S. Ponce, P.M. Vila, R.D. Hersch
Proc. 19th IEEE Symposium on Mass Storage Systems & Tenth Goddard Conf. on Mass Storage Systems and Technologies, Univ. of Maryland, College Park, Maryland, USA, April 2002, 181-192
We present here a new way of indexing and retrieving data in huge datasets having a high dimensionality. The proposed method speeds up the selecting process by replacing scans of the whole data by scans of matching data. It makes use of two levels of catalogs that allow efficient data preselections. First level catalogs only contain a small subset of the data items selected according to given criteria. The first level catalogs allow to carry out queries and to preselect items. Then, a refined query can be carried out on the preselected data items within the full dataset. A second level catalog maintains the list of existing first level catalogs and the type and kind of data items they are storing.
We established a mathematical model of our indexing technique and show that it considerably speeds up the access to LHCb experiment event data at CERN (European Laboratory for Particle Physics).
Download the full paper: PDF 310 KB