SDN-based multi-class QoS-guaranteed inter-data center traffic management

Abstract

When allocating network bandwidth to multiple classes of applications in inter-data center communication, coordi nation always yields a better utilization of the backbone network. Yet, it often comes at a prohibitively heavy computational and communication cost, making it thus far not a practically viable approach. SDN helped in bridging the communication cost gap by enabling centralized control, and SDN has been recently applied in such inter-DC traffic management. However, the computational cost is still an issue as the efficient and fast response of the centralized traffic engineering algorithm has become crucial to the practicality of such SDN-based approach. In this paper, we present MCTEQ, a utility-optimization-based joint-bandwidth al location for inter-DC communication with multiple traffic classes, that handles priorities between traffic classes in a soft manner and explicitly considers the delay requirement of Interactive flows.MCTEQ being NP-hard, we apply approximation techniques to lean on the mature and efficient LP solver and obtain fast and accurate approximations. We demonstrate via experiments with Google's inter-DC backbone topology that MCTEQ achieves about 160 Gbps higher network utilization than the existing SWAN solution, yet runs 2.5 times faster. In particular, MCTEQ guarantees that the allocated bandwidth for Interactive flows strictly meets their end-to-end delay requirements.

Quality of Service (QoS) in Software Defined Networking (SDN): A survey

“…6) [43,44] A distributed QoS routing architecture for scalable video streaming over multi-domain OpenFlow networks [45] A hierarchic network architecture with an inter-AS QoS routing approach [46,47] Design of Broker-based FlowBroker architecture for QoS support [48,49] Design of MCTEQ model proposing a joint bandwidth allocation for trafffic classes [50] Use of SDN and OPS nodes for QoS support [51] Design [31,62] ToS/DSCP-based classification approach for QoS [63] A hierarchical autonomic QoS model by adopting SDN [64] A QoS configuration API using OVSDB protocol QoE-Aware Mechanisms (Sec. 9)…”

“…MCTEQ [48,49] model proposes a joint bandwidth allocation to multiple traffic classes. It uses SDN concept to give preference to higher priority traffic in grabbing bandwidth by associating its utility with a larger weight while considering endto-end delay requirement of interactive applications.…”

Kuijia: Traffic Rescaling in Software-Defined Data Center WANs

“…We have assumed that all traffic has the same priority before failures thus far. In practice, it is common for networks to use multiple priorities to differentiate applications with distinct performance requirements [22,23]. Kuijia can be extended to this setting so that high priority victim flows could also obtain as much bandwidth as possible after rerouting.…”

Joint QoS and Congestion Control Based on Traffic Prediction in SDN

“…The work [24] follows a similar approach by minimizing (traffic load)/capacity of each link. A resource allocation approach with three classes that focus on the delay of high priority traffic is introduced in [25]. The Ghosh scheme [26] prevents flow from violating a predefined threshold by minimizing end-to-end delay and maximizing network throughput.…”