Using multiple hash functions to improve IP lookups
Andrei Z. Broder,Michael Mitzenmacher +1 more
- Vol. 3, pp 1454-1463
Reads0
Chats0
TLDR
This work describes an approach for obtaining good hash tables based on using multiple hashes of each input key (which is an IP address), which proves extremely suitable in instances where the goal is to have one hash bucket fit into a cache line.Abstract:
High performance Internet routers require a mechanism for very efficient IP address lookups. Some techniques used to this end, such as binary search on levels, need to construct quickly a good hash table for the appropriate IP prefixes. We describe an approach for obtaining good hash tables based on using multiple hashes of each input key (which is an IP address). The methods we describe are fast, simple, scalable, parallelizable, and flexible. In particular, in instances where the goal is to have one hash bucket fit into a cache line, using multiple hashes proves extremely suitable. We provide a general analysis of this hashing technique and specifically discuss its application to binary search on levels.read more
Figures
Table 6: Simulation results, random insertions, 3 hoi es. 
Figure 1: The 2-left s heme. A newly inserted item, labeled z, is pla ed in the less lled of two random bu kets, one from the left and one from the right. Ties are broken to the left. A sear h for z may require sear hing both of the bu kets in whi h z might have been pla ed. 
Table 1: Loads in the uid limit (n bu kets, 1 hoi e). Entries represent the fra tion of bu kets with that load. 
Table 5: Simulation results, random insertions, 2 hoi es. 
Table 9: Simulation results, 2 CRCs as hash fun tions, with blo ked inputs (stride 1). 
Table 10: Simulation results, 2 CRCs as hash fun tions, with blo ked inputs (stride 256).
Citations
More filters
Proceedings ArticleDOI
Ethane: taking control of the enterprise
TL;DR: Ethane allows managers to define a single network-wide fine-grain policy, and then enforces it directly, and this design is backwards-compatible with existing hosts and switches.
Book ChapterDOI
Efficient Private Matching and Set Intersection
TL;DR: In this paper, the problem of computing the intersection of private datasets of two parties, where the datasets contain lists of elements taken from a large domain, was considered and protocols based on the use of homomorphic encryption and balanced hashing were proposed.
Efficient private matching and set intersection
TL;DR: This work considers the problem of computing the intersection of private datasets of two parties, where the datasets contain lists of elements taken from a large domain, and presents protocols, based on the use of homomorphic encryption and balanced hashing, for both semi-honest and malicious environments.
Journal ArticleDOI
Cuckoo hashing
TL;DR: In this paper, a simple dictionary with worst case constant lookup time was presented, equaling the theoretical performance of the classic dynamic perfect hashing scheme of Dietzfelbinger et al.
Journal ArticleDOI
Theory and Practice of Bloom Filters for Distributed Systems
TL;DR: An overview of the basic and advanced probabilistic techniques is given, reviewing over 20 variants and discussing their application in distributed systems, in particular for caching, peer-to-peer systems, routing and forwarding, and measurement data summarization.
References
More filters
Book
Markov Processes: Characterization and Convergence
TL;DR: In this paper, the authors present a flowchart of generator and Markov Processes, and show that the flowchart can be viewed as a branching process of a generator.
Journal ArticleDOI
Universal classes of hash functions
TL;DR: An input independent average linear time algorithm for storage and retrieval on keys that makes a random choice of hash function from a suitable class of hash functions.
Journal ArticleDOI
The power of two choices in randomized load balancing
TL;DR: This work uses a limiting, deterministic model representing the behavior as n/spl rarr//spl infin/ to approximate the behavior of finite systems and provides simulations that demonstrate that the method accurately predicts system behavior, even for relatively small systems.
Journal ArticleDOI
Solutions of ordinary differential equations as limits of pure jump markov processes
TL;DR: In a great variety of fields, e.g., biology, epidemic theory, physics, and chemistry, ordinary differential equations are used to give continuous deterministic models for dynamic processes which are actually discrete and random in their development as discussed by the authors.
Proceedings ArticleDOI
Scalable high speed IP routing lookups
TL;DR: This paper describes a new algorithm for best matching prefix using binary search on hash tables organized by prefix lengths that scales very well as address and routing table sizes increase and introduces Mutating Binary Search and other optimizations that considerably reduce the average number of hashes to less than 2.