Dominic Battré, A. Höing, Martin Raack, Ulf Rerrer-Brusch, O. Kao
Many load balancing strategies have been proposed for distributed hash tables, like Pastry. These strategies assume that hash functions spread even skewed key distributions almost evenly over the ID space. They neglect the problem that many applications produce data with common keys (multi-sets) that entail hash collisions and therewith load imbalance concerning query and storage load. A second drawback of using hash functions in DHTs is the lack of range queries needed in many scenarios. This paper presents a solution for how to use the routing structure of the P2P network Pastry to create a new alphanumerical overlay with very little additional costs. This overlay is capable of storing data in a totally ordered manner instead of using hashed keys. Therewith, it enables range queries and sophisticated load balancing. We discuss the impact on Pastry that arises when nodes are relocated during load balancing. This possibly causes a skewed distribution of nodes in the circular id space. We demonstrate the feasibility of our idea including advantages and problems through an evaluation of simulations.
{"title":"Extending Pastry by an Alphanumerical Overlay","authors":"Dominic Battré, A. Höing, Martin Raack, Ulf Rerrer-Brusch, O. Kao","doi":"10.1109/CCGRID.2009.65","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.65","url":null,"abstract":"Many load balancing strategies have been proposed for distributed hash tables, like Pastry. These strategies assume that hash functions spread even skewed key distributions almost evenly over the ID space. They neglect the problem that many applications produce data with common keys (multi-sets) that entail hash collisions and therewith load imbalance concerning query and storage load. A second drawback of using hash functions in DHTs is the lack of range queries needed in many scenarios. This paper presents a solution for how to use the routing structure of the P2P network Pastry to create a new alphanumerical overlay with very little additional costs. This overlay is capable of storing data in a totally ordered manner instead of using hashed keys. Therewith, it enables range queries and sophisticated load balancing. We discuss the impact on Pastry that arises when nodes are relocated during load balancing. This possibly causes a skewed distribution of nodes in the circular id space. We demonstrate the feasibility of our idea including advantages and problems through an evaluation of simulations.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116692629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wim Depoorter, R. Y. V. Bossche, K. Vanmechelen, J. Broeckhove
The ef¿cient scheduling of jobs is an essential part of any grid resource management system. At its core, it involves ¿nding a solution to a problem which is NP-complete by reduction to the knapsack problem. Consequently, this problem is often tackled by using heuristics to derive a more pragmatic solution. Other than the use of heuristics, simpli¿cations and abstractions of the workload model may also be employed to increase the tractability of the scheduling problem. A possible abstraction in this context is the use of Divisible Load Theory (DLT), in which it is assumed that an application consists of an arbitrarily divisible load (ADL). Many applications however, are composed of a number of atomic tasks and are only modularly divisible. In this paper we evaluate the consequences of the ADL assumption on the performance of economic scheduling approaches for grids, in the context of CPU-bound modularly divisible applications with hard deadlines. Our goal is to evaluate to what extent DLT can still serve as a useful workload abstraction for obtaining tractable scheduling algorithms in this setting. The focus of our evaluation is on the recently proposed tsfGrid heuristic for economic scheduling of grid workloads which operates under the assumptions of ADL. We demonstrate the effect of the ADL assumption on the actual instantiation of schedules and on the user value realized by the RMS. In addition we describe how the usage of a DLT heuristic in a high-level admission controller for a mechanism which does take into account the atomicity of individual tasks, can signi¿cantly reduce communication and computational overhead.
{"title":"Evaluating the Divisible Load Assumption in the Context of Economic Grid Scheduling with Deadline-Based QoS guarantees","authors":"Wim Depoorter, R. Y. V. Bossche, K. Vanmechelen, J. Broeckhove","doi":"10.1109/CCGRID.2009.36","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.36","url":null,"abstract":"The ef¿cient scheduling of jobs is an essential part of any grid resource management system. At its core, it involves ¿nding a solution to a problem which is NP-complete by reduction to the knapsack problem. Consequently, this problem is often tackled by using heuristics to derive a more pragmatic solution. Other than the use of heuristics, simpli¿cations and abstractions of the workload model may also be employed to increase the tractability of the scheduling problem. A possible abstraction in this context is the use of Divisible Load Theory (DLT), in which it is assumed that an application consists of an arbitrarily divisible load (ADL). Many applications however, are composed of a number of atomic tasks and are only modularly divisible. In this paper we evaluate the consequences of the ADL assumption on the performance of economic scheduling approaches for grids, in the context of CPU-bound modularly divisible applications with hard deadlines. Our goal is to evaluate to what extent DLT can still serve as a useful workload abstraction for obtaining tractable scheduling algorithms in this setting. The focus of our evaluation is on the recently proposed tsfGrid heuristic for economic scheduling of grid workloads which operates under the assumptions of ADL. We demonstrate the effect of the ADL assumption on the actual instantiation of schedules and on the user value realized by the RMS. In addition we describe how the usage of a DLT heuristic in a high-level admission controller for a mechanism which does take into account the atomicity of individual tasks, can signi¿cantly reduce communication and computational overhead.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130208296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The increasing ageing population around the world presents an unprecedented challenge in developing economically viable healthcare systems for our societies. To overcome this challenge and maintain a decent level of healthcare, further innovation and deployment of information technologies in the field of healthcare are the keys. Our earlier work puts forward "An Active Grid Infrastructure for Elderly Care" solution whereby elderly people are monitored non-intrusively to provide essential health information about them; the information concerning their condition is kept in an "active" health record; and resources involved in the system can be shared by multiple caregivers or organizations allowing them to collaborate in developing relevant care programs for these elderly persons. This paper focuses on the design of the collaborative component of the solution. A framework is proposed for an integrated Grid system that supports collaborative task planning and workflow development. The system will enable healthcare professionals to access the necessary resources, collaborate with each other to develop and execute treatment workflows in a user-friendly and intuitive manner. The paper will discuss the requirements and design principles for key components of the system and present its preliminary implementation.
{"title":"A Novel Collaborative Grid Framework for Distributed Healthcare","authors":"Hoang M. Phung, D. Hoang, E. Lawrence","doi":"10.1109/CCGRID.2009.74","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.74","url":null,"abstract":"The increasing ageing population around the world presents an unprecedented challenge in developing economically viable healthcare systems for our societies. To overcome this challenge and maintain a decent level of healthcare, further innovation and deployment of information technologies in the field of healthcare are the keys. Our earlier work puts forward \"An Active Grid Infrastructure for Elderly Care\" solution whereby elderly people are monitored non-intrusively to provide essential health information about them; the information concerning their condition is kept in an \"active\" health record; and resources involved in the system can be shared by multiple caregivers or organizations allowing them to collaborate in developing relevant care programs for these elderly persons. This paper focuses on the design of the collaborative component of the solution. A framework is proposed for an integrated Grid system that supports collaborative task planning and workflow development. The system will enable healthcare professionals to access the necessary resources, collaborate with each other to develop and execute treatment workflows in a user-friendly and intuitive manner. The paper will discuss the requirements and design principles for key components of the system and present its preliminary implementation.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128236867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jobs on high-performance computing systems are deployed mostly with the sole goal of minimizing completion times. This performance demand has been satisfied without paying much attention to power/energy consumption. Consequently, that has become a major concern in high-performance computing systems. In this paper, we address the problem of scheduling precedence-constrained parallel applications on such systems—specifically with heterogeneous resources—accounting for both application completion time and energy consumption. Our scheduling algorithm adopts dynamic voltage scaling (DVS) to minimize energy consumption. DVS can be used with a number of recent commodity processors that are enabled to operate in different voltage supply levels at the expense of sacrificing clock frequencies. In the context of scheduling, this multiple voltage facility implies that there is a trade-off between the quality of schedules and energy consumption. Our algorithm effectively balances these two performance goals using a novel objective function, which takes into account both goals; this claim is verified by the results obtained from our extensive comparative evaluation study.
{"title":"Minimizing Energy Consumption for Precedence-Constrained Applications Using Dynamic Voltage Scaling","authors":"Young Choon Lee, Albert Y. Zomaya","doi":"10.1109/CCGRID.2009.16","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.16","url":null,"abstract":"Jobs on high-performance computing systems are deployed mostly with the sole goal of minimizing completion times. This performance demand has been satisfied without paying much attention to power/energy consumption. Consequently, that has become a major concern in high-performance computing systems. In this paper, we address the problem of scheduling precedence-constrained parallel applications on such systems—specifically with heterogeneous resources—accounting for both application completion time and energy consumption. Our scheduling algorithm adopts dynamic voltage scaling (DVS) to minimize energy consumption. DVS can be used with a number of recent commodity processors that are enabled to operate in different voltage supply levels at the expense of sacrificing clock frequencies. In the context of scheduling, this multiple voltage facility implies that there is a trade-off between the quality of schedules and energy consumption. Our algorithm effectively balances these two performance goals using a novel objective function, which takes into account both goals; this claim is verified by the results obtained from our extensive comparative evaluation study.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121420815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Using peer-to-peer overlays to notify users whenevera new update occurs is a promising approach to supportweb based publish subscribe systems like really simple syndication (RSS). Such a peer-to-peer approach can scale well by reducing load at the source and also guarantee timeliness of notifications. Several such overlay based approaches have been proposed in recent years. However, malicious peers may pretend to relay but actually not, and thus deny service, or even propagate counterfeit updates - thus rendering a peer-to-peer mechanism not only useless, but even harmful (e.g., by false updates). We propose overlay independent randomized strategies to mitigate these ill-effects of malicious peers at a marginal overhead, thus enjoying the benefits of peer-to-peer dissemination, along with the assurance of content integrity in RSS like web-based publish-subscribe applications without altering currently deployed server infrastructure.
{"title":"Reliable P2P Feed Delivery","authors":"Anwitaman Datta, Xin Liu","doi":"10.1109/CCGRID.2009.32","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.32","url":null,"abstract":"Using peer-to-peer overlays to notify users whenevera new update occurs is a promising approach to supportweb based publish subscribe systems like really simple syndication (RSS). Such a peer-to-peer approach can scale well by reducing load at the source and also guarantee timeliness of notifications. Several such overlay based approaches have been proposed in recent years. However, malicious peers may pretend to relay but actually not, and thus deny service, or even propagate counterfeit updates - thus rendering a peer-to-peer mechanism not only useless, but even harmful (e.g., by false updates). We propose overlay independent randomized strategies to mitigate these ill-effects of malicious peers at a marginal overhead, thus enjoying the benefits of peer-to-peer dissemination, along with the assurance of content integrity in RSS like web-based publish-subscribe applications without altering currently deployed server infrastructure.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130542557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Garg, S. Son, M. Kandemir, P. Raghavan, R. Prabhakar
In order to meet the increasing demands of present and upcoming data-intensive computer applications, there has been a major shift in the disk subsystem, which now consists of more disks with higher storage capacities and higher rotational speeds. These have made the disk subsystem a major consumer of power, making disk power management an important issue. People have considered the option of spinning down the disk during periods of idleness or serving the requests at lower rotational speeds when performance is not an issue. Accurately predicting future disk idle periods is crucial to such schemes. This paper presents a novel disk-idleness prediction mechanism based on Markov models and explains how this mechanism can be used in conjunction with a three-speed disk. Our experimental evaluation using a diverse set of workloads indicates that (i) prediction accuracies achieved by the proposed scheme are very good (87.5% on average); (ii) it generates significant energy savings over the traditional power-saving method of spinning down the disk when idle (35.5% onaverage); (iii) it performs better than a previously proposed multi-speed disk management scheme (19% on average); and (iv) the performance penalty is negligible (less than 1% on average). Overall, our implementation and experimental evaluation using both synthetic disk traces and traces extracted from real applications demonstrate the feasibility of a Markov-model-based approach to saving disk power.
{"title":"Markov Model Based Disk Power Management for Data Intensive Workloads","authors":"R. Garg, S. Son, M. Kandemir, P. Raghavan, R. Prabhakar","doi":"10.1109/CCGRID.2009.67","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.67","url":null,"abstract":"In order to meet the increasing demands of present and upcoming data-intensive computer applications, there has been a major shift in the disk subsystem, which now consists of more disks with higher storage capacities and higher rotational speeds. These have made the disk subsystem a major consumer of power, making disk power management an important issue. People have considered the option of spinning down the disk during periods of idleness or serving the requests at lower rotational speeds when performance is not an issue. Accurately predicting future disk idle periods is crucial to such schemes. This paper presents a novel disk-idleness prediction mechanism based on Markov models and explains how this mechanism can be used in conjunction with a three-speed disk. Our experimental evaluation using a diverse set of workloads indicates that (i) prediction accuracies achieved by the proposed scheme are very good (87.5% on average); (ii) it generates significant energy savings over the traditional power-saving method of spinning down the disk when idle (35.5% onaverage); (iii) it performs better than a previously proposed multi-speed disk management scheme (19% on average); and (iv) the performance penalty is negligible (less than 1% on average). Overall, our implementation and experimental evaluation using both synthetic disk traces and traces extracted from real applications demonstrate the feasibility of a Markov-model-based approach to saving disk power.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130899968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hui Jin, Xian-He Sun, Ziming Zheng, Z. Lan, Bing Xie
As the scale and complexity of parallel systems continue to grow, failures become more and more an inevitable fact for solving large-scale applications. In this research, we present an analytical study to estimate execution time in the presence of failures of directed acyclic graph (DAG) based Scientific Applications and provide a guideline for performance optimization. The study is four fold. We first introduce a performance model to predict individual subtask computation time under failures. Next, a layered, iterative approach is adopted to transform a DAG into a layered DAG, which reflects full dependencies among all the subtasks. Then, the expected execution time under failures of the DAG is derived based on stochastic analysis. Unlike existing models, this newly proposed performance model provides both the variance and distribution. It is practical and can be put to real use. Finally, based on the model, performance optimization, weak point identification and enhancement are proposed. Intensive simulations with real system traces are conducted to verify the analytical findings. They show that the newly proposed model and weak point enhancement mechanism work well.
{"title":"Performance under Failures of DAG-based Parallel Computing","authors":"Hui Jin, Xian-He Sun, Ziming Zheng, Z. Lan, Bing Xie","doi":"10.1109/CCGRID.2009.55","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.55","url":null,"abstract":"As the scale and complexity of parallel systems continue to grow, failures become more and more an inevitable fact for solving large-scale applications. In this research, we present an analytical study to estimate execution time in the presence of failures of directed acyclic graph (DAG) based Scientific Applications and provide a guideline for performance optimization. The study is four fold. We first introduce a performance model to predict individual subtask computation time under failures. Next, a layered, iterative approach is adopted to transform a DAG into a layered DAG, which reflects full dependencies among all the subtasks. Then, the expected execution time under failures of the DAG is derived based on stochastic analysis. Unlike existing models, this newly proposed performance model provides both the variance and distribution. It is practical and can be put to real use. Finally, based on the model, performance optimization, weak point identification and enhancement are proposed. Intensive simulations with real system traces are conducted to verify the analytical findings. They show that the newly proposed model and weak point enhancement mechanism work well.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130935193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Krefting, S. Canisius, A. Hoheisel, H. Loose, T. Tolxdorff, T. Penzel
The analysis of biosignals, such as the electroencephalogram EEG or the electrocardiogram (ECG), is essential for diagnosis in many medical areas, in particular sleep medicine and sleep research. A standard method in this field is the polysomnography, a multidimensional biosignal recording during the whole bedtime phase. Within the SIESTA project, a European multicenter study, comprehensive clinical and polysommnographic records from over 300 persons has been collected. To make the data available for researchers as reference for clinical research and development of new analysis tools, the SIESTA database is implemented into a grid infrastructure. To date, the complete data is stored into the grid and different algorithms for automated ECG analysis are implemented. The database can be queried and the matching data can be analysed on record level and collection level. The application is modelled as a workflow and integrated into the grid using a workflow manager. A graphical user interface is implemented as a grid portlet. It allows the initialization of new computation tasks as well as the monitoring and result-retrieval from already launched analyses.
{"title":"Grid-Based Sleep Research: Analysis of Polysomnographies Using a Grid Infrastructure","authors":"D. Krefting, S. Canisius, A. Hoheisel, H. Loose, T. Tolxdorff, T. Penzel","doi":"10.1109/CCGRID.2009.52","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.52","url":null,"abstract":"The analysis of biosignals, such as the electroencephalogram EEG or the electrocardiogram (ECG), is essential for diagnosis in many medical areas, in particular sleep medicine and sleep research. A standard method in this field is the polysomnography, a multidimensional biosignal recording during the whole bedtime phase. Within the SIESTA project, a European multicenter study, comprehensive clinical and polysommnographic records from over 300 persons has been collected. To make the data available for researchers as reference for clinical research and development of new analysis tools, the SIESTA database is implemented into a grid infrastructure. To date, the complete data is stored into the grid and different algorithms for automated ECG analysis are implemented. The database can be queried and the matching data can be analysed on record level and collection level. The application is modelled as a workflow and integrated into the grid using a workflow manager. A graphical user interface is implemented as a grid portlet. It allows the initialization of new computation tasks as well as the monitoring and result-retrieval from already launched analyses.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126519913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computing is being transformed to a model consisting of services that are commoditised and delivered in a manner similar to utilities such as water, electricity, gas, and telephony. In such a model, users access services based on their requirements without regard to where the services are hosted. Several computing paradigms have promised to deliver this utility computing vision and they include Grid computing, P2P computing, and more recently Cloud computing. The latter term denotes the infrastructure as a “Cloud” in which businesses and users are able to access applications from anywhere in the world on demand. Hence, Cloud computing can be classed as a new paradigm for the dynamic creation of next-generation Data Centers by assembling services of networked Virtual Machines (VMs). Thus, the computing world is rapidly transforming towards developing software for millions to consume as a service rather than creating software for millions to run on their PCs.
{"title":"Market-Oriented Cloud Computing: Vision, Hype, and Reality of Delivering Computing as the 5th Utility","authors":"R. Buyya","doi":"10.1109/CCGRID.2009.97","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.97","url":null,"abstract":"Computing is being transformed to a model consisting of services that are commoditised and delivered in a manner similar to utilities such as water, electricity, gas, and telephony. In such a model, users access services based on their requirements without regard to where the services are hosted. Several computing paradigms have promised to deliver this utility computing vision and they include Grid computing, P2P computing, and more recently Cloud computing. The latter term denotes the infrastructure as a “Cloud” in which businesses and users are able to access applications from anywhere in the world on demand. Hence, Cloud computing can be classed as a new paradigm for the dynamic creation of next-generation Data Centers by assembling services of networked Virtual Machines (VMs). Thus, the computing world is rapidly transforming towards developing software for millions to consume as a service rather than creating software for millions to run on their PCs.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130650792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Omer Ozan Sonmez, B. Grundeken, H. Mohamed, A. Iosup, D. Epema
The use of today's multicluster grids exhibits periods of submission bursts with periods of normal use and even of idleness. To avoid resource contention, many users employ observational scheduling, that is, they postpone the submission of relatively low-priority jobs until a cluster becomes (largely) idle. However, observational scheduling leads to resource contention when several such users crowd the same idle cluster. Moreover, this job execution model either delays the execution of more important jobs, or requires extensive administrative support for job and user priorities. Instead, in this work we investigate the use of cycle scavenging to run jobs on grid resources politely yet efficiently, and with an acceptable administrative cost. We design a two-level cycle scavenging scheduling architecture that runs unobtrusively alongside regular grid scheduling. We equip this scheduler with two novel cycle scavenging scheduling policies that enforce fair resource sharing among competing cycle scavenging users. We show through experiments with real and synthetic applications in a real multicluster grid that the proposed architecture can execute jobs politely yet efficiently.
{"title":"Scheduling Strategies for Cycle Scavenging in Multicluster Grid Systems","authors":"Omer Ozan Sonmez, B. Grundeken, H. Mohamed, A. Iosup, D. Epema","doi":"10.1109/CCGRID.2009.46","DOIUrl":"https://doi.org/10.1109/CCGRID.2009.46","url":null,"abstract":"The use of today's multicluster grids exhibits periods of submission bursts with periods of normal use and even of idleness. To avoid resource contention, many users employ observational scheduling, that is, they postpone the submission of relatively low-priority jobs until a cluster becomes (largely) idle. However, observational scheduling leads to resource contention when several such users crowd the same idle cluster. Moreover, this job execution model either delays the execution of more important jobs, or requires extensive administrative support for job and user priorities. Instead, in this work we investigate the use of cycle scavenging to run jobs on grid resources politely yet efficiently, and with an acceptable administrative cost. We design a two-level cycle scavenging scheduling architecture that runs unobtrusively alongside regular grid scheduling. We equip this scheduler with two novel cycle scavenging scheduling policies that enforce fair resource sharing among competing cycle scavenging users. We show through experiments with real and synthetic applications in a real multicluster grid that the proposed architecture can execute jobs politely yet efficiently.","PeriodicalId":118263,"journal":{"name":"2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid","volume":"368 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134388572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：