Joint Static and Dynamic Traffic Scheduling in Data Center Networks

@article{Cao2016JointSA,
  title={Joint Static and Dynamic Traffic Scheduling in Data Center Networks},
  author={Zizhong Cao and Murali S. Kodialam and T. V. Lakshman},
  journal={IEEE/ACM Transactions on Networking},
  year={2016},
  volume={24},
  pages={1908-1918}
}
The advent and continued growth of large data centers has led to much interest in switch architectures that can economically meet the high capacities needed for interconnecting the thousands of servers in these data centers. Various multilayer architectures employing thousands of switches have been proposed in the literature. We make use of the observation that the traffic in a data center is a mixture of relatively static and rapidly fluctuating components, and develop a combined scheduler for… 

Figures from this paper

Costly Circuits, Submodular Schedules: Hybrid Switch Scheduling for Data Centers
TLDR
This paper demonstrates a lightweight, simple and nearly-optimal scheduling algorithm that trades-off configuration costs with the benefits of reconfiguration that match the traffic demands and sees that indirect routing leads to exponential connectivity.
A Dynamical and Load-Balanced Flow Scheduling Approach for Big Data Centers in Clouds
TLDR
Experimental results demonstrate that theDLBS approach significantly outperforms other representative load-balanced scheduling algorithms Round Robin and LOBUS; and the higher imbalance degree data flows in data centers exhibit, the more improvement the DLBS approach will bring to the data centers.
An Efficient Flow Detection and Scheduling Method in Data Center Networks
TLDR
A port forwarding load-balanced scheduling (PFLBS) approach for Fat-tree based DCNs that simplifies the switch's functionality and makes the routing lookup operation unnecessary and decreases the flow completion time and improve the average throughput significantly.
End-to-end scheduling for all-optical data centers
TLDR
This paper considers the end-to-end scheduling for all-optical data center networks with zero in-network buffer and non-negligible reconfiguration delay and presents a framework for scheduling with reconfigurations delay that decouples the rate of scheduling from the rates of monitoring.
Efficient Dynamic Load-Balance Flow Scheduling in Cloud for Big Data Centers
TLDR
Experimental results demonstrate that theDLBS approach signicantly outperforms other load-balanced scheduling algorithms Round Robin and LOBUS; and the higher imbalance degree data ows in data centers exhibit, the more improvement the DLBS approach will bring to the data centers.
An Appropriate scheduling using Dynamic load balancing approach for bigdata in cloud
TLDR
This paper proposes a dynamical load-balanced scheduling (DLBS) approach for dynamically balancing the work load and also increase the maximizing through put and demonstrates that this approach significantly outperforms other representative loadbalanced scheduling algorithms Round Robin and LOBUS.
Time-Division based Scheduling Scheme for Hybrid Optical/Electrical Data Center Network
TLDR
An OCS-based scheduling scheme named Time-Division Scheduling (TDS), which groups OCSes and reconfigures different groups in sequential time slots, instead of periodically reconfiguring all OCSe, is proposed.
Datacenter Traffic Control: Understanding Techniques and Tradeoffs
TLDR
It is found that a combination of different traffic control techniques may be necessary at particular entities and layers in the network to improve the variety of performance metrics, and despite significant research efforts, there are still open problems that demand further attention from the research community.
Datacenter Traffic Control: Understanding Techniques and Trade-offs
TLDR
Various characteristics of datacenter traffic control including management schemes, transmission control, traffic shaping, prioritization, load balancing, multipathing, and traffic scheduling are discussed.
A port-based forwarding load-balancing scheduling approach for cloud datacenter networks
TLDR
This paper proposes a port-based forwarding load balancing scheduling (PFLBS) approach for Fat-tree based DCNs with some new features which can overcome the disadvantages of the existing load balancing methods in the following aspects.
...
1
2
3
...

References

SHOWING 1-10 OF 41 REFERENCES
Maintaining packet order in two-stage switches
  • I. Keslassy, N. McKeown
  • Computer Science
    Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies
  • 2002
TLDR
This paper presents an algorithm called full frames first (FFF), that prevents mis-sequencing while maintaining the performance benefits (in terms of throughput and delay) of the basic two-stage switch.
A Versatile Scheme for Routing Highly Variable Traffic in Service Overlays and IP Backbones
TLDR
This paper develops linear programming formulations and a fast combinatorial algorithm for routing under the scheme so as to maximize throughput (or, minimize maximum link utilization) and compares the throughput performance of the scheme with that of the optimal scheme among the class of all schemes that are allowed to even make the routing dependent on the traffic matrix.
Fastpass: A Centralized “Zero-Queue” Datacenter Network
TLDR
This paper describes Fastpass, a datacenter network architecture built using this principle that achieves high throughput comparable to current networks at a 240x reduction is queue lengths, and achieves much fairer and consistent flow throughputs than the baseline TCP.
Designing a Predictable Internet Backbone Network
TLDR
This paper proposes that backbone networks use Valiant Load-balancing over a fully-connected logical mesh, which is provably the lowest capacity network with these characteristics, and provides fast convergence after failure, making it possible to support real-time applications.
Flyways To De-Congest Data Center Networks
TLDR
A study of application demands from a production datacenter of servers shows that except for a few outliers, application demands can be generally met by a network that is slightly oversubscribed, and advises a hybrid architecture to tackle the hotspots that remain.
The Load-Balanced Router
TLDR
A simple distributed algorithm is introduced that can avoid packet reordering while providing delay and capacity guarantees in the Internet, and it is proved that among all possible switch fabrics with no reconfigurations, a specific load-balanced switch fabric uniquely achieves the maximum possible guaranteed capacity.
A Survey on Optical Interconnects for Data Centers
TLDR
A thorough survey on optical interconnects for next generation data center networks is presented and a qualitative categorization and comparison of the proposed schemes based on their main features such as connectivity and scalability are provided.
MicroTE: fine grained traffic engineering for data centers
TLDR
This study reveals that existing traffic engineering techniques perform 15% to 20% worse than the optimal solution, and develops MicroTE, a system that adapts to traffic variations by leveraging the short term and partial predictability of the traffic matrix.
On direct routing in the valiant load-balancing architecture
It is very hard to design a network with performance guarantees, partly because it is hard to estimate the future traffic matrix. With no knowledge of the traffic matrix, one can use the valiant
Path selection and bandwidth allocation in MPLS networks
...
1
2
3
4
5
...