Mahout: Low-overhead datacenter traffic management using end-host-based elephant detection

Curtis, A. R.; Kim, Won‐Ho; Yalagandula, Praveen

doi:10.1109/infcom.2011.5934956

Cited by 330 publications

(174 citation statements)

References 14 publications

Supporting

Mentioning

172

Contrasting

Unclassified

Order By: Relevance

“…The remaining 10% of the services are elephant services. An elephant service requires a high amount of slots (ten times more than a mice), and its holding time is also larger in comparison with a mice service -video on demand and file transfer backup are common examples of elephant services [18].…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Evaluating the benefits of combined and continuous Fog-to-Cloud architectures

Ramírez

Masip-Bruin

Marín‐Tordera

et al. 2017

Computer Communications

View full text Add to dashboard Cite

The need to extend the features of Cloud computing to the edge of the network has fueled the development of new computing architectures, such as Fog computing. When put together, the combined and continuous use of fog and cloud computing, lays the foundation for a new and highly heterogeneous computing ecosystem, making the most out of both, cloud and fog. Incipient research efforts are devoted to propose a management architecture to properly manage such combination of resources, such as the reference architecture proposed by the OpenFog Consortium or the recent Fog-to-Cloud (F2C). In this paper, we pay attention to such a combined ecosystem and particularly evaluate the potential benefits of F2C in dynamic scenarios, considering computing resources mobility and different traffic patterns. By means of extensive simulations we specifically study the aspects of service response time, network bandwidth occupancy, power consumption and service disruption probability. The results indicate that a combined fog-to-cloud architecture brings significant performance benefits in comparison with the traditional standalone Cloud, e.g., over 50% reduction in terms of power consumption.

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Evaluating the benefits of combined and continuous Fog-to-Cloud architectures

Ramírez

Masip-Bruin

Marín‐Tordera

et al. 2017

Computer Communications

View full text Add to dashboard Cite

show abstract

“…B4 [12] allows to define application priority and uses multipath routing/tunneling to optimize link usage. Mahout [6] detects elephant flows at the end hosts and uses placement algorithms to compute paths for them. NoF [21] raises the network programming level by allowing the application specialists to program the network through high-level constructs.…”

Section: Background and Related Workmentioning

confidence: 99%

“…The existing works using SDN for forwarding communications through multiple paths use information collected from end-hosts or network devices [2], [6], [12]. To our knowledge, this is the first work using the well-behaved patterns expressed by SciApps to forward their communication flows through multiple network paths, considering latency and bandwidth requirements.…”

Section: Introductionmentioning

confidence: 99%

Softening Up the Network for Scientific Applications

Trois

Bona

Fabro

et al. 2017

2017 25th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

View full text Add to dashboard Cite

“…3 To reduce the workload and improve the efficiency on control plane, many elephant flow detection approaches had been proposed by several studies. [6][7][8][9][10][11] These elephant flow detection methods can be classified into 4 categories: (1) pull-based statistics, [6][7][8] (2) host-based trigger, 9 (3) sampling, 10 and (4) host-based detection. 11 All these methodologies mentioned are preconfigured with a fixed value, which will cause a lot of false positive errors and false negative errors.…”

Section: Introductionmentioning

confidence: 99%

“…[6][7][8][9][10][11] These elephant flow detection methods can be classified into 4 categories: (1) pull-based statistics, [6][7][8] (2) host-based trigger, 9 (3) sampling, 10 and (4) host-based detection. 11 All these methodologies mentioned are preconfigured with a fixed value, which will cause a lot of false positive errors and false negative errors. For example, the traffic of a flow in daytime is much less than that in night so that the detection system will possibly regard all the flows as mice flows in daytime while regard those as elephant flows in night.…”

Section: Introductionmentioning

confidence: 99%

An adaptive approach for elephant flow detection with the rapidly changing traffic in data center network

et al. 2017

View full text Add to dashboard Cite

SummarySoftware-defined network, which separates control plane from the underlying physical devices, has the advantages of global visibility and high flexibility. Among the most typical applications in software-defined network, there is significant interest on classifying flows, especially for elephant flow detection. Previous studies show that detecting and rerouting elephant flows (flows that transfer significant amount of data) effectively can lead to a 113% improvement in aggregate throughput compared with the traditional routing. However, the threshold of the existing detection approach was preconfigured without the consideration of the rapidly changing traffic in data center networks. This phenomenon could cause high detection error rate. To address this problem, we propose an adaptive approach for elephant flow detection, which could efficiently identify elephant flows with low latency and low overhead. Particularly, to meet the demands of the traffic characteristics in data center networks, dynamical traffic learning algorithm is adopted to configure the threshold value real timely and dynamically. Numerical results and experimental tests show that the mean error rate of detection is only 4.61% and the maximum number of packet-in messages is minimum compared to other methods.

show abstract

Mahout: Low-overhead datacenter traffic management using end-host-based elephant detection

Cited by 330 publications

References 14 publications

Evaluating the benefits of combined and continuous Fog-to-Cloud architectures

Evaluating the benefits of combined and continuous Fog-to-Cloud architectures

Softening Up the Network for Scientific Applications

An adaptive approach for elephant flow detection with the rapidly changing traffic in data center network

Contact Info

Product

Resources

About