Kerstin Voss

Risk-aware Migrations For Prepossessing SLAs

SLAs were developed in order to guarantee the customers desired quality of service. To prepossess SLAs even in the case of system failures, migrating the job to an alternative resource is a well-known fault-tolerance mechanism. In this paper we start to consider migrations in a risk-aware concept. We plan to introduce risk assessment and management technologies into the grid fabric in order to ensure prepossessing SLAs. The most benefits are seen in a risk-aware scheduling and initiating precautionary fault-tolerance mechanism. This paper focusses on precautionary migrations which should prevent an SLA violation. A motivating scenario presents the variety of required actions in a system with high workload for several migration alternatives. The important aspects of jobs and resources are explained. Furthermore, we present a measurement to estimate the effects of migrating to an alternative resource. This will be one decision criteria in the migration process. Future work will complete the risk-aware scheduling of migrations

Assessgrid, economic issues underlying risk awareness in grids

In order to improve the attractiveness and drive the commercial uptake of Grid technologies, the establishment of Service Level Agreements (SLAs) is required. The AssessGrid project contributes to this aim by introducing risk-aware Grid architectural components. Grid service users, brokers and providers benefit from risk assessment functionalities in all phases of service provisioning and utilisation. This paper focuses on the economic issues which result from this new risk-aware approach to Grid computing. Multiple open economic research questions are discussed from the perspective of users, brokers and providers, which point out the potential impact of AssessGrid in this area.

Quality assurance of Grid service provisioning by risk aware managing of resource failures

Quality assurance is a key aspect in scope of the provisioning of grid services since end-users ask for specific quality of service (QoS) criteria defined in service level agreements (SLA). To commit to an SLA, grid providers need a risk analysis during SLA negotiation in order to estimate the probability of an SLA violation. In addition, such a risk analysis is necessary in the post-negotiation phase, in order to find the most profitable solution if not all SLAs can be fulfilled. Current job failure rates in grids (10-45%) highlight the necessity of fault-tolerance mechanisms. If not enough resources exist to compensate for all resource outages, the provider has to prefer those jobs which are in expectation the most profitable ones. Hence, this quality assurance ensures that obligations from the most important jobs will be fulfilled.

Gaining users’ trust by publishing failure probabilities

In order to attract users with business-critical jobs to the Grid, they must trust the reliability of the services they request. Service Level Agreements (SLAs) have been a first approach to contractually define the Quality of Service (QoS) for a job execution. However, SLAs are not really accepted in the Grid world since resource providers are cautious agreeing them, and users not confident receiving the negotiated QoS. The AssessGrid project offers concepts to help providers gain the users’ trust by publishing the probability of failure of SLAs, leading to an increase of users’ confidence once these probabilities are clearly stated. Users can use this information as a decision factor in the SLA negotiation process. This paper presents the idea of AssessGrid in the scope of increasing trust in the SLA provisioning by integrating risk awareness in the Grid layers. Since only reliable information can create trust, an impartial evaluation of the provider’s trustworthiness is being developed in AssessGrid.

Recursive Evaluation of Fault Tolerance Mechanisms for SLA Management

Service level agreements (SLAs) have been introduced into the grid in order to build a basis for its commercial uptake. The challenge for Grid providers in agreeing and operating SLA-bound jobs is to ensure their fulfillment even in the case of failures. Hence, fault-tolerance mechanisms are an essential means of the providers SLA management. The high utilization of commercial operated clusters leads to scenarios in which typically a job migration effects other jobs scheduled. The effects result from the unavailability of enough free resources which would be needed to catch all resource outages. Consequently before initiating a migration, its effects for other jobs have to be compared and the initiation of fault- tolerance (FT-) mechanisms have to be evaluated recursively. This paper presents a measurement for the benefit of initiating a FT-mechanism, the recursive evaluation, and termination condition. Performing such an impact evaluation of an initiated chain of FT-mechanisms is often more profitable than performing a single FT-mechanism and accordingly this is important for the Grid commercialization.

Virtual Execution Environments for ensuring SLA-compliant Job Migration in Grids

OpenCCS is an SLA-aware resource management system which uses transparent checkpointing of applications and migration of checkpoint datasets for ensuring SLA-compliance also in case of resource outages. Migration of checkpoints presumes a high grade of compatibility between source and target resource. Hence, even in large Grid systems only a small number of resources are eligible migration targets. This short paper describes the concept of virtual execution environments and how they increase the number of potential migration targets. It will also outline an implementation within OpenCCS.

Enhance Self-managing Grids by Risk Management

Risk management (RM) processes are used in various application fields since often possible threats should be identified, evaluated, and avoided. In the grid resource failures are common and likely threats which slow down the establishment of service level agreements (SLAs). Introducing RM into the self-managing grid is beneficial to estimate and react on such threats. The assessed probabilities for resource failures can be used as a decisive factor in different scenarios. In particular, the resource allocation profits from risk information since jobs can be mapped under consideration of their importance and the stability of available resources. Each RM process is particularly developed for one application field since the threats, the consequences, and the retaliatory actions are individual. The difference between conventional RM processes and the grid integrated one is that the Grid should be self-managing. This implies that after the configuration RM processes have to be performed totally automatical. This paper presents the Grid RM process which bases on the standard for RM processes developed from the federation of European risk management associations (FERMA).

Virtual Execution Environments and the Negotiation of Service Level Agreements in Grid Systems

Service Level Agreements (SLAs) have focal importance if the commercial customer should be attracted to the Grid. An SLA-aware resource management system has already been realize, able to fulfill the SLA of jobs even in the case of resource failures. For this, it is able to migrate checkpointed jobs over the Grid. At this, virtual execution environments allow to increase the number of potential migration targets significantly. In this paper we outline the concept of such virtual execution environments and focus on the SLA negotiation aspects.

Comparing Fault Tolerance Mechanisms for Self-Organizing Resource Management in Grids

Grid users require the established usage of service level agreements (SLAs). To prevent SLA violations in the case of failures, current research focuses on the development of fault-tolerance (FT-) mechanisms like migration. My new approach integrates risk assessment into the Grid fabric in order to estimate the risk for resource failures. In systems with high workload the initiation of a FT-mechanism causes effects for other jobs. In order to find the most profitable solution, the different effects have to be estimated and compared. This paper presents an automatic process for the comparison and selection of a FT-mechanism in a risk- aware, self-organizing resource management system which takes into account different resource stabilities.

Large-Scale Knowledge Management for Collaborative Work

Collaborative work is performed these days independent from organizational and geographical bounds. The number of participants and usage scenarios result in a need for large-scale distributed knowledge management. In this paper we present Wasabi as a platform for such environments by considering e-Health as an example field of application. Thee-Health scenario has specific requirements to handle complex data objects and to strictly ensure data privacy. This paper describes how to handle such complex data objects within a knowledge management system. In order to ensure data privacy, the integration of known authorization and authentication mechanisms in Wasabi and their usability for distributed knowledge environments are discussed.