Abstract

As a data-intensive computing application, high-energy physics requires to process and store massive data at the PB or EB level. It requires high performance data access and large volume of data storage as well. Some enterprises and research organizations are beginning to use tiered storage architectures, using tapes, disks or solid drives at the same time to reduce hardware purchase costs and power consumption. Tiered storage requires data management software to migrate less active data to lower cost storage devices. Thus an automated data migration strategy is very necessary. Data access requests are driven by the behavior of users or programs. There must be associations between different files that are accessed consecutively. This paper proposes a method to predict the heat of data access and use data heat trend as the basis criteria for data migration. This paper proposes a deep learning algorithm model to predict the evolution trend of data access heat. This paper discussed the implementation of some initial parts of the system. Then some preliminary experiments are conducted with these parts.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call