New Storage Devices and the Future of Database Management

被引:3
作者
Kuznetsov, Sergey D. [1 ,2 ,3 ,4 ]
机构
[1] RAS, Ivannikov Inst Syst Programming, 25 Alexander Solzhenitsyn Str, Moscow 109004, Russia
[2] Lomonosov Moscow State Univ, GSP-1, Moscow 119991, Russia
[3] Moscow Inst Phys & Technol, 9 Inst Skiy Per, Dolgoprudnyi 141700, Moscow Region, Russia
[4] Natl Res Univ Higher Sch Econ HSE, 11 Myasnitskaya Str, Moscow 101000, Russia
来源
BALTIC JOURNAL OF MODERN COMPUTING | 2018年 / 6卷 / 01期
关键词
SQL-oriented DBMS; hard disk drive with movable heads; cost-based query optimization; in-memory DBMS; flash-based solid-state drive; non-volatile main memory;
D O I
10.22364/bjmc.2018.6.1.01
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
At the beginning of the paper, it is demonstrated that the technology of the most widely used SQL-oriented database management systems (DBMS) is inextricably linked with the technology of hard disk drives with movable heads (HDD). Features of HDD affect the data structures and algorithms for performing operations, methods of managing the buffer pool of the DBMS, transaction management, query optimization, etc. At present, new types of data storage hardware have appeared: block solid-state drives (SSD) and storage-class memory (SCM). SSD characteristics made it expedient to develop a DBMS in terms of their exclusive use, but so far, no such DBMS has been created, and SSDs are used simply instead of HDDs in DBMSs that do not take into account their features. The availability of SCM enables radical simplification of the architecture of the database systems and significantly improve their performance. To do this, we need to rethink many of the ideas used in disk-based databases.
引用
收藏
页码:1 / 12
页数:12
相关论文
共 34 条
[1]  
[Anonymous], 1983, DATA STRUCTURES ALGO
[2]  
[Anonymous], 2017, INTEL 64 IA 32 ARCHI
[3]  
[Anonymous], 2010, ACM SIGMOD INT C MAN
[4]   How to Build a Non-Volatile Memory Database Management System [J].
Arulraj, Joy ;
Pavlo, Andrew .
SIGMOD'17: PROCEEDINGS OF THE 2017 ACM INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2017, :1753-1758
[5]  
Bayer R., 1972, ACTA INFORM, V1, P173, DOI [10.1145/1734663.1734671, 10.1007/BF00288683, DOI 10.1007/BF00288683]
[6]  
Cheung S., 2013, ORACLE TIMES 10 DATA
[7]  
CHI P, 2016, P 21 AS S PAC DES AU, P109
[8]   PARALLEL DATABASE-SYSTEMS - THE FUTURE OF HIGH-PERFORMANCE DATABASE-SYSTEMS [J].
DEWITT, D ;
GRAY, J .
COMMUNICATIONS OF THE ACM, 1992, 35 (06) :85-98
[9]  
DeWitt D. J., 1981, Proceedings of the Seventh International Conference on Very Large Data Bases, P199
[10]  
DeWitt D. J., 1984, SIGMOD Record, V14, P1, DOI 10.1145/971697.602261