ABSTRACT
The management of Grid systems commonly lacks information for identifying the failures that may hinder the timely completion of jobs, and cause the wasting of computing resources. Monitoring can certainly help, but novel approaches need to be conceived for such large and geographically distributed systems. We propose a Grid Architecture for scalable Monitoring and Enhanced dependable job ScHeduling (GAMESH). GAMESH is a completely distributed and highly efficient management infrastructure for the dissemination of monitoring data and troubleshooting of job execution failures in large-scale and multi-domain Grid environments. Challenged in a real deployment and compared to other Grid management systems, GAMESH demonstrates to (i) ensure measurements of both computing resources and conditions of task scheduling at geographically sparse sites, while inducing a low overhead on the entire infrastructure, and (ii) enable failure-aware scheduling and improve overall system performance, even in the presence of failures, by coordinating local job schedulers at multiple domains.
- W. Abdulal and S. Ramachandram. Reliability-Aware Genetic Scheduling Algorithm in Grid Environment. In Communication Systems and Network Technologies (CSNT), 2011 International Conference on, 2011. Google ScholarDigital Library
- Adaptive Computing. TORQUE Resource Manager, December 2015. http://www.adaptivecomputing.com/products/open-source/torque/.Google Scholar
- B. Tierney et al. A grid monitoring architecture. In Global Grid Forum, 2002.Google Scholar
- D. Batista and N. da Fonseca. A survey of self-adaptive grids. Communications Magazine, IEEE, 48(7):94--100, 2010. Google ScholarDigital Library
- CERN. CERN LHC, September 2015. http://lhc.web.cern.ch/lhc/.Google Scholar
- CERN. CERN WLCG, September 2015. http://wlcg.web.cern.ch/.Google Scholar
- M. Cinque, D. Cotroneo, F. Frattini, and S. Russo. To Cloudify or Not to Cloudify: the Question for a Scientific Data Center. Cloud Computing, IEEE Transactions on, PP(99):1--1, 2015. Google ScholarDigital Library
- D. Cotroneo, F. Frattini, R. Natella, and R. Pietrantuono. Performance Degradation Analysis of a Supercomputer. In Proc. of Int. Symp. on Software Reliability Engineering Workshops (ISSREW), 2013.Google ScholarCross Ref
- S. Guo, H.-Z. Huang, Z. Wang, and M. Xie. Grid service reliability modeling and optimal task scheduling considering fault recovery. Reliability, IEEE Transactions on, 60(1):263--274, 2011.Google Scholar
- I. Legrand et al. Monalisa: An agent based, dynamic service system to monitor, control and optimize distributed systems. Computer Physics Communications, 180(12):2472--2498, 2009.Google ScholarCross Ref
- Italian Grid Infrastructure. Troubleshooting guide for CREAM, September 2015. https://wiki.italianGrid.it/twiki/bin/view/CREAM/TroubleshootingGuide.Google Scholar
- J. M. Schopf et al. Monitoring the grid with the globus toolkit mds4. Journal of Physics: Conference Series, 46:521--525, 2006.Google ScholarCross Ref
- M. Chtepen et al. Adaptive task checkpointing and replication: Toward efficient fault-tolerant grids. Parallel and Distributed Systems, IEEE Transactions on, 20(2):180--190, 2009. Google ScholarDigital Library
- M. L. Massie, B. N. Chun, and D. E. Culler. The Ganglia distributed monitoring system: design, implementation, and experience. Parallel Computing, 30(7):817--840, 2004.Google ScholarCross Ref
- Object Management Group. Data Distribution Service Specification 1.2, September 2015. http://www.omg.org/spec/DDS/1.2.Google Scholar
- Rice University - Division of Information Technology. Why Are My Jobs Not Running?, September 2015. http://rcsg.rice.edu/rcsg/shared/scheduling.html.Google Scholar
- Universita degli Studi di Napoli Federico II. SCOPE datacenter, December 2015. http://www.scope.unina.it:8080/web/guest/home en.Google Scholar
- F. Xhafa and A. Abraham. Computational models and heuristic methods for grid scheduling problems. Future Generation Computer Systems, 26(4):608--621, 2010. Google ScholarDigital Library
Index Terms
- Scalable monitoring and dependable job scheduling support for multi-domain grid infrastructures
Recommendations
Dependable Grid Workflow Scheduling Based on Resource Availability
Due to the highly dynamic feature, dependable workflow scheduling is critical in the Grid environment. Various scheduling algorithms have been proposed, but seldom consider the resource reliability. Current Grid systems mainly exploit fault tolerance ...
Monitoring of Grid scientific workflows
Large-Scale Programming Tools and EnvironmentsScientific workflows are a means of conducting in silico experiments in modern computing infrastructures for e-Science, often built on top of Grids. Monitoring of Grid scientific workflows is essential not only for performance analysis but also to ...
Using the black-box approach with machine learning methods in order to improve job scheduling in GRID environments
This article focuses on mapping jobs to resources with use of off-the-shelf machine learning methods. The machine learning methods are used in the black-box manner, having a wide variety of parameters for internal cross validation. In the article we ...
Comments