Scheduling Data Placement Activities in Grid
Tevfik Kosar, Miron Livny
Todays scientific applications have huge data requirements, and these requirements continue to increase drastically every year. Furthermore, these data are generally accessed by many users from all across the country, or even the globe. So, there tends to be a predominant necessity to move huge amounts of data around wide area networks to complete the computation cycle, which brings with it the problem of efficient and reliable data placement. Current approach to solve this problem of data placement is either doing it manually, or employing simple scripts which do not have any automation or fault tolerance capabilites. Our goal is to make data placement activities first class citizens in the Grid just like the computational jobs. They will be queued, scheduled, monitored and managed, and even check-pointed. More importantly, it will be made sure that they complete without any human interaction.
Download this report (PDF)
Return to tech report index