GEARSHIFT: Guaranteeing availability requirements in SLAs using hybrid fault tolerance

Abstract

Abstract-The dependability of ICT systems is vital for today's society. However, operational systems are not fault free. Providers and customers have to define clear availability requirements and penalties on the delivered services by using SLAs. Fulfilling the stipulated availability may be expensive. The lack of mechanisms that allow a fine control of the SLA risk may lead to overdimension the provided resources. Therefore, a relevant question for ICT service providers is: How to guarantee the SLA availability in a cost efficient way? This paper studies how to combine different fault tolerant techniques with different costs and properties, in order to economically fulfill a given SLA requirement. GEARSHIFT is a mechanism that enables ICT providers to set the fault tolerance technique (gear ratio) needed, depending on the current service conditions and requirements. We illustrate how to use the proposed model in a backbone network scenario, using measurements from a production national network. Finally, we show that the total costs of delivering an ICT service follow a simple convex function, which allows an easy selection of the optimal risk by tuning properly the combination of fault tolerant techniques.

Assessing the risk of violating SLA dependability requirements in software-defined networks

“…However, different recovery mechanisms may have different cost. An idea of how to select the optimal recovery strategy based on the related cost and the estimated SLA violation risk has been presented in [14]. Now, being able to estimate the risk of violation of the dependabilityrelated SLOs for each SLA in SDNs, service providers may plan future expenditures more effectively.…”

“…Every SLA, for which the risk of violating the service degradation requirement is estimated using the proposed method, should be extended with at least the α and τ parameters agreed on with the customer. Based on the recent work applicable to typical computer and communication networks [14], it is possible to make riskaware decisions on the preferred use of different dependability provisioning techniques in the case of SDNs. Although the implementation of specific solutions in real networks is usually complex, we provide the possible directions as the first step, and we use simulation to illustrate the potential use cases.…”

“…The currently used metrics in SLAs mainly refer to service downtime which has not been explicitly defined in the case of SDNs. The existing proposals cover non-SDN networks in which an ICT service is either available or not [3]- [5], [14]. At the same time, in SDNs, traffic flows established before a failure may still be successfully forwarded through a network, while the new flows between the same pair of nodes may be rejected due to the unavailability of the logicallycentralized controller.…”

Dependability of the NFV Orchestrator: State of the Art and Research Challenges

“…Due to the passive condition of the replicas they need extra time to take responsibility in case of failure recovery. Finally, hybrid techniques such as the one presented in [59] can combine different recovery mechanisms that make use of a given specific approach on a given time, depending on the current needs and status of the systems.…”

Effective Risk Assessment in Resilient Communication Networks

“…While Value-at-Risk was postulated to be used in communications networks for risk quantification in network security [20,21] and resilience [8,9], there are no efficient theoretical models to predict VaR when it is applied in network resilience. At the modelling level, we use some elements of the methodology similar to more recent works on network reliability, such as [22][23][24][25], yet we also deal with the modelling of whole distributions, and we add penalty [26], SLA [27,28], and compensation policy [8] concerns.…”