research-article

Scalable logging through emerging non-volatile memory

Authors:

Tianzheng Wang and

Ryan JohnsonAuthors Info & Claims

Proceedings of the VLDB Endowment, Volume 7, Issue 10

Pages 865 - 876

https://doi.org/10.14778/2732951.2732960

Published: 01 June 2014 Publication History

Abstract

Emerging byte-addressable, non-volatile memory (NVM) is fundamentally changing the design principle of transaction logging. It potentially invalidates the need for flush-before-commit as log records are persistent immediately upon write. Distributed logging---a once prohibitive technique for single node systems in the DRAM era---becomes a promising solution to easing the logging bottleneck because of the non-volatility and high performance of NVM.

In this paper, we advocate NVM and distributed logging on multicore and multi-socket hardware. We identify the challenges brought by distributed logging and discuss solutions. To protect committed work in NVM-based systems, we propose passive group commit, a lightweight, practical approach that leverages existing hardware and group commit. We expect that durable processor cache is the ultimate solution to protecting committed work and building reliable, scalable NVM-based systems in general. We evaluate distributed logging with logging-intensive workloads and show that distributed logging can achieve as much as ~3x speedup over centralized logging in a modern DBMS and that passive group commit only induces minuscule overhead.

References

[1]

AgigaTech. AGIGARAM non-volatile system, 2013.

[2]

Bhandari, K., Chakrabarti, D. R., and Boehm, H.-J. Implications of CPU caching on byte-addressable non-volatile memory programming. HP Technical Report HPL-2012-236, 2012.

[3]

Buck, D. A. Ferroelectrics for digital information storage and switching. MIT Report R-212, 1952.

[4]

Caulfield, A. M., et al. Understanding the impact of emerging non-volatile memories on high-performance, IO-intensive computing. SC, pp. 1--11, 2010.

Digital Library

[5]

Chen, S. FlashLogging: exploiting flash devices for synchronous logging performance. SIGMOD, pp. 73--86, 2009.

Digital Library

[6]

Chen, S., Gibbons, P. B., and Nath, S. Rethinking database algorithms for phase change memory. CIDR, pp. 21--31, 2011.

[7]

Cho, S. and Lee, H. Flip-N-Write: A simple deterministic technique to improve PRAM write performance, energy and endurance. MICRO, pp. 347--357, 2009.

Digital Library

[8]

Coburn, J., et al. From ARIES to MARS: Transaction support for next-generation, solid-state drives. SOSP, pp. 197--212, 2013.

Digital Library

[9]

Condit, J., et al. Better I/O through byte-addressable, persistent memory. SOSP, pp. 133--146, 2009.

Digital Library

[10]

Fang, R., et al. High performance database logging using storage class memory. ICDE, pp. 1221--1231, 2011.

Digital Library

[11]

Gao, S., et al. PCMLogging: reducing transaction logging overhead with PCM. CIKM, pp. 2401--2404, 2011.

Digital Library

[12]

Gawlick, D. and Kinkade, D. Varieties of concurrency control in IMS/VS fast path. HP Technical Report TR-85.6, 1985.

[13]

Graefe, G. A survey of b-tree logging and recovery techniques. TODS, 37(1): 1:1--1:35, 2012.

Digital Library

[14]

Hosomi, M., et al. A novel nonvolatile memory with spin torque transfer magnetization switching: spin-ram. IEDM, pp. 459--462, 2005.

[15]

Intel. Write Combining Memory Implementation Guidelines, 1998.

[16]

Intel. Intel 64 and IA-32 Architectures Optimization Reference Manual, 2007.

[17]

Jiang, L., et al. Improving write operations in MLC phase change memory. HPCA, pp. 1--10, 2012.

Digital Library

[18]

Jog, A., et al. Cache revive: Architecting volatile STT-RAM caches for enhanced performance in CMPs. DAC, pp. 243--252, 2012.

Digital Library

[19]

Johnson, R., Pandis, I., and Ailamaki, A. Improving OLTP scalability using speculative lock inheritance. PVLDB, pp. 479--489, 2009.

Digital Library

[20]

Johnson, R., et al. Shore-MT: a scalable storage manager for the multicore era. EDBT, pp. 24--35, 2009.

Digital Library

[21]

Johnson, R., et al. Aether: a scalable approach to logging. PVLDB, pp. 681--692, 2010.

Digital Library

[22]

Johnson, R., et al. Scalability of write-ahead logging on multicore and multisocket hardware. VLDBJ, pp. 239--263, 2012.

Digital Library

[23]

Kawahara, T. Scalable spin-transfer torque RAM technology for normally-off computing. IEEE Design Test of Computers, 28(1):52--63, 2011.

Digital Library

[24]

Lamport, L. Time, clocks, and the ordering of events in a distributed system. CACM, pp. 558--565, 1978.

Digital Library

[25]

Lee, B. C., Ipek, E., Mutlu, O., and Burger, D. Architecting phase change memory as a scalable DRAM alternative. ISCA, pp. 2--13, 2009.

Digital Library

[26]

Lomet, D., Anderson, R., Rengarajan, T., and Spiro, P. How the Rdb/VMS data sharing system became fast, 1992.

[27]

Mellor, C. HP 100TB Memristor drives by 2018 if you're lucky, admits tech titan. The Register, 2013.

[28]

Mohan, C., et al. ARIES: a transaction recovery method supporting fine-granularity locking and partial roll backs using write-ahead logging. TODS, 17(1):94--162, 1992.

Digital Library

[29]

Narayanan, D. and Hodson, O. Whole-system persistence. ASPLOS, pp. 401--410, 2012.

Digital Library

[30]

Neuvonen, S., Wolski, A., Manner, M., and Raatikka, V. Telecom Application Transaction Processing Benchmark.

[31]

On, S. T., et al. Flag Commit: Supporting efficient transaction recovery in flash-based DBMSs. TKDE, 24(9):1624--1639, 2012.

Digital Library

[32]

Ooishi, M. Rohm demonstrates nonvolatile CPU, power consumption cut by 90%. Tech-On!, 2007.

[33]

Pandis, I., Johnson, R., Hardavellas, N., and Ailamaki, A. Data-oriented transaction execution. PVLDB, pp. 928--939, 2010.

Digital Library

[34]

Pandis, I., Tözün, P., Johnson, R., and Ailamaki, A. PLP: Page latch-free shared-everything OLTP. PVLDB, pp. 610--621, 2011.

Digital Library

[35]

Pelley, S., Wenisch, T. F., Gold, B. T., and Bridge, B. Storage management in the NVRAM era. PVLDB, pp. 121--132, 2014.

Digital Library

[36]

Qureshi, M. K., et al. Enhancing lifetime and security of PCM-based main memory with Start-gap wear leveling. MICRO, pp. 14--23, 2009.

Digital Library

[37]

Ramakrishnan, R. and Gehrke, J. Database Management Systems. McGraw-Hill, 3rd edn., 2002.

Digital Library

[38]

Saadeldeen, H., et al. Memristors for neural branch prediction: A case study in strict latency and write endurance challenges. CF, pp. 26:1--26:10, 2013.

Digital Library

[39]

Speer, J. and Kirchberg, M. C-ARIES: A multi-threaded version of the ARIES recovery algorithm. Database and Expert Systems Applications, pp. 319--328, 2007.

Digital Library

[40]

Stonebraker, M., et al. The end of an architectural era: (it's time for a complete rewrite). PVLDB, pp. 1150--1160, 2007.

Digital Library

[41]

Strukov, D. B., Snider, G. S., Stewart, D. R., and Williams, R. S. The missing memristor found. Nature, 453(7191):80--83, 2008.

[42]

Transaction Processing Performance Council. TPC benchmarks B and C.

[43]

Viking Technology. ArxCis-NV NVDIMM, 2013.

[44]

Wong, H. S. P., et al. Phase change memory. Proceedings of the IEEE, 98(12):2201--2227, 2010.

[45]

Zhao, J., et al. Kiln: closing the performance gap between systems with and without persistence support. MICRO, pp. 421--432, 2013.

Digital Library

[46]

Zhou, P., Zhao, B., Yang, J., and Zhang, Y. A durable and energy efficient main memory using phase change memory technology. ISCA, pp. 14--23, 2009.

Digital Library

Cited By

Chen ZHu DChe WSun JChen H(2024)A quantitative evaluation of persistent memory hash indexesThe VLDB Journal — The International Journal on Very Large Data Bases10.1007/s00778-023-00812-133:2(375-397)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.1007/s00778-023-00812-1
Huang KWang TZhou QMeng Q(2023)The Art of Latency Hiding in Modern Database EnginesProceedings of the VLDB Endowment10.14778/3632093.363211717:3(577-590)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.14778/3632093.3632117
Koutsoukos DBhartia RFriedman MKlimovic AAlonso G(2023)NVM: Is it Not Very Meaningful for Databases?Proceedings of the VLDB Endowment10.14778/3603581.360358616:10(2444-2457)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.14778/3603581.3603586
Show More Cited By

Recommendations

Managing Non-Volatile Memory in Database Systems
SIGMOD '18: Proceedings of the 2018 International Conference on Management of Data

Non-volatile memory (NVM) is a new storage technology that combines the performance and byte addressability of DRAM with the persistence of traditional storage devices like flash (SSD). While these properties make NVM highly promising, it is not yet ...
Read More
Efficient logging in non-volatile memory by exploiting coherency protocols

Non-volatile memory technologies such as PCM, ReRAM and STT-RAM allow data to be saved to persistent storage significantly faster than hard drives or SSDs. Many of the use cases for non-volatile memory requires persistent logging since it enables a set ...
Read More
Redesign the Memory Allocator for Non-Volatile Main Memory
Special Issue on Hardware and Algorithms for Learning On-a-chip and Special Issue on Alternative Computing Systems

The non-volatile memory (NVM) has the merits of byte-addressability, fast speed, persistency and low power consumption, which make it attractive to be used as main memory. Commonly, user process dynamically acquires memory through memory allocators. ...
Read More

Comments

Information & Contributors

Information

Published In

cover image Proceedings of the VLDB Endowment

Proceedings of the VLDB Endowment Volume 7, Issue 10

June 2014

146 pages

ISSN:2150-8097

Editors:
H. V. Jagadish
University of Michigan
,
Aoying Zhou
East Normal University, China

Issue’s Table of Contents

Publisher

VLDB Endowment

Publication History

Published: 01 June 2014

Published in PVLDB Volume 7, Issue 10

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

109
Total Citations
View Citations
774
Total Downloads

Downloads (Last 12 months)52
Downloads (Last 6 weeks)4

Other Metrics

View Author Metrics

Citations

Cited By

Chen ZHu DChe WSun JChen H(2024)A quantitative evaluation of persistent memory hash indexesThe VLDB Journal — The International Journal on Very Large Data Bases10.1007/s00778-023-00812-133:2(375-397)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.1007/s00778-023-00812-1
Huang KWang TZhou QMeng Q(2023)The Art of Latency Hiding in Modern Database EnginesProceedings of the VLDB Endowment10.14778/3632093.363211717:3(577-590)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.14778/3632093.3632117
Koutsoukos DBhartia RFriedman MKlimovic AAlonso G(2023)NVM: Is it Not Very Meaningful for Databases?Proceedings of the VLDB Endowment10.14778/3603581.360358616:10(2444-2457)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.14778/3603581.3603586
An MPark JWang TNam BLee S(2023)NV-SQL: Boosting OLTP Performance with Non-Volatile DIMMsProceedings of the VLDB Endowment10.14778/3583140.358315916:6(1453-1465)Online publication date: 1-Feb-2023
https://dl.acm.org/doi/10.14778/3583140.3583159
Ruan CZhang YBi CMa XChen HLi FYang XLi CAboulnaga AXu YAamodt TJerger NSwift M(2023)Persistent Memory Disaggregation for Cloud-Native Relational DatabasesProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 310.1145/3582016.3582055(498-512)Online publication date: 25-Mar-2023
https://dl.acm.org/doi/10.1145/3582016.3582055
Chen ZYang XLi FCheng XHu QMiao ZXie RWu XWang KSong ZSun HZhuang ZYang YXu JYin LZhou WWang S(2022)CloudJumpProceedings of the VLDB Endowment10.14778/3554821.355483415:12(3432-3444)Online publication date: 1-Aug-2022
https://dl.acm.org/doi/10.14778/3554821.3554834
Freitag MKemper ANeumann T(2022)Memory-optimized multi-version concurrency control for disk-based database systemsProceedings of the VLDB Endowment10.14778/3551793.355183215:11(2797-2810)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.14778/3551793.3551832
He YLu DHuang KWang T(2022)Evaluating persistent memory range indexesProceedings of the VLDB Endowment10.14778/3551793.355180815:11(2477-2490)Online publication date: 29-Sep-2022
https://dl.acm.org/doi/10.14778/3551793.3551808
Lee SLerner ARyser APark KJeon CPark JSong YCudré-Mauroux PIves ZBonifati AEl Abbadi A(2022)X-SSD: A Storage System with Native Support for Database Logging and ReplicationProceedings of the 2022 International Conference on Management of Data10.1145/3514221.3526188(988-1002)Online publication date: 10-Jun-2022
https://dl.acm.org/doi/10.1145/3514221.3526188
Ziegler TBinnig CLeis VIves ZBonifati AEl Abbadi A(2022)ScaleStore: A Fast and Cost-Efficient Storage Engine using DRAM, NVMe, and RDMAProceedings of the 2022 International Conference on Management of Data10.1145/3514221.3526187(685-699)Online publication date: 10-Jun-2022
https://dl.acm.org/doi/10.1145/3514221.3526187
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents