BOINC (Berkeley Open Infrastructure for Network Computing) is a software system that makes it easy for scientists to create and operate public-resource computing projects. It supports diverse applications, including those with large storage or communication requirements. PC owners can participate in multiple BOINC projects, and can specify how their resources are allocated among these projects. We describe the goals of BOINC, the design issues that we confronted, and our solutions to these problems.
{"title":"BOINC: a system for public-resource computing and storage","authors":"David P. Anderson","doi":"10.1109/GRID.2004.14","DOIUrl":"https://doi.org/10.1109/GRID.2004.14","url":null,"abstract":"BOINC (Berkeley Open Infrastructure for Network Computing) is a software system that makes it easy for scientists to create and operate public-resource computing projects. It supports diverse applications, including those with large storage or communication requirements. PC owners can participate in multiple BOINC projects, and can specify how their resources are allocated among these projects. We describe the goals of BOINC, the design issues that we confronted, and our solutions to these problems.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116099644","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}
Beth A. Kirschner, T. Hacker, William A. Adamson, B. Athey
A large and diverse consortium of grid clusters, as can be found in a university setting, requires a flexible authorization model that is scalable, extensible and easy to administer. Current approaches to grid authorization suffer from administrative interfaces that don't scale, authorization models that don't provide needed functionality, or both. This paper proposes a solution with initial implementation that uses existing standards to support the requirements of such a consortium of grid clusters. Our solution eliminates the need to manage authentication and authorization on a per-host basis, and implements a mechanism to temporarily bind a grid user to a local guest account on grid resource.
{"title":"Walden: a scalable solution for grid account management","authors":"Beth A. Kirschner, T. Hacker, William A. Adamson, B. Athey","doi":"10.1109/GRID.2004.66","DOIUrl":"https://doi.org/10.1109/GRID.2004.66","url":null,"abstract":"A large and diverse consortium of grid clusters, as can be found in a university setting, requires a flexible authorization model that is scalable, extensible and easy to administer. Current approaches to grid authorization suffer from administrative interfaces that don't scale, authorization models that don't provide needed functionality, or both. This paper proposes a solution with initial implementation that uses existing standards to support the requirements of such a consortium of grid clusters. Our solution eliminates the need to manage authentication and authorization on a per-host basis, and implements a mechanism to temporarily bind a grid user to a local guest account on grid resource.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122638799","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}
Interactivity on the grid is an interesting aspect of many ongoing research projects. In this context, the glogin tool provides a light-weight solution for bidirectional, interactive and secure connections between arbitrary grid nodes and the users' clients. By submitting it as a regular grid job, glogin establishes itself as a bridgehead for tunneling of arbitrary traffic into and out of the grid. With this approach, glogin is able to offer different interactive services, such as standard shell functionality, TCP forwarding (including remote X11 displays), and grid-enabled virtual private networks (VPN). The current implementation o/glogin uses the Globus Toolkit GT2, although other grid middleware toolkits may utilize the same technology.
{"title":"glogin - a multifunctional, interactive tunnel into the grid","authors":"H. Rosmanith, D. Kranzlmüller","doi":"10.1109/GRID.2004.33","DOIUrl":"https://doi.org/10.1109/GRID.2004.33","url":null,"abstract":"Interactivity on the grid is an interesting aspect of many ongoing research projects. In this context, the glogin tool provides a light-weight solution for bidirectional, interactive and secure connections between arbitrary grid nodes and the users' clients. By submitting it as a regular grid job, glogin establishes itself as a bridgehead for tunneling of arbitrary traffic into and out of the grid. With this approach, glogin is able to offer different interactive services, such as standard shell functionality, TCP forwarding (including remote X11 displays), and grid-enabled virtual private networks (VPN). The current implementation o/glogin uses the Globus Toolkit GT2, although other grid middleware toolkits may utilize the same technology.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129102326","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}
M. Fisher, Charles Kubicek, P. McKee, I. Mitrani, J. Palmer, Rob Smith
A grid hosting environment is described, where servers may be reconfigured dynamically from one type of work to another in response to changes in demand. The problem of carrying out these reconfigurations in the most efficient manner is addressed by means of stochastic modelling and optimization. A heuristic policy, which is close to optimal over a wide range of parameters, is introduced. A prototype system based on existing resource management software has been developed to demonstrate the concepts described
{"title":"Dynamic Allocation of Servers in a Grid Hosting Environment","authors":"M. Fisher, Charles Kubicek, P. McKee, I. Mitrani, J. Palmer, Rob Smith","doi":"10.1109/GRID.2004.24","DOIUrl":"https://doi.org/10.1109/GRID.2004.24","url":null,"abstract":"A grid hosting environment is described, where servers may be reconfigured dynamically from one type of work to another in response to changes in demand. The problem of carrying out these reconfigurations in the most efficient manner is addressed by means of stochastic modelling and optimization. A heuristic policy, which is close to optimal over a wide range of parameters, is introduced. A prototype system based on existing resource management software has been developed to demonstrate the concepts described","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129142272","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}
DIRAC (distributed infrastructure with remote agent control) has been developed by the CERN LHCb physics experiment to facilitate large scale simulation and user analysis tasks spread across both grid and nongrid computing resources. It consists of a small set of distributed stateless core services, which are centrally managed, and agents which are managed by each computing site. DIRAC utilizes concepts from existing distributed computing models to provide a lightweight, robust, and flexible system. This paper discusses the architecture, performance, and implementation of the DIRAC system which has recently been used for an intensive physics simulation involving more than forty sites, 90 TB of data, and in excess of one thousand 1 GHz processor-years.
{"title":"DIRAC: a scalable lightweight architecture for high throughput computing","authors":"Andrei Tsaregorodtsev, V. Garonne, I. Stokes-Rees","doi":"10.1109/GRID.2004.22","DOIUrl":"https://doi.org/10.1109/GRID.2004.22","url":null,"abstract":"DIRAC (distributed infrastructure with remote agent control) has been developed by the CERN LHCb physics experiment to facilitate large scale simulation and user analysis tasks spread across both grid and nongrid computing resources. It consists of a small set of distributed stateless core services, which are centrally managed, and agents which are managed by each computing site. DIRAC utilizes concepts from existing distributed computing models to provide a lightweight, robust, and flexible system. This paper discusses the architecture, performance, and implementation of the DIRAC system which has recently been used for an intensive physics simulation involving more than forty sites, 90 TB of data, and in excess of one thousand 1 GHz processor-years.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132240527","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}
We present algorithms for the scheduling sequential tasks on a network enabled server (NES) environment. This article is an extension of the paper: "A Study of Deadline Scheduling for Client-Server Systems on the Computational Grid" by Takefusa et al. We mainly discuss a deadline scheduling with priority strategy that is more appropriate for multiclient, multiserver case. Importance is first given to the task's priority and then the task is allocated to the server that can meet the task's deadline. This may cause that some already allocated tasks on the server miss their deadline. We also augment the benefits of scheduling algorithms with load measurements (which is done with the use of a forecasting tool called FAST) and fallback mechanisms. The experimental results show that the deadline scheduling with priority along with fallback mechanism can increase the overall number of tasks executed by the NES.
{"title":"Deadline scheduling with priority for client-server systems on the grid","authors":"E. Caron, P. Chouhan, F. Desprez","doi":"10.1109/GRID.2004.18","DOIUrl":"https://doi.org/10.1109/GRID.2004.18","url":null,"abstract":"We present algorithms for the scheduling sequential tasks on a network enabled server (NES) environment. This article is an extension of the paper: \"A Study of Deadline Scheduling for Client-Server Systems on the Computational Grid\" by Takefusa et al. We mainly discuss a deadline scheduling with priority strategy that is more appropriate for multiclient, multiserver case. Importance is first given to the task's priority and then the task is allocated to the server that can meet the task's deadline. This may cause that some already allocated tasks on the server miss their deadline. We also augment the benefits of scheduling algorithms with load measurements (which is done with the use of a forecasting tool called FAST) and fallback mechanisms. The experimental results show that the deadline scheduling with priority along with fallback mechanism can increase the overall number of tasks executed by the NES.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131585722","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}
S. Shirasuna, Aleksander Slominski, Liang Fang, Dennis Gannon
Security is one of the most important features for grid services. There are several specifications used to add security to grid services, and some of them have been implemented and are in use. However, since most of the security mechanisms involve slow XML manipulations, adding security to grid services introduces a big performance penalty. In this paper, we introduce various security mechanisms and compare their features and performance. Our evaluation shows that transport level security (SSL) is faster than message level security, and should be used if there is no special requirement to use message level security. For message level security, WS-SecureConversation is generally fast, but has a scalability problem.
{"title":"Performance comparison of security mechanisms for grid services","authors":"S. Shirasuna, Aleksander Slominski, Liang Fang, Dennis Gannon","doi":"10.1109/GRID.2004.50","DOIUrl":"https://doi.org/10.1109/GRID.2004.50","url":null,"abstract":"Security is one of the most important features for grid services. There are several specifications used to add security to grid services, and some of them have been implemented and are in use. However, since most of the security mechanisms involve slow XML manipulations, adding security to grid services introduces a big performance penalty. In this paper, we introduce various security mechanisms and compare their features and performance. Our evaluation shows that transport level security (SSL) is faster than message level security, and should be used if there is no special requirement to use message level security. For message level security, WS-SecureConversation is generally fast, but has a scalability problem.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127056382","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. Stewart, R. Keller, Richard Repasky, M. Hess, Dave Hart, Matthias S. Müller, R. Sheppard, U. Wössner, Martin Aumüller, Huian Li, Donald K. Berry, J. Colbourne
Maximum likelihood analysis is a powerful technique for inferring evolutionary histories from genetic sequence data. During the fall of 2003, an international team of computer scientists, biologists, and computer centers created a global grid to analyze the evolution of hexapods (arthropods with six legs). We created a global grid of computers using systems located in eight countries, spread across six continents (every continent but Antarctica). This work was done as part of the SC03 HPC challenge, and this project was given an HPC challenge award for the "most distributed application". More importantly, the creation of this computing grid enabled investigation of important questions regarding the evolution of arthropods - research that would not have otherwise been undertaken. Grid computing thus leads directly to new scientific insights.
{"title":"A global grid for analysis of arthropod evolution","authors":"C. Stewart, R. Keller, Richard Repasky, M. Hess, Dave Hart, Matthias S. Müller, R. Sheppard, U. Wössner, Martin Aumüller, Huian Li, Donald K. Berry, J. Colbourne","doi":"10.1109/GRID.2004.1","DOIUrl":"https://doi.org/10.1109/GRID.2004.1","url":null,"abstract":"Maximum likelihood analysis is a powerful technique for inferring evolutionary histories from genetic sequence data. During the fall of 2003, an international team of computer scientists, biologists, and computer centers created a global grid to analyze the evolution of hexapods (arthropods with six legs). We created a global grid of computers using systems located in eight countries, spread across six continents (every continent but Antarctica). This work was done as part of the SC03 HPC challenge, and this project was given an HPC challenge award for the \"most distributed application\". More importantly, the creation of this computing grid enabled investigation of important questions regarding the evolution of arthropods - research that would not have otherwise been undertaken. Grid computing thus leads directly to new scientific insights.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114847498","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}
V. Bhat, S. Klasky, S. Atchley, Micah Beck, D. McCune, M. Parashar
We have developed a threaded parallel data streaming approach using logistical networking (LN) to transfer multiterabyte simulation data from computers at NERSC to our local analysis/visualization cluster, as the simulation executes, with negligible overhead. Data transfer experiments show that this concurrent data transfer approach is more favorable compared with writing to local disk and later transferring this data to be post-processed. Our algorithms are network aware, and can stream data at up to 97 Mbs on a 100 Mbs link from CA to NJ during a live simulation, using less than 5% CPU overhead at NERSC. This method is the first step in setting up a pipeline for simulation workflow and data management.
{"title":"High performance threaded data streaming for large scale simulations","authors":"V. Bhat, S. Klasky, S. Atchley, Micah Beck, D. McCune, M. Parashar","doi":"10.1109/GRID.2004.36","DOIUrl":"https://doi.org/10.1109/GRID.2004.36","url":null,"abstract":"We have developed a threaded parallel data streaming approach using logistical networking (LN) to transfer multiterabyte simulation data from computers at NERSC to our local analysis/visualization cluster, as the simulation executes, with negligible overhead. Data transfer experiments show that this concurrent data transfer approach is more favorable compared with writing to local disk and later transferring this data to be post-processed. Our algorithms are network aware, and can stream data at up to 97 Mbs on a 100 Mbs link from CA to NJ during a live simulation, using less than 5% CPU overhead at NERSC. This method is the first step in setting up a pipeline for simulation workflow and data management.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116870818","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 grids require the underlying network infrastructure to be properly configured in order to have appropriate communications among the grids' nodes. The management of networks and the management of grids are currently executed by different tools operated by different administrative personnel. Eventually, the grid communication requirements need corresponding support from the network management tools, but such requirements are fulfilled only when grid administrators manually asks network administrators for corresponding configurations. In this paper we propose a policy translation mechanism that creates network policies given grid requirements expressed in grid policies. We also present a system prototype that allows (a) grid administrators to define grid policies, and (b) network administrators to define translating rules. These rules are used by the proposed translation mechanism to generate the necessary underlying network configuration policies.
{"title":"On translating grid requirements to network configurations through policy-based management","authors":"R. Neisse, L. Granville, M. Almeida, L. Tarouco","doi":"10.1109/GRID.2004.46","DOIUrl":"https://doi.org/10.1109/GRID.2004.46","url":null,"abstract":"Computing grids require the underlying network infrastructure to be properly configured in order to have appropriate communications among the grids' nodes. The management of networks and the management of grids are currently executed by different tools operated by different administrative personnel. Eventually, the grid communication requirements need corresponding support from the network management tools, but such requirements are fulfilled only when grid administrators manually asks network administrators for corresponding configurations. In this paper we propose a policy translation mechanism that creates network policies given grid requirements expressed in grid policies. We also present a system prototype that allows (a) grid administrators to define grid policies, and (b) network administrators to define translating rules. These rules are used by the proposed translation mechanism to generate the necessary underlying network configuration policies.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122659054","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：