improved.
> 
> In Abril, when ipv6.google.com was launched, the avg latency from my 
> network was about 140% higher when comparing to www.google.com.
> 
> *Now* it's about 10% *lower*! (about ~5ms in absolute values). So,
> someone 
> tweaked something, somewhere regarding v6 routing :-)
> 
> IMHO, this also may indicate that there is still something along the 
> path in the v4 side which may need some tunning... ;-)
> 
> 
> Best Regards,
> Carlos
> (Portuguese NREN)

From gert at space.net  Fri Nov  7 15:00:52 2008
From: gert at space.net (Gert Doering)
Date: Fri, 7 Nov 2008 15:00:52 +0100
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <alpine.LRH.2.00.0811071007140.7052@netcore.fi>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
Message-ID: <20081107140052.GR89033@Space.Net>

Hi,

On Fri, Nov 07, 2008 at 10:09:06AM +0200, Pekka Savola wrote:
> Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by 
> default. DUH!

Whut?  Why?  Is it sold as an "Ethernet switch" or as an "IPv4 Ethernet"?

Stupid idea.

Gert Doering
        -- NetMaster
-- 
Total number of prefixes smaller than registry allocations:  128645

SpaceNet AG                        Vorstand: Sebastian v. Bomhard
Joseph-Dollinger-Bogen 14          Aufsichtsratsvors.: A. Grundner-Culemann
D-80807 Muenchen                   HRB: 136055 (AG Muenchen)
Tel: +49 (89) 32356-444            USt-IdNr.: DE813185279

From dave at maxgigapop.net  Fri Nov  7 23:25:02 2008
From: dave at maxgigapop.net (Dave Diller)
Date: Fri, 7 Nov 2008 17:25:02 -0500
Subject: Juniper EX and IPv6
In-Reply-To: <alpine.LRH.2.00.0811071007140.7052@netcore.fi>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
Message-ID: <3B151F00-7E2A-49C3-B8F6-776EA2DE66EF@maxgigapop.net>

>
> Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by  
> default. DUH!

What version of code was this?  It seems to work for me as is with  
trunked ports, on 9.2R1.10.

I've got an EX in the lab, with a GE trunked to each of two T-series.   
I just put an IPv6 address on the router subinterfaces and was able to  
ping across after the ~10 second neighbor discovery process.  I don't  
remember intentionally configuring anything to "enable" passing v6  
through the box since I wasn't aware of this until now.

EX interfaces are plain vanilla:

     ge-0/0/1 {
         mtu 9216;
         unit 0 {
             family ethernet-switching {
                 port-mode trunk;
                 vlan {
                     members [ 55 66 ];
                 }
             }
         }
     }


-dd

From mleber at he.net  Sat Nov  8 05:28:03 2008
From: mleber at he.net (Mike Leber)
Date: Fri, 07 Nov 2008 20:28:03 -0800
Subject: fixed configuration 48 port layer 3 routers
In-Reply-To: <491385BB.1060301@he.net>
References: <491385BB.1060301@he.net>
Message-ID: <49151553.4050502@he.net>


BTW, thank you to everybody for the suggestions.  We'll work on getting 
quotes and hardware to test.

Mike.

-- 
+---------------- H U R R I C A N E - E L E C T R I C ----------------+
| Mike Leber        Wholesale IPv4 and IPv6 Transit      510 580 4100 |
| Hurricane Electric                                           AS6939 |
| mleber at he.net     Internet Backbone & Colocation      http://he.net |
+---------------------------------------------------------------------+

From pekkas at netcore.fi  Sat Nov  8 07:56:03 2008
From: pekkas at netcore.fi (Pekka Savola)
Date: Sat, 8 Nov 2008 08:56:03 +0200 (EET)
Subject: Juniper EX and IPv6
In-Reply-To: <3B151F00-7E2A-49C3-B8F6-776EA2DE66EF@maxgigapop.net>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
	<3B151F00-7E2A-49C3-B8F6-776EA2DE66EF@maxgigapop.net>
Message-ID: <alpine.LRH.2.00.0811080853520.1189@netcore.fi>

On Fri, 7 Nov 2008, Dave Diller wrote:
>> Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by default. 
>> DUH!
>
> What version of code was this?  It seems to work for me as is with trunked 
> ports, on 9.2R1.10.
>
> I've got an EX in the lab, with a GE trunked to each of two T-series.  I just 
> put an IPv6 address on the router subinterfaces and was able to ping across 
> after the ~10 second neighbor discovery process.  I don't remember 
> intentionally configuring anything to "enable" passing v6 through the box 
> since I wasn't aware of this until now.
>
> EX interfaces are plain vanilla:
>
>    ge-0/0/1 {
>        mtu 9216;
>        unit 0 {
>            family ethernet-switching {
>                port-mode trunk;
>                vlan {
>                    members [ 55 66 ];
>                }
>            }
>        }
>    }

This was 9.2.  We tested only non-tagged regular ports and had to add 
something like this:

interfaces {
   vlan {
     unit 0 {
       family inet6;
     }
   }
}

-- 
Pekka Savola                 "You each name yourselves king, yet the
Netcore Oy                    kingdom bleeds."
Systems. Networks. Security. -- George R.R. Martin: A Clash of Kings

From udo at stueberl.de  Sat Nov  8 12:34:04 2008
From: udo at stueberl.de (Udo Steinegger)
Date: Sat, 8 Nov 2008 12:34:04 +0100
Subject: Juniper EX and IPv6
In-Reply-To: <alpine.LRH.2.00.0811080853520.1189@netcore.fi>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
	<3B151F00-7E2A-49C3-B8F6-776EA2DE66EF@maxgigapop.net>
	<alpine.LRH.2.00.0811080853520.1189@netcore.fi>
Message-ID: <E276385B-23C3-46E5-8506-8EFE09CE318A@stueberl.de>

Pekka,

You need family ethernet-switching rather than family
Inet6 on your Interface/unit.
Guess that was your problem.

My setup:
Host--ex4200--ex4200--host

Works just Fine with JunOS 9.x, with x equals to 0, 1 and 2

Hope that helps

Cheers
Udo
--

Am 08.11.2008 um 07:56 schrieb Pekka Savola <pekkas at netcore.fi>:

> On Fri, 7 Nov 2008, Dave Diller wrote:
>>> Juniper EX-switches (when in L2 mode) don't forward IPv6 frames by  
>>> default. DUH!
>>
>> What version of code was this?  It seems to work for me as is with  
>> trunked ports, on 9.2R1.10.
>>
>> I've got an EX in the lab, with a GE trunked to each of two T- 
>> series.  I just put an IPv6 address on the router subinterfaces and  
>> was able to ping across after the ~10 second neighbor discovery  
>> process.  I don't remember intentionally configuring anything to  
>> "enable" passing v6 through the box since I wasn't aware of this  
>> until now.
>>
>> EX interfaces are plain vanilla:
>>
>>   ge-0/0/1 {
>>       mtu 9216;
>>       unit 0 {
>>           family ethernet-switching {
>>               port-mode trunk;
>>               vlan {
>>                   members [ 55 66 ];
>>               }
>>           }
>>       }
>>   }
>
> This was 9.2.  We tested only non-tagged regular ports and had to  
> add something like this:
>
> interfaces {
>  vlan {
>    unit 0 {
>      family inet6;
>    }
>  }
> }
>
> -- 
> Pekka Savola                 "You each name yourselves king, yet the
> Netcore Oy                    kingdom bleeds."
> Systems. Networks. Security. -- George R.R. Martin: A Clash of Kings
>

From pekkas at netcore.fi  Sat Nov  8 15:25:50 2008
From: pekkas at netcore.fi (Pekka Savola)
Date: Sat, 8 Nov 2008 16:25:50 +0200 (EET)
Subject: Juniper EX and IPv6
In-Reply-To: <E276385B-23C3-46E5-8506-8EFE09CE318A@stueberl.de>
References: <491385BB.1060301@he.net>
	<2EBCE509-4421-4D45-A601-4CF4108D5628@stueberl.de>
	<alpine.LRH.2.00.0811071007140.7052@netcore.fi>
	<3B151F00-7E2A-49C3-B8F6-776EA2DE66EF@maxgigapop.net>
	<alpine.LRH.2.00.0811080853520.1189@netcore.fi>
	<E276385B-23C3-46E5-8506-8EFE09CE318A@stueberl.de>
Message-ID: <alpine.LRH.2.00.0811081617480.9137@netcore.fi>

On Sat, 8 Nov 2008, Udo Steinegger wrote:
> You need family ethernet-switching rather than family
> Inet6 on your Interface/unit.
> Guess that was your problem.
>
> My setup:
> Host--ex4200--ex4200--host
>
> Works just Fine with JunOS 9.x, with x equals to 0, 1 and 2

In our case, it wasn't enough.  Example:

interfaces {
     ...
     ge-0/0/39 {
         unit 0 {
             family ethernet-switching;
         }
     }
     ...
     vlan {
         unit 0 {
             family inet {
                 filter {
                     input ACL;
                 }
                 address x.x.x.x/24;
             }
             family inet6; <== had to be added
         }
     }

vlans {
     default {
         vlan-id 1;
         l3-interface vlan.0; <== had to be added
     }
}

I'd suspect that adding family inet and a v4 address for management 
purposes made the software confused whether it should be a switch or 
router; however, v4 packets were switched fine without adding these 
two options, v6 weren't.

-- 
Pekka Savola                 "You each name yourselves king, yet the
Netcore Oy                    kingdom bleeds."
Systems. Networks. Security. -- George R.R. Martin: A Clash of Kings

From truman at suspicious.org  Sun Nov  9 01:23:11 2008
From: truman at suspicious.org (truman at suspicious.org)
Date: Sun, 9 Nov 2008 00:23:11 +0000
Subject: Juniper EX and IPv6
Message-ID: <333889517-1226190194-cardhu_decombobulator_blackberry.rim.net-1230367407-@bxe005.bisx.prodap.on.blackberry>

After the interesting post regarding ipv6 forwarding on ex-series, I asked one our engineers to test this out. Everything worked fine with no specific IPv6 configuration on the EX running junos 9.3

Details below:

it works fine in 9.3 .

M10i ------- EX -------- M160


EX in L2 mode with trunk-port to M10i and M160, and also configured a L3-interface vlan.10 on EX,  both transit and local originated icmp6 traffic works fine.


lab at m10i-re0# run show interfaces terse ge-0/0/0 
Interface               Admin Link Proto    Local                 Remote
ge-0/0/0                up    up  
ge-0/0/0.0              up    up   inet     20.1.1.1/24     
                                   inet6    fe80::205:8500:af3:b000/64
                                            fec0:1:1:1::1/64
                                   mpls    


lab at m160# run show interfaces terse ge-6/1/0 
Interface               Admin Link Proto    Local                 Remote
ge-6/1/0                up    up  
ge-6/1/0.0              up    up   inet     20.1.1.2/24     
                                   inet6    fe80::290:6900:a4e:3f13/64
                                            fec0:1:1:1::2/64


lab at EX4200-IPG# run show interfaces terse vlan.10 
Interface               Admin Link Proto    Local                 Remote
vlan.10                 up    up   inet6    fe80::219:e2ff:fe50:a300/64
                                            fec0:1:1:1::3/64



lab at m10i-re0# run ping fec0:1:1:1::2    
PING6(56=40+8+8 bytes) fec0:1:1:1::1 --> fec0:1:1:1::2
16 bytes from fec0:1:1:1::2, icmp_seq=0 hlim=64 time=1.022 ms
16 bytes from fec0:1:1:1::2, icmp_seq=1 hlim=64 time=0.849 ms
16 bytes from fec0:1:1:1::2, icmp_seq=2 hlim=64 time=0.985 ms
^C
--- fec0:1:1:1::2 ping6 statistics ---
3 packets transmitted, 3 packets received, 0% packet loss
round-trip min/avg/max/std-dev = 0.849/0.952/1.022/0.074 ms

[edit]
lab at m10i-re0# run ping fec0:1:1:1::3    
PING6(56=40+8+8 bytes) fec0:1:1:1::1 --> fec0:1:1:1::3
16 bytes from fec0:1:1:1::3, icmp_seq=0 hlim=64 time=1.069 ms
16 bytes from fec0:1:1:1::3, icmp_seq=1 hlim=64 time=0.763 ms
16 bytes from fec0:1:1:1::3, icmp_seq=2 hlim=64 time=1.097 ms
16 bytes from fec0:1:1:1::3, icmp_seq=3 hlim=64 time=1.029 ms
^C
--- fec0:1:1:1::3 ping6 statistics ---
4 packets transmitted, 4 packets received, 0% packet loss
round-trip min/avg/max/std-dev = 0.763/0.989/1.097/0.133 ms


lab at m10i-re0# run show ipv6 neighbors 
IPv6 Address                 Linklayer Address  State       Exp Rtr Interface
fec0:1:1:1::2                00:90:69:4e:3f:13  stale       1044 yes ge-0/0/0.0  
fec0:1:1:1::3                00:19:e2:50:a3:00  stale       1113 yes ge-0/0/0.0  



lab at EX4200-IPG# run show version 
fpc0:
--------------------------------------------------------------------------
Hostname: EX4200-IPG
Model: ex4200-24f
JUNOS Base OS boot [9.3-20080816.0]
JUNOS Base OS Software Suite [9.3-20080816.0]
JUNOS Kernel Software Suite [9.3-20080816.0]
JUNOS Crypto Software Suite [9.3-20080816.0]
JUNOS Online Documentation [9.3-20080816.0]
JUNOS Enterprise Software Suite [9.3-20080816.0]
JUNOS Packet Forwarding Engine Enterprise Software Suite [9.3-20080816.0]
JUNOS Routing Software Suite [9.3-20080816.0]
JUNOS Web Management [9.3-20080816.0]

Kind regards,
Truman Boyes


------Original Message------
From: Pekka Savola
Sender: ipv6-ops-bounces+truman=suspicious.org at lists.cluenet.de
To: Udo Steinegger
Cc: ipv6-ops at lists.cluenet.de
Sent: Nov 8, 2008 9:25 AM
Subject: Re: Juniper EX and IPv6

On Sat, 8 Nov 2008, Udo Steinegger wrote:
> You need family ethernet-switching rather than family
> Inet6 on your Interface/unit.
> Guess that was your problem.
>
> My setup:
> Host--ex4200--ex4200--host
>
> Works just Fine with JunOS 9.x, with x equals to 0, 1 and 2

In our case, it wasn't enough.  Example:

interfaces {
     ...
     ge-0/0/39 {
         unit 0 {
             family ethernet-switching;
         }
     }
     ...
     vlan {
         unit 0 {
             family inet {
                 filter {
                     input ACL;
                 }
                 address x.x.x.x/24;
             }
             family inet6; <== had to be added
         }
     }

vlans {
     default {
         vlan-id 1;
         l3-interface vlan.0; <== had to be added
     }
}

I'd suspect that adding family inet and a v4 address for management 
purposes made the software confused whether it should be a switch or 
router; however, v4 packets were switched fine without adding these 
two options, v6 weren't.

-- 
Pekka Savola                 "You each name yourselves king, yet the
Netcore Oy                    kingdom bleeds."
Systems. Networks. Security. -- George R.R. Martin: A Clash of Kings



Sent via BlackBerry? from Telstra