Internet exchange point
From Wikipedia, the free encyclopedia
An Internet exchange point (IX or IXP) is a physical infrastructure that allows different Internet service providers (ISPs) to exchange Internet traffic between their networks (autonomous systems) by means of mutual peering agreements, which allow traffic to be exchanged without cost. IXPs reduce the portion of an ISP's traffic which must be delivered via their upstream transit providers, thereby reducing the Average Per-Bit Delivery Cost of their service. Furthermore, the increased number of paths learned through the IXP improves routing efficiency and fault-tolerance.
The primary purpose of an IXP is to allow networks to interconnect directly, via the exchange, rather than through one or more 3rd party networks. The advantages of the direct interconnection are numerous, but the primary reasons are cost, latency, and bandwidth. Traffic passing through an exchange is typically not billed by any party, whereas traffic to an ISP's upstream provider is. The direct interconnection, often located in the same city as both networks, avoids the need for data to travel to other cities (potentially on other continents) to get from one network to another, thus reducing latency. The third advantage, speed, is most noticeable in areas that have poorly developed long-distance connections. ISPs in these regions might have to pay between 10 or 100 times more for data transport than ISPs in North America, Europe or Japan. Therefore, these ISPs typically have slower, more limited connections to the rest of the internet. However, a connection to a local IXP may allow them to transfer data without limit, and without cost, vastly improving the bandwidth between customers of the two adjacent ISPs.
A typical IXP consists of one or more network switches, to which each of the participating ISPs connect. Prior to the existence of switches, IXPs typically utilized FOIRL hubs or FDDI rings, migrating to Ethernet and FDDI switches as those became available in 1993 and 1994. ATM switches were briefly used at a few IXPs in the late 1990s, accounting for approximately 4% of the market at their peak, and there was an abortive attempt by the Stockholm IXP, NetNod, to use SRP/DPT (an ill-fated conjoinment of FDDI and SONET), but Ethernet has prevailed, accounting for more than 95% of all existing Internet exchange switch fabrics. All Ethernet port speeds are to be found at modern IXPs, ranging from 10 Mbit/s ports in use in small developing-country IXes, to ganged 10 Gbit/s ports in major centers like Seoul, New York, London, Frankfurt, Amsterdam, and Palo Alto.
When an IXP incurs any operating costs, those costs are typically shared among all of its participants. At the more expensive exchanges, participants pay a monthly or annual fee, usually determined by the speed of the port or ports which they're using, or much less commonly by the volume of traffic which they're passing across the exchange (fees based on volume of traffic are unpopular because they provide a counterincentive to growth of the exchange). Some exchanges also have a setup fee, to offset the costs of the switch port and any media adaptors (GBICs, SFPs, XFPs, XENPAKs, et cetera) which the new participant requires, and the labor of configuring it to serve them.
[edit] Interchange of traffic across an Internet Exchange Point
A connection to an IXP does not by itself cause any traffic to be exchanged; it is a physical presence on a shared medium, nothing more.
In order to have Internet traffic flow between two participants on an IXP, the two participants must initiate BGP peering between themselves, and choose to announce routes over the peering relationship - either routes to their own addresses, or routes to addresses of other ISPs that they connect to, possibly via other mechanisms. The other party to the peering can then apply route filtering, where it chooses to accept those routes, and route traffic accordingly, or to ignore those routes, and use other routes to reach those addresses.
In many cases, an ISP will both have a direct link to another ISP and accept a route (normally ignored) to the other ISP through the IXP; if the direct link fails, traffic will then start flowing over the IXP. In this way, the IXP acts as a backup link.