Mike H. MacGregor

Learn More
The total transmission capacity required by a transport network to satisfy demand and protect it from failures contributes significantly to its cost, especially in long-haul networks. Previously, the spare capacity of a network with a given set of working span sizes has been optimized to facilitate span restoration [11], [12]. Path restorable networks can,(More)
Workload distribution is critical to the performance of network processor based parallel forwarding systems. Scheduling schemes that operate at the packet level, e.g., round-robin, cannot preserve packet-ordering within individual TCP connections. Moreover, these schemes create duplicate information in processor caches and therefore are inefficient in(More)
The problem of finding shortest paths arises in many contexts; testing restoration algorithms and developing design packages for large telecommunications networks are two cases where the simple task of finding sets of restoration paths can consume up to 95 per cent of the execution time of an application program. This paper presents experimental studies of(More)
This paper presents a new routing algorithm for a wireless ATM LAN. The LAN combines positive aspects of connectionoriented and datagram communications schemes in its usage of the ATM VP/VC concept. In this scheme, a set of VPI trees, rooted at each node in the LAN, are preestablished. This has the effect of emulating “connectionless” networking which(More)
Packet scheduling in parallel forwarding systems is a hard problem. Two major goals of a scheduler that distributes incoming packets to multiple forwarding engines are to achieve high system utilization (by balancing the load evenly among the multiple engines) and to maintain packet ordering within individual <i>flows</i>. Additionally, from the viewpoint(More)
Fair Queuing was invented to ensure that every flow gets its fair share of the total bandwidth. Efficient Fair Queuing Using Deficit Round-Robin, DRR, proposed by Shreedhar and Varghese [1], reduces the work to process each packet from O(log(n)) to O(1). DRR was also extended to accommodate latency-critical flows. DRR+ uses a timer to police each(More)
By investigating flow level characteristics of Internet traffic, we are able to trace the root of load imbalance in hash-based load-splitting schemes. We model flow popularity distributions as Zipf-like and prove that under typical Internet traffic mix, a hash scheme cannot balance workload statistically, not even in the long run. We then develop a novel(More)
We estimate that approximately 40% of current Internet traffic is due to Web crawlers retrieving pages for indexing. We address this problem by introducing an efficient indexing system based on active networks. Our approach employs strategically placed active routers that constantly monitor passing Internet traffic, analyze it, and then transmit the index(More)