The market for multiplayer online games is rapidly growing in concert with the growth in broadband Internet connection services. Since such games share a virtual space among many players, it is important to match players to a group so that they share low-latency connections with each other. This is because the latency between them affects the perceived quality of their experience. In this paper, we propose a topology-aware matching algorithm using players' geographical locations. We focus on synchronous multiplayer games that require a latency comparable to a delay of one frame. This paper describes the algorithm and its evaluation by simulations.

Recently, content delivery services using the P2P architecture have been growing rapidly over the Internet. ISPs are suffering from network congestion due to the increase in traffic volume. For efficient delivery of P2P traffic, the IETF ALTO WG (Application-Layer Traffic Optimization) has been working on the standardization of the ALTO service for controlling P2P traffic. In addition, ALTO services have a ranking service, which is providing the ranking value indicating the peer selection priority using the BGP attribute. In this paper, we propose the mechanism of an ISP-Friendly with ALTO-like server called “n-Tracker”, which provides a ranking service that applies the ISP's own policy flexibly. This mechanism defines the ranking value according to the P2P peer selection policy for the ISP using not only the BGP attributes received from external ASes but also ISP own policies statically configured by ISP operators. We evaluated the performance of the n-Tracker, which was running on a 1U PC server. For example, we evaluated the processing time to reflect the policies when it received the approximately 310,000 BGP routes and the n-Tracker's average response time for each request from the client. We validated that they took 19.57 sec and 2.30 msec, respectively. In addition, we showed that the priority for the peers changed depending on the configuration of the policies configured in the n-Tracker, and we validated that download traffic could be controlled by the peer selection policy.

The Border Gateway Protocol (BGP) is one of the key components of today's Internet infrastructure. Many ISPs rely on BGP for convergence of inter-domain routes upon BGP link failures. However, the convergence of BGP requires several seconds of downtime, which may cause critical performance degradation of applications. In this paper, we propose the use of an intra-domain routing protocol to provide IP fast reroute for BGP link failures. The proposed scheme extends OSPF to restore the nexthop IP address associated with the BGP link failure. Since the reachability of the nexthop is restored at the IGP layer, no convergence is required at the BGP layer. We also introduce a recursive lookup mechanism for forwarding of packets to achieve fast update of the forwarding table. Evaluation using a prototype and real BGP prefixes observed in the Internet showed that the proposed scheme is capable of reducing the current recovery time by 13.40 seconds. The proposed scheme performs recovery with limited routers and is effective where Route Reflectors are in place.

The current interdomain routing protocol, BGP, is not resilient to a path failure due to its single-path and slowly-converging route calculation. This paper proposes a novel approach to improve the resilience of the interdomain communication by enabling a set of ASes to form an alliance for themselves. The alliance members cooperatively discover a set of disjoint paths using not only the best routes advertised via BGP but also the ones unadvertised. Since such a set of disjoint paths are unlikely to share a link or an AS failure, a member AS can provide a pair of the other members with a transit to circumvent the failure. We evaluate how many disjoint paths we could discover from both advertised and hidden (unadvertised) routes by analyzing publicly available BGP route data. Our feasibility study indicates that an alliance of ASes can establish a set of disjoint paths between arbitrary pair of its alliance members to improve the resilience of interdomain routing among the members.

If a problem with IP communication occurs, IP network operators refer to the routing tables of the affected routers to check the routes to the destinations. There are a number of methods currently used for referring to routing tables. However, operators cannot refer to past routing tables using existing methods. The past routing tables are useful for IP network operation. For example, operators can find out how the influence of a network problem on routes spreads to the network by checking fluctuations in each routerpsilas routing table. In this paper, we propose a method of collecting every routerpsilas routing table within a domain based on the monitoring of routing protocols. In our method, we collect routing protocol messages and calculate all routerspsila routing tables within a domain in a concentrated manner using the same way where each router within a domain calculates its routing table. Routing tables are calculated whenever route status in IP networks changes, and calculated routing tables are stored so that operators can refer to them at any time in the future.

As the Internet has become a communication infrastructure, inter-domain routing instabilities have become prone to serious problems. Some studies have proposed methods that infer instabilities and their locations by clustering BGP update messages collected at multiple observation points and are based on post-processing using public messages. However, to realize real-time processing, which is vital for network operations, single point observation is a feasible option with costs and today's competitive environments in mind. Therefore, we propose an inference method including a new clustering algorithm that is suitable for messages collected at a single observation point. We also describe the empirical results used to validate our method.

It is important to monitor routing protocols for stable operation of IP networks. In this paper, we focus on Open Shortest Path First (OSPF), a widely deployed intra-domain routing protocol. Routers running OSPF advertise their link states on Link State Advertisements (LSAs) to the network so the location of OSPF failures on the IP network can be detected by monitoring LSAs. However, in order to identify OSPF failures correctly, it is necessary to consider the association of multiple flooded LSAs when OSPF failures occurred and LSA delay. In this paper, we propose a method of OSPF failure identification based on LSA flooding analysis taking these aspects into account.