Search

Deployment and maintenance of current data center networks is costly and prone to errors. In order to avoid manual configuration, many of them require centralized administrators which constitute a clear bottleneck, while distributed approaches do not guarantee sufficient flexibility or robustness. This paper describes and evaluates GA3 (Generalized Automatic Address Assignment), a discovery protocol that assigns multiple unique labels to all the switches in a hierarchical network, without any modification of hosts or the standard Ethernet frames. Labeling is distributed and uses probes. These labels can be leveraged for shortest path routing without tables, as in the case of the Torii protocol, but GA3 also allows other label-based routing protocols (such as PortLand or ALIAS). Additionally, GA3 can detect miswirings in the network. Furthermore, control traffic is only necessary upon network deployment rather than periodically. Simulation results showed a reduced convergence time of less than 2 s and 100 kB/s of bandwidth (to send the GA3 frames) in the worst case for popular data center topologies, which outperforms other similar protocols., Comunidad de Madrid

This paper describes and evaluates Torii, a layer 2 data centre network fabric protocol. The main features of Torii are being fully distributed, scalable, fault-tolerant and with automatic setup. Torii is based on multiple, tree-based, topological media access control addresses that are used for table-free forwarding over multiple equal-cost paths, and it is capable of rerouting frames around failed links on the fly without needing a central fabric manager for any function. To the best of our knowledge, it is the first protocol that does not require the exchange of periodic messages to work under normal conditions and to recover from link failures, as Torii exchanges messages just once. Moreover, another important characteristic of Torii is that it is compatible with a wide range of data centre topologies. Simulation results show an excellent distribution of traffic load and latencies, similar to the shortest path protocols. Copyright © 2014 John Wiley & Sons, Ltd.

This paper describes Path-Moose, a scalable tree-based shortest path bridging protocol. Both ARP-Path and Path-Moose protocols belong to a new category of bridges that we name All-path, because all paths of the network are explored simultaneously with a broadcast frame distributed over all network links to find a path or set a multicast tree. Path-Moose employs the ARP-based low latency routing mechanism of the ARP-Path protocol on a bridge basis instead of a per-single-host basis. This increases scalability by reducing forwarding table entries at core bridges by a factor of fifteen times for big data center networks and achieves a faster reconfiguration by an approximate factor of ten. Reconfiguration time is significantly shorter than ARP-Path (zero in many cases) because, due to the sharing of network paths by the hosts connected to same edge bridges, when a host needs the path it has already been recovered by another user of the path. Evaluation through simulations shows protocol correctness and confirms the theoretical evaluation results. This work was supported in part by grants from Comunidad de Madrid and Universidad de Alcal´a through the following projects: MEDIANET-CM (S-2009/TIC-468), EMARECE (PII1I09-0204-4319) and CMAC (UAH2011/EXP-016). Publicado

The work at: The 37th IEEE Conference on Local Computer Networks (LCN). Clearwater, Florida, USA. Date: 22-25 October 2012 This paper describes Flow-Path, an AllPath flowbased switching protocol that features improved load adaptive properties. Upon arrival of a new flow to the network, it explores every possible path reaching from source to destination host and selects the lowest latency path at the moment. It is based on the same basic principle than ARPPath, that is, snooping the ARP protocol dialog (request and reply messages) to explore all available paths at the same time that address resolution takes place, but it is flow-based instead of source address-based. While preserving the main advantages of ARP-Path: shortest path bridging exploiting the full network topology, Flow-Path has the advantages of full independence of flows at the time of path creation and guarantees path symmetry (congruency) and increased path diversity. Flow-Path thus improves load distribution, at the expense of increased address table size in each bridge. This work was supported in part by grants from Comunidad de Madrid and Comunidad de Castilla-La Mancha through Projects MEDIANET-CM (S-2009/TIC- 1468) and EMARECE (PII1I09-0204-4319). Publicado

This work is at: The 36th IEEE Conference on Local Computer Networks (LCN) took place 04/10/2011 - 07/10/2011 in Bonn (Germany). This web site to: http://www.ieeelcn.org/prior/LCN36/index.html This demo shows, in a small data center demo network topology the ARP Path bridges functionality and robustness over varied platforms and their interoperability. ARP-Path bridges set up on-demand shortest paths between hosts using the standard ARP Request, but flooded over all links, to find the lowest latency path to the destination host. ARP Path is loop free, uses the standard Ethernet frame and compatible with hosts and routers.Data center demo network consists of ten ARP Path bridges. Eight bridges are implemented with standard Openflow switches (four NEC PF8800/PF5240 Open flow capable switches and four Soekris boxes running Open flow Switch implementation) and the other two are implemented on OpenWRT. A previous demo showed (in remote lab) the protocol operation over four NetFPGA boards executing Openflow[7]. Demo shows network operation with standard applications like video, demonstrating the protocol robustness, zero configuration, fast network reconfiguration upon link failures and after mobility of a host.. Implementations in Linux and Openflow show inherent robustness and fast reconfiguration. Additionally, information and video of the Sigcomm 2011 demo with implementation of ARP Path protocol on a network of four NetFPGA boards (pure hardware implementation) is also posted [8]. Publicado

This article describes a scalable, self-configuring architecture for campus networks, the ABridges architecture. It is a two-tiered hierarchy of layer two switches in which network islands running independent rapid spanning tree protocols communicate through a core formed by island root bridges (ABridges). ABridges use AMSTP, a simplified and self configuring version of MSTP protocol, to establish shortest paths in the core using multiple spanning tree instances, one instance rooted at each core edge ABridge. The architecture is very efficient in terms of network usage and path length due to the ability of AMSTP to provide optimum paths in the core mesh, while RSTP is used to aggregate efficiently the traffic at islands networks, where sparsely connected, tree-like topologies are frequent and recommended. Convergence speed is as fast as existing Rapid Spanning Tree and Multiple Spanning Tree Protocols. TRUE pub