Computer Science Thesis Oral

Tuesday, May 1, 2018 - 11:00am


ASA Conference Room 6115 Gates Hillman Centers



Network system operation is typically divided into control and data planes--- while the data plane is responsible for processing individual messages or packets, the control plane computes the configuration of devices and optimizes system-wide performance. Unfortunately, the control plane of each network system or protocol layer typically operates independently, resulting in poor interactions between control planes across systems. I propose four general control plane coordination mechanisms to overcome these problems, based on how much information can be shared between control planes. If no information is shared, control planes simply "react" to data plane changes as a rudimentary form of coordination. If all information can be shared, "transparency" in decision making can remove most poor interactions. In many scenarios, however, only some information can be shared (e.g., between control planes running in different companies). Coordination in these scenarios depends on data plane overlap; designs with separate data planes (e.g., BGP-BGP interactions) can use "priority ranking" (i.e., providing a list of preferences for resources without needing to show how these preferences were decided), and designs with shared data planes (e.g., BGP-OSPF interactions) can use "hierarchical partitioning" (i.e., making coarse-grained decisions globally, and fine-grained decisions locally).

In this thesis, I show how to apply these techniques in three common scenarios. Transparency can boost performance in layered systems, as I show with Etalon, in the context of reconfigurable datacenters. Priority ranking can better optimize for cost in administratively separate systems, as I show with VDX, in the context of content brokering. And hierarchical partitioning can improve responsiveness in internet-scale systems, as I show with VDN, in the context of live video streaming.

Thesis Committee:
Srinivasan Seshan (Chair)
Peter Steenkiste
Vyas Sekar
Bruce Maggs (Duke University / Akamai Technologies, Inc.)

For More Information, Contact:


Thesis Oral