High Throughput Data Center Topology Design

@inproceedings{Singla2014HighTD,
  title={High Throughput Data Center Topology Design},
  author={Ankit Singla and Brighten Godfrey and Alexandra Kolla},
  booktitle={NSDI},
  year={2014}
}
With high throughput networks acquiring a crucial role in supporting data-intensive applications, a variety of data center network topologies have been proposed to achieve high capacity at low cost. While this work explores a large number of design points, even in the limited case of a network of identical switches, no proposal has been able to claim any notion of optimality. The case of heterogeneous networks, incorporating multiple line-speeds and port-counts as data centers grow over time… Expand
Space Shuffle: A Scalable, Flexible, and High-Performance Data Center Network
  • Ye Yu, Chen Qian
  • Computer Science
  • IEEE Transactions on Parallel and Distributed Systems
  • 2014
TLDR
A novel flexible data center network architecture, Space Shuffle (S2), which applies greedy routing on multiple ring spaces to achieve high-throughput, scalability, and flexibility and the proposed greedy routing protocol of S2 effectively exploits the path diversity of densely connected topologies and enables key-based routing. Expand
Space Shuffle: A Scalable, Flexible, and High-Bandwidth Data Center Network
TLDR
A novel flexible data center network architecture, Space Shuffle (S2), is designed, which applies greedy routing on multiple ring spaces to achieve high-throughput, scalability, and flexibility and effectively exploits the path diversity of densely connected topologies and enables key-based routing. Expand
Designing data center networks using bottleneck structures
TLDR
It is shown that interference-free patterns correspond to the important set of patterns that display data locality properties and use these theoretical insights to study three widely used interconnects---fat-trees, folded-Clos and dragonfly topologies. Expand
Fat-FREE Topologies
TLDR
It is taken that alongside the development of reconfigurable topologies, the community should also invest in developing superior traffic engineering over static networks other than fat-trees as an alternate path forward, and a rigorous quantification of the difference between the power of two techniques for handling dynamic, unpredictable traffic with limited network resources. Expand
A throughput-centric view of the performance of datacenter topologies
TLDR
It is shown that using throughput to evaluatedatacenter performance instead of bisection bandwidth can alter conclusions in prior work about datacenter cost, manageability, and reliability. Expand
Demand-Aware Network Designs of Bounded Degree
TLDR
A general lower bound based on the entropy of the communication pattern D is derived, and asymptotically optimal network-aware design algorithms for important distribution families, such as sparse distributions and distributions of locally bounded doubling dimensions are presented. Expand
Flier: Flow-level congestion-aware routing for direct-connect data centers
TLDR
Evaluations show that Flicr consistently outperforms other state-of-the-art load balancing designs, achieving 25–60% lower average flow completion time compared to adaptive routing and is also more robust against link failures and has 5–8 χ better performance relative to other schemes in the presence of link failures. Expand
Static Yet Flexible: Expander Data Center Network Fabrics
TLDR
The work raises new potential inquiries pertaining to the vast space of routing logic and their parametrization, engineering challenges in the deployment of expanders, exploration and topology-independent characterization of workload in the data center, further verification through use of other simulators or physical deployment, and theoretical understanding of the capabilities of dynamic topologies. Expand
Failure-Resilient Routing for Server-Centric Data Center Networks with Random Topologies
Data center networks with random topologies provide several promising features, such as near-optimal bisection bandwidth and flexibility of incremental growth. However, network failures areExpand
Superways: A Datacenter Topology for Incast-heavy workloads
TLDR
This work proposes Superways, a heterogeneous datacenter topology that provides higher bandwidth for some servers to absorb incasts, as incasts occur only at a small number of servers that aggregate responses from other senders. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
A scalable, commodity data center network architecture
TLDR
This paper shows how to leverage largely commodity Ethernet switches to support the full aggregate bandwidth of clusters consisting of tens of thousands of elements and argues that appropriately architected and interconnected commodity switches may deliver more performance at less cost than available from today's higher-end solutions. Expand
Dcell: a scalable and fault-tolerant network structure for data centers
TLDR
Results from theoretical analysis, simulations, and experiments show that DCell is a viable interconnection structure for data centers and can be incrementally expanded and a partial DCell provides the same appealing features. Expand
Measuring and Understanding Throughput of Network Topologies
TLDR
This paper develops a framework to benchmark the throughput of network topologies, using a two-pronged approach, and shows how to measure worst-case throughput by generating a near-worst-case TM for any given topology. Expand
REWIRE: An optimization-based framework for unstructured data center network design
TLDR
A data center network design framework, that is called REWIRE, to design networks using an optimization algorithm, which significantly outperforms previous solutions and has up to 100-500% more bisection bandwidth and less end-to-end network latency than equivalent-cost DCNs built with best practices. Expand
VL2: a scalable and flexible data center network
TLDR
VL2 is a practical network architecture that scales to support huge data centers with uniform high capacity between servers, performance isolation between services, and Ethernet layer-2 semantics, and is built on a working prototype. Expand
LEGUP: using heterogeneity to reduce the cost of data center network upgrades
TLDR
The theory of heterogeneous Clos networks is developed and it is shown that the construction needs only as much link capacity as the classic Clos network to route the same traffic matrices and this bound is the optimal. Expand
PortLand: a scalable fault-tolerant layer 2 data center network fabric
TLDR
Through the design and implementation of PortLand, a scalable, fault tolerant layer 2 routing and forwarding protocol for data center environments, it is shown that PortLand holds promise for supporting a ``plug-and-play" large-scale, data center network. Expand
Small-world datacenters
TLDR
This paper proposes an unorthodox topology for datacenters that eliminates all hierarchical switches in favor of connecting nodes at random according to a small-world-inspired distribution, and shows that Small-World Datacenters can achieve higher bandwidth and fault tolerance compared to both conventional hierarchical datacenter as well as the recently proposed CamCube topology. Expand
Jellyfish: Networking Data Centers Randomly
TLDR
Jellyfish is a high-capacity network interconnect which, by adopting a random graph topology, yields itself naturally to incremental expansion, and is more cost-efficient than a fat-tree. Expand
Proteus: a topology malleable data center network
TLDR
Proteus is proposed, an all-optical architecture targeting unprecedented topology-flexibility, lower complexity and higher energy efficiency, that is, an oversubscribed network architectures that can adapt the topology to meet traffic demands. Expand
...
1
2
3
4
...