Advertisement

Datenbank-Spektrum

, Volume 18, Issue 2, pp 121–127 | Cite as

On the Diversity of Memory and Storage Technologies

  • Ismail Oukid
  • Lucas Lersch
Kurz erklärt
  • 120 Downloads

Abstract

The last decade has seen tremendous developments in memory and storage technologies, starting with Flash Memory and continuing with the upcoming Storage-Class Memories. Combined with an explosion of data processing, data analytics, and machine learning, this led to a segmentation of the memory and storage market. Consequently, the traditional storage hierarchy, as we know it today, might be replaced by a multitude of storage hierarchies, with potentially different depths, each tailored for specific workloads. In this context, we explore in this “Kurz Erklärt” the state of memory technologies and reflect on their future use with a focus on data management systems.

Keywords

Storage Main Memory Flash SSD DRAM Storage-Class Memory Non-Volatile Memory 

References

  1. 1.
    Appuswamy R, Borovica R, Graefe G, Ailamaki A (2017) The five minute rule thirty years later and its impact on the storage hierarchy. Proceedings of the 7th International Workshop on Accelerating Analytics and Data Management Systems Using Modern Processor and Storage Architectures.Google Scholar
  2. 2.
    Arulraj J, Perron M, Pavlo A (2016) Write-behind logging. Proceedings VLDB Endowment 10(4):337–348CrossRefGoogle Scholar
  3. 3.
    Bjørling M (2018) Open-Channel Solid State Drives. https://openchannelssd.readthedocs.io/en/latest/. Accessed 25 Apr 2018
  4. 4.
    Bjørling M, González J, Bonnet P (2017) LightNVM: the Linux open-channel SSD subsystem. 15th USENIX Conference on File and Storage Technologies (FAST), USENIX Association, pp 359–374Google Scholar
  5. 5.
    Boroumand A, Ghose S, Kim Y, Ausavarungnirun R, Shiu E, Thakur R, Kim D, Kuusela A, Knies A, Ranganathan P et al (2018) Google workloads for consumer devices: mitigating data movement bottlenecks. Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems, ACM, pp 316–331Google Scholar
  6. 6.
    Chen S, Jin Q (2015) Persistent B+-trees in non-volatile main memory. Proceedings VLDB Endowment 8(7):786–797CrossRefGoogle Scholar
  7. 7.
    Chen S, Gibbons PB, Nath S (2011) Rethinking database algorithms for phase change memory. Fifth Biennial Conference on Innovative Data Systems Research (CIDR), pp 21–31Google Scholar
  8. 8.
    Choe J (2017) Intel 3D XPoint Memory Die Removed from Intel Optane PCM (Phase Change Memory). http://techinsights.com/about-techinsights/overview/blog/intel-3D-xpoint-memory-die-removed-from-intel-optane-pcm/. Accessed 25 Apr 2018Google Scholar
  9. 9.
    Dayarathna M, Wen Y, Fan R (2016) Data center energy consumption modeling: a survey. IEEE Commun Surv Tutor 18(1):732–794CrossRefGoogle Scholar
  10. 10.
    Dong X, Wu X, Sun G, Xie Y, Li H, Chen Y (2008) Circuit and microarchitecture evaluation of 3D stacking magnetic RAM (MRAM) as a universal memory replacement. 45th ACM/IEEE Design Automation Conference., IEEE, pp 554–559Google Scholar
  11. 11.
    Fang R, Hsiao HI, He B, Mohan C, Wang Y (2011) High performance database logging using storage class memory. IEEE 27th International Conference on Data Engineering (ICDE). IEEE, Hannover, pp 1221–1231Google Scholar
  12. 12.
    Gen-Z Consortium (2018) Gen-Z Core Specification 1.0. https://genzconsortium.org/specifications/core-specification-1-0/. Accessed 25 Apr 2018
  13. 13.
    Govoreanu B, Kar G, Chen Y, Paraschiv V, Kubicek S, Fantini A, Radu I, Goux L, Clima S, Degraeve R et al (2011) 10x10nm 2 Hf/HfO x crossbar resistive RAM with excellent performance, reliability and low-energy operation. IEEE International Electron Devices Meeting (IEDM). IEEE, Washington, pp 31–36Google Scholar
  14. 14.
    Hardock S, Petrov I, Gottstein R, Buchmann A (2013) NoFTL: database systems on FTL-less flash storage. Proceedings VLDB Endowment 6(12):1278–1281CrossRefGoogle Scholar
  15. 15.
    Hardock S, Petrov I, Gottstein R, Buchmann A (2017) From in-place updates to in-place appends: revisiting out-of-place updates on flash. Proceedings of the 2017 ACM International Conference on Management of Data (SIGMOD). ACM, Chicago, pp 1571–1586Google Scholar
  16. 16.
    Huang J, Schwan K, Qureshi MK (2014) NVRAM-aware logging in transaction systems. Proceedings VLDB Endowment 8(4):389–400CrossRefGoogle Scholar
  17. 17.
  18. 18.
  19. 19.
    Intel (2018) Persistent Memory Development Kit. http://pmem.io/pmdk/libpmem/. Accessed 25 Apr 2018
  20. 20.
  21. 21.
    ITRS (2015) International Technology Roadmap for Semiconductors 2.0, Beyond CMOS. http://www.semiconductors.org/clientuploads/Research_Technology/ITRS/2015/6_2015%20ITRS%202.0%20Beyond%20CMOS.pdf. Accessed 25 Apr 2018Google Scholar
  22. 22.
    Kimura H (2015) FOEDUS: OLTP engine for a thousand cores and NVRAM. Proceedings of the 2015 ACM International Conference on Management of Data (SIGMOD). Melbourne, ACM, pp 691–706Google Scholar
  23. 23.
    Klima T (2016) Using Non-volatile Memory (NVDIMM-N) as Byte-Addressable Storage in Windows Server 2016. https://channel9.msdn.com/events/build/2016/p470. Accessed 25 Apr 2018
  24. 24.
    Klimovic A, Litz H, Kozyrakis C (2017) Reflex: remote flash ≈ local flash. Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). ACM, Xi’an, pp 345–359Google Scholar
  25. 25.
    Kraft B (2017) SSD-Langzeittest beendet: Exitus bei 9,1 Petabyte. https://www.heise.de/newsticker/meldung/SSD-Langzeittest-beendet-Exitus-bei-9-1-Petabyte-3755009.html. Accessed 25 Apr 2018Google Scholar
  26. 26.
    Lantz P, Rao DS, Kumar S, Sankaran R, Jackson J (2014) Yat: a validation framework for persistent memory software. USENIX Annual Technical Conference, pp 433–438Google Scholar
  27. 27.
    Lee BC, Zhou P, Yang J, Zhang Y, Zhao B, Ipek E, Mutlu O, Burger D (2010) Phase-change technology and the future of main memory. IEEE Micro.  https://doi.org/10.1109/MM.2010.24 Google Scholar
  28. 28.
    Lee SK, Lim KH, Song H, Nam B, Noh SH (2017) Wort: write optimal radix tree for persistent memory storage systems. 15th USENIX Conference on File and Storage Technologies (FAST). USENIX Association, Santa Clara, pp 257–270Google Scholar
  29. 29.
    Lehner W (2017) The data center under your desk: how disruptive is modern hardware for DB system design? Proceedings VLDB Endowment 10(12):2018–2019CrossRefGoogle Scholar
  30. 30.
    Lehner W, Ungethüm A, Habich D (2018) Diversity of processing units. Datenbank Spektrum 18(1):57–62CrossRefGoogle Scholar
  31. 31.
    Lersch L, Oukid I, Schreter I, Lehner W (2017) Rethinking DRAM caching for LSMs in an NVRAM environment. 21th European Conference on Advances in Databases and Information Systems (ADBIS). Springer, NicosiaCrossRefGoogle Scholar
  32. 32.
    Levandoski JJ, Lomet DB, Sengupta S (2013) The Bw-tree: a B-tree for new hardware platforms. IEEE 29th International Conference on Data Engineering (ICDE). IEEE, Brisbane, pp 302–313Google Scholar
  33. 33.
    Li Y, He B, Yang RJ, Luo Q, Yi K (2010) Tree indexing on solid state drives. Proceedings VLDB Endowment 3(1-2):1195–1206CrossRefGoogle Scholar
  34. 34.
    Linux (2018) LIBNVDIMM Documentation. https://www.kernel.org/doc/Documentation/nvdimm/nvdimm.txt. Accessed 25 Apr 2018
  35. 35.
    Micron (2018) 3D XPoint Technology. https://www.micron.com/products/advanced-solutions/3d-xpoint-technology. Accessed 25 Apr 2018
  36. 36.
    Mike P, Intel (2016) An Intro to MCDRAM (High-Bandwidth Memory) on Knights Landing. https://software.intel.com/en-us/blogs/2016/01/20/an-intro-to-mcdram-high-bandwidth-memory-on-knights-landing. Accessed 25 Apr 2018Google Scholar
  37. 37.
    Mittal S, Vetter JS (2016) A survey of software techniques for using non-volatile memories for storage and main memory systems. IEEE Trans Parallel Distrib Syst 27(5):1537–1550CrossRefGoogle Scholar
  38. 38.
    Mutlu O (2013) Memory scaling: a systems architecture perspective. Fifth IEEE International Memory Workshop (IMW). IEEE, Monterey, pp 21–25Google Scholar
  39. 39.
    Nanavati M et al (2016) Non-volatile storage: implications of the datacenter’s shifting center. Commun Acm 50(1):58–63Google Scholar
  40. 40.
    OpenCAPI Consortium (2018) OpenCAPI Specifications. https://opencapi.org/technical/specifications/. Accessed 25 Apr 2018
  41. 41.
    Oukid I, Lehner W, Kissinger T, Willhalm T, Bumbulis P (2015) Instant recovery for main-memory databases. Seventh Biennial Conference on Innovative Data Systems Research (CIDR).Google Scholar
  42. 42.
    Oukid I, Booss D, Lespinasse A, Lehner W (2016) On testing persistent-memory-based software. Proceedings of the 12th International Workshop on Data Management on New Hardware. ACM, San Francisco, p 5Google Scholar
  43. 43.
    Oukid I, Lasperas J, Nica A, Willhalm T, Lehner W (2016) FPtree: a hybrid SCM-DRAM persistent and concurrent B‑tree for storage class memory. Proceedings of the 2016 ACM International Conference on Management of Data (SIGMOD). ACM, San Francisco, pp 371–386Google Scholar
  44. 44.
    Oukid I, Booss D, Lespinasse A, Lehner W, Willhalm T, Gomes G (2017) Memory management techniques for large-scale persistent-main-memory systems. Proceedings VLDB Endowment 10(11):1166–1177CrossRefGoogle Scholar
  45. 45.
    van Renen A, Leis V, Kemper A, Neumann T, Hashida T, Oe K et al (2018) Managing non-volatile memory in database systems. Proceedings of the 2018 ACM International Conference on Management of Data (SIGMOD). ACM, Houston. (to appear)CrossRefGoogle Scholar
  46. 46.
  47. 47.
  48. 48.
    Schroeder B, Lagisetty R, Merchant A (2016) Flash reliability in production: the expected and the unexpected. 14th USENIX FAST.Google Scholar
  49. 49.
  50. 50.
    Statista (2017) Global market share held by DRAM chip vendors 2011-2017. https://www.statista.com/statistics/271726/global-market-share-held-by-dram-chip-vendors-since-2010/. Accessed 25 Apr 2018Google Scholar
  51. 51.
    Viglas SD (2014) Write-limited sorts and joins for persistent memory. Proceedings VLDB Endowment 7(5):413–424CrossRefGoogle Scholar
  52. 52.
    Wang T, Johnson R (2014) Scalable logging through emerging non-volatile memory. Proceedings VLDB Endowment 7(10):865–876CrossRefGoogle Scholar
  53. 53.
    Yang J, Wei Q, Wang C, Chen C, Yong K, He B (2015) NV-tree: a consistent and workload-adaptive tree structure for non-volatile memory. IEEE Trans Comput 65(7):2169–2183MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag GmbH Deutschland, ein Teil von Springer Nature 2018

Authors and Affiliations

  1. 1.SAP SEWalldorfGermany
  2. 2.TU DresdenDresdenGermany

Personalised recommendations