Use this URL to cite or link to this record in EThOS:
Title: Hybrid architecture for high performance lookup
Author: Perez, Keyssy Guerra
ISNI:       0000 0004 5372 650X
Awarding Body: Queen's University Belfast
Current Institution: Queen's University Belfast
Date of Award: 2015
Availability of Full Text:
Full text unavailable from EThOS.
Please contact the current institution’s library for further details.
In this research improved header lookup and flow rule update speeds over conventional lookup algorithms is investigated. A detailed study if several well-known lookup algorithms reveals that individual packet header fields lookups and combining the lookup results achieved high lookup speed. The traditional packet classification solutions are not suitable for the actial network requirements, which are being promoted as the basis for Software-Defined Networking (SON) and the OpenFlow protocol. The proposed hybrid lookup architecture is comprised of various lookup algorithms, which are 'selected for packet classification based on the requirements of applications or functions, such as SDN. SDN introduces programmability to the network, with the opportunity to dynamically route traffic based on flow descriptions. Thus, improving the network processing performance with the . proposed configurable solution will/directly support the proposed capability of programmability in SDN. The hardware implementation of the proposed configurable lookup architecture, which is able to work at line rate, is evaluated for different combinations of ~he set of lookup algorithms. Recent Open Flow switches tend to perform packet header lookup through the multiple lookup tables to enable new protocols, such as VxLAN. Hence, an extension of the proposed architecture is also developed based on multiple table lookup. The extended architecture takes advantages of lookup speed and flexibility from the previous architecture for 15-field lookup at the current line rate of 40-1 00 Gbps.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available