Abstract. As data volumes processed by large-scale distributed dataintensive applications grow at high-speed, an increasing I/O pressure is put on the underlying storage service, w...
Load balancing is an important consideration when running data-parallel programs. While traditional techniques trade off the cost of load imbalance with the overhead of mitigating...
Data intensive applications on clusters often require requests quickly be sent to the node managing the desired data. In many applications, one must look through a sorted tree str...
Grid enabled physics analysis requires a Workload Management System (WMS) that takes care of finding suitable computing resources to execute data intensive jobs. A typical exampl...
Commodity computer clusters are often composed of hundreds of computing nodes. These generally off-the-shelf systems are not designed for high reliability. Node failures therefore...