Network-wide routing-oblivious heavy hitters

Basat, Ran Ben; Einziger, Gil; Feibish, Shir Landau; Moraney, Jalil; Raz, Danny

doi:10.1145/3230718.3230729

Cited by 30 publications

(41 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A network-wide heavy hitter uses distributed information, which can be made available by programmable switches, to accurately and effectively monitor heavy hitters from a global perspective. Harrison et al [22] and Basat et al [21] have proposed two different strategies to monitor network-wide heavy hitters. In Harrison's strategy [22], at the end of each time interval, if any heavy hitter has been detected through a local threshold-based mechanism in P4-enabled switches, the controller polls the programmable switches and uses a different (global) thresholdbased mechanism to decide whether local heavy hitters are network-wide heavy hitters or not.…”

Section: B Network-wide Heavy-hitter Detection In Programmable Data mentioning

confidence: 99%

“…However, in their strategy, packets belonging to the same flow are counted multiple times by different switches, and this duplicated information is not discarded by the controller while estimating networkwide heavy hitters: for this reason, it is very difficult to correctly set the global threshold. Basat's work [21] provides a solid method for network-wide heavy-hitter detection by using a data streaming model, but the introduced communication overhead and occupied memory are significant. Another key limitation is that the hash functions needed by their strategy do not exist in practice.…”

Section: B Network-wide Heavy-hitter Detection In Programmable Data mentioning

confidence: 99%

See 1 more Smart Citation

An Incrementally-Deployable P4-Enabled Architecture for Network-Wide Heavy-Hitter Detection

Ding

Savi

Antichi

et al. 2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

The advent of Software-Defined Networking with OpenFlow first, and subsequently the emergence of programmable data planes, has boosted lots of research around many networking aspects: monitoring, security, traffic engineering. In the context of monitoring, most of the proposed solutions show the benefits of data plane programmability by simplifying the network complexity with a one big-switch abstraction. Only few papers look at network-wide solutions, but consider the network only composed by programmable devices. In this paper, we argue that the primary challenge for a successful adoption of those solutions is the deployment problem: how to compose and monitor a network consisting of both legacy and programmable switches? We propose an approach for incrementally deploy programmable devices in an ISP network with the goal of monitoring as many distinct network flows as possible. While assessing the benefits of our solution, we realized that proposed network-wide monitoring algorithms might not be optimized for a partial deployment scenario. We then also developed and implemented in P4 a novel strategy capable of detecting networkwide heavy flows: results show that it can achieve better accuracy than state-of-the-art solutions while relying on less information from the data plane and leading to only marginal additional packet processing time.

show abstract

Section: B Network-wide Heavy-hitter Detection In Programmable Data mentioning

confidence: 99%

Section: B Network-wide Heavy-hitter Detection In Programmable Data mentioning

confidence: 99%

An Incrementally-Deployable P4-Enabled Architecture for Network-Wide Heavy-Hitter Detection

Ding

Savi

Antichi

et al. 2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…Sampling is also at the core of the distributed counting algorithm proposed by Basat et al [37]. This method surely represents the main competitor of our proposal, being able to solve the flow frequency estimation problem.…”

Section: Related Workmentioning

confidence: 99%

“…Nonetheless, the two methods differ for several characteristics, among which the use of sampling, instead of sketches as in our algorithm, represent the main difference. This allows the method [37] to achieve a better memory footprint (roughly O(σ −2 ), where σ is the target error parameter, instead of O(σ −3 )), allowing to store a single counter instead of a counter for each sketch bucket. Nonetheless, this comes at the expense of a bigger computational complexity, requiring each probe to maintain an ordered list of χ packets (with complexity O(log χ), instead of O(1) -complexity of the sketch) and the controller to merge the N lists sent by the N probes (with complexity O(χlogχ), instead of O (1) as in our case).…”

Section: Related Workmentioning

confidence: 99%

A Probabilistic Counting Framework for Distributed Measurements

2019

View full text Add to dashboard Cite

The technological maturity attained by general purpose processors and network interface cards makes today's commodity PCs viable and high performing alternatives to specialized hardware for deploying network devices, such as switches, routers, and generic middleboxes. In addition, the flexibility of the software solution seems to be perfectly in line with the emerging trend towards the data-plane programming abstractions brought by recent proposals such as Openflow and the P4 language. However, if programming abstractions provide the way elementary instructions (primitives) are combined together, the development of such processing primitives is left to the network programmer. Although the type of such functions is strongly domain specific, we can safely assume that the counting primitive is easily required in a great deal of practical contexts. This paper presents a counting framework based on probabilistic sketches and LogLog counters for estimating the cardinality of large multi-sets of data. The proposed data structure is designed to be fast and compact for ready use in the on-line chain of processing of network devices running at multi-gigabit speeds. The complete implementation is provided within the probabilistic data structures (pds) library which has been designed, developed, experimentally assessed, and released as open-source for free download. Although the paper specifically presents two possible use-cases, the pds library can be used in rather general scenarios, even outside the networking domain. INDEX TERMS Approximate counting, loglog counter, multi-set cardinality, network applications, reversible sketches.

show abstract

“…The majority of these solutions rely on the assumption that a centralized controller collects and merges measurements from different monitoring points to obtain a network-wide view. This task is challenging when the same packet may pass through several monitoring points, as packets can be double-counted [5]. Existing measurement solutions either assume that each packet is measured at a single monitoring point or that the routing of each packet is known by the controller.…”

Section: Music-defined Telemetrymentioning

confidence: 99%

Music-Defined Networking

Hogan

Esposito

2018

Proceedings of the 17th ACM Workshop on Hot Topics in Networks

View full text Add to dashboard Cite

For several years researchers have used the term "network orchestration" as a metaphor. In this paper, we make the metaphor reality; we describe a novel approach to network orchestration that leverages sounds to augment or replace various network management operations. We test our Music-Defined Networking approach with both a real and a virtual network testbed, on several mechanisms and applications: from datacenter server fan failure detection to authentication, from load balancing to explicit congestion notification and detection of heavy hitter flows. Our approach can be used with and without a Software-Defined Network controller. Despite its limitations, we believe that sound-based network management has potential to be further explored as an effective and inexpensive out-of-band orchestration technique.

show abstract

Network-wide routing-oblivious heavy hitters

Cited by 30 publications

References 33 publications

An Incrementally-Deployable P4-Enabled Architecture for Network-Wide Heavy-Hitter Detection

An Incrementally-Deployable P4-Enabled Architecture for Network-Wide Heavy-Hitter Detection

A Probabilistic Counting Framework for Distributed Measurements

Music-Defined Networking

Contact Info

Product

Resources

About