PortLand

Abstract

This paper considers the requirements for a scalable, easily manageable, fault-tolerant, and efficient data center network fabric. Trends in multi-core processors, end-host virtualization, and commodities of scale are pointing to future single-site data centers with millions of virtual end points. Existing layer 2 and layer 3 network protocols face some combination of limitations in such a setting: lack of scalability, difficult management, inflexible communication, or limited support for virtual machine migration. To some extent, these limitations may be inherent for Ethernet/IP style protocols when trying to support arbitrary topologies. We observe that data center networks are often managed as a single logical network fabric with a known baseline topology and growth model. We leverage this observation in the design and implementation of PortLand, a scalable, fault tolerant layer 2 routing and forwarding protocol for data center environments. Through our implementation and evaluation, we show that PortLand holds promise for supporting a ``plug-and-play" large-scale, data center network.

GANA-VDC: Application-Aware with Bandwidth Guarantee in Cloud Datacenters

“…This system is built based on Portland layer-2 fabric considerations. Contrary to Portland [16], in our underlying physical network topology, we use interconnected OpenFlow switches instead of commodity switches. The main work of GANA-VDC implemented in the hypervisor contains four main components ( Figure 4 Forwarding Pattern Dispatcher: Two forwarding patterns are provided in GANA-VDC where tenants can determine which pattern to use.…”

“…Finally, the encapsulation component encapsulates the packet, using a source routing protocol. When a server sends a packet, the encapsulation component invokes a call to the fabric manager in Portland [16] to learn the real destination switch location and tunnels the original packet in accordance with the source routing protocol. Thereby, this eliminates the ARP in layer-2 networks scalability problems.…”

“…This paper presents GANA-VDC, a network virtualization framework supporting bandwidth allocation in cloud data centers. In this work, we observe primarily the network remains physically interconnected as a fat-tree to a second layer scalable and fault-tolerant routing and forwarding protocol, for cloud data center using commodity switches [16]. However, the commodity switches closure restricts internal information access and control, prohibiting application-aware networking.…”

A guided tour of data-center networking

“…Further, each layer 2 switch will participate in an STP (spanning tree protocol) or use the TRILL (transparent interconnect of lots of links) link-state protocol to exchange routing information and avoid transient routing loops that may arise while the link state is exchanged among peers. Neither layer 2 nor layer 3 routing is perfectly suited to data-center networks, so to overcome these limitations many new routing algorithms have been proposed (for example, PortLand 1,18 and VL2 11 ). Routing.…”

Quickly Converging Renumbering in Network with Hierarchical Link-State Routing Protocol

“…A several approaches that do not use link-state routing protocols are proposed in order to construct data centers with a large number of servers. Al-Fares et al [4] and Niranjan Mysore et al [5] enable routing without a link-state routing protocol by restricting a network topology to the one called fat-tree. Mudigonda et al [6] uses VLANs for providing multi-paths.…”