Optimizing the "one big switch" abstraction in software-defined networks

By Nanxi Kang, Zhenming Liu, Jennifer Rexford, David Walker. Conference on Emerging Network Experiment and Technology, 2013

307 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/4c8a2c0ac9f3e1acf93c5c789af7bbd8a8875017

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

Citations in the corpus

One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon (2016, methodology): “UnivMon should provide a “one big switch” abstraction for monitoring to the management applications running atop UnivMon, so that the estimates appear as if all the trafﬁc entering the network was monitored at a giant switch [34].”
Packet Transactions: High-Level Programming for Line-Rate Switches (2015, methodology): “SNAP [24] programs stateful data-plane algorithms using a network transaction: an atomic block of code that treats the entire network as one switch [44].”
Efficient Coflow Scheduling Without Prior Knowledge (2015, methodology): “Non-Blocking Fabric In our analysis, we abstract out the entire datacenter fabric as one non-blocking switch [10, 15, 20, 9, 31, 26] and consider machine uplinks and downlinks as the only sources of contention (Figure 1a).”
A Survey and a Layered Taxonomy of Software-Defined Networking (2014, background): “[80] Flow tables size Algorithm for rules placement that distributes forwarding policies and supports dynamic incremental update of policies Rule placement algorithm within the controller to satisfy switch table-size constraints”
A survey: Control plane scalability issues and approaches in Software-Defined Networking (SDN) (2017, unknown): “1007/978- 3- 642- 35668- 1 _ 32 [17] N.”
Efficient coflow scheduling with Varys (2014, unknown): “In our analysis, we consider a network model where the entire datacenter fabric is abstracted out as one non-blocking switch [8,11,27,33] interconnecting all the machines (Figure 1), and we focus only on its ingress and egress ports (e.g., machine NICs).”
HULA: Scalable Load Balancing Using Programmable Data Planes (2016, background): “Load balancing also provides the abstraction of a single large output-queued switch for the entire network [1–3], which in turn simpliﬁes bandwidth allocation across tenants [4,5], ﬂows [6], or groups of ﬂows [7].”