Prior measurement studies of the Internet have explored traffic and topology, but have largely ignored edge hosts. While the number of Internet hosts is very large, and many are hidden behind firewalls or in private address space, there is much to be learned from examining the population of visible hosts, those with public unicast addresses that respond to messages. In this paper we introduce two new approaches to explore the visible Internet. Applying statistical population sampling, we use censuses to walk the entire Internet address space, and surveys to probe frequently a fraction of that space. We then use these tools to evaluate address usage, where we find that only 3.6% of allocated addresses are actually occupied by visible hosts, and that occupancy is unevenly distributed, with a quarter of responsive /24 address blocks (subnets) less than 5% full, and only 9% of blocks more than half full. We show about 34 million addresses are very stable and visible to our probes (about 16% of responsive addresses), and we project from this up to 60 million stable Internet-accessible computers. The remainder of allocated addresses are used intermittently, with a median occupancy of 81 minutes. Finally, we show that many firewalls are visible, measuring significant diversity in the distribution of firewalled block size. To our knowledge, we are the first to take a census of edge hosts in the visible Internet since 1982, to evaluate the accuracy of active probing for address census and survey, and to quantify these aspects of the Internet.

No abstract

When nodes of a communication network have identical input-and output-link capacities, i t is possible to use as few as one packet buffer per link, if we are willing to deflect-or misroute-a subset of simultaneously arriving fixed-length packets from preferred to alternate output links. This scheme, known as deflection routing, can achieve very fast packet switching in regular networks and has been proposed as the basic routing and switching protocol of several all-optical networks. The performance models of deflection-routing networks that have appeared in the literature have assumed that time is slotted and packets arrive at nodes on time-slot boundaries. In practice, however, slotted operation is difficult to implement in all-optical networks. In this paper we evaluate by simulation the performance of deflection routing in unslotted networks. The evaluations show a surprising degradation of throughput in unslotted deflectionrouting networks, compared to slotted networks, and reveal situations where severe congestion occurs. To overcome these limitations we propose the use of specific control mechanisms in unslotted networks that allow us to eliminate congestion and to improve substantially the network throughput.

Summary. This paper examines task allocation in fault-tolerant distributed systems. The problem is formulated as a constrained sum of squares minimization problem. The computational complexity of this problem prompts us to consider an efficient approximation algorithm. We show that the ratio of the performance of the approximation algorithm to that of the optimal solution is bounded by 9m/(8(m-r+l)), where m is the number of processors to be allocated and r is the number of times each task is to be replicated. Experience with the algorithm suggests that even better performance ratios can be expected. List of Important Symbols

As routing tables in core Internet routers grow to exceed 100 000 entries, it is becoming essential to develop methods to reduce the lookup time required to forward packets toward their destinations. In this paper, we employ a bank of novel thermally tuned fiber-Bragg-grating-based optical correlators to construct an "optical bypass" to accelerate conventional electronic Internet routers. The correlators are configured as a routing table cache that can quickly determine the destination port for a fraction of the incoming traffic by examining only a subset of the bits in an IP packet's 32-bit destination address.We also demonstrate a novel multiwavelength correlator based on fiber Bragg grating that can simultaneously recognize the header bits on multiple wavelengths for use in wavelength-division-multiplexed (WDM) systems. Using the optical bypass, routing table lookup times are reduced by an order of magnitude from microseconds to nanoseconds and are limited only by the speed of the optical switch. Index Terms-Optical communications, optical correlators, optical signal processing, wavelength-division-multiplexed (WDM) networks. I. INTRODUCTION I N present-day fiber-optic networks, data packets are converted to electrical form at each node to process their headers and make routing decisions, as shown in Fig. 1(a). As routing tables grow in size, more memory accesses are required to determine the next-hop address and appropriate output port to which to forward each packet. The associated increase in routing-table lookup times is becoming a significant source of latency in the network core. To make matters worse, the transmission capacity of optical fibers is rapidly increasing, forcing the routers to accommodate more packets, more often. Since routing tables will Manuscript