Fast hash table lookup using extended bloom filter

Song, Haoyu; Dharmapurikar, Sarang; Turner, Jonathan S.; Lockwood, John W.

doi:10.1145/1080091.1080114

Cited by 231 publications

(200 citation statements)

References 24 publications

Supporting

Mentioning

199

Contrasting

Order By: Relevance

“…Fast Hash Table [10], Cuckoo Hashing [11], and Tree Bitmap [12]), we adopt the basic Naïve Hash Table (NHT) [13] because NHT supports parallelisable fast lookups in multiple memories without additional memory overhead, and new replacement policies can be added with minimal effort.…”

Section: Addressing Schemementioning

confidence: 99%

See 1 more Smart Citation

Tracking elephant flows in internet backbone traffic with an FPGA-based cache

Žádník

Canini

Moore

et al. 2009

2009 International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

This paper presents an FPGA-friendly approach to tracking elephant flows in network traffic. Our approach, SingleStep Segmented Least Recently Used (S 3 -LRU) policy, is a network traffic-friendly replacement policy for maintaining flow states in a Naïve Hash Table (NHT). We demonstrate that our S 3 -LRU approach preserves elephant flows: conservatively promoting potential elephants and evicting lowrate flows in LRU manner. Our approach keeps flow-state of any elephant since start-of-day and provides a significant improvement over filtering approaches proposed in previous work. Our FPGA-based implementation of the S 3 -LRU in combination with an NHT suites well the parallel access to block memories while capitalising on the retuning of parameters through dynamic-reprogramming.

show abstract

Section: Addressing Schemementioning

confidence: 99%

“…Many indexing schemes were suggested (e.g., [12]) but the most popular ones are variations of hash tables [10,11].…”

Section: Related Workmentioning

confidence: 99%

Tracking elephant flows in internet backbone traffic with an FPGA-based cache

Žádník

Canini

Moore

et al. 2009

2009 International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

show abstract

“…1 However, extraction of 2D matching features at high-speed edge routers is not an easy task. We will address this issue in Sections III and IV.…”

Section: A Motivationmentioning

confidence: 99%

An efficient data structure for network anomaly detection

Fan

et al. 2008

Security Comm Networks

View full text Add to dashboard Cite

Abstract-Despite the rapid advance in networking technologies, detection of network anomalies at high-speed switches/routers is still far from maturity. To push the frontier, two major technologies need to be addressed. The first one is efficient feature-extraction algorithms/hardware that can match a line rate in the order of Gb/s; the second one is fast and effective anomaly detection schemes. In this paper, we focus on design of efficient data structure and algorithms for feature extraction. Specifically, we propose a novel data structure that extracts socalled two-directional (2D) matching features, which are shown to be effective indicators of network anomalies. Our key idea is to use a Bloom filter array to trade off a small amount of accuracy in feature extraction, for much less space and time complexity, so that our data structure can catch up with a line rate in the order of Gb/s. Different from the existing work, our data structure has the following properties: 1) dynamic Bloom filter, 2) combination of a sliding window with Bloom filter, and 3) using an insertion-removal pair to enhance Bloom filter with a removal operation. Our analysis and simulation demonstrate that the proposed data structure has a better space/time tradeoff than conventional algorithms. For example, for a fixed time complexity, the conventional algorithm (i.e., hash table [1]-[8]) requires a memory of 1.01G bits while our data structure requires a memory of only 62.9M bits, at the cost of losing 1% accuracy in feature extraction.

show abstract

“…During the lookup process, a specific row index is generated by the hash function and the row is searched to find the target key. An important design goal in this case is to minimize the worst-case length of the linked lists and to balance the bucket population by using Bloom filters-like data structures [5,6,7].…”

Section: Introductionmentioning

confidence: 99%

CHAP: Enabling Efficient Hardware-Based Multiple Hash Schemes for IP Lookup

et al. 2009

View full text Add to dashboard Cite

Abstract. Building a high performance IP lookup engine remains a challenge due to increasingly stringent throughput requirements and the growing size of IP tables. An emerging approach for IP lookup is the use of set associative memory architecture, which is basically a hardware implementation of an open addressing hash table with the property that each row of the hash table can be searched in one memory cycle. While open addressing hash tables, in general, provide good average-case search performance, their memory utilization and worst-case performance can degrade quickly due to bucket overflows. This paper presents a new simple hash probing scheme called CHAP (Content-based HAsh Probing) that tackles the hash overflow problem. In CHAP, the probing is based on the content of the hash table, thus avoiding the classical side effects of probing. We show through experimenting with real IP tables how CHAP can effectively deal with the overflow.

show abstract

Fast hash table lookup using extended bloom filter

Cited by 231 publications

References 24 publications

Tracking elephant flows in internet backbone traffic with an FPGA-based cache

Tracking elephant flows in internet backbone traffic with an FPGA-based cache

An efficient data structure for network anomaly detection

CHAP: Enabling Efficient Hardware-Based Multiple Hash Schemes for IP Lookup

Contact Info

Product

Resources

About