IPPS '95 Proceedings of the 9th International Symposium on Parallel Processing
Principles and Practices of Interconnection Networks
Principles and Practices of Interconnection Networks
A scalable, commodity data center network architecture
Proceedings of the ACM SIGCOMM 2008 conference on Data communication
PortLand: a scalable fault-tolerant layer 2 data center network fabric
Proceedings of the ACM SIGCOMM 2009 conference on Data communication
BCube: a high performance, server-centric network architecture for modular data centers
Proceedings of the ACM SIGCOMM 2009 conference on Data communication
Data Center Switch Architecture in the Age of Merchant Silicon
HOTI '09 Proceedings of the 2009 17th IEEE Symposium on High Performance Interconnects
HyperX: topology, routing, and packaging of efficient large-scale networks
Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis
Energy proportional datacenter networks
Proceedings of the 37th annual international symposium on Computer architecture
Symbiotic routing in future data centers
Proceedings of the ACM SIGCOMM 2010 conference
Helios: a hybrid electrical/optical switch architecture for modular data centers
Proceedings of the ACM SIGCOMM 2010 conference
ElasticTree: saving energy in data center networks
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Hedera: dynamic flow scheduling for data center networks
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
A cost comparison of datacenter network architectures
Proceedings of the 6th International COnference
| Hi-index | 0.00 |
Data-center network designers now have many choices for high-bandwidth, multi-path network topologies. Some of these topologies also allow the designer considerable freedom to set parameters (for example, the number of ports on a switch, link bandwidths, or switch-to-switch wiring patterns) at design time. This freedom of choice, however, requires the designer to balance among bandwidth, latency, reliability, parts cost, and other real-world details. Designers need help in exploring this design space, and especially in finding optimal network designs. We describe the specific challenges that designers face, and we present Perseus, a framework for quickly guiding a network designer to a small set of candidate designs. We identify several optimization problems that can be accommodated within this framework, and present solution algorithms for many of these problems.