E. Jeanvoine, Louis Rilling, C. Morin, Daniel Leprince
Using grid resources to execute scientific applications requiring a large amount of computing power is attractive but not easy from the user point of view. Vigne is a grid operating system designed to provide users with a simplified view of a grid. Vigne deals with the huge number of nodes in a large-scale grid and with the nodes' dynamic behavior by using peer-to-peer overlays as a keystone. In this paper, we show why it is highly desirable to use structured and unstructured peer-to-peer overlays for building the high-level services of Vigne grid operating system. To show the interest of our approach, we detail the features of two Vigne services built on top of peer-to-peer overlays. We also present experimental results obtained on the Grid'5000 testbed showing the scalability of the Vigne infrastructure based on overlays and its practical interest for the implementation of Vigne distributed services
{"title":"Using Overlay Networks to Build Operating System Services for Large Scale Grids","authors":"E. Jeanvoine, Louis Rilling, C. Morin, Daniel Leprince","doi":"10.1109/ISPDC.2006.54","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.54","url":null,"abstract":"Using grid resources to execute scientific applications requiring a large amount of computing power is attractive but not easy from the user point of view. Vigne is a grid operating system designed to provide users with a simplified view of a grid. Vigne deals with the huge number of nodes in a large-scale grid and with the nodes' dynamic behavior by using peer-to-peer overlays as a keystone. In this paper, we show why it is highly desirable to use structured and unstructured peer-to-peer overlays for building the high-level services of Vigne grid operating system. To show the interest of our approach, we detail the features of two Vigne services built on top of peer-to-peer overlays. We also present experimental results obtained on the Grid'5000 testbed showing the scalability of the Vigne infrastructure based on overlays and its practical interest for the implementation of Vigne distributed services","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116016012","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}
C. Alexa, V. Boldea, M. Ciubancan, S. Constantinescu, S. Dita, D. Pantea, T. Preda, M. Jalobeanu, G. Popeneciu
GRID technology is able to connect an unlimited number of computer systems and to distribute the tasks among all the connected nodes. In this paper we present the extension of IFIN-HH ATLAS-GRID facilities with ITIM Cluj-Napoca computing power, building a distributed grid system. Also shown are the functionality tests as a single grid configuration. Since March 30 the ITIM Cluj-Napoca site is configured and connected to IFIN-HH ATLAS-GRID, through RoEduNet. Supported by the Romanian R&D Agency through CEEX program, this project combines particle physics phenomenology and grid technologies for distributed computing and analysis
{"title":"IFIN -- ITIM Distributed GRID System","authors":"C. Alexa, V. Boldea, M. Ciubancan, S. Constantinescu, S. Dita, D. Pantea, T. Preda, M. Jalobeanu, G. Popeneciu","doi":"10.1109/ISPDC.2006.30","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.30","url":null,"abstract":"GRID technology is able to connect an unlimited number of computer systems and to distribute the tasks among all the connected nodes. In this paper we present the extension of IFIN-HH ATLAS-GRID facilities with ITIM Cluj-Napoca computing power, building a distributed grid system. Also shown are the functionality tests as a single grid configuration. Since March 30 the ITIM Cluj-Napoca site is configured and connected to IFIN-HH ATLAS-GRID, through RoEduNet. Supported by the Romanian R&D Agency through CEEX program, this project combines particle physics phenomenology and grid technologies for distributed computing and analysis","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132468996","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}
This paper addresses a new routing strategy keeping the power of each node as an important constraint for routing in a fully decentralized mesh networks utilizing the additional advantages of a directional antenna. Unlike the most widely used principles in routing this strategy doesn't always focus on minimizing the number of hops but also ensures that the battery power of each node is utilized optimally as well. In this proposed strategy if the node has depleted its power then alternate paths would be calculated for routing, selecting the nodes such that it is hop-efficient and power-optimized. This strategy also ensures a perfect load balancing or load sharing among the network. Using directional antenna ensures that its range extension capabilities coupled with the space division multiple access mechanism provide additional enhancements to the strategy. Moreover the power requirement of the directional antenna is also much less then its omni directional counterpart. We clearly illustrate and quantify the benefits of the proposed strategy and protocol scalability using simulations
{"title":"Hop-Efficient and Power-Optimized Routing Strategy in a Decentralized Mesh Network Using Directional Antenna","authors":"Sanjay Chatterjee, Siuli Roy, S. Bandyopadhyay","doi":"10.1109/ISPDC.2006.28","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.28","url":null,"abstract":"This paper addresses a new routing strategy keeping the power of each node as an important constraint for routing in a fully decentralized mesh networks utilizing the additional advantages of a directional antenna. Unlike the most widely used principles in routing this strategy doesn't always focus on minimizing the number of hops but also ensures that the battery power of each node is utilized optimally as well. In this proposed strategy if the node has depleted its power then alternate paths would be calculated for routing, selecting the nodes such that it is hop-efficient and power-optimized. This strategy also ensures a perfect load balancing or load sharing among the network. Using directional antenna ensures that its range extension capabilities coupled with the space division multiple access mechanism provide additional enhancements to the strategy. Moreover the power requirement of the directional antenna is also much less then its omni directional counterpart. We clearly illustrate and quantify the benefits of the proposed strategy and protocol scalability using simulations","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"16 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132915086","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}
This article shows how the idea of continuous software testing by Rothermel and Harrold (1996) of a world wide working group can be well integrated into the grid computing paradigm using the Globus Toolkit (Saff and Ernst, 2004). This kind of testing assumes a lot of computational resources provided by a regression test center. The interaction with the test center is done through Web services implemented by the new developed Unit Test Center Grid Web Service (UTCGWS). UTCGWS is the interface to the developer IDEs and does compiling, deploying, distributing regression test and information managing. For the distribution of unit tests in a grid environment a simple distribution algorithm has been developed
{"title":"Continuous Software Test Distributed Execution and Integrated into the Globus Toolkit","authors":"C. Reich, Bettina Scharpf","doi":"10.1109/ISPDC.2006.15","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.15","url":null,"abstract":"This article shows how the idea of continuous software testing by Rothermel and Harrold (1996) of a world wide working group can be well integrated into the grid computing paradigm using the Globus Toolkit (Saff and Ernst, 2004). This kind of testing assumes a lot of computational resources provided by a regression test center. The interaction with the test center is done through Web services implemented by the new developed Unit Test Center Grid Web Service (UTCGWS). UTCGWS is the interface to the developer IDEs and does compiling, deploying, distributing regression test and information managing. For the distribution of unit tests in a grid environment a simple distribution algorithm has been developed","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124281838","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}
In this paper we formulate and study a new scheduling problem called selfish multi-user task scheduling. This problem assumes that there are several users, each of them having multiple tasks that need processing on a set of parallel identical machines. Each user is selfish and her goal is to minimize the makespan of her own tasks. We model this problem as a non-cooperative, extensive-form game. We use the subgame perfect equilibrium solution concept to analyze the game which provides insight into the problem's properties. We compute the price of anarchy to quantify the costs due to lack of coordination among the users
{"title":"Selfish Multi-User Task Scheduling","authors":"T. E. Carroll, Daniel Grosu","doi":"10.1109/ISPDC.2006.44","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.44","url":null,"abstract":"In this paper we formulate and study a new scheduling problem called selfish multi-user task scheduling. This problem assumes that there are several users, each of them having multiple tasks that need processing on a set of parallel identical machines. Each user is selfish and her goal is to minimize the makespan of her own tasks. We model this problem as a non-cooperative, extensive-form game. We use the subgame perfect equilibrium solution concept to analyze the game which provides insight into the problem's properties. We compute the price of anarchy to quantify the costs due to lack of coordination among the users","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123547532","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}
Optimistically terminating consensus (OTC) is a variant of consensus that decides if all correct processes propose the same value. It is surprisingly easy to implement: processes broadcast their proposals and decide if sufficiently many processes report the same proposal. This paper shows an OTC-based framework which can reconstruct all major asynchronous consensus algorithms, even in Byzantine settings, with no overhead in latency or the required number of processes. This result does not only deepen our understanding of consensus, but also reduces the problem of designing new, modular distributed agreement protocols to choosing the parameters of OTC
{"title":"Optimistically Terminating Consensus: All Asynchronous Consensus Protocols in One Framework","authors":"Piotr Zielinski","doi":"10.1109/ISPDC.2006.37","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.37","url":null,"abstract":"Optimistically terminating consensus (OTC) is a variant of consensus that decides if all correct processes propose the same value. It is surprisingly easy to implement: processes broadcast their proposals and decide if sufficiently many processes report the same proposal. This paper shows an OTC-based framework which can reconstruct all major asynchronous consensus algorithms, even in Byzantine settings, with no overhead in latency or the required number of processes. This result does not only deepen our understanding of consensus, but also reduces the problem of designing new, modular distributed agreement protocols to choosing the parameters of OTC","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"55 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126928268","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}
In this article we introduce a new iterative method for integral partition called the feedback guided dynamic integral partition (FGDIP) algorithm. The problem to study is the partition of a definite integral into p identical sub-integrals. The method generates iteratively a sequence of integral bounds by re-balancing the previous integral partition to achieve a better one. A simple convergence condition is also proposed. Experimental results show that the proposed method FGDIP achieves better performance than the classical Newton's method
{"title":"Feedback Guided Dynamic Integral Partition","authors":"S. Tabirca, T. Tabirca, L. Yang, Len Freeman","doi":"10.1109/ISPDC.2006.26","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.26","url":null,"abstract":"In this article we introduce a new iterative method for integral partition called the feedback guided dynamic integral partition (FGDIP) algorithm. The problem to study is the partition of a definite integral into p identical sub-integrals. The method generates iteratively a sequence of integral bounds by re-balancing the previous integral partition to achieve a better one. A simple convergence condition is also proposed. Experimental results show that the proposed method FGDIP achieves better performance than the classical Newton's method","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124673837","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}
L. Philippe, S. Damy, B. Herrmann, I. Djama, S. Dahan
The Internet development and the availability of reliable networks led to the emergence of grid architectures. The aim of these architectures is to take benefit of widely distributed resources to improve execution possibilities. Depending on their properties, these architectures are usually classified into desktop grids, resources grids and application based grids. Application based grids provide an easy access to applications deployed on the grid on the ASP (application service provider) mode. When these grids grow of orders of magnitude, application lookup will become a costly activity of the grid. In this article, we study how a lookup algorithm scales when the size of the grid grows up. We exhibit a "lookup throughput" which characterizes the grid interconnections graph and the lookup algorithm
{"title":"Evaluation of a Large Scale Lookup Algorithm in ASP Based Grids","authors":"L. Philippe, S. Damy, B. Herrmann, I. Djama, S. Dahan","doi":"10.1109/ISPDC.2006.24","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.24","url":null,"abstract":"The Internet development and the availability of reliable networks led to the emergence of grid architectures. The aim of these architectures is to take benefit of widely distributed resources to improve execution possibilities. Depending on their properties, these architectures are usually classified into desktop grids, resources grids and application based grids. Application based grids provide an easy access to applications deployed on the grid on the ASP (application service provider) mode. When these grids grow of orders of magnitude, application lookup will become a costly activity of the grid. In this article, we study how a lookup algorithm scales when the size of the grid grows up. We exhibit a \"lookup throughput\" which characterizes the grid interconnections graph and the lookup algorithm","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124714807","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}
Scheduling is an important factor for the efficient execution of computational workflows on grid environments. A large number of static scheduling heuristics has been presented in the literature. These algorithms allocate tasks before job execution starts and assume a precise knowledge of timing information, which may be difficult to obtain in general. To overcome this limitation of static strategies, dynamic scheduling strategies may be needed for a changing environment such as the grid. While they incur runtime overheads, they may better adapt to timing changes during job execution. In this work, we analyse five well-known heuristics (min-min, max-min, sufferage, HEFT and random) when used as static and dynamic scheduling strategies in a grid environment in which computing resources exhibit congruent performance differences. The analysis shows that non-list based heuristics are more sensitive than list-based heuristics to inaccuracies in timing information. Static list-based heuristics perform well in the presence of low or moderate inaccuracies. Dynamic versions of these heuristics may be needed only in environments where high inaccuracies are observed. Our analysis also shows that list-based heuristics significantly outperform non-list based heuristics in all cases and, therefore, constitute the most suitable strategies by which to schedule workflows either statically or dynamically
{"title":"Analysis of Dynamic Heuristics for Workflow Scheduling on Grid Systems","authors":"María M. López, E. Heymann, M. A. Senar","doi":"10.1109/ISPDC.2006.9","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.9","url":null,"abstract":"Scheduling is an important factor for the efficient execution of computational workflows on grid environments. A large number of static scheduling heuristics has been presented in the literature. These algorithms allocate tasks before job execution starts and assume a precise knowledge of timing information, which may be difficult to obtain in general. To overcome this limitation of static strategies, dynamic scheduling strategies may be needed for a changing environment such as the grid. While they incur runtime overheads, they may better adapt to timing changes during job execution. In this work, we analyse five well-known heuristics (min-min, max-min, sufferage, HEFT and random) when used as static and dynamic scheduling strategies in a grid environment in which computing resources exhibit congruent performance differences. The analysis shows that non-list based heuristics are more sensitive than list-based heuristics to inaccuracies in timing information. Static list-based heuristics perform well in the presence of low or moderate inaccuracies. Dynamic versions of these heuristics may be needed only in environments where high inaccuracies are observed. Our analysis also shows that list-based heuristics significantly outperform non-list based heuristics in all cases and, therefore, constitute the most suitable strategies by which to schedule workflows either statically or dynamically","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129678549","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}
P2P data stores excel if availability of inserted data items must be guaranteed. Their inherent mechanisms to counter peer population dynamics make them suitable for a wide range of application domains. This paper presents and analyzes the fusion maintenance operation. It aims at reorganizing parts of our P2P data store in case the peer population shrinks so much that data availability is threatened. To this end, we present a formal cost model that peers use to estimate the optimal invocation point of a fusion. Finally, we present experimental results that validate our cost model by simulating various network conditions
{"title":"Improving Churn Resistance of P2P Data Stores Based on the Hypercube","authors":"D. Fahrenholtz, V. Turau","doi":"10.1109/ISPDC.2006.31","DOIUrl":"https://doi.org/10.1109/ISPDC.2006.31","url":null,"abstract":"P2P data stores excel if availability of inserted data items must be guaranteed. Their inherent mechanisms to counter peer population dynamics make them suitable for a wide range of application domains. This paper presents and analyzes the fusion maintenance operation. It aims at reorganizing parts of our P2P data store in case the peer population shrinks so much that data availability is threatened. To this end, we present a formal cost model that peers use to estimate the optimal invocation point of a fusion. Finally, we present experimental results that validate our cost model by simulating various network conditions","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"13 22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132894504","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：