Yves Lemieux

OpenFlow supporting inter-domain virtual machine migration

Today, Data Center Networks (DCNs) are re-architected in different new architectures in order to alleviate several emergent issues related to server virtualization and new traffic patterns, such as the limitation of bi-section bandwidth and workload migration. However, these new architectures will remain either proprietary or hidden in administrative domains, and interworking protocols will remain in-process of standardization for a time longer than the usually required time to market. Therefore, interworking cloud DCNs to provide the federated clouds is a very challenging issue that seems to be potentially alleviated by a software-defined networking (SDN) approach such as Openflow. In this paper, we propose a network infrastructure as a services (IaaS) software middleware solution based on Openflow in order to abstract the DCN architecture specifities and instantly interconnect DCNs. As a proof of concept we implement an experimental scenario dealing with virtual machine migration. Then, we evaluate the network setup and the migration delay. The use of the IaaS middleware allows automating these operations. OpenFlow solves the problem of interconnecting heterogeneous Data Centers and its implementation offers interesting delay values.

UMTS-to-IP QoS mapping for voice and video telephony services

Quality of service mapping between UMTS services and IP transport is crucial for maintaining a suitable end-to-end delay for emerging UMTS multimedia telephony. However, due to incompatibilities in QoS classifications within these two technologies, straightforward mapping is impossible and current proposals within the 3GPP could lead to unpredictable and undesirable behavior for certain services. In this article we focus on two very important UMTS services, voice and video telephony, and establish the QoS issues that exist for these services. We then propose a refined QoS mapping that differentiates between the transmission of voice and video-telephony and a weighted fair queuing scheduler to schedule the transmissions. Through a simulation study, we show the effect on the queuing delays of both traffic types when their WFQ weights vary and then derive an optimal weight that provides the best overall delays for multimedia telephony services.

On the Flexibility of MPLS Applications over an OpenFlow-Enabled Network

In todays networks, a node usually has a static role that cannot be easily changed without an expensive upgrade. In MPLS architecture, despite the flexible forwarding data plane not tied to a single forwarding technology, each MPLS node has to be dedicated for a specific role depending on its position in the edge or the core of the MPLS network domain. This paper proposes an approach to address the flexibility of an MPLS node to play multiple roles for different MPLS domains built on top of an underlying OpenFlow-enabled physical network. The pipelined approach through tables introduced in the version 1.1 and later of the OpenFlow specification allows the change of the packet processing behavior by just updating the memory structures -- such as the TCAM and hash tables. It exploits the power of the OpenFlow rules-based paradigm to demonstrate the high level programmability to achieve the deossification of an MPLS infrastructure. In order to validate our proposal, we have implemented our approach over a 100Gbps switch box built on network processors and tested it with three applications to evaluate its flexibility. The results show that the local software to hardware update of a Label Switched Path (LSP) can be made in 2.2ms, in average, and the deployment of a Label Switched Router (LSR) application with 400 labels takes only 392.5ms.

Challenges and complexities in application of LCA approaches in the case of ICT for a sustainable future

In this work, three of many ICT-specific challenges of LCA are discussed. First, the inconsistency versus uncertainty is reviewed with regard to the meta-technological nature of ICT. As an example, the semiconductor technologies are used to high- light the complexities especially with respect to energy and water consumption. The need for specific representations and metric to separately assess products and technologies is discussed. It is highlighted that applying product-oriented approaches would result in abandoning or disfavoring of new technologies that could otherwise help toward a better world. Second, several believed- untouchable hot spots are highlighted to emphasize on their importance and footprint. The list includes, but not limited to, i) User Computer-Interfaces (UCIs), especially screens and displays, ii) Network-Computer Interlaces (NCIs), such as electronic and optical ports, and iii) electricity power interfaces. In addition, considering cross-regional social and economic impacts, and also taking into account the marketing nature of the need for many ICTs product and services in both forms of hardware and soft- ware, the complexity of End of Life (EoL) stage of ICT products, technologies, and services is explored. Finally, the impact of smart management and intelligence, and in general software, in ICT solutions and products is highlighted. In particular, it is observed that, even using the same technology, the significance of software could be highly variable depending on the level of intelligence and awareness deployed. With examples from an interconnected network of data centers managed using Dynamic Voltage and Frequency Scaling (DVFS) technology and smart cooling systems, it is shown that the unadjusted assessments could be highly uncertain, and even inconsistent, in calculating the management components significance on the ICT impacts.

Achieving High Availability at the Application Level in the Cloud

Cloud computing is an emerging paradigm that is gaining more attention by the day. Even with the increased number of applications that are being deployed in the Cloud, the question remains, is the Cloud ready to host applications adhering to telecommunication-grade requirements? In this paper we target the issue of the high-availability (HA) requirement in the Cloud from an application perspective. We present an approach that enables the dynamic incorporation of HA features into the deployed applications, which raises the discussion about the feasibility of having HA-as-a-Service, per application, in the Cloud.

Performance model for mapping processing tasks to OpenFlow switch resources

In a recent effort to push forward the powerful concept of software defined networks, OpenFlow has gained a lot of popularity as a practical approach to split the data and the control planes by standardizing an open interface that allow remote software controllers to dictate the forwarding behavior of network devices. The latest flexible version 1.1 of OpenFlow is limited to software forwarding plane implementations. In order to deliver high performance, we implement an OpenFlow v1.1 hardware forwarding plane based on network processors. Delivering the optimal performance requires finding the optimal mapping of OpenFlow tasks to hardware resources which is already known as an NP-hard combinatorial problem. In our work, we propose a performance model that helps choose a better mapping without the burden of implementing and comparing all possible mappings on network processor. Our model assumes that the performance bottleneck of the hardware forwarding pipeline comes from the lookup tasks. This is generally the case of OpenFlow lookup tasks based on more than 14 tuple headers and requiring high latency external memories in order to provide a large number of possible flow entries. Our model, validated using real hardware implementations comparisons, shows that the lookup tasks that use the same external memories in the same pipeline are not worth parallelizing. In fact, mapping them to different parallel processing elements will only increase the response time of the lookup memory which will slow down the forwarding pipeline.

Virtual slice assignment in large-scale cloud interconnects

Software-defined networking is an emerging method for providing flexible and scalable network connectivity in both intra- and inter-datacenter interconnects with regard to various requirements, including traffic-awareness, quality of service, energy efficiency, and renewable-power intermittency. This article investigates issues and solutions for the software-defined planning of a virtual slice that involves multiple virtual machines with interdependent constraints spanning a network of distributed data-centers. A flexible and optimized virtual-slice assignment that considers server consolidation and multipath forwarding can address large-scale cloud computing services. Simulations on large-scale testbeds, such as the GreenStar Network and the Green Telco Cloud, showed that the proposed model achieves good performance in terms of flexibility and energy efficiency.

Modelling of electricity mix in temporal differentiated life-cycle-assessment to minimize carbon footprint of a cloud computing service

The information and communications technologies (ICT) sector is seeking to reduce the electricity consumption of data processing centres. Among the initiatives to improve energy efficiency is the shift to cloud computing technology. Thanks to very favourable geographical conditions, the Canadian energy mix is highly suited to the implementation of data centres, especially in light of the significant potential of renewable energy, which can help to curb greenhouse gas emissions. In the green sustainable Telco cloud (GSTC) project, an efficient cloud computing network would be set up to optimize renewable energy use based on several data centres. This study aimed to develop a temporally differentiated life cycle assessment (LCA) model, adapted to short-term predictions, to provide a regionalized inventory to model electricity generation. Purpose of this model is (i) to calculate more accurately the carbon emissions of ICT systems and (ii) to minimize the daily carbon emissions of the GSTC servers. This paper focuses mainly on the electricity generation modelling during the use phase in the context of the life cycle assessment methodology. Considering the time scale of the model, the difference between the annual fixed average and a shorter period may be highly relevant, in particular when assessing the green house gases (GHG) emissions of a process such as an ICT system, which mainly operates during peak load hours. The time dependent grid mix modelling makes it possible to manage the server load migrations between data centres on an hourly basis. Index Terms—Life cycle assessment, data centre, carbon footprint, dynamic power mix.

Life cycle assessment of videoconferencing with call management servers relying on virtualization

Abstract — Recently, data centres have been called out for their particularly high energy consumption, which already accounts for 1.5% of the total global electricity consumption and is among the world’s fastest growing energy consumptions. To reduce the data centres’ environmental impacts, technologies such as free cooling and sustainable power sources are used. Another newly developed strategy to improve the energy efficiency of data centres is virtualization, which makes it possible to install several operating systems, known as virtual machines (VMs), so that several tasks and users can share a single server. To evaluate the environmental advantages and burdens of this strategy, assessments tools are required. Several studies have already quantified the energetic and environmental benefits of virtualization but often only considered the use phase and CO 2 improvement. This study uses life cycle assessment (LCA) to evaluate the environmental impacts of Internet use in videoconferencing (VC). Preliminary results show the advantages of virtualization in the manufacturing, use and end-of-life phases. Indeed, when virtualization is implemented, one server can be allocated to several tasks. Therefore, the environmental burden of use and manufacturing will be allocated to the various tasks, decreasing the impact of each one.

DiffServ QoS performance evaluation of multimedia telephony

The Differentiated Services architecture (DiffServ) is a scalable and economic solution which provides relative QoS to different kind of services. Due to the critical QoS constraints of conversational multimedia services (including voice and video-telephony), a QoS mapping between those services and DiffServ classes must be well defined. Voice and video-telephony services are always mapped within the same EF Premium class to provide them with the best service. However, voice and video have divergent stochastic characteristics. Consequently, this standard mapping leads to heterogeneous traffic multiplexing within the same queues in the aggregating routers, which may deteriorate the best service always provided to voice. Thus, we have proposed a refined mapping which differentiates them. In order to carry out a performance study of voice/video packet scheduling, we have considered two different traffic models for voice and video. Simulation results show that WFQ scheduling with a well chosen weight performs better than FIFO and PQ. In our case, a weight of 0.25 for the voice class gives the optimal overall delay performance for multimedia telephony.