Abstract
We present a novel storage manager for multi-dimensional arrays that arise in scientific applications, which is part of a larger scientific data management system called TileDB. In contrast to existing solutions, TileDB is optimized for both dense and sparse arrays. Its key idea is to organize array elements into ordered collections called fragments. Each fragment is dense or sparse, and groups contiguous array elements into data tiles of fixed capacity. The organization into fragments turns random writes into sequential writes, and, coupled with a novel read algorithm, leads to very efficient reads. TileDB enables parallelization via multi-threading and multi-processing, offering thread-/process-safety and atomicity via lightweight locking. We show that TileDB delivers comparable performance to the HDF5 dense array storage manager, while providing much faster random writes. We also show that TileDB offers substantially faster reads and writes than the SciDB array database system with both dense and sparse arrays. Finally, we demonstrate that TileDB is considerably faster than adaptations of the Vertica relational column-store for dense array storage management, and at least as fast for the case of sparse arrays.
- Apache Kylin. http://kylin.apache.org/.Google Scholar
- Broad Institute, Intel work together to develop tools to accelerate biomedical research. http://genomicinfo.broadinstitute.org/acton/media/13431/broad-intel-collaboration.Google Scholar
- Charm++. http://charm.cs.illinois.edu/research/charm.Google Scholar
- Enabling a Strict Consistency Semantics Model in Parallel HDF5. https://www.hdfgroup.org/HDF5/doc/Advanced/PHDF5FileConsistencySemantics/PHDF5FileConsistencySemantics.pdf.Google Scholar
- GenericIO. http://trac.alcf.anl.gov/projects/genericio.Google Scholar
- HDF5 for Python. http://www.h5py.org/.Google Scholar
- Legion Parallel System. http://legion.stanford.edu/.Google Scholar
- National Oceanic and Atmospheric Administration. Marine Cadastre. http://marinecadastre.gov/ais/.Google Scholar
- NetCDF. http://www.unidata.ucar.edu/software/netcdf.Google Scholar
- Parallel HDF5. https://www.hdfgroup.org/HDF5/PHDF5/.Google Scholar
- PLASMA. http://www.netlib.org/plasma/.Google Scholar
- PostgreSQL. http://www.postgresql.org/.Google Scholar
- PyTables. http://www.pytables.org/.Google Scholar
- ROMIO: A High-Performance, Portable MPI-IO Implementation. http://www.mcs.anl.gov/projects/romio/.Google Scholar
- ScaLAPACK. http://www.netlib.org/scalapack/.Google Scholar
- The HDF5 Format. http://www.hdfgroup.org/HDF5/.Google Scholar
- P. Baumann, A. Dehmel, P. Furtado, R. Ritsch, and N. Widmann. The Multidimensional Database System RasDaMan. In SIGMOD, 1998. Google ScholarDigital Library
- P. G. Brown. Overview of SciDB: Large Scale Array Storage, Processing and Analysis. In SIGMOD, 2010. Google ScholarDigital Library
- R. Cornacchia, S. Héman, M. Zukowski, A. P. Vries, and P. Boncz. Flexible and Efficient IR Using Array Databases. The VLDB Journal, 17(1):151--168, 2008. Google ScholarDigital Library
- S. Idreos, F. Groffen, N. Nes, S. Manegold, K. S. Mullender, and M. L. Kersten. MonetDB: Two Decades of Research in Column-oriented Database Architectures. IEEE Data Engin. Bulletin, 35(1):40--45, 2012.Google Scholar
- A. Lamb, M. Fuller, R. Varadarajan, N. Tran, B. Vandiver, L. Doshi, and C. Bear. The Vertica Analytic Database: C-store 7 Years Later. Proc. VLDB Endow., 5(12):1790--1801, 2012. Google ScholarDigital Library
- P. O'Neil, E. Cheng, D. Gawlick, and E. O'Neil. The Log-structured Merge-tree (LSM-tree). Acta Inf., 33(4):351--385, 1996. Google ScholarDigital Library
- M. Rosenblum and J. K. Ousterhout. The design and implementation of a log-structured file system. ACM TOCS, 10(1):26--52, Feb. 1992. Google ScholarDigital Library
- F. Rusu and Y. Cheng. A Survey on Array Storage, Query Languages, and Systems. ArXiv e-prints, 2013.Google Scholar
- E. Soroush, M. Balazinska, and D. Wang. ArrayStore: A Storage Manager for Complex Parallel Array Processing. In SIGMOD, 2011. Google ScholarDigital Library
- A. R. van Ballegooij. RAM: A Multidimensional Array DBMS. In EDBT Extended Database Technology Workshops, 2004. Google ScholarDigital Library
Recommendations
A scalable array storage for efficient maintenance of future data
AbstractArray-based storage system employs a renewed interest in the featured applications for their easy maintenance in the context of large volume data. However, the conventional schemes of array storages suffer from lack of scalability for dynamic data ...
Comments