Towards predictable datacenter networks

BallaniHitesh,; CostaPaolo,; KaragiannisThomas,; RowstronAnt,

doi:10.1145/2043164.2018465

Cited by 191 publications

(49 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers in cloud datacenters have concentrated on providing a sophisticated solution for supporting VN performance separation in the cloud data center. Presenting diverse bandwidth allocation VN models, such as traffic matrix [13]; engendering a fixed bandwidth, e.g., the hose model with invariable bandwidth [14] or where the bandwidth varies with time [24] or a TAG model based on a communication structure between applications [19]. Choosing from this variety, researchers design their proper version of VN to PN mapping algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…Recent works on VN have suggested a different model to allocate bandwidth, such as one based on traffic matrices [13]. Bandwidth entails a fixed variable, yet the hose model engenders invariable bandwidth [14], temporally alternating bandwidth [24], or a TAG model based on a between-application communication structure [34]. In agreement with these models, an algorithmic mapping from VN to PN [35] unifies the tenant service modeling to enable an SLA-aware cloud, focusing primarily on a generic methodology for cloud service representation.…”

Section: Gana Modelmentioning

confidence: 99%

“…This is usually considered a multi-commodity flow problem, demonstrating an NP-hard single unsplittable source flow [11]. Through the years, several virtual network mapping heuristics have been proposed; in our research, we found the four most profound in cloud datacenter [12][13][14][15]. To the best of our knowledge, virtual network mapping algorithms adopt serialized VM-centered VN to PN mapping patterns, requiring each VM to be first mapped to a suitable position to fulfill the given conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GANA-VDC: Application-Aware with Bandwidth Guarantee in Cloud Datacenters

et al. 2019

View full text Add to dashboard Cite

Allocating bandwidth guarantees to applications in the cloud has become increasingly demanding and essential as applications compete to share cloud network resources. However, cloud-computing providers offer no network bandwidth guarantees in a cloud environment, predictably preventing tenants from running their applications. Existing schemes offer tenants practical cluster abstraction solutions emulating underlying physical network resources, proving impractical; however, providing virtual network abstractions has remained an essential step in the right direction. In this paper, we consider the requirements for enabling the application-aware network with bandwidth guarantees in a Virtual Data Center (VDC). We design GANA-VDC, a network virtualization framework supporting VDC application-aware networking with bandwidth guarantees in a cloud datacenter. GANA-VDC achieves scalability using an interceptor to translate OpenFlow features to prompt fine-grained Quality of Service (QoS). Facilitating the expression of diverse network resource demands, we also propose a new Virtual Network (VN) to Physical Network (PN) mapping approach, Graph Abstraction Network Architecture (GANA), which we innovatively introduce in this paper, allowing tenants to provide applications with cloud networking environment, thereby increasing the preservation performance. Our results show GANA-VDC can provide bandwidth guarantee and achieve low time complexity, yielding higher network utility.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Gana Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GANA-VDC: Application-Aware with Bandwidth Guarantee in Cloud Datacenters

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It offers a virtual dedicated network environment for applications in the cloud and leads to predictable performance by providing resource guarantees including bandwidth, CPU and memory. Different virtual cluster abstraction models are proposed to accurately specify resource demands according to the characteristics of submitted applications, such as Pipe [8], VC [9], SVC [10], etc. However, the resource allocation for virtual cluster is a NP problem which is known as the virtual cluster embedding problem.…”

mentioning

confidence: 99%

“…Many heuristic algorithms are accordingly proposed. Oktopus [9] introduces a virtual cluster model named VC, and designs a locality-aware heuristic algorithm which tries to allocate the requested VMs of VC to servers by minimizing the number of switches on the communication path. Through the locality-aware allocation strategy, maximum bandwidth reservation for network links at higher levels of substrate network topology can be obtained, and more future VC requests are expected to be accepted.…”

mentioning

confidence: 99%

Bandwidth-Guaranteed Resource Allocation and Scheduling for Parallel Jobs in Cloud Data Center

Chen

Liu

et al. 2018

Symmetry

View full text Add to dashboard Cite

Cloud Computing has emerged as a powerful and promising way for running high performance computing (HPC) jobs. Most HPC jobs are designed under multi-processes paradigm and involve frequent communication and synchronization among parallel processes. However, as the underlying resources of cloud data centers are always shared among multiple tenants, the competition of jobs for limited bandwidth resources lead to unpredictable completion times for jobs in the cloud, which may lead to QoS violation and inefficient utilization of resources when scheduling parallel jobs in the cloud. To tackle the issue, it is essential to provide bandwidth guarantees for parallel jobs running in the cloud. Offering a dedicated virtual cluster (VC) for running applications in the cloud is a popular way to guarantee bandwidth demands. Motivated by these problems, in this paper, we firstly design a time-aware virtual cluster (TVC) request model for parallel jobs and consider how to embed requested TVCs of jobs into cloud efficiently under parallel job scheduling framework. An adaptive bandwidth-aware heuristic algorithm, which is denoted as AdaBa, is proposed to improve the job accept rate by adjusting the priorities of servers to accommodate the VMs of TVC adaptively according to the relative size of requested bandwidth demand. Then, a bandwidth-guaranteed migration and backfilling scheduling algorithm, which is denoted as BgMBF, is designed to schedule parallel jobs and the bandwidth demands are guaranteed by AdaBa. To obtain high job responsiveness performance, a bandwidth-reserved job backfilling strategy is designed when the requested TVC for current scheduled job cannot be allocated in the cloud. The migration cost of BgMBF is also considered and an enhanced version BgMBFSDF is then proposed to minimize the number of migration when the execution time of jobs are known. Through extensive simulation experiments on popular parallel workloads, our proposed TVC embedding algorithm AdaBa achieves up to 15 percent of improvement on accept rate compared with existing algorithms such as Oktupus and greedy algorithm. Our proposed BgMBF and BgMBFSDF also significantly outperform other popular scheduling algorithms integrated with AdaBa on average response time and average bounded slow down.

show abstract

Network Virtualization and Network Hypervisors

Blenk

Kellerer

2022

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Modern communication networks have to deal with dynamically changing requirements of emerging applications. In order to support such heterogeneous requirements on the same substrate network, concepts for network abstraction and network programmability are essential to offer applications that individually tailored views on the network. Network virtualization is the basic concept to provide an abstraction of a substrate network that can be offered to a network application provider. Here, a network hypervisor realizes the level of indirection between substrate network and virtual network(s). Additional programmability can be offered through the concept of Software‐Defined Networking (SDN). SDN provides a network abstraction based on a centralized view on a network to program individual features such as forwarding rules inside a network. This chapter gives an overview of the networking concept of network virtualization as the example of the virtualization of SDN‐based networks. The combination of network virtualization and Software‐Defined Networking provides full network abstraction and adaptability. We detail the basic features of a network hypervisor, abstraction and isolation, and provide the example of FlowVisor as a prominent network hypervisor example in the state of the art.

show abstract

Towards predictable datacenter networks

Cited by 191 publications

References 18 publications

GANA-VDC: Application-Aware with Bandwidth Guarantee in Cloud Datacenters

GANA-VDC: Application-Aware with Bandwidth Guarantee in Cloud Datacenters

Bandwidth-Guaranteed Resource Allocation and Scheduling for Parallel Jobs in Cloud Data Center

Network Virtualization and Network Hypervisors

Contact Info

Product

Resources

About