Andrew S. Grimshaw, William A. Wulf, James C. French, Alfred C. Weaver, and Paul F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....using the same communication and computation mechanisms that applications use resulting in forecasts that accurately reflect the true performance an application can expect to obtain. Separate implementations of the NWS have been developed using sockets and for the Globus Nexus [11] and Legion [12] metacomputing environments, each of which provides a software infrastructure that supports highperformance distributed and parallel computing. 2.2 The JavaNws The JavaNws is a Java implementation of a subset of the NWS toolkit that provides measurement and prediction for network resources. The ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....independently managed computers. These large scale metacomputers are capable of delivering greater execution performance to an application than is available at any one of their constituent sites [4] Moreover, performance oriented distributed software infrastructures such as Globus [12] Legion [18], Condor [26] NetSolve [7] and HPJava [6] are attempting to knit vast collections of machines into computational grids [13] from which compute cycles can be obtained in the way electrical power is obtained from an electrical power utility. One vexing quality of these ensemble systems is that ....

....context, shortterm predictability also has utility. Lastly, our observations coincide with those made recently by Dinda and O Halloran [10] with respect to observed autocorrelation structure and Unix load average measurements. This is fortuitous since several large scale metacomputing systems [18, 12, 26] use Unix load average to perceive system load. We extend this previous work by attempting to quantify the measurement error inherent in using load average as a measure of CPU availability, and by quantifying the e ectiveness of the current NWS forecasting techniques on this type of data. In ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....using the same communication and computation mechanisms that applications use resulting in forecasts that accurately reflect the true performance an application can expect to obtain. Separate implementations of the NWS have been developed using sockets and for the Globus Nexus [10] and Legion [12] metacomputing environments, each of which provides a software infrastructure that supports highperformance distributed and parallel computing. 2.2 The JavaNws The JavaNws is a Java implementation of a subset of the NWS toolkit that provides measurement and prediction for network resources. The ....

Andrew S. Grimshaw, William A. Wulf, James C. French, Alfred C. Weaver, and Paul F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....independently managed computers. These large scale metacomputers are capable of delivering greater execution performance to an application than is available at any one of their constituent sites [4] Moreover, performance oriented distributed software infrastructures such as Globus [12] Legion [18], Condor [26] NetSolve [7] and HPJava [6] are attempting to knit vast collections of machines into computational grids [13] from which compute cycles can be obtained in the way electrical power is obtained from an electrical power utility. Supported by NSF grant ASC 9701333 and Advanced ....

....context, short term predictability also has utility. Lastly, our observations coincide with those made recently by Dinda and O Halloran [10] with respect to observed autocorrelation structure and Unix load average measurements. This is fortuitous since several large scale metacomputing systems [18, 12, 26] use Unix load average to perceive system load. We extend this previous work by attempting to quantify the measurement error inherent in using load average as a measure of CPU availability, and by quantifying the effectiveness of the current NWS forecasting techniques on this type of data. In ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....ability to predict the TCP IP end to end throughput and latency that is attainable by an application using systems located at different sites. Such network forecasts are needed both to support scheduling [5] and by the metacomputing software infrastructure to develop quality of service guarantees [10, 17]. Keywords: scheduling, metacomputing, quality of service, statistical forecasting, network performance monitoring 1 Introduction As network technology advances, the resulting improvements in interprocess communication speeds make it possible to use interconnected but separate computer systems ....

....and as such, term the service the Network Weather Service (NWS) We have developed the NWS for use by schedulers in a networked computational environment. The AppLeS scheduling methodology [4, 2] makes extensive use of its facilities and we are currently implementing versions for Legion [17, 25] and Globus Nexus [10, 15] Initial scheduling results using the NWS are promising [5] In this paper, we focus on the problem of network performance forecasting within the context of scheduling, and the predictive methodologies that we have chosen to explore initially. We have developed a ....

[Article contains additional citation context not shown here]

Grimshaw, A. S., Wulf, W. A., French, J. C., Weaver, A. C., and Reynolds, P. F. Legion: The next logical step towrd a nationwide virtual computer. Tech. Rep. CS-94-21, University of Virginia, 1994.

.... x email: jhayes cs.ucsd.edu These large scale metacomputers are capable of delivering greater execution performance to an application than is available at any one of their constituent sites [4] Moreover, performance oriented distributed software infrastructures such as Globus [12] Legion [18], Condor [26] NetSolve [7] and HPJava [6] are attempting to knit vast collections of machines into computational grids [13] from which compute cycles can be obtained in the way electrical power is obtained from an electrical power utility. One vexing quality of these ensemble systems is that ....

....context, shortterm predictability also has utility. Lastly, our observations coincide with those made recently by Dinda and O Halloran [10] with respect to observed autocorrelation structure and Unix load average measurements. This is fortuitous since several large scale metacomputing systems [18, 12, 26] use Unix load average to perceive system load. We extend this previous work by attempting to quantify the measurement error inherent in using load average as a measure of CPU availability, and by quantifying the effectiveness of the current NWS forecasting techniques on this type of data. In ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....well, however, and lacked the robustness necessary to make the NWS a reliable system service. Moreover, we wished to extend the monitoring and forecasting capabilities of the system to meet the needs of various performance oriented distributed software infrastructures such as Globus [12] Legion [18], Condor [27] and Netsolve [7] As such, we hoped to improve the portability, the extensibility, and the reliability of the system over prior implementations. The NWS is designed to maximize four possibly conflicting functional characteristics. It must meet these goals despite the highly dynamic ....

....forecasts. For infrequent or casual users, the system also provides continuous access to NWS forecasts through the world wide web. 6. 1 C API The programming interface provided to applications is intended to be lightweight and easily integrated into applications written for systems such as Legion [18], Globus [12] Condor [27] MPI [11] and PVM [17] Two functions make up this lightweight interface and separate the two phases of a forecaster connection, InitForecaster( and RequestForecasts( The InitForecaster( function opens a socket connection to a Forecaster and passes a list of ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....available to schedulers and other resource management mechanisms at runtime so that they may determine the quality ofservice that will be available from each resource. We describe the architecture of the NWS and implementations that we have developed and are currently deploying for the Legion [11] and Globus Nexus [7] metacomputing infrastructures. We also detail NWS forecasts of resource performance using both the Legion and Globus Nexus implementations. Our results show that simple forecasting techniques substantially outperform measurements of current con email: rich cs.ucsd.edu, ....

....it must be implemented using the same communication and computation mechanisms that applications use so that forecasts accurately reflect the true performance an application can expect to obtain. Initially, we have developed separate implementations of the NWS for the Globus Nexus [8] and Legion [11] metacomputing environments, each of which provides a software infrastructure that supports highperformance distributed and parallel computing. As part of the AppLeS (Application Level Schedulers) project [2, 1] we are developing scheduling agents that make decisions based on applicationlevel ....

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....ability to predict the TCP IP end to end throughput and latency that is attainable by an application using systems located at different sites. Such network forecasts are needed both to support scheduling [5] and by the metacomputing software infrastructure to develop quality of service guarantees [10, 17]. Keywords: scheduling, metacomputing, quality ofservice, statistical forecasting, network performance monitoring 1. Introduction As network technology advances, the resulting improvements in interprocess communication speeds make it possible to use interconnected but separate computer systems ....

....schedules that are sensitive to load variation. In [5, 4] we report on the efficacy this technique for parallel applications in production distributed computing environments. As a result of its success, we are currently implementing versions for two production metacomputing systems: Legion [17] and Globus Nexus [10] In [15] the authors report similarly positive results for parallel applications using dynamic performance forecasting as the basis for scheduling, and other work indicates that dynamic information can be used to enhance the performance of world wideweb applications [7] In ....

[Article contains additional citation context not shown here]

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

....available to schedulers and other resource management mechanisms at runtime so that they may determine the quality of service that will be available from each resource. We describe the architecture of the NWS and implementations that we have developed and are currently deploying for the Legion [13] and Globus Nexus [7] metacomputing infrastructures. We also detail NWS forecasts of resource performance using both the Legion and Globus Nexus implementations. Our results show that simple forecasting techniques substantially outperform measurements of current conditions (commonly used to gauge ....

....and computation mechanisms that applications use so that forecasts accurately reflect the true performance an application can expect to obtain. Initially, we have developed separate implementations of the NWS using sockets (based on the netperf [15] utility) and for the Globus Nexus [8] and Legion [13] metacomputing environments, each of which provides a software infrastructure that supports high performance distributed and parallel computing. As part of the AppLeS (ApplicationLevel Schedulers) project [2, 1] we are developing scheduling agents that make decisions based on application level ....

[Article contains additional citation context not shown here]

A. S. Grimshaw, W. A. Wulf, J. C. French, A. C. Weaver, and P. F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

No context found.

Andrew S. Grimshaw, William A. Wulf, James C. French, Alfred C. Weaver, and Paul F. Reynolds. Legion: The next logical step towrd a nationwide virtual computer. Technical Report CS-94-21, University of Virginia, 1994.

No context found.

Grimshaw, A. S., Wulf, W. A., French, J. C., Weaver, A. C., and Reynolds, P. F. Legion: The next logical step towrd a nationwide virtual computer. Tech. Rep. CS-94-21, University of Virginia, 1994.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC