A scalable, commodity data center network architecture
Proceedings of the ACM SIGCOMM 2008 conference on Data communication
VL2: a scalable and flexible data center network
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
The nature of data center traffic: measurements & analysis
Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference
c-Through: part-time optics in data centers
Proceedings of the ACM SIGCOMM 2010 conference
Hedera: dynamic flow scheduling for data center networks
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Design, implementation and evaluation of congestion control for multipath TCP
Proceedings of the 8th USENIX conference on Networked systems design and implementation
Augmenting data center networks with multi-gigabit wireless links
Proceedings of the ACM SIGCOMM 2011 conference
Improving datacenter performance and robustness with multipath TCP
Proceedings of the ACM SIGCOMM 2011 conference
Opening up black box networks with CloudTalk
HotCloud'12 Proceedings of the 4th USENIX conference on Hot Topics in Cloud Ccomputing
Netmap: a novel framework for fast packet I/O
USENIX ATC'12 Proceedings of the 2012 USENIX conference on Annual Technical Conference
| Hi-index | 0.00 |
Various full bisection designs have been proposed for datacenter networks. They are provisioned for the worst case in which every server wishes to send flat out and there is no congestion anywhere in the network. However, these topologies are prone to considerable under-utilization in the average case encountered in practice. To utilize spare bandwidth we propose GRIN, a simple, cheap and easily deployable solution that simply wires up any free ports datacenter servers may have. GRIN allows each server to use up to a maximum amount of bandwidth dependent on its available network ports and the number of idle uplinks in the same rack. This design can be used to augment almost any existing datacenter network, with little initial effort and no additional maintenance costs.