Cuckoo Filters and Bloom Filters: Comparison and Application to Packet Classification

Reviriego, Pedro; Martinez, Jorge; Larrabeiti, David; Pontarelli, Salvatore

doi:10.1109/tnsm.2020.3024680

Cited by 40 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, on average adaptation would reduce the false positive rate as the benefits of the first case are larger than the losses introduced by the second case. This is due to the harmonic averaging done in equation (6). Therefore, the larger the differences between Z 1 and Z 2 , the greater the benefits of adaptation.…”

Section: Discussionmentioning

confidence: 99%

“…This fast checking has been traditionally implemented with Bloom filters [1] that are commonly used in networking systems [2], [3]. More recently, the cuckoo filter [4], [5] has also been widely adopted in a similar manner, offering some advantages over Bloom filters like the support of deletions or a lower false positive probability when the number of memory bits per element stored in the filter is large [6]. Cuckoo filters have, however, also disadvantages, for example in terms of a relatively high false positive rate when occupancy is low and most cells are empty [6] and in lookup speed [7].…”

Section: Introductionmentioning

confidence: 99%

“…More recently, the cuckoo filter [4], [5] has also been widely adopted in a similar manner, offering some advantages over Bloom filters like the support of deletions or a lower false positive probability when the number of memory bits per element stored in the filter is large [6]. Cuckoo filters have, however, also disadvantages, for example in terms of a relatively high false positive rate when occupancy is low and most cells are empty [6] and in lookup speed [7]. In fact, Bloom filters can be implemented in such a way that lookups only require one memory access [8], whereas cuckoo filters require two memory accesses for negative lookups that would be the majority in practical scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive One Memory Access Bloom Filters

Reviriego

Sánchez‐Macian

Rottenstreich

et al. 2022

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

Bloom filters are widely used to perform fast approximate membership checking in networking applications. The main limitation of Bloom filters is that they suffer from false positives that can only be reduced by using more memory. Recently, exploiting the fact that in many cases a few elements are queried many times on the filter, has been proposed to increase accuracy in other filters with a similar functionality. The idea is that once an element returns a false positive, the filter is adapted so that future queries for that element will not return a false positive. However, to the best of our knowledge, so far no scheme has been presented to support dynamic adaptation in Bloom filters. In this paper, one memory access Bloom filters are used to design an adaptation scheme that can effectively remove false positives while completing all queries in a single memory access. The proposed filters are well suited for scenarios on which the number of memory bits per element is low and thus complement the existing adaptive cuckoo filters that are not efficient in that case. The evaluation results using packet traces show that the proposed adaptive Bloom filters can significantly reduce the false positive rate in networking applications with the single memory access. In particular, when using as few as four bits per element, false positive rates below 5% are achieved.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive One Memory Access Bloom Filters

Reviriego

Sánchez‐Macian

Rottenstreich

et al. 2022

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Cuckoo Filter [22] is an efficient alternative to Counter Bloom [23]. Its basic structure is shown in Fig.…”

Section: B Filtermentioning

confidence: 99%

FATSS: Filter-Assisted Tuple Space Search for Packet Classification

Wang

Wei

Wang

et al. 2022

2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)

View full text Add to dashboard Cite

Packet Classification is a key part of supporting lots of network functions. Various algorithms have been proposed over the years to meet the increasing performance requirements of packet classification. Tuple space search (TSS) is one of the most popular algorithms and well-suited to scenarios requiring efficient online updates. However, the huge number of tuples in the algorithm leads to numerous memory accesses during packet classification, which limits the classification performance. This paper proposes a novel model named FATSS, which uses Filters to Assist the Tuple Space Search algorithm and reduces the number of tuple accesses. We first create the ImCuckoo Filter by improving the Cuckoo Filter from its structure, capacity and hash calculation. Then, we embed ImCuckoo Filter into TSS in two ways (online and offline) to adapt to diverse scenarios and requirements. By the experiments, it can be found that the ImCuckoo Filter can reduce more than 80% of tuple accesses. Furthermore, the access time of the filter is no more than 60% compared with that of the hash table. The experimental results show that the classification time of FATSS is 17%-19% faster than that of existing widely used algorithms.

show abstract

“…Counting Bloom Filter is useful in Computer Network, Network Security and Privacy [9]. Therefore, there are diverse Bloom Filters available to address the various problems of diverse domains [10]- [14]. Bloom Filter is categorized into two key categories, namely, counting and non-counting Bloom Filter.…”

Section: Introductionmentioning

confidence: 99%

countBF: A General-purpose High Accuracy and Space Efficient Counting Bloom Filter

Nayak¹,

Patgiri²

2021

Preprint

View full text Add to dashboard Cite

Bloom Filter is a probabilistic data structure for the membership query, and it has been intensely experimented in various fields to reduce memory consumption and enhance a system's performance. Bloom Filter is classified into two key categories: counting Bloom Filter (CBF), and non-counting Bloom Filter. CBF has a higher false positive probability than standard Bloom Filter (SBF), i.e., CBF uses a higher memory footprint than SBF. But CBF can address the issue of the false negative probability. Notably, SBF is also false negative free, but it cannot support delete operations like CBF. To address these issues, we present a novel counting Bloom Filter based on SBF and 2D Bloom Filter, called countBF. countBF uses a modified murmur hash function to enhance its various requirements, which is experimentally evaluated. Our experimental results show that countBF uses 1.96× and 7.85× less memory than SBF and CBF respectively, while preserving lower false positive probability and execution time than both SBF and CBF. The overall accuracy of countBF is 99.999921, and it proves the superiority of countBF over SBF and CBF. Also, we compare with other state-of-the-art counting Bloom Filters.

show abstract

Cuckoo Filters and Bloom Filters: Comparison and Application to Packet Classification

Cited by 40 publications

References 22 publications

Adaptive One Memory Access Bloom Filters

Adaptive One Memory Access Bloom Filters

FATSS: Filter-Assisted Tuple Space Search for Packet Classification

countBF: A General-purpose High Accuracy and Space Efficient Counting Bloom Filter

Contact Info

Product

Resources

About