Adaptive grid applications require up-to-date network resource measurements and predictions to help steer their adaptation to meet performance goals. To this end, we are interested in monitoring the available bandwidth of the underlying networks in the most accurate and least obtrusive way. Bandwidth is either measured by actively injecting data probes into the network or by passively monitoring existing traffic, but there is a definite trade-off between the active approach, which is invasive, and the passive approach, which is rendered ineffective during periods of network idleness. We are developing the Wren bandwidth monitoring tool, which uses packet traces of existing application traffic to measure available bandwidth. We demonstrate that the principles supporting active bandwidth tools can be applied to passive traces of the LAN and WAN traffic generated by high-performance grid applications. We use our results to form a preliminary characterization of the application traffic required by available bandwidth techniques to produce effective measurements. Our results indicate that a low overhead, passive monitoring system supplemented with active measurements can be built to obtain a complete picture of the network's performance.
{"title":"Using passive traces of application traffic in a network monitoring system","authors":"M. Zangrilli, B. Lowekamp","doi":"10.1109/HPDC.2004.38","DOIUrl":"https://doi.org/10.1109/HPDC.2004.38","url":null,"abstract":"Adaptive grid applications require up-to-date network resource measurements and predictions to help steer their adaptation to meet performance goals. To this end, we are interested in monitoring the available bandwidth of the underlying networks in the most accurate and least obtrusive way. Bandwidth is either measured by actively injecting data probes into the network or by passively monitoring existing traffic, but there is a definite trade-off between the active approach, which is invasive, and the passive approach, which is rendered ineffective during periods of network idleness. We are developing the Wren bandwidth monitoring tool, which uses packet traces of existing application traffic to measure available bandwidth. We demonstrate that the principles supporting active bandwidth tools can be applied to passive traces of the LAN and WAN traffic generated by high-performance grid applications. We use our results to form a preliminary characterization of the application traffic required by available bandwidth techniques to produce effective measurements. Our results indicate that a low overhead, passive monitoring system supplemented with active measurements can be built to obtain a complete picture of the network's performance.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127653265","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}
Storage clusters consisting of thousands of disk drives are now being used both for their large capacity and high throughput. However, their reliability is far worse than that of smaller storage systems due to the increased number of storage nodes. RAID technology is no longer sufficient to guarantee the necessary high data reliability for such systems, because disk rebuild time lengthens as disk capacity grows. We present fast recovery mechanism (FARM), a distributed recovery approach that exploits excess disk capacity and reduces data recovery time. FARM works in concert with replication and erasure-coding redundancy schemes to dramatically lower the probability of data loss in large-scale storage systems. We have examined essential factors that influence system reliability, performance, and costs, such as failure detections, disk bandwidth usage for recovery, disk space utilization, disk drive replacement, and system scales, by simulating system behavior under disk failures. Our results show the reliability improvement from FARM and demonstrate the impacts of various factors on system reliability. Using our techniques, system designers will be better able to build multipetabyte storage systems with much higher reliability at lower cost than previously possible.
{"title":"Evaluation of distributed recovery in large-scale storage systems","authors":"Qin Xin, E. L. Miller, T. Schwarz","doi":"10.1109/HPDC.2004.12","DOIUrl":"https://doi.org/10.1109/HPDC.2004.12","url":null,"abstract":"Storage clusters consisting of thousands of disk drives are now being used both for their large capacity and high throughput. However, their reliability is far worse than that of smaller storage systems due to the increased number of storage nodes. RAID technology is no longer sufficient to guarantee the necessary high data reliability for such systems, because disk rebuild time lengthens as disk capacity grows. We present fast recovery mechanism (FARM), a distributed recovery approach that exploits excess disk capacity and reduces data recovery time. FARM works in concert with replication and erasure-coding redundancy schemes to dramatically lower the probability of data loss in large-scale storage systems. We have examined essential factors that influence system reliability, performance, and costs, such as failure detections, disk bandwidth usage for recovery, disk space utilization, disk drive replacement, and system scales, by simulating system behavior under disk failures. Our results show the reliability improvement from FARM and demonstrate the impacts of various factors on system reliability. Using our techniques, system designers will be better able to build multipetabyte storage systems with much higher reliability at lower cost than previously possible.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124460231","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}
Distributed applications use predictions of network traffic to sustain their performance by adapting their behavior The timescale of interest is application-dependent and thus it is natural to ask how predictability depends on the resolution, or degree of smoothing, of the network traffic signal. To help answer this question we empirically study the one-step-ahead predictability, measured by the ratio of mean squared error to signal variance, of network traffic at different resolutions. A one-step-ahead prediction at a coarse resolution is a prediction of the average behavior over a long interval We apply a wide range of linear and nonlinear time series models to a large number of packet traces, generating different resolution views of the traces through two methods: the simple binning approach used by several extant network measurement tools, and by wavelet-based approximations. The wavelet-based approach is a natural way to provide multiscale prediction to applications. We find that predictability seems to be highly situational in practice - it varies widely from trace to trace. Unexpectedly, predictability does not always increase as the signal is smoothed. Half of the time there is a sweet spot at which the ratio is minimized and predictability is clearly the best. Also surprisingly, predictors that can capture non-stationarity and nonlinearity provide benefits only at very coarse resolutions.
{"title":"An empirical study of the multiscale predictability of network traffic","authors":"Y. Qiao, J. Skicewicz, P. Dinda","doi":"10.1109/HPDC.2004.3","DOIUrl":"https://doi.org/10.1109/HPDC.2004.3","url":null,"abstract":"Distributed applications use predictions of network traffic to sustain their performance by adapting their behavior The timescale of interest is application-dependent and thus it is natural to ask how predictability depends on the resolution, or degree of smoothing, of the network traffic signal. To help answer this question we empirically study the one-step-ahead predictability, measured by the ratio of mean squared error to signal variance, of network traffic at different resolutions. A one-step-ahead prediction at a coarse resolution is a prediction of the average behavior over a long interval We apply a wide range of linear and nonlinear time series models to a large number of packet traces, generating different resolution views of the traces through two methods: the simple binning approach used by several extant network measurement tools, and by wavelet-based approximations. The wavelet-based approach is a natural way to provide multiscale prediction to applications. We find that predictability seems to be highly situational in practice - it varies widely from trace to trace. Unexpectedly, predictability does not always increase as the signal is smoothed. Half of the time there is a sweet spot at which the ratio is minimized and predictability is clearly the best. Also surprisingly, predictors that can capture non-stationarity and nonlinearity provide benefits only at very coarse resolutions.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121013335","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 presents a data management solution which allows fast virtual machine (VM) instantiation and efficient run-time execution to support VMs as execution environments in grid computing. It is based on novel distributed file system virtualization techniques and is unique in that: 1) it provides on-demand access to VM state for unmodified VM monitors; 2) it supports user-level and write-back disk caches, per-application caching policies and middleware-driven consistency models; and 3) it supports the use of meta-data associated with files to expedite data transfers. The paper reports on its performance in a WAN setup using VMware-based VMs. Results show that the solution delivers performance over 30% better than native NFS and can bring application-perceived overheads below 10% relatively to a local disk setup. The solution also allows a VM with 1.6GB virtual disk and 320MB virtual memory to be cloned within 160 seconds when it is first instantiated (and within 25 seconds for subsequent clones).
{"title":"Distributed file system support for virtual machines in grid computing","authors":"Ming Zhao, Jian Zhang, Renato J. O. Figueiredo","doi":"10.1109/HPDC.2004.10","DOIUrl":"https://doi.org/10.1109/HPDC.2004.10","url":null,"abstract":"This paper presents a data management solution which allows fast virtual machine (VM) instantiation and efficient run-time execution to support VMs as execution environments in grid computing. It is based on novel distributed file system virtualization techniques and is unique in that: 1) it provides on-demand access to VM state for unmodified VM monitors; 2) it supports user-level and write-back disk caches, per-application caching policies and middleware-driven consistency models; and 3) it supports the use of meta-data associated with files to expedite data transfers. The paper reports on its performance in a WAN setup using VMware-based VMs. Results show that the solution delivers performance over 30% better than native NFS and can bring application-perceived overheads below 10% relatively to a local disk setup. The solution also allows a VM with 1.6GB virtual disk and 320MB virtual memory to be cloned within 160 seconds when it is first instantiated (and within 25 seconds for subsequent clones).","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125697482","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}
Service composition is highly desirable in peer-to-peer (P2P) systems where application services are naturally dispersed on distributed peers. However, it is challenging to provide high quality and failure resilient service composition in P2P systems due to the decentralization requirement and dynamic peer arrivals/departures. We present an integrated P2P service composition framework called SpiderNet to address the challenges. At service setup phase, SpiderNet performs a novel bounded composition probing protocol to provide scalable quality-aware and resource-efficient sendee composition in a fully distributed fashion. Moreover, SpiderNet supports directed acyclic graph composition topologies and explores exchangeable composition orders for enhanced service quality. During service runtime, SpiderNet provides proactive failure recovery to overcome dynamic changes (e.g., peer departures) in P2P systems. The proactive failure recovery scheme maintains a small number of dynamically selected backup compositions to achieve quick failure recovery for soft realtime streaming applications. We have implemented a prototype of SpiderNet and conducted extensive experiments using both large-scale simulations and wide-area network testbed. Experimental results show the feasibility and efficiency of the SpiderNet service composition solution for P2P systems.
{"title":"SpiderNet: an integrated peer-to-peer service composition framework","authors":"Xiaohui Gu, K. Nahrstedt, Bin Yu","doi":"10.1109/HPDC.2004.32","DOIUrl":"https://doi.org/10.1109/HPDC.2004.32","url":null,"abstract":"Service composition is highly desirable in peer-to-peer (P2P) systems where application services are naturally dispersed on distributed peers. However, it is challenging to provide high quality and failure resilient service composition in P2P systems due to the decentralization requirement and dynamic peer arrivals/departures. We present an integrated P2P service composition framework called SpiderNet to address the challenges. At service setup phase, SpiderNet performs a novel bounded composition probing protocol to provide scalable quality-aware and resource-efficient sendee composition in a fully distributed fashion. Moreover, SpiderNet supports directed acyclic graph composition topologies and explores exchangeable composition orders for enhanced service quality. During service runtime, SpiderNet provides proactive failure recovery to overcome dynamic changes (e.g., peer departures) in P2P systems. The proactive failure recovery scheme maintains a small number of dynamically selected backup compositions to achieve quick failure recovery for soft realtime streaming applications. We have implemented a prototype of SpiderNet and conducted extensive experiments using both large-scale simulations and wide-area network testbed. Experimental results show the feasibility and efficiency of the SpiderNet service composition solution for P2P systems.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125955917","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. Gullapalli, S. Dyke, P. Hubbard, Doru Marcusiu, L. Pearlman, C. Severance
The NEESgrid project is revolutionizing the way earthquake engineering (EE) researchers collaborate to plan, perform, share and publish research even while being geographically separated. The proposed demonstration is in complement to the NEESgrid paper titled "Distributed Hybrid Earthquake Engineering Experiments: Experiences with a Ground-Shaking Grid Application" also presented at this conference. It showcases some of NEESgrid"s features and capabilities in the area of distributed hybrid experiments, as well as new features developed since the distributed hybrid experiment was conducted. These new features and capabilities are in the areas of simulation portal, electronic notebook, data modeling, and improved live streaming of near real time sensor and video data.
{"title":"Showcasing the features and capabilities of NEESgrid: a grid based system for the earthquake engineering domain","authors":"S. Gullapalli, S. Dyke, P. Hubbard, Doru Marcusiu, L. Pearlman, C. Severance","doi":"10.1109/HPDC.2004.31","DOIUrl":"https://doi.org/10.1109/HPDC.2004.31","url":null,"abstract":"The NEESgrid project is revolutionizing the way earthquake engineering (EE) researchers collaborate to plan, perform, share and publish research even while being geographically separated. The proposed demonstration is in complement to the NEESgrid paper titled \"Distributed Hybrid Earthquake Engineering Experiments: Experiences with a Ground-Shaking Grid Application\" also presented at this conference. It showcases some of NEESgrid\"s features and capabilities in the area of distributed hybrid experiments, as well as new features developed since the distributed hybrid experiment was conducted. These new features and capabilities are in the areas of simulation portal, electronic notebook, data modeling, and improved live streaming of near real time sensor and video data.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127330579","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. Ripeanu, M. Bowman, J. Chase, Ian T Foster, Milan Milenkovic
PlanetLab and Globus Toolkit are gaining widespread adoption in their respective communities. Although designed to solve different problems - PlanetLab is deploying a worldwide infrastructure testbed for experimenting with network services, while Globus is offering general, standards-based, software for running distributed applications over aggregated, shared resources - both build infrastructures that enable federated, extensible, and secure resource sharing across trust domains. Thus, it is instructive to compare their resource management solutions. To this end, we review the approaches taken in the two systems, attempt to trace back to starting assumptions the differences in these approaches, and explore scenarios where the two platforms can cooperate to the benefit of both user communities. We believe that this is a key first step to identifying pieces that could be shared by the two communities, pieces that are complementary, and how Globus and PlanetLab might ultimately evolve together.
{"title":"Globus and PlanetLab resource management solutions compared","authors":"M. Ripeanu, M. Bowman, J. Chase, Ian T Foster, Milan Milenkovic","doi":"10.1109/HPDC.2004.17","DOIUrl":"https://doi.org/10.1109/HPDC.2004.17","url":null,"abstract":"PlanetLab and Globus Toolkit are gaining widespread adoption in their respective communities. Although designed to solve different problems - PlanetLab is deploying a worldwide infrastructure testbed for experimenting with network services, while Globus is offering general, standards-based, software for running distributed applications over aggregated, shared resources - both build infrastructures that enable federated, extensible, and secure resource sharing across trust domains. Thus, it is instructive to compare their resource management solutions. To this end, we review the approaches taken in the two systems, attempt to trace back to starting assumptions the differences in these approaches, and explore scenarios where the two platforms can cooperate to the benefit of both user communities. We believe that this is a key first step to identifying pieces that could be shared by the two communities, pieces that are complementary, and how Globus and PlanetLab might ultimately evolve together.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115035657","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}
A. Chervenak, Naveen Palavalli, S. Bharathi, C. Kesselman, Robert Schwartzkopf
We describe the implementation and evaluate the performance of a replica location service that is part of the Globus Toolkit Version 3.0. A replica location service (RLS) provides a mechanism for registering the existence of replicas and discovering them. Features of our implementation include the use of soft state update protocols to populate a distributed index and optional Bloom filter compression to reduce the size of these updates. Our results demonstrate that RLS performance scales well for individual servers with millions of entries and up to 100 requesting threads. We also show that the distributed RLS index scales well when using Bloom filter compression for wide area updates.
我们将描述作为Globus Toolkit Version 3.0一部分的副本位置服务的实现并评估其性能。副本位置服务(RLS)提供了一种机制，用于注册副本的存在并发现它们。我们实现的功能包括使用软状态更新协议来填充分布式索引和可选的Bloom过滤器压缩来减少这些更新的大小。我们的结果表明，对于具有数百万条目和多达100个请求线程的单个服务器，RLS性能可以很好地扩展。我们还表明，当使用布隆过滤器压缩进行广域更新时，分布式RLS索引可以很好地扩展。
{"title":"Performance and scalability of a replica location service","authors":"A. Chervenak, Naveen Palavalli, S. Bharathi, C. Kesselman, Robert Schwartzkopf","doi":"10.1109/HPDC.2004.27","DOIUrl":"https://doi.org/10.1109/HPDC.2004.27","url":null,"abstract":"We describe the implementation and evaluate the performance of a replica location service that is part of the Globus Toolkit Version 3.0. A replica location service (RLS) provides a mechanism for registering the existence of replicas and discovering them. Features of our implementation include the use of soft state update protocols to populate a distributed index and optional Bloom filter compression to reduce the size of these updates. Our results demonstrate that RLS performance scales well for individual servers with millions of entries and up to 100 requesting threads. We also show that the distributed RLS index scales well when using Bloom filter compression for wide area updates.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122504627","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}
Increasingly, a number of applications rely on, or can potentially benefit from, analysis and monitoring of data streams. Moreover, many of these applications involve high volume data streams and require distributed processing of data arising from a distributed set of sources. Thus, we believe that a grid environment is well suited for flexible and adaptive analysis of these streams. This paper reports the design and initial evaluation of a middleware for processing distributed data streams. Our system is referred to as GATES (grid-based adaptive execution on streams). This system is designed to use the existing grid standards and tools to the extent possible. It flexibly achieves the best accuracy that is possible while maintaining the real-time constraint on the analysis. We have developed a self-adaptation algorithm for this purpose. Results from a detailed evaluation of this system demonstrate the benefits of distributed processing, and the effectiveness of our self-adaptation algorithm.
{"title":"GATES: a grid-based middleware for processing distributed data streams","authors":"Liang Chen, Kolagatla Reddy, G. Agrawal","doi":"10.1109/HPDC.2004.16","DOIUrl":"https://doi.org/10.1109/HPDC.2004.16","url":null,"abstract":"Increasingly, a number of applications rely on, or can potentially benefit from, analysis and monitoring of data streams. Moreover, many of these applications involve high volume data streams and require distributed processing of data arising from a distributed set of sources. Thus, we believe that a grid environment is well suited for flexible and adaptive analysis of these streams. This paper reports the design and initial evaluation of a middleware for processing distributed data streams. Our system is referred to as GATES (grid-based adaptive execution on streams). This system is designed to use the existing grid standards and tools to the extent possible. It flexibly achieves the best accuracy that is possible while maintaining the real-time constraint on the analysis. We have developed a self-adaptation algorithm for this purpose. Results from a detailed evaluation of this system demonstrate the benefits of distributed processing, and the effectiveness of our self-adaptation algorithm.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122339326","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}
UT Grid is a comprehensive campus cyberinfrastructure project to integrate the numerous and diverse computational, visualization, storage, data and information, and instrument/device resources of The University of Texas at Austin (UT). This joint project between UT Austin and IBM has a focus and approach with important fundamental differences from multiinstitution grids and discipline-specific grids. These distinctions, coupled with new locally-developed software for providing both portal and shell-based user interfaces to numerous grid software technologies, facilitate rapid deployment, adoption, and evolution of UT Grid, while enabling it to serve as a platform for both production computing (for research and education) and grid computing research. The first stages of UT grid are well under way after only two months: the construction of grid user portals and grid user nodes as interfaces, and the integration of serial and parallel computing resources for high-throughput computing.
{"title":"UT Grid: a comprehensive campus cyberinfrastructure","authors":"J. Boisseau","doi":"10.1109/HPDC.2004.39","DOIUrl":"https://doi.org/10.1109/HPDC.2004.39","url":null,"abstract":"UT Grid is a comprehensive campus cyberinfrastructure project to integrate the numerous and diverse computational, visualization, storage, data and information, and instrument/device resources of The University of Texas at Austin (UT). This joint project between UT Austin and IBM has a focus and approach with important fundamental differences from multiinstitution grids and discipline-specific grids. These distinctions, coupled with new locally-developed software for providing both portal and shell-based user interfaces to numerous grid software technologies, facilitate rapid deployment, adoption, and evolution of UT Grid, while enabling it to serve as a platform for both production computing (for research and education) and grid computing research. The first stages of UT grid are well under way after only two months: the construction of grid user portals and grid user nodes as interfaces, and the integration of serial and parallel computing resources for high-throughput computing.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117250418","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：