Publication date: 24/08/2018

Namesort descending Role

Examining board:

Namesort descending Role

Summary: Recently, we have seen the increasing use of information and communication technologies. Institutions and users simply require high-quality connectivity of their data, expecting instant access anytime, anyWHERE. An essential element for providing quality in the connectivity is the architecture of the communication network in Data Center Networks (DCNs). This is because a significant part of Internet traffic is based on data communication and processing that takes place within the Data Center (DC) infrastructure. However, the routing protocols, the forwarding model, and management that are currently running, prove to be insufficient to meet the current demands for cloud connectivity. This is mainly due to the dependency on the table lookup operation, that leads to an end-to-end latency increment. Besides, traditional recovery mechanisms have used additional states in the switch tables, increasing the complexity of management routines, and drastically reducing the scalability for routes protection. Another difficulty is the multicast communication within DC, existing solutions are complex to implement and do not support group configuration at the current required rates.

In this context, this thesis explores the numerical system of residues centered in the Chinese remainder theorem (CRT) as a foundation, applied in the design of a new routing system for DCN. More specifically, we introduce RDNA architecture that advances the state-of-the-art from a simplification of the forwarding model to the core, based on the remainder of the division (modulo). In this sense, the route is defined as a residue between a route identification and local identification (prime numbers) assigned to the core switches. Edge switches receive inputs by configuring flows according to the network policy defined by the controller. Each flow is mapped to the edge, through a primary and an emergency route identification. These residue operations allow forwarding the packet through the respective output port. In failure situations, the emergency route identification enables fast recovery by sending the packets through an alternate output port.

RDNA is scalable by assuming a 2-tier Clos Network topology widely used in DCNs. In order to compare RDNA with other works of the literature, we analyzed the scalability in terms of the number of bits required for unicast and multicast communication. In the analysis, the number of nodes in the network, the degree of the nodes and the number of physical hosts for each topology were varied. In unicast communication, the RDNA reduced by 4.5 times the header size, compared to the COXCast proposal. In multicast communication, a linear programming model is designed to minimize a polynomial function. RDNA reduced header size by up to 50\% compared to the same number of members per group.

As proof of concept, two prototypes were implemented, one in the Mininet emulated environment and another in the NetFPGA SUME platform. The results presented that RDNA achieves deterministic latency in packet forwarding, 600 nanoseconds in switching time per core element, ultra-fast failure recovery in the order of microseconds and no latency variation (no jitter) in the core network.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910