ElasticTree: saving energy in data center networks
Citations
3,589 citations
2,119 citations
2,013 citations
Cites background from "ElasticTree: saving energy in data ..."
...[53] indicates that much research has been focused on improved servers and cooling (70% of total energy) through better hardware or software management, but the data center’s network infrastructure (which accounts for 10-20% of the total energy cost) still consumed 3 billion kWh in 2006....
[...]
1,968 citations
1,132 citations
Cites background or methods from "ElasticTree: saving energy in data ..."
...[29] route all flows with the controller to achieve energy-aware routing; however, it may be possible to perform energy-aware routing without full flow visibility....
[...]
...This separation between forwarding rules and policy allows for innovative and promising network management solutions such as NOX [26, 45] and other proposals [29, 39, 49], but these solutions may not be realizable on many networks because the flow-based networking platform they are built on— OpenFlow—is not scalable....
[...]
...Beyond this use case, we believe that DevoFlow can simplify the design of high-performance OpenFlow switches and enable scalable management architectures to be built on OpenFlow for data center QoS, multicast, routing-as-a-service [14], network virtualization [43], and energy-aware routing [29]....
[...]
..., [5, 29, 33, 39, 43]),...
[...]
...While OpenFlow was originally proposed for campus and wide-area networks, others have made quantified arguments that OpenFlow is a viable approach to high-performance networks, such as data center networks [45], and it has been used in proposals for traffic management in the data center [5,29]....
[...]
References
3,549 citations
"ElasticTree: saving energy in data ..." refers background or methods in this paper
...As services scale beyond ten thousand servers, inflexibility and insufficient bisection bandwidth have prompted researchers to explore alternatives to the traditional 2N tree topology (shown in Figure 1(a)) [1] with designs such as VL2 [10], PortLand [24], DCell [16], and BCube [15]....
[...]
...The MST+1 configuration requires one additional edge switch per pod, and one additional switch in the core, to enable any single aggregation or core-level switch to fail without disconnecting a server....
[...]
2,499 citations
"ElasticTree: saving energy in data ..." refers background in this paper
...We now show an example of the system in action....
[...]
2,350 citations
"ElasticTree: saving energy in data ..." refers background or methods in this paper
...As services scale beyond ten thousand servers, inflexibility and insufficient bisection bandwidth have prompted researchers to explore alternatives to the traditional 2N tree topology (shown in Figure 1(a)) [1] with designs such as VL2 [10], PortLand [24], DCell [16], and BCube [15]....
[...]
...The same computation works for other topologies, such as the aggregated Clos used by VL2 [10], which has 10G links above the edge layer and 1G links to each host....
[...]
...In addition, by decoupling power optimization from routing, our method can be applied alongside any fat tree routing algorithm, including OSPF-ECMP, valiant load balancing [10], flow classification [1] [2], and end-host path selection [23]....
[...]
...Other complementary research in data center networks has focused on scalability [24][10], switching layers that can incorporate different policies [20], or architectures with programmable switches [11]....
[...]
1,756 citations
"ElasticTree: saving energy in data ..." refers background in this paper
...Data centers aim to provide reliable and scalable computing infrastructure for massive Internet services....
[...]
1,681 citations
"ElasticTree: saving energy in data ..." refers background in this paper
...NOX: NOX is a centralized platform that provides network visibility and control atop a network of OpenFlow switches [13]....
[...]