A spatial index for hybrid storage

ABSTRACT

The introduction of flash SSDs has accelerated the performance of DBMSes. However, the intrinsic characteristics of flash motivated many researchers to investigate new efficient data structures. The emergence of 3DXPoint, a new non-volatile memory, sets new challenges: 3DXPoint features low latency and high IOPS even at small queue depths. However, the cost of 3DXPoint is 4 times higher than that of a flash-based device, rendering hybrid storage systems a good alternative. In this paper we pursue exploiting the efficiency of both 3DXPoint and flash-based devices introducing H-Grid, a variant of Grid-File for hybrid storage. H-Grid uses a flash SSD as main store and a small 3DXPoint device to persist the hottest data. The performance of the proposed index is experimentally evaluated, comparing it against GFFM, a flash efficient implementation of Grid File. The results show that H-Grid is faster than GFFM execution on a flash SSD, reducing the single point search time from 35% up to 43%.

References

1. D. Agrawal, D. Ganesan, R. Sitaraman, Y. Diao, and S. Singh. Lazy-adaptive tree: An optimized index structure for flash devices. Proceedings of the VLDB Endowment, 2(1):361--372, 2009.
2. M. Canim, G. A. Mihaila, B. Bhattacharjee, K. A. Ross, and C. A. Lang. Ssd bufferpool extensions for database systems. Proceedings of the VLDB Endowment, 3(1-2):1435--1446, 2010.
3. A. C. Carniel, R. R. Ciferri, and C. D. de Aguiar Ciferri. A generic and efficient framework for spatial indexing on flash-based solid state drives. In Advances in Databases and Information Systems, pages 229--243. Springer, 2017.
4. F. Chen, D. A. Koufaty, and X. Zhang. Hystor: making the best use of solid state drives in high performance storage systems. In Proceedings of the international conference on Supercomputing, pages 22--32. ACM, 2011.
5. A. Fevgas and P. Bozanis. Grid-file: Towards to a flash efficient multi-dimensional index. In International Conference on Database and Expert Systems Applications, pages 285--294. Springer, 2015.
6. A. Fevgas and P. Bozanis. Lb-grid: An ssd efficient grid file. Data Knowledge Engineering, 2019 in press.
7. M. Hadjieleftheriou. libspatialindex 1.8.5, 2019. {Online; accessed 20-Feb-2019}.
8. F. T. Hady, A. Foong, B. Veal, and D. Williams. Platform storage performance with 3d xpoint technology. Proceedings of the IEEE, 105(9):1822--1833, 2017.
9. K. Hinrichs. Implementation of the grid file: Design concepts and experience. BIT Numerical Mathematics, 25(4):569--592, 1985.
10. P. Jin, X. Xie, N. Wang, and L. Yue. Optimizing r-tree for flash memory. Expert Systems with Applications, 2015.
11. P. Jin, C. Yang, C. S. Jensen, P. Yang, and L. Yue. Read/write-optimized tree indexing for solid-state drives. The VLDB Journal, 25(5):695--717, 2016.
12. P. Jin, P. Yang, and L. Yue. Optimizing b+-tree for hybrid storage systems. Distributed and parallel Databases, 33(3):449--475, 2015.
13. I. Koltsidas and V. Hsu. IBM Storage and NVM express Revolution. Technical report, IBM, 2017.
14. G. Li, P. Zhao, L. Yuan, and S. Gao. Efficient implementation of a multi-dimensional index structure over flash memory storage systems. The Journal of Supercomputing, 64(3):1055--1074, 2013.
15. L. Li, P. Jin, C. Yang, S. Wan, and L. Yue. Xb+-tree: A novel index for pcm/dram-based hybrid memory. In Australasian Database Conference, pages 357--368. Springer, 2016.
16. Y. Li, B. He, Q. Luo, and K. Yi. Tree indexing on flash disks. In Data Engineering, 2009. ICDE'09. IEEE 25th International Conference on, pages 1303--1306. IEEE, 2009.
17. S. Lin, D. Zeinalipour-Yazti, V. Kalogeraki, D. Gunopulos, and W. A. Najjar. Efficient indexing data structures for flash-based sensor devices. ACM Transactions on Storage (TOS), 2(4):468--503, 2006.
18. J. D. Little and S. C. Graves. Little's law. In Building intuition, pages 81--100. Springer, 2008.
19. X. Liu and K. Salem. Hybrid storage management for database systems. Proceedings of the VLDB Endowment, 6(8):541--552, 2013.
20. Y. Liu, X. Ge, X. Huang, and D. H. Du. Molar: A cost-efficient, high-performance hybrid storage cache. In Cluster Computing (CLUSTER), 2013 IEEE International Conference on, pages 1--5. IEEE, 2013.
21. Y. Lv, X. Chen, G. Sun, and B. Cui. A probabilistic data replacement strategy for flash-based hybrid storage system. In Asia-Pacific Web Conference, pages 360--371. Springer, 2013.
22. R. Micheloni. 3D Flash memories. Springer, 2016.
23. J. Nievergelt, H. Hinterberger, and K. C. Sevcik. The Grid file: Aan adaptable, symmetric multikey file structure. ACM Transactions on Database Systems, 9(1):38--71, 1984.
24. J. Niu, J. Xu, and L. Xie. Hybrid storage systems: A survey of architectures and algorithms. IEEE ACCESS, 6:13385--13406, 2018.
25. H. Roh, S. Kim, D. Lee, and S. Park. As b-tree: A study of an efficient b+-tree for ssds. Journal of Information Science and Engineering, 30(1):85--106, 2014.
26. H. Roh, S. Park, S. Kim, M. Shin, and S.-W. Lee. B+-tree index optimization by exploiting internal parallelism of flash-based solid state drives. Proceedings of the VLDB Endowment, 5(4):286--297, 2011.
27. H. Roh, S. Park, M. Shin, and S.-W. Lee. Mpsearch: Multi-path search for tree-based indexes to exploit internal parallelism of flash ssds. IEEE Data Eng. Bull., 37(2):3--11, 2014.
28. G. Roumelis, A. Fevgas, M. Vassilakopoulos, A. Corral, P. Bozanis, and Y. Manolopoulos. Bulk-loading and bulk-insertion algorithms for xbr-trees in solid state drives. Computing, 2019. available online.
29. H. Samet. Applications of spatial data structures. Addison-Wesley, 1990.
30. M. Sarwat, M. F. Mokbel, X. Zhou, and S. Nath. Fast: a generic framework for flash-aware spatial trees. In Advances in Spatial and Temporal Databases, pages 149--167. Springer, 2011.
31. J. Yang and D. J. Lilja. Reducing relational database performance bottlenecks using 3d xpoint storage technology. In 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE), pages 1804--1808. IEEE, 2018.
32. J. Zhang, M. Kwon, D. Gouk, S. Koh, C. Lee, M. Alian, M. Chun, K. N. Kandemir MTaylan, J. Kim, and M. Jung. Flashshare: Punching through server storage stack from kernel to firmware for ultra-low latency ssds. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pages 477--492, 2018.

Index Terms

• Information systems

  • Data management systems

    • Data structures

      • Data access methods