Towards Sustainable High-Performance Transaction Processing in Cloud-based DBMS

被引:0
|
作者
Sul, Woong [1 ]
Yeom, Heon Y. [1 ]
Jung, Hyungsoo [2 ]
机构
[1] Seoul Natl Univ, Seoul, South Korea
[2] Hanyang Univ, Seoul, South Korea
关键词
D O I
10.1007/s10586-018-2826-3
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Cloud-based databases often decouple database instances from physical storage to provide reliability and high availability to users. This design can robustly handle a single point of failure but needs substantial effort to attain good performance. In this paper, we analyze the decoupled architecture and present important optimization issues that we found while implementing this design. For implementing the prototyped system, we decouple MariaDB into a database instance and storage managing both transaction log and data pages. We also explore design considerations for transaction processing performance in the front-end side and efficient way of guaranteeing data durability in the back-end side. We evaluate the prototyped system using standard database benchmarks, and experimental results show that adopting the decoupled architecture for cloud-based DBMSs needs to address numerous optimization issues for achieving better performance.
引用
收藏
页码:135 / 145
页数:11
相关论文
共 50 条
  • [1] Towards Sustainable High-Performance Transaction Processing in Cloud-based DBMS: Design considerations and optimization for transaction processing performance in service-oriented DBMS organization
    Sul W.
    Yeom H.Y.
    Jung H.
    Cluster Computing, 2019, 22 (01) : 135 - 145
  • [2] PERFORMANCE ISSUES IN HIGH-PERFORMANCE TRANSACTION PROCESSING ARCHITECTURES
    BHIDE, A
    STONEBRAKER, M
    LECTURE NOTES IN COMPUTER SCIENCE, 1989, 359 : 277 - 300
  • [3] A Framework for Supporting Repetition and Evaluation in the Process of Cloud-Based DBMS Performance Benchmarking
    Erdelt, Patrick K.
    PERFORMANCE EVALUATION AND BENCHMARKING (TPCTC 2020), 2021, 12752 : 75 - 92
  • [4] High-Performance Transaction Processing in Journaling File Systems
    Son, Yongseok
    Kim, Sunggon
    Yeom, Young
    Han, Hyuck
    PROCEEDINGS OF THE 16TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES, 2018, : 227 - 240
  • [5] Towards Cloud-Based Knowledge Capturing Based on Natural Language Processing
    Nawroth, Christian
    Schmedding, Matthaeus
    Brocks, Holger
    Kaufmann, Michael
    Fuchs, Michael
    Hemmje, Matthias
    1ST INTERNATIONAL CONFERENCE ON CLOUD FORWARD: FROM DISTRIBUTED TO COMPLETE COMPUTING, 2015, 68 : 206 - 216
  • [6] Transaction Management for Cloud-Based Graph Databases
    Koloniari, Georgia
    Pitoura, Evaggelia
    ALGORITHMIC ASPECTS OF CLOUD COMPUTING, ALGOCLOUD 2015, 2016, 9511 : 99 - 113
  • [7] Two-Tier Storage DBMS for High-Performance Query Processing
    Eo, Sang-Hun
    Li, Yan
    Kim, Ho-Seok
    Bae, Hae-Young
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2008, 4 (01): : 9 - 16
  • [8] Towards high-performance, efficient and sustainable material processing technologies for aerospace applications
    Jun MA
    MWFU
    Stefania BRUSCHI
    Heng LI
    Chinese Journal of Aeronautics, 2025, 38 (01) : 6 - 7+3
  • [9] Towards high-performance, efficient and sustainable material processing technologies for aerospace applications
    Ma, Jun
    Fu, M. . W.
    Bruschi, Stefania
    Li, Heng
    CHINESE JOURNAL OF AERONAUTICS, 2025, 38 (01)
  • [10] A Cloud-based Disassembly Planning Approach towards Sustainable Management of WEEE
    Xia, Kai
    Gao, Liang
    Chao, Kuo-Ming
    Wang, Lihui
    2015 IEEE 12TH INTERNATIONAL CONFERENCE ON E-BUSINESS ENGINEERING (ICEBE), 2015, : 203 - 208