Aleksandar Lazarevic's research while affiliated with University College London and other places

Publications (11)

Article
Full-text available
Wider adoption of the Grid concept has led to an increasing amount of federated computational, storage and visualisation resources being available to scientists and researchers. Distributed and heterogeneous nature of these resources renders most of the legacy cluster monitoring and management approaches inappropriate, and poses new challenges in w...
Article
As Grid computing is becoming an inevitable future, managing, scheduling and monitoring dynamic, heterogeneous resources will present new challenges. Solutions will have to be agile and adaptive, support self-organization and autonomous management, while maintaining optimal resource utilisation. Presented in this paper are basic principles and arch...
Article
Effective resource utilisation monitoring and highly granular yet adaptive measurements are prerequisites for a more efficient Grid scheduler. We present a suite of measurement applications able to monitor per-process resource utilisation, and a customisable tool for emulating observed utilisation models.
Article
Full-text available
The Grid technology is evolving into a global, service-orientated architecture, a universal platform for delivering future high demand computational services. Strong adoption of the Grid and the utility computing concept is leading to an increasing number of Grid installations running a wide range of applications of different size and complexity. I...
Article
As the Grid evolves from a high performance cluster middleware to a multipurpose utility computing framework, a good understanding of Grid applications, their statistics and utilisation patterns is required. This study looks at job execution times and resource utilisations in a Grid environment, and their significance in cluster and network dimensi...
Article
Full-text available
This paper presents basic concepts, architectural principles and algorithms for efficient resource and security management in cluster computing environments and the Grid. The work presented in this paper is funded by BTExacT and the EPSRC project SO-GRM (GR/S21939).
Article
This transfer thesis presents a novel, probabilistic approach to scheduling applications on computational Grids based on their historical behaviour, current state of the Grid and predictions of the future execution times and resource utilisation of such applications. The work lays a foundation for enabling a more intuitive, user-friendly and effect...

Citations

... In our previous publication [10], we have reported on the data collection and analysis process. The observations here presented are based on the analysis of wallclock execution times -real time value of process execution time which is larger or, for a perfectly optimised process, equal to the actual CPU time. ...
... These might include such parameters as operating system, dynamic libraries, supporting applications, minimal amounts of physical memory required, or specialised hardware. This pruned set of resources will then be passed to Self-Organized Resource Discovery protocol (SORD)[6]. Considering the application requirements as stated in the profiles, and the maximum possible computational output of each of the machines, SORD will query several close neighbours and few distant nodes to discover the optimal node for application execution.Figure 2. Effect of OS level scheduling and short-term turnaround time prediction We introduce the " subscribed load " paradigm to circumvent the volatility of low-level scheduling in multi-tasking OS running on commodity-hardware. These systems employ soft-limiting schedulers without the ability to exclusively reserve or limit the amount of CPU time any single process is utilising. ...
... At the groundwork level of a Grid accounting system, there is a monitoring service which functions as the raw data collector of the usage at every resource. The raw data here refers to the information kept regarding a job executed by a Grid user, containing information such as in the Resource Usage Record (RUR) [9,12,17] kept by a monitoring system [20,21,22,23,24]. The list of essential resource components included in the RUR by the GGF RUR Working Group is as listed in Table 1. ...
... A widely used application performance metric is the Critical Path Length (CPL) [10]; the longest path in the weighted DAG. In the present case its ensemble mean < CP L > from the allocation process is used as main performance metric. ...