FRFC: Fast Table Building Algorithm for Recursive Flow Classification

Pak, Wooguil; Bahk, Saewoong

doi:10.1109/lcomm.2010.100810.100572

Cited by 9 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it is impossible to support partial table update; hence, it has a very long table update time. To overcome these problems, tables can be built with partitioning techniques. For example, FRFC generates tables in a partitioning manner but searches in a non-partitioning manner [16]. It divides the ruleset into small partitions and builds RFC tables for each partition; these tables are then merged.…”

Section: Cross-productingmentioning

confidence: 99%

“…For comparison, we selected RFC and FRFC as nonpartitioning algorithms [11], [16]. We also selected packet classification using maximum entropy hash (MEH, shortly) and HyperCuts as partitioning algorithms [12], [3].…”

Section: Performance Evaluationmentioning

confidence: 99%

“…However, it does not always guarantee the highest classification speed because the overhead of inter-partition search 1 increases with the ruleset size [3]. Thus, non-partitioning algorithms, such as the cross-producting algorithm, facilitate highspeed classification unless large table sizes and long building times are considered [11], [15], [16].…”

mentioning

confidence: 99%

See 2 more Smart Citations

High Performance and High Scalable Packet Classification Algorithm for Network Security Systems

Pak

Choi

2015

IEEE Trans. Dependable and Secure Comput.

Self Cite

View full text Add to dashboard Cite

Packet classification is a core function in network and security systems; hence, hardware-based solutions, such as packet classification accelerator chips or T-CAM (Ternary Content Addressable Memory), have been widely adopted for high-performance systems. With the rapid improvement of general hardware architectures and growing popularity of multi-core multi-threaded processors, software-based packet classification algorithms are attracting considerable attention, owing to their high flexibility in satisfying various industrial requirements for security and network systems. For high classification speed, these algorithms internally use large tables, whose size increases exponentially with the ruleset size; consequently, they cannot be used with a large rulesets. To overcome this problem, we propose a new software-based packet classification algorithm that simultaneously supports high scalability and fast classification performance by merging partition decision trees in a search table. While most partitioning-based packet classification algorithms show good scalability at the cost of low classification speed, our algorithm shows very high classification speed, irrespective of the number of rules, with small tables and short table building time. Our test results confirm that the proposed algorithm enables network and security systems to support heavy traffic in the most effective manner.Index Terms-Packet classification, partitioning, cache-aware table structure, integrated inter-and intra-table search.

show abstract

Section: Cross-productingmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

High Performance and High Scalable Packet Classification Algorithm for Network Security Systems

Pak

Choi

2015

IEEE Trans. Dependable and Secure Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, the existing studies, such as RFC [6,7], Grid of Trie [8], HiCuts [9] and HyperCuts [10], on packet classification could facilitate the research on efficient lookup of flow tables in OpenFlow switches. RFC algorithm could achieve high network throughput, but it demanded large storage space, which cannot be applicable for classification of large rule base; and thus RFC is not suitable for the lookup in large and complex flow tables of OpenFlow switches.…”

Section: Related Workmentioning

confidence: 99%

H‐SOFT: a heuristic storage space optimisation algorithm for flow table of OpenFlow

Chen

et al. 2014

Concurrency and Computation

View full text Add to dashboard Cite

OpenFlow has become the key standard and technology for software defined networking which has been widely adopted in various environments. However, the global deployment of OpenFlow encountered several issues, such as the increasing number of fields and complex structure of flow entries, making the size of flow table in OpenFlow switches explosively grows which results in hardware implementation difficulty. To this end, this paper presents the modelling on the minimisation for storage space of flow table, and proposes a Heuristic Storage space Optimisation algorithm for Flow Table (H-SOFT) to solve this optimisation problem. The H-SOFT algorithm degrades the complex and high-dimensional fields of a flow table into multiple flow tables with simple and low-dimensional fields based on the co-existence and conflict relationships among fields to release the un-used storage space due to blank fields. Extensive simulation experiments demonstrate that the H-SOFT algorithm can effectively reduce the storage space of flow table. In particular, with frequent updates on flow entries, the storage space compression rate of flow table is stable and can achieve at ~70%. Moreover, in comparison with the optimal solution, the H-SOFT algorithm can achieve the similar compression rate with much lower execution time.

show abstract

“…Recently, researchers have been actively investigating algorithmic alternatives for TCAM, such ashash‐based algorithms [16, 17], decision‐tree techniques [18–26]and decomposition‐based schemes [22, 27–29]. Among them, techniques based on decomposition have been recognised as some of themost promising approaches for designing high‐throughput network devices, since theycan leverage the parallelism offered by modern hardware to accelerate lookupperformance.…”

Section: Introductionmentioning

confidence: 99%

Memory‐efficient recursive scheme for multi‐field packet classification

Bai

et al. 2019

IET Communications

View full text Add to dashboard Cite

FRFC: Fast Table Building Algorithm for Recursive Flow Classification

Cited by 9 publications

References 3 publications

High Performance and High Scalable Packet Classification Algorithm for Network Security Systems

High Performance and High Scalable Packet Classification Algorithm for Network Security Systems

H‐SOFT: a heuristic storage space optimisation algorithm for flow table of OpenFlow

Memory‐efficient recursive scheme for multi‐field packet classification

Contact Info

Product

Resources

About