Aquesta és una còpia de la versió author's final draft d'un article publicat a la revista Cluster computing. Abstract A real challenge sits in front of the business solutions these days, in the context of the big amount of data generated by complex software applications: eciently using the given limited resources to accomplish specific operations and tasks. Depending on the type of application dealing with, when trying to deliver a certain service in a specific time and with a limited budget, a sequential application may be redesigned in a convenient way so that it will become scalable and able to run on multiple resources. In this context, Many Task Computing (MTC) model brings together loosely coupled applications, composed of many dependent/independent tasks, which will work together for a common result. When asking for a certain service, the most frequently constraints addressed by the user are deadline and budget. However, depending on the tasks nature used in MTC, other constraints may also occur: tasks may be data intensive or computing intensive, independent or dependent, uni-processor or multi-processor. In this context, we propose a multiobjective scheduling algorithm of many tasks in Hadoop for Big Data processing, named MOMTH. The algorithm evaluation was realized in Scheduling Load Simulator, integrated in Hadoop and easy to use. We compared the proposed algorithm with FIFO and Fair Schedulers and we obtained similar performance for our approach.

No abstract

No abstract

As Cloud Computing offers support to more and more complex applications, the need to verify and validate computing models under fault constraints becomes more important, aiming to ensure applications performance. Doing this experimental validation in the early development phase and with small costs require a cloud simulation tool. An extensible framework for Cloud simulation and modeling is CloudSim. This paper proposes a new module for CloudSim consisting of a fault injector based on a specification language. The aim is to assist simulation to be more realistic and includes concrete conditions and constraints. The impact is on testing Cloud applications and help test fault tolerant applications by specifying defect patterns and failing components. The evaluation of the fault injection module is done by measuring the behavior and performance of a tool based on CloudSim, named CloudAnalyst. Several metrics are determined and measured for experimental validation, and conclusions are drawn.

No abstract