Salvatore Di Girolamo, P. Schmid, Thomas Schulthess, Torsten Hoefler:
SimFS: A Simulation Data Virtualizing File System Interface
(In Proceedings of the 33st IEEE International Parallel & Distributed Processing Symposium (IPDPS'19), presented in Rio de Janeiro, Brazil, IEEE, May 2019)
Abstract
Nowadays simulations can produce petabytes of data to be stored in parallel filesystems or large-scale databases. This data is accessed over the course of decades often by thousands of analysts and scientists. However, storing these volumes of data for long periods of time is not cost effective and, in some cases, practically impossible. We propose to transparently virtualize the simulation data, relaxing the storage requirements by not storing the full output and re-simulating the missing data on demand. We develop SimFS, a file system interface that exposes a virtualized view of the simulation output to the analysis applications and manages the re-simulations. SimFS monitors the access patterns of the analysis applications in order to (1) decide the data to keep stored for faster accesses and (2) to employ prefetching strategies to reduce the access time of missing data. Virtualizing simulation data allows us to trade storage for computation: this paradigm becomes similar to traditional on-disk analysis (all data is stored) or in situ (no data is stored) according with the storage resources that are assigned to SimFS. Overall, by exploiting the growing computing power and relaxing the storage capacity requirements, SimFS offers a viable path towards exa-scale simulations.
Documents
download article: download slides:
Recorded talk (best effort)
BibTeX
@inproceedings{simfs, author={Salvatore Di Girolamo and P. Schmid and Thomas Schulthess and Torsten Hoefler}, title={{SimFS: A Simulation Data Virtualizing File System Interface}}, year={2019}, month={May}, booktitle={Proceedings of the 33st IEEE International Parallel \& Distributed Processing Symposium (IPDPS'19)}, location={Rio de Janeiro, Brazil}, publisher={IEEE}, source={http://www.unixer.de/~htor/publications/}, }
