Longest Prefix Matching Algorithms Research Articles

Can Longest Prefix Matching Make The Path Length Shorter?

It has been recognized that the existing routing architecture of today’s Internet is facing scalability problems. Although deployment of CIDR (Classless Inter-Domain Routing) slows the growth of global routing tables, LPM (longest prefix matching), which is greedily pursuing for more-specific prefixes, seriously restricts the advance of scalable routing. The prevalent LPM algorithm for routing lookup is considered the best path to the destination, which logically makes sense. However, we find that LPM algorithm does not necessarily provide shortest path length for routing lookup in most cases with comparison experiment. To find more general prefixes, we first present SPM (shortest prefix matching) algorithm, and then make a comparative evaluation between SPM and LPM by using the metric of average AS path length. In conclusion, we analyze the reasons that cause longer average AS path length for LPM algorithm in most cases and discuss the impact of LPM to scaling routing.

Longest prefix matching using bloom filters

We introduce the first algorithm that we are aware of to employ Bloom filters for longest prefix matching (LPM). The algorithm performs parallel queries on Bloom filters, an efficient data structure for membership queries, in order to determine address prefix membership in sets of prefixes sorted by prefix length. We show that use of this algorithm for Internet Protocol (IP) routing lookups results in a search engine providing better performance and scalability than TCAM-based approaches. The key feature of our technique is that the performance, as determined by the number of dependent memory accesses per lookup, can be held constant for longer address lengths or additional unique address prefix lengths in the forwarding table given that memory resources scale linearly with the number of prefixes in the forwarding table. Our approach is equally attractive for Internet Protocol Version 6 (IPv6) which uses 128-bit destination addresses, four times longer than IPv4. We present a basic version of our approach along with optimizations leveraging previous advances in LPM algorithms. We also report results of performance simulations of our system using snapshots of IPv4 BGP tables and extend the results to IPv6. Using less than 2 Mb of embedded RAM and a commodity SRAM device, our technique achieves average performance of one hash probe per lookup and a worst case of two hash probes and one array access per lookup.

Versatile optical code-based MPLS for circuit, burst, and packet switchings

We will present versatile optical code (OC)-based photonic MPLS, so-called OC-MPLS which ranges from circuit switching, burst switching, to packet switching. OC-label is an identifier attached to the data, of which information is mapped onto an optical code, a sequence of optical pulses. The OC-label recognition is performed by the optical correlation between an incoming OC-label and the OC-label entries. Unique to the OC-label processing is that it is analog operation entirely in optical domain, and no optical logic operation is involved, therefore, the processing speed is only limited by the propagation delay in the optical correlator, which is a passive optical device. This is a key to the ultrahigh-speed processing capability. Circuit switching of OC-label switched path (OC-LSP) is characterized by the finer data granularity than the wavelength path of GMPS, resulting in a better bandwidth efficiency. In a one-way reservation protocol of photonic burst switching, the OC-labeled control packet improves the throughput by nearly cutting the offset time between the control packet and the following data burst. OC-labeled header of the packet can enables the ultrafast routing in photonic packet switching. To exploit the ultrafast routing capability, a new packet switch architecture is investigated, in which the longest-prefix match algorithm as well as WDM buffering into the fiber delay lines are introduced.

Parallelisation of trie-based longest prefix matching for fast IP address lookups

IP address lookup is an important design issue for the high performance packet forwarding engine. The forwarding engine performs a longest prefix matching on the address lookup for an incoming IP packet to determine the next hop. A parallelisation scheme of longest prefix matching algorithms based on path-compressed trie is proposed. The proposed scheme reduces memory access time of IP address lookup while keeping memory spaces of parallel elements balanced.