Physics experiments that generate large amounts of data need to be able to share it with researchers around the world .High performance grids facilitate the distribution of such data to geographically remote places.Dy...Physics experiments that generate large amounts of data need to be able to share it with researchers around the world .High performance grids facilitate the distribution of such data to geographically remote places.Dynamic replication can be used as a technique to reduce bandwidth consumption and access latency in accessuing these huge amounts of data.We describe a simulation framework that we have developed to model a grid scenario,which enables comparative studies of alternative dynamic replication strategies.We present preliminary results obtained with this simulator,in which we evaluate the performance of six different replication strategies for three different kinds of access patterns.The simulation results show that the best strategy has significant savings in latency and bandwidth consumption if the access patterns contain a moderate amount of gerographical locality.展开更多
The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being...The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being exposed to for the first time,we now see considerable consensus on Grid architecture,a solid and widely adopeted technology base,major funding initiatives,a wide variety of projects developing applications and technologies,and major deployment projects aimed at creating robust Grid infrastructures,I provide a summary of major developments and trends,focusing on the Globus open source Grid software project and the GriPhyN data grid project.展开更多
文摘Physics experiments that generate large amounts of data need to be able to share it with researchers around the world .High performance grids facilitate the distribution of such data to geographically remote places.Dynamic replication can be used as a technique to reduce bandwidth consumption and access latency in accessuing these huge amounts of data.We describe a simulation framework that we have developed to model a grid scenario,which enables comparative studies of alternative dynamic replication strategies.We present preliminary results obtained with this simulator,in which we evaluate the performance of six different replication strategies for three different kinds of access patterns.The simulation results show that the best strategy has significant savings in latency and bandwidth consumption if the access patterns contain a moderate amount of gerographical locality.
文摘The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being exposed to for the first time,we now see considerable consensus on Grid architecture,a solid and widely adopeted technology base,major funding initiatives,a wide variety of projects developing applications and technologies,and major deployment projects aimed at creating robust Grid infrastructures,I provide a summary of major developments and trends,focusing on the Globus open source Grid software project and the GriPhyN data grid project.