云计算英文资料A Service for Data-Intensive Computations on Virtual Clusters.pdfVIP

A Service for Data-Intensive Computations on Virtual Clusters Rainer Schmidt, Christian Sadilek, and Ross King Austrian Research Centers GmbH - ARC Digital Memory Engineering Donau-City-Str. 1, 1220 Vienna, Austria rainer.schmidt@univie.ac.at Abstract The Planets IF workflow engine implements a component- oriented enactor that governs life-cycle operation of the var- Digital Preservation deals with the long-term storage, ious preservation components, such as instantiation, com- access, and maintenance of digital data objects. In or- munication, and data provenance. Distributed preservation der to prevent a loss of information, digital libraries and workflows are conducted from high-level components that archives are increasingly faced with the need to electron- abstract the underlying protocol layers. A crucial aspect of ically preserve vast amounts of data while having limited the preservation system is the establishment of a distributed, computational resources in-house. However, due to the po- reliable, and scalable computational tier. A typical preser- tentially immense data sets and computationally intensive vation workflow may consist of a set of components for data tasks involved, preservation systems have become a recog- characterization, migration, and verification and may be ap- nized challenge for e-science. We argue that grid and cloud plied to millions of digital objects. In principle, these work- technology can provide the crucial technology for building flows could be easily par