Results 1 -
6 of
6
Prospects of Collaboration between Compute Providers by means of Job Interchange
- PROCEEDINGS OF THE 13TH JOB SCHEDULING STRATEGIES FOR PARALLEL PROCESSING, LNCS
, 2007
"... This paper empirically explores the advantages of the collaboration between different parallel compute sites in a decentralized grid scenario. To this end, we assume independent users that submit their jobs to their local site installation. The sites are allowed to decline the local execution of job ..."
Abstract
-
Cited by 14 (5 self)
- Add to MetaCart
(Show Context)
This paper empirically explores the advantages of the collaboration between different parallel compute sites in a decentralized grid scenario. To this end, we assume independent users that submit their jobs to their local site installation. The sites are allowed to decline the local execution of jobs by offering them to a central job pool. In our analysis we evaluate the performance of three job sharing algorithms that are based on the commonly used algorithms First-Come-First-Serve, EASY Backfilling, and List-Scheduling. The simulation results are obtained using real workload traces and compared to single site results. We show that simple job pooling is beneficial for all sites even if the local scheduling systems remain unchanged. Further, we show that it is possible to achieve shorter response times for jobs compared to the best single-site scheduling results.
New Challenges of Parallel Job Scheduling
"... Abstract. The workshop on job scheduling strategies for parallel processing (JSSPP) studies the myriad aspects of managing resources on parallel and distributed computers. These studies typically focus on largescale computing environments, where allocation and management of computing resources prese ..."
Abstract
-
Cited by 9 (0 self)
- Add to MetaCart
(Show Context)
Abstract. The workshop on job scheduling strategies for parallel processing (JSSPP) studies the myriad aspects of managing resources on parallel and distributed computers. These studies typically focus on largescale computing environments, where allocation and management of computing resources present numerous challenges. Traditionally, such systems consisted of massively parallel supercomputers, or more recently, large clusters of commodity processor nodes. These systems are characterized by architectures that are largely homogeneous and workloads that are dominated by both computation and communication-intensive applications. Indeed, the large majority of the articles in the rst ten JSSPP workshops dealt with such systems and addressed issues such as queuing systems and supercomputer workloads. In this paper, we discuss some of the recent developments in parallel computing technologies that depart from this traditional domain of problems. In particular, we identify several recent and in uential technologies that could have a signi cant impact on the future of research on parallel scheduling. We discuss some of the more speci c research challenges that these technologies introduce to the JSSPP community, and propose to enhance the scope of future JSSPP workshops to include these topics. 1
Genetic Fuzzy Systems applied to Online Job Scheduling
"... Abstract — This paper presents a comparison of three different design concepts for Genetic Fuzzy systems. We apply a Symbiotic Evolution that uses the Michigan approach and two approaches that are based on the Pittsburgh approach: a complete optimization of the problem and a Cooperative Coevolutiona ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
Abstract — This paper presents a comparison of three different design concepts for Genetic Fuzzy systems. We apply a Symbiotic Evolution that uses the Michigan approach and two approaches that are based on the Pittsburgh approach: a complete optimization of the problem and a Cooperative Coevolutionary algorithm. The three different Genetic Fuzzy systems are applied to a real-world online problem, the generation of scheduling strategies for Massively Parallel Processing systems. The Genetic Fuzzy systems must classify different scheduling states and decide about a corresponding scheduling strategy within each scheduling state. The main challenge arise in the delayed reward given by a critic. Therefore, it is impossible to directly evaluate the assignment of scheduling strategies to scheduling states. In our paper, the three design concepts are evaluated with real workload traces considering result quality, computational effort, convergence behavior, and robustness. I.
Intelligence, ” at the Technische Universität Dortmund and was printed with financial support of the Deutsche Forschungsgemeinschaft. A Hybrid Markov Chain Modeling Architecture for Workload on Parallel Computers
, 2008
"... Abstract. This paper proposes a comprehensive modeling architecture for workloads on parallel computers using Markov chains in combination with state dependent empirical distribution functions. This hybrid approach is based on the requirements of scheduling algorithms: the model considers the four e ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. This paper proposes a comprehensive modeling architecture for workloads on parallel computers using Markov chains in combination with state dependent empirical distribution functions. This hybrid approach is based on the requirements of scheduling algorithms: the model considers the four essential job attributes submission time, number of required processors, estimated processing time, and actual processing time. To assess the goodness-of-fit of a workload model the similarity of sequences of real jobs and jobs generated from the model needs to be captured. We propose to reduce the complexity of this task and to evaluate the model by comparing the results of a widely-used scheduling algorithm instead. This approach is demonstrated with commonly used scheduling objectives like the Average Weighted Response Time and total Utilization. We compare their outcomes on the simulated workload traces from our model with those of an original workload trace from a real Massively Parallel Processing system installation. To verify this new evaluation technique, standard criteria for assessing the goodness-of-fit for workload models are additionally applied. 1
Intelligence in Scheduling (CI-Sched 2007) Greedy Scheduling with Complex Objectives
"... Abstract — We present a methodology for automatically generating an online scheduling process for an arbitrary objective with the help of Evolution Strategies. The scheduling problem comprises independent parallel jobs and multiple identical machines and occurs in many real Massively Parallel Proces ..."
Abstract
- Add to MetaCart
Abstract — We present a methodology for automatically generating an online scheduling process for an arbitrary objective with the help of Evolution Strategies. The scheduling problem comprises independent parallel jobs and multiple identical machines and occurs in many real Massively Parallel Processing systems. The system owner defines the objective that may consider job waiting times and priorities of user groups. Our scheduling process is a variant of the simple and commonly used Greedy scheduling algorithm in combination with a repeated sorting of the waiting queue. This sorting uses a criterion whose parameters are evolutionary optimized. We evaluate our new scheduling process with real workload data and compare it to the best offline solutions and to the online results of the standard EASY backfill algorithm. To this end, we partition the user of the workloads into groups and select an exemplary objective that prioritizes some of those groups over others. I.
Cooperative negotiation and scheduling of . . .
- FUTURE GENERATION COMPUTER SYSTEMS
, 2008
"... ..."
