Years after the initial development of the current routing protocols we still lack an understanding of the impact of various parameters on the routes chosen in today's Internet. Network operators are struggling to optimize their routing, but the effectiveness of those efforts is limited.In this article, we study sensitivity of routing stretch and diversity metrics to factors such as policies, topology, IGP weights etc. using statistical techniques. We confirm previous findings that routing policies and AS size (in number of routers) are the dominating factors. Surprisingly, we find that intra-domain factors only have marginal impact on global path properties.Moreover, we study path inflation by comparing against the paths that are shortest in terms of AS-level/router-level hops or geographic distances. Overall, the majority of routes incur reasonable stretch. From the experience with our Internet-scale simulations, we find it hard to globally optimize path selection with respect to the geographic length of the routes, as long as inter-domain routing protocols do not include an explicit notion of geographic distance in the routing information.

Routing policies are typically partitioned into a few classes that capture the most common practices in use today [1]. Unfortunately, it is known that the reality of routing policies [2] and peering relationships is far more complex than those few classes [1,3]. We take the next step of searching for the appropriate granularity at which policies should be modeled. For this purpose, we study how and where to configure per-prefix policies in an AS-level model of the Internet, such that the selected paths in the model are consistent with those observed in BGP data from multiple vantage points.By comparing business relationships with per-prefix filters, we investigate the role and limitations of business relationships as a model for policies. We observe that popular locations for filtering correspond to valleys where no path should be propagated according to inferred business relationships. This result reinforces the validity of the valley-free property used for business relationships inference. However, given the sometimes large path diversity ASs have, business relationships do not contain enough information to decide which path will be chosen as the best. To model how individual ASs choose their best paths, we introduce a new abstraction: next-hop atoms. Next-hop atoms capture the different sets of neighboring ASs an AS uses for its best routes. We show that a large fraction of next-hop atoms correspond to per-neighbor path choices. A non-negligible fraction of path choices, however, correspond to hot-potato routing and tie-breaking within the BGP decision process, very detailed aspects of Internet routing.

Abstract-A Link-State Update Policy (LSUP) has the task to distribute information regarding the network resources, and is therefore considered to be an integral part of future Quality of Service (QoS) routing protocols. The argument is that in order to guarantee QoS to applications, one must know the available resources. Unfortunately, the high dynamics in available resources complicates the development of an LSUP, which on its turn will result in high deployment costs for Internet Service Providers. In this paper we will re-examine whether the gain in network performance, which is expected under the deployment of LSUPs, will outweigh its investment and complexity costs. To capture the complete range of possible LSUPs, we take a pragmatic approach and confine ourselves to examining two extreme strategies: routing with exact resource information and routing with no resource information.Our study comprises of an analytical exercise and extensive simulations on various network topologies under a large range of network loads. Our objective is to determine where static information provides acceptable network performance and where dynamic LSUPs are indispensable.

In this paper we present DeSiNe, a modular flow-level network simulator. DeSiNe is aimed at performance analysis and benchmarking of Quality of Service routing algorithms and traffic engineering extensions. Several well-known QoS routing algorithms and traffic engineering extensions have been implemented in DeSiNe. The flow-level nature provides scalability, such that large networks and heavy-traffic conditions are possible. In this paper, the functional and structural design of DeSiNe are presented and the usability and various features are illustrated by means of several examples. The source code of DeSiNe is publicly available.

Abstract. Studies of the Internet have typically focused either on the routing system, i.e. the paths chosen to reach a given destination, or on the evolution of traffic on a physical link. In this paper, we combine routing and traffic, and study for the first time the evolution of the traffic on the Internet topology. We rely on the traffic and routing data of a large transit provider, spanning almost a month. We compute distances between the traffic graph over small and large timescales. We find that the global traffic distribution on the AS graph largely differs from traffic observed at small timescales. However, variations between consecutive time periods are relatively limited, i.e. the topology spanned by the traffic from one time period to the next is small. This difference between local and global traffic distribution is found in the timescales at which traffic dynamics occurs on AS-level links. Small timescales, i.e. less than a few hours, do not account for a significant fraction of the traffic dynamics. Most of the traffic variability is concentrated at timescales of days. Models of Internet traffic on its topology should thus focus on capturing the long-term changes in the global traffic pattern.