Anycast 101

Fri Dec 17 14:55:47 UTC 2004

On 17-dec-04, at 15:27, William Allen Simpson wrote:

>> In short: a customer must pplb across two routers at the same ISP, 
>> and each of those routers must have different preferred paths to 
>> different anycast instances. This isn't going to happen often, but 
>> it's not impossible, and it's not bad engineering on the customer's 
>> or ISP's part if it does, IMO.

> You're wrong.  That's VERY bad engineering!

> PPLB requires 2 routers, one at each end of the link bundle.

It doesn't really require that. Redundancy requires that the routers at 
the ends of two links both be different. Having one router at one end 
and two at the other is a good compromise in many situations.

> More than 1 router at any end will lead to a lot more problems than
> anycast, including multicast and any stateful protocol (like TCP).

How many people run multicast exactly? And that's precisely the reason 
why multicast is a different SAFI so you get to have different 
multicast and unicast routing.

As for TCP, it would be very useful if someone were to run the 
following experiment:
                        +-------+
                        |router2|
                        +-------+
                      /           \
+------+   +-------+               +-------+   +------+
|host a+---+router1|               |router4+---+host b|
+------+   +-------+               +-------+   +------+
                      \           /
                        +-------+
                        |router3|
                        +-------+

(Assuming the links to the hosts are (for instance) gigabit and the 
ones between the routers fast ethernet. If they're all the same speed 
you're only going to see out of order packets when the later packet is 
smaller than the earlier packet, which is inconsistent with a TCP 
session running at full blast.)

Setup #1: per destination load balancing from router1 to routers 2 and 3

Setup #2: per packet load balancing from router1 to routers 2 and 3

So setup #1 will get no reordering, but is limited to 100 Mbps. Setup 
#2 will see reordering, but has a total bandwidth of 200 Mbps. Which 
going to perform better?

> For one thing, the load balancing will be only in 1 direction, and will
> lead to congestion in the reverse path....  Self defeating.

Traffic patterns aren't the same in both directions in many/most cases, 
so one direction may be enough.