Hardware accelerator to speed up packet processing in NDN router

Yu, Weiwen; Pao, Derek

doi:10.1016/j.comcom.2016.06.004

Cited by 13 publications

(11 citation statements)

References 38 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data packet can be cached according to the router's caching policy, which may lead to the update of the CS. (2) If no matching entry exists in the PIT (because of lifetime or other reasons), then the data packet is dropped [9]. Once an interest packet arrives at an interface of the NDN router, as shown in Figure 2 [8], the following procedure is executed:…”

Section: Figure1mentioning

confidence: 99%

“…(2) If no matching entry exists in the PIT (because of lifetime or other reasons), then the data packet is dropped [9].…”

Section: Naming In Ndnmentioning

confidence: 99%

“…Yu et al [9] implemented a combination of BF and linear-chained HT by co-design of hardware and software. The PIT operations are integrated into one command.…”

Section: • Hybrid Approachesmentioning

confidence: 99%

“…When storing name content as a fingerprint, name string comparison is easily avoided via checking the fingerprint only; however, in any case, one insert operation is needed to store the content name on DRAM memory [30].The overflow table of the D-left HT, which stores the item that cannot be matched in the HT, may facilitate the resolution of the bucket overflow issue, but it slows down the lookup process. In addition, the possibility of duplication in fingerprint matching within the same hash bucket should be considered [9]. Multiple hash functions outperform the single hash function, but the former requires considerable memory for traversing all the candidate buckets to find the least loaded bucket [10].…”

Section: Ht-based Schemesmentioning

confidence: 99%

“…In addition, when counter overflow arises, the CBF cannot correctly perform update operations. When the counters use more bits, the CBF may not be stored on-chip [9]. In NDN, the BF must be stored in DRAM because the expected number of rules is large.…”

Section: Bf-based Schemesmentioning

confidence: 99%

See 4 more Smart Citations

Name Lookup in Named Data Networking: A Review

Al-qutwani

Wang

2019

Information

View full text Add to dashboard Cite

Named data networking (NDN) is an alternative model to the current traditional IP-based Internet by improving content distribution in a network with content name. In NDN, content is sent/received based on its name rather than its address. Forwarding is still considered the bottleneck of NDN despite the effort in naming, routing, mobility, and security. NDN requires per-packet update that is preceded by a one-name lookup operation, which results in heavy time processing. The content names consume a large amount of memory, which causes the fast growth of NDN tables. To review the current solutions for NDN name lookup, this paper explores the existing NDN approaches and architectures by using a novel classification method. Furthermore, name lookup approaches were analyzed and compared in a novel manner. This survey highlighted the issues that affect name lookup performance in NDN, such as scalability, memory consumption, time efficiency, latency, and validity. We pointed out directions for future work and open issues to improve NDN name lookup in minimizing implementation cost and enhancing performance.

show abstract

Section: Figure1mentioning

confidence: 99%

“…(2) If no matching entry exists in the PIT (because of lifetime or other reasons), then the data packet is dropped [9].…”

Section: Naming In Ndnmentioning

confidence: 99%

“…Yu et al [9] implemented a combination of BF and linear-chained HT by co-design of hardware and software. The PIT operations are integrated into one command.…”

Section: • Hybrid Approachesmentioning

confidence: 99%

Section: Ht-based Schemesmentioning

confidence: 99%

Section: Bf-based Schemesmentioning

confidence: 99%

See 3 more Smart Citations

Name Lookup in Named Data Networking: A Review

Al-qutwani

Wang

2019

Information

View full text Add to dashboard Cite

show abstract

2DNCF-PIT: Two-Dimensional Neighbor-Based Cuckoo Filter for Pending Interest Table Lookup in Named Data Networking

Mahmoudi

Ahmadi

2022

J Netw Syst Manage

View full text Add to dashboard Cite

Named data networking is one of the recommended architectures for the future of the Internet. In this communication architecture, the content name is used instead of the IP address. To achieve this purpose, a new data structure is added to the nodes of named data networking which is called Pending Interest Table (PIT). Scalability, memory consumption, and integration are the significant challenges in PIT design as it needs to be updated for each packet, and it saves the name of the packet. This paper introduces a new data structure for PIT called DiCuPIT. DiCuPIT is a distributed data structure for the PIT table, that works based on the Cuckoo filter and can cover the three features as above-mentioned. By implementing this PIT, the lookup time shows a 36% reduction compared to the methods based on the Bloom filter and 40% based on hash tables. Moreover, the memory consumption is reduced by 68% compared to the hash tables-based mechanisms and 31% compared to the methods based on the Bloom filter.

show abstract