• Journal of Communications and Networks
• /
• v.3 no.4
• /
• pp.374-382
• /
• 2001

Nowadays, the commonly used table lookup scheme for IP routing is based on the sc-called classless interdomain routing (CIDR). With CIDR, routers must find out the best matching prefix (BMP) for IP packets forwarding, this complicates the IP lookup. Currently, this process is mainly performed in software and several schemes hale been proposed for hardware implementation. Since the IP lookup performance is a major design issue for the new generation routers, in this article we investigate the properties of the routing table and present a new approach for IP lookups, our approach is not based Gn BMP and significantly reduces the complexity, thus the computation cast of existing schemes can be significantly reduced. We also propose an efficient IP lookup algorithm, with which we improve the binary search on prefixes to 30 millions of packets per second (MPPS) and 5,000 route updates/s under the same experiment setup with an even larger routing table.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11C
• /
• pp.43-50
• /
• 2001

The IP routing uses the longest-matching prefix to determine the destination. Fast lookup should be required for the high speed routing. We propose a modified LC-trie, called multiple LC-trie, which is suitable data structure for fast address-lookups in software implementation. To reduce the number of memory accesses, our scheme analyzes the distribution of IP address access pattern, and constructs multiple LC:-tries for frequently accessed IP addresses. Our experimental results show that our scheme can perform faster than the original LC-trie schemes.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.5 s.347
• /
• pp.137-146
• /
• 2006

IP address lookup has become a major bottleneck of packet forwarding and a critical issue for high-speed networking techniques in routers. In this paper, we propose an efficient high-speed IP address lookup scheme using adaptive multiple hashing and prefix grouping. According to our analysis results based on routing data distributions, we grouped prefix lengths and selected the number of hash functions in each group adaptively. As a result, we can reduce collisions caused by hashing. Accordingly, a forwarding table of our scheme has good memory efficiency, and thus is organized with the proper number of memory modules. Also, the proposed scheme has the fast building and searching mechanisms to develop the forwarding table only during a single memory access.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12B
• /
• pp.1103-1111
• /
• 2008

Internet routers forward an incoming packet to an output port toward its final destination through IP address lookup. Since each incoming packet should be forwarded in wire-speed, it is essential to provide the high-speed search performance. In this paper, IP address lookup algorithms using binary search are studied. Most of the binary search algorithms do not provide a balanced search, and hence the required number of memory access is excessive so that the search performance is poor. On the other hand, binary-search-on-range algorithm provides high-speed search performance, but it requires a large amount of memory. This paper shows an optimized binary-search-on-range structure which reduces the memory requirement by deleting unnecessary entries and an entry field. By this optimization, it is shown that the binary-search-on-range can be performed in a routing table with a similar or lesser number of entries than the number of prefixes. Using real backbone routing data, the optimized structure is compared with the original binary-search-on-range algorithm in terms of search performance. The performance comparison with various binary search algorithms is also provided.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4B
• /
• pp.403-418
• /
• 2009

IP version 6 (IPv6) is a new If addressing scheme that has 128-bit address space. IPv6 is proposed to solve the address space problem of IP version 4 (IPv4) which has 32-bit address space. For a given IPv6 routing set, if a forwarding table is built using a trio structure, the trio has a lot more levels than that for IPv4. Hence, for IPv6 address lookup, the binary search on trio levels would be more appropriate and give better search performance than linear search on trio levels. This paper proposes a new IPv6 address lookup algorithm performing binary search on trio levels. The proposed algorithm uses a Bloom filter in pre-filtering levels which do not have matching nodes, and hence it reduces the number of off-chip memory accesses. Simulation has been performed using actual IPv6 routing sets, and the result shows that an IPv6 address lookup can be performed with 1-3 memory accesses in average for a routing data set with 1096 prefixes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8B
• /
• pp.691-700
• /
• 2006

Based on the destination IP address of incoming packets, the Internet routers determine next hops and forward packets toward final destinations through If address lookup. The bandwidth of communication links increases exponentially fast as well as the routing table size grows significant as the number of single host networks attached to the Internet increases. Since packets should be processed at wire-speed, the increased link speed reduces the processing time of a packet in routers, and hence more efficient and fast IP address lookup algorithms and architectures are required in the next generation routers. Most of the previous IP lookup schemes compare routing prefixes of shorter length first with a given input IP address. Since IP address lookup needs to find the most specific route of the given input, search continues until the longest matched prefix is found while it keeps remembering the current test matching prefix. In this paper, based on binary search on prefix length, we proposed a new IP address lookup algorithm which compares longer prefixes first. The proposed scheme is consisted of multiple tries with prefixes on leaves only. The trie composed of the longest prefixes is primarily searched whether there is a match with the given input. This processing is repeated for the trio of the next longer prefixes until there finds a match. Hence the proposed algorithm provides the fast search speed. The proposed algorithm also provides the incremental update of prefixes while the previous binary search on length scheme does not provide the incremental update because of pre-processing requirement. In this paper, we performed extensive simulations and showed the performance comparisons with related works.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.7B
• /
• pp.647-659
• /
• 2003

LPM(Longest Prefix Matching)searching in If address lookup is a major bottleneck of IP packet processing in the high speed router. In the conventional lookup table for the LPM searching in CAM(Content Addressable Memory) the complexity of fast update take 0(1). In this paper, we designed pipeline architecture for fast update of 0(1) cycle of lookup table and high throughput and low area complexity on LPM searching. Lookup-table architecture was designed by CAM(Content Addressable Memory)away that uses 1bit RAM(Random Access Memory)cell. It has three pipeline stages. Its LPM searching rate is affected by both the number of key field blocks in stage 1 and stage 2, and distribution of matching Point. The RTL(Register Transistor Level) design is carried out using Verilog-HDL. The functional verification is thoroughly done at the gate level using 0.35${\mu}{\textrm}{m}$ CMOS SEC standard cell library.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2B
• /
• pp.71-79
• /
• 2006

Address lookup is an essential function in the Internet routers, and it determines overall router performance. In this paper, we have thoroughly investigated the binary-search-based address lookup algorithms and proposed a new algorithm based on binary search on prefix lengths. Most of the existing binary search schemes perform binary search on prefix values, and hence the lookup speed is proportional to the length of prefixes or the log function of the number of prefixes. The previous algorithm based on binary search on prefix lengths has superior lookup performance than others. However, the algorithm requires very complicated pre-computation of markers and best matching prefixes in internal nodes since naive binary search is not possible in their scheme. This complicated pre-computation makes the composition of the routing table and incremental update very difficult. By using leaf-pushing, the proposed algorithm in this paper removes the complicated pre-computation of the Previous work in performing the binary search on prefix lengths. The performance evaluation results show that the proposed scheme has very good performance in lookup speed compared with previous works.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.5B
• /
• pp.378-389
• /
• 2006

An IP address lookup scheme has become a critical issue increasingly for high-speed networking techniques due to the advent of IPv6 based on 128bit. In this paper, a novel global IPv6 unicast address lookup scheme is proposed for next generation internet routers. The proposed scheme perform a variable multiple hashing based on prefix grouping. Accordingly, it should not only minimize overflows with the proper number of memory modules, but also reduce a memory size required to organize forwarding tables. It has the fast building and searching mechanisms for forwarding tables during only a single memory access. Besides, it is easy to update forwarding tables incrementally. In the simulation using CERNET routing data as a 6bone test phase, we compared the proposed scheme with a similar scheme using a uniform multiple hashing. As a result, we verified that the number of overflows is reduced by 50% and the size of memory for forwarding tables is shrunken by 15% with 8 tables.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.93-100
• /
• 2010

In this paper, we propose a technique which makes it faster to delete prefixes in an IP address lookup architecture based on parallel TCAMs. In previous deletion schemes, more than one memory movement is needed for the prefix ordering and keeping the available memory space consecutive. For deletion, our scheme stores the address of the deleted prefix in a stack implemented by SRAM instead of actual movement in TCAM. Since SRAM has very short latency compared to TCAM, the proposed scheme can accomplish fast updating. From the experiment with the real forwarding table and update trace, we evaluate the performance of our scheme in terms of the memory access time for the prefix insertion and deletion. The experiment result also shows good performance with considerably small size of stack.