Performance evaluation of an autonomic network‐aware metascheduler for Grids

Abstract

SUMMARYGrid technologies have enabled the aggregation of geographically distributed resources in the context of a particular application. The network remains an important requirement for any Grid application, as entities involved in a Grid system (such as users, services, and data) need to communicate with each other over a network. The performance of the network must therefore be considered when carrying out tasks such as scheduling, migration or monitoring of jobs. Surprisingly, many existing quality of service efforts ignore the network and focus instead on processor workload and disk access time. Making use of the network in an efficient and fault-tolerant manner is challenging. In a previous contribution, we proposed an autonomic network-aware scheduling architecture that is capable of adapting its behavior to the current status of the environment. Now, we present a performance evaluation in which our proposal is compared with a conventional scheduling strategy. We present simulation results that show the benefits of our approach.

Autonomic Network-Aware Metascheduling for Grids: A Comprehensive Evaluation

“…We improve upon this by considering a more realistic way of checking the status of the network. Also, we extend our previous proposal by means of considering autonomic computing (Caminero et al (2009a;). This means that our model will use feedback from resources and network elements in order to improve system performance.…”

“…Our scheduler will therefore adapt its behavior according to the status of the system, paying special attention to the status of the network. Our scenario is depicted in Figure 2 and has the following entities (Caminero et al (2009a;):…”

“…In a VO, entities communicate with each other using an interconnection network -resulting in the network playing an essential role in Grid systems (Roy (2001)). In (Caminero et al (2009a)), authors proposed an autonomic network-aware Grid scheduling architecture as a possible solution, which can make scheduling decisions based on the current status of the system (with particular focus on network capability). This architecture focuses on the interchange of I/O files between users and computing resources, and the impact these interchanges have on the performance received by users.…”

From volunteer to trustable computing: Providing QoS-aware scheduling mechanisms for multi-grid computing environments

“…And prediction pushes for future knowledge of the resources in order to evaluate in advance their availability, performance, etc. There is a wide variety of algorithms for both of them [9,10,11]. In addition, QoS mechanisms like policy, security, redundancy and fault-tolerance, can also be found very important since they are designed to increase the guarantees on each job execution.…”

“…This has been actively researched in [11,53,54] by the study of different algorithms for resource behavior forecasting (such as exponential smoothing [55]) with interesting results. For instance, in [55] a comparison between using or not exponential smoothing prediction methods at the scheduling decisions is presented, highlighting their impact on the performance improvement.…”