Analyzing the Performance of Spatial Indices on Flash Memories using a Flash Simulator

Spatial databases improve the spatial query processing by employing spatial indices. Due to the advantages of flash memories over magnetic disks like faster reads and writes, there is a special interest in managing spatial indices in these memories. However, many flash memories employ a Flash Translation Layer that does not provide open access to many important statistics, restricting the performance analysis of spatial indices. Flash simulators are promising tools to improve the performance analysis of spatial indices. In this paper, we analyze the performance of several distinct configurations of spatial indices by using a flash simulator and a real flash-based solid state drive. As a result, we provide correlations between these results to check the accuracy of a flash simulator in the spatial indexing context. In addition, we discuss the possibility of using a flash simulator as a first step for benchmarking spatial indices. That is, we check if the results provided by a flash simulator can be used to decrease the number of configurations to be evaluated in real flash memories, reducing the required time of an empirical analysis.

[1]  Ralf Hartmut Güting Dr.rer.nat.  An introduction to spatial database systems , 2005, The VLDB Journal.

[2]  Cristina Dutra de Aguiar Ciferri,et al.  A Generic and Efficient Framework for Spatial Indexing on Flash-Based Solid State Drives , 2017, ADBIS.

[3]  José Maria Monteiro,et al.  Hardware-aware Database Systems: A New Era for Database Technology is Coming - Vision Paper , 2016, SBBD.

[4]  Cristina Dutra de Aguiar Ciferri,et al.  The performance relation of spatial indexing on hard disk drives and solid state drives , 2016, GEOINFO.

[5]  Youngjae Kim,et al.  FlashSim: A Simulator for NAND Flash-Based Solid-State Drives , 2009, 2009 First International Conference on Advances in System Simulation.

[6]  Suman Nath,et al.  Generic and efficient framework for search trees on flash memory storage systems , 2013, GeoInformatica.

[7]  Jeffrey S. Vetter,et al.  A Survey of Software Techniques for Using Non-Volatile Memories for Storage and Main Memory Systems , 2016, IEEE Transactions on Parallel and Distributed Systems.

[8]  Jing Li,et al.  Log-Compact R-Tree: An Efficient Spatial Index for SSD , 2011, DASFAA Workshops.

[9]  Peiquan Jin,et al.  Optimizing R-tree for flash memory , 2015, Expert Syst. Appl..

[10]  Cong Xu,et al.  NVSim: A Circuit-Level Performance, Energy, and Area Model for Emerging Nonvolatile Memory , 2012, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[11]  Hans-Peter Kriegel,et al.  On the impact of flash SSDs on spatial indexing , 2010, DaMoN '10.

[12]  Peiquan Jin,et al.  Flash-DBSim: A simulation tool for evaluating Flash-based database algorithms , 2009, 2009 2nd IEEE International Conference on Computer Science and Information Technology.

[13]  Mahmut T. Kandemir,et al.  Revisiting widely held SSD expectations and rethinking system-level implications , 2013, SIGMETRICS '13.

[14]  Tei-Wei Kuo,et al.  An efficient R-tree implementation over flash-memory storage systems , 2003, GIS '03.

[15]  Sang-Won Lee,et al.  A survey of Flash Translation Layer , 2009, J. Syst. Archit..

[16]  Oliver Günther,et al.  Multidimensional access methods , 1998, CSUR.