Στην εργασία παρουσιάζεται η μελέτη, η πιστοποίηση και η εφαρμογή των μηχανισμών εκείνων που οδηγούν στην παροχή end-to-end QoS σε ενοποιημένα L2 και MPLS δίκτυα. / In a real IP network such as the Internet, the basic type of service offered is the
best effort one. In the best effort service all packets are treated equally and there
are no guarantees, variations or attempt to enforce justice. However, the
network seeks to promote as much traffic as possible with “reasonable” quality.
Network congestion is a frequent phenomenon that is introduced when a
network device stores packets at the output queue as it receives more packets
from those that it can transmit. During congestion packets suffer from delay and
once the output queue becomes full, these packets are dropped.
However, there are applications that require certain guarantees (especially
regarding delay and packet drops) such as real-time data transmission
applications (e.g. IP telephony, voice over IP) and videoconference. Quality
guarantees for these applications can be ensured if they can cross empty or nearempty network queues. This can only be achieved through mechanisms that can
ensure the capacity and availability of the network queues.
A means to provide quality guarantees to certain types of traffic is the special
management of certain packets compared to the other. At this point the term
Quality of Service (QoS) is introduced. A definition for QoS is: "the ability of a
network element to provide a level of guarantee to a subset of traffic that ensures
that the requirements of the service can be achieved with a defined (high)
probability". In reality, the mechanisms of QoS do not provide larger network
capacity or something similar, but they rather provide better network
management so that it can be used more effectively and it can meet and address
the requirements of the applications.
In recent years, efforts have focused on providing quality of service at the
network layer (Layer 3) so that it can be also applied on the Internet. Using
architectures such as IntServ and DiffServ it is now possible to provide quality
service at the network layer. However, the requirement for end-to-end QoS along
with the expansion of networks towards switching equipment, creates the need
for the application of QoS in the next lower layer, that is the data link layer
(Layer 2). Hence, it should be borne in mind that the interoperability between
the network and data link layers will lead to the provision of a single, transparent
level of QoS.
Based on the above, it becomes clear that in order to achieve end-to-end QoS,
apart from the need for extension of the QoS to the data link layer there is also
the need and requirement of interoperability with existing implementations in the network layer. In this direction, this dissertation focuses on studying the
application of QoS to the data link layer. Furthermore, given the provision of
quality of service to the IP layer, this dissertation considers the integration of
QoS provision at Layer 2 and Layer 3. Therefore, the objective of this dissertation
is twofold: a) QoS provision over Layer2-Ethernet networks and b) QoS
provision over Layer 2 VPNs.
For the implementation of Layer 2 QoS over Ethernet networks the IEEE 802.1p
standard has been proposed. This standard has 3 bits length and is part of Tag
Control Information field. During this dissertation performance tests were
carried out on switches sorting traffic under CoS, which results in 8 different
classes of traffic. Furthermore, queue configuration techniques on switches have
been studied along with the cases of per port/per 802 .1q priorities and traffic
classification.
For the implementation of L2 QoS over VPNs there are techniques that are
strongly related to the VPN type. This dissertation presents cases that L2 MPLS
VPNs are used for the provisioning of either point-to-point (EoMPLS) or point-tomultipoint (VPLS) VPNs. In addition, research has been carried out for the
extension of QoS provision over L2 MPLS VPNs to end-points that is purely L2
domain. The analysis at L2 domain was realized with the IEEE 802.1 p standard.
Furthermore, the ability to provide QoS over multipoint L2 VPNs has been
studied. Initially, the focus was on L3 devices (routers) and it was then extended
to L2 using IEEE 802.1 p. Thus, the overall implementation was based on the
combined use of 802.1p, DSCP and MPLS EXP.
In addition, this dissertation presents methods, techniques and configurations of
switches and routers that allow for the expansion of QoS from the network layer
at a lower layer, thereby providing a consistent QoS level both at Layer 3 and
Layer 2.
Finally, the automated delivery/provision of these services in a real production
network, GRNET, is presented. More specifically, the modeling of L2 QoS-enabled
switches is described along with the automated configuration production for
providing integrated QoS and issues related to the discovery, mapping and
monitoring of QoS in switches using the SNMP protocol. The effectiveness of
Layer 2 QoS mechanisms was tested and reinforced with experiments, which
were conducted small scale at first in the lab and in the department of the
University and then moved on to large scale at the production network of
GRNET. The experiments showed that regardless of the expansion of a network
towards Layer 2 devices, it is feasible to provide a unified QoS framework.
All the above resulted in the provisioning of end-to-end QoS services at GRNET’s
network.
| Identifer | oai:union.ndltd.org:upatras.gr/oai:nemertes:10889/4230 |
| Date | 07 April 2011 |
| Creators | Πουλόπουλος, Λεωνίδας |
| Contributors | Μπούρας, Χρήστος, Poulopoulos, Leonidas, Βαρβαρίγος, Μάνος, Βλάχος, Κυριάκος, Μπούρας, Χρήστος |
| Source Sets | University of Patras |
| Language | gr |
| Detected Language | English |
| Type | Thesis |
| Rights | 0 |
| Relation | Η ΒΚΠ διαθέτει αντίτυπο της διατριβής σε έντυπη μορφή στο βιβλιοστάσιο διδακτορικών διατριβών που βρίσκεται στο ισόγειο του κτιρίου της. |
Page generated in 0.0028 seconds