Jacques Philippe Sauvé

Running Bag-of-Tasks applications on computational grids: the MyGrid approach

We here discuss how to run Bag-of-Tasks applications on computational grids. Bag-of-Tasks applications (those parallel applications whose tasks are independent) are both relevant and amendable for execution on grids. However, few users currently execute their Bag-of-Tasks applications on grids. We investigate the reason for this state of affairs and introduce MyGrid, a system designed to overcome the identified difficulties. MyGrid provides a simple, complete and secure way for a user to run Bag-of-Tasks applications on all resources she has access to. Besides putting together a complete solution useful for real users, MyGrid embeds two important research contributions to grid computing. First, we introduce some simple working environment abstractions that hide machine configuration heterogeneity from the user. Second, we introduce work queue with replication (WQR), a scheduling heuristics that attains good performance without relying on information about the grid or the application, although consuming a few more cycles. Note that not depending on information makes WQR much easier to deploy in practice

Faults in grids: why are they so bad and what can be done about it?

Computational grids have the potential to become the main execution platform for high performance and distributed applications. However, such systems are extremely complex and prone to failures. We present a survey with the grid community on which several people shared their actual experience regarding fault treatment. The survey reveals that, nowadays, users have to be highly involved in diagnosing failures, that most failures are due to configuration problems (a hint of the areas immaturity), and that solutions for dealing with failures are mainly application-dependent. Going further, we identify two main reasons for this state of affairs. First, grid components that provide high-level abstractions when working, do expose all gory details when broken. Since there are no appropriate mechanisms to deal with the complexity exposed (configuration, middleware, hardware and software issues), users need to be deeply involved in the diagnosis and correction of failures. To address this problem, one needs a way to coordinate different support teams working at the grids different levels of abstraction. Second, fault tolerance schemes today implemented on grids tolerate only crash failures. Since grids are prone to more complex failures, such those caused by heisenbugs, one needs to tolerate tougher failures. Our hope is that the very heterogeneity, that makes a grid a complex environment, can help in the creation of diverse software replicas, a strategy that can tolerate more complex failures.

An Introductory Overview and Survey of Business-Driven IT Management

Business-driven IT management (BDIM) is a new, evolutionary and comprehensive IT management approach that aims to improve IT infrastructure, service quality and business results at the same time. To that end, it needs to model and numerically estimate IT-business linkage. BDIM concepts are finding ways into ITIL-based management processes as well as into new IT infrastructure product offerings such as autonomic computing in order to add increased value to the business. In the hope of contributing to define and characterize this new approach, this paper presents an introductory overview of BDIM, discusses its main concepts, illustrates gains over conventional IT management approaches and offers a survey of some recent work on the topic in the literature.

SLA design from a business perspective

A method is proposed whereby values for Service Level Objectives (SLOs) of an SLA can be chosen to reduce the sum IT infrastructure cost plus business financial loss. Business considerations are brought into the model by including the business losses sustained when IT components fail or performance is degraded. To this end, an impact model is fully developed in the paper. A numerical example consisting of an e-commerce business process using an IT service dependent on three infrastructure tiers (web tier, application tier, database tier) is used to show that the resulting choice of SLOs can be vastly superior to ad hoc design. A further conclusion is that infrastructure design and the resulting SLOs can be quite dependent on the “importance” of the business processes (BPs) being serviced: higher-revenue BPs deserve better infrastructure and the method presented shows exactly how much better the infrastructure should be.

A decision support tool to optimize scheduling of IT changes

Change management is one of the most critical processes in IT management. Some of the reasons are the sheer number of changes and the difficulty of evaluating the impact of changes on the IT services being provided. Through carrying out a survey with IT managers and practitioners, we have found that, among the activities performed during change management, change scheduling (allocating changes to change windows) is the most problematic one. In this paper we solve the change scheduling problem by using a business-driven approach that evaluates the impact of a change schedule in terms of the financial loss imposed on the service provider. Toward this aim, we model the impact of SLA violations when the implementation of changes is done after their deadline. A change scheduling optimization problem is then formalized and its solution is applied to a typical scenario. The results show that optimizing the scheduling of changes can result in significant savings to an IT support organization.

A Study of Fairness in Packet-Switching Networks

The use of channel scheduling to improve a measure of fairness in packet-switching networks is investigated. This fairness measure is based on mean end-to-end delays derived from Kleinrocks classical model. The network designer can incorporate any desired relative delay among user classes into this fairness measure. It is found that scheduling is helpful in reallocating delay among user classes and can be used to improve the fairness of a network. It is also shown that a parameterized queueing discipline can be used to further improve fairness. A conservation theorem characterizing the effects of scheduling on overall mean end-to-end delay is established. The results are applicable to both fixed and random routing and are found to be relatively insensitive to fluctuations in traffic.

Business-driven IT management - upping the ante of IT : exploring the linkage between it and business to improve both IT and business results

Unlike the conventional way of managing IT that uses technical objectives and metrics only, such as availability, response time, and throughput, business-driven IT management (BDIM) drives IT management decisions from a business perspective by adding business measures, such as profit, cost, and customer experience. Research on BDIM is gathering interest in both academia and industry worldwide. This article introduces BDIM, discusses how it can be enacted, and illustrates its benefits and gains over conventional IT management.

Research Challenges of Business-Driven IT Management

Business-driven IT management (BDIM) aims at managing enterprise IT infrastructure and services efficiently and at improving business results at the same time. BDIM is based on mappings between IT technical performance metrics and business relevant metrics and exploit the linkage to provide decision support to IT management so as to maximize business value and IT-Business alignment. As an example, the number of successfully executed IT infrastructure changes can be mapped to financial loss due to the service disruption experienced by customers when the changes take place. Up to now, there has been some research effort in proposing and applying BDIM solutions to IT management with potential gains for the business. However, much remains to be researched, prototyped and validated before this new IT management discipline can become widely applicable. This paper presents a research agenda for BDIM. After reviewing BDIM concepts and proposing a framework to assist in defining and describing BDIM usage domains, the paper discusses ongoing work and outlines some research challenges.

A quantitative approach to IT investment allocation to improve business results

This paper proposes using financial loss functions to estimate the impact that IT service level agreements (SLAs) have on business process performance. For that, an organizing framework based on balanced scorecard concepts is first presented to tie those functions to strategic business processes; and then, the impact of service levels on business performance is estimated using quantitative techniques from management science. The result is a quantitative approach for SLA objective setting and investment allocation to improve business results. The approach serves as decision support for investment policies within an ITIL financial management for IT services context. Application to the case of a drugstore chain showed that the approach is instrumental in analyzing complex IT service-business process interdependency scenarios. The approach helped the chains executives identify and recommend which IT services should receive investments

Change Priority Determination in IT Service Management Based on Risk Exposure

In the Change Management process within IT Service Management, some activities need to evaluate the risk exposure associated with changes to be made to the infrastructure and services. The paper presents a method to evaluate risk exposure associated with a change. Further, we show how to use the risk exposure metric to automatically assign priorities to changes. The formal model developed for this purpose captures the business perspective by using financial metrics in the evaluation of risk. Thus the method is an example of Business-Driven IT Management. A case study, performed in conjunction with a large IT service provider, is reported and provides good results when compared to decisions made by human managers.