Abstract
3D charge-trap based SSDs have become an emerging storage solution in recent years. One-shot-programming in 3D charge-trap based SSDs could deliver a maximized system I/O throughput at the cost of degraded Quality-of-Service performance. This paper proposes RLOSP, a reinforcement learning based approach to improve the QoS performance for 3D charge-trap based SSDs. By learning the I/O patterns of the workload environments as well as the device internal status, the proposed approach could properly choose requests in the device queue, and allocate physical addresses for these requests during one-shot-programming. In this manner, the storage device could deliver an improved QoS performance. Experimental results reveal that the proposed approach could reduce the worst-case latency at the \(99.9^{th}\) percentile by 37.5–59.2%, with an optimal system I/O throughput.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
15 December 2020
In the published version the subfigures (g) and (h) in Fig. 7 have been removed.
References
Chen, J., Wang, Y., Zhou, A.C., Mao, R., Li, T.: PATCH: process-variation-resilient space allocation for open-channel SSD with 3D flash. In: Teich, J., Fummi, F. (eds.) Design, Automation & Test in Europe Conference & Exhibition, DATE 2019, Florence, Italy, 25–29 March 2019, pp. 216–221. IEEE (2019). https://doi.org/10.23919/DATE.2019.8715197
Chen, S., Chang, Y., Liang, Y., Wei, H., Shih, W.: An erase efficiency boosting strategy for 3D charge trap NAND flash. IEEE Trans. Comput. 67(9), 1246–1258 (2018). https://doi.org/10.1109/TC.2018.2818118
Chen, S.H., Chen, Y.T., Wei, H.W., Shih, W.K.: Boosting the performance of 3D charge trap nand flash with asymmetric feature process size characteristic. In: 2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2017)
Chen, T., Chang, Y., Ho, C., Chen, S.: Enabling sub-blocks erase management to boost the performance of 3D NAND flash memory. In: Proceedings of the 53rd Annual Design Automation Conference, DAC 2016, Austin, TX, USA, 5–9 June 2016, pp. 92:1–92:6. ACM (2016). https://doi.org/10.1145/2897937.2898018
Ji, C., et al.: Inspection and characterization of app file usage in mobile devices. ACM Trans. Storage (TOS) 16(4), 1–25 (2020)
Du, Y., Zhou, Y., Zhang, M., Liu, W., Xiong, S.: Adapting layer RBERs variations of 3D flash memories via multi-granularity progressive LDPC reading. In: Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019, Las Vegas, NV, USA, 02–06 June 2019, p. 37. ACM (2019). https://doi.org/10.1145/3316781.3317759
Samsung Electronics: K9F8G08UXM Flash Memory Datasheet, March 2007
Gugnani, S., Lu, X., Panda, D.K.: Analyzing, modeling, and provisioning QoS for NVMe ssds. In: Sill, A., Spillner, J. (eds.) 11th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2018, Zurich, Switzerland, 17–20 December 2018, pp. 247–256. IEEE Computer Society (2018). https://doi.org/10.1109/UCC.2018.00033
Hu, Y., Jiang, H., Feng, D., Tian, L., Luo, H., Zhang, S.: Performance impact and interplay of SSD parallelism through advanced commands, allocation strategy and data granularity. In: Proceedings of the International Conference on Supercomputing, pp. 96–107 (2011)
Jung, M., Choi, W., Srikantaiah, S., Yoo, J., Kandemir, M.T.: HIOS: a host interface I/O scheduler for solid state disks. In: ACM/IEEE 41st International Symposium on Computer Architecture, ISCA 2014, Minneapolis, MN, USA, 14–18 June 2014, pp. 289–300. IEEE Computer Society (2014). https://doi.org/10.1109/ISCA.2014.6853216
Jung, S., Song, Y.H.: Garbage collection for low performance variation in NAND flash storage systems. IEEE Trans. CAD Integr. Circ. Syst. 34(1), 16–28 (2015). https://doi.org/10.1109/TCAD.2014.2369501
Kang, W., Shin, D., Yoo, S.: Reinforcement learning-assisted garbage collection to mitigate long-tail latency in SSD. ACM Trans. Embedded Comput. Syst. 16(5s), 134:1–134:20 (2017). https://doi.org/10.1145/3126537
Lee, H., Lee, M., Eom, Y.I.: Mitigating write interference on SSD in home cloud server. In: IEEE International Conference on Consumer Electronics, ICCE 2018, Las Vegas, NV, USA, 12–14 January 2018, pp. 1–3. IEEE (2018). https://doi.org/10.1109/ICCE.2018.8326216
Liu, C., Kotra, J., Jung, M., Kandemir, M.T.: PEN: design and evaluation of partial-erase for 3D NAND-based high density SSDs. In: Agrawal, N., Rangaswami, R. (eds.) 16th USENIX Conference on File and Storage Technologies, FAST 2018, Oakland, CA, USA, 12–15 February 2018, pp. 67–82. USENIX Association (2018). https://www.usenix.org/conference/fast18/presentation/liu
Liu, C., Kotra, J.B., Jung, M., Kandemir, M.T., Das, C.R.: SOML read: rethinking the read operation granularity of 3D NAND SSDs. In: Bahar, I., Herlihy, M., Witchel, E., Lebeck, A.R. (eds.) Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2019, Providence, RI, USA, 13–17 April 2019, pp. 955–969. ACM (2019). https://doi.org/10.1145/3297858.3304035
Lu, Y., Shu, J., Zhang, J.: Mitigating synchronous I/O overhead in file systems on open-channel SSDs. TOS 15(3), 17:1–17:25 (2019). https://doi.org/10.1145/3319369
Luo, Y., Ghose, S., Cai, Y., Haratsch, E.F., Mutlu, O.: HeatWatch: improving 3D NAND flash memory device reliability by exploiting self-recovery and temperature awareness. In: IEEE International Symposium on High Performance Computer Architecture, HPCA 2018, Vienna, Austria, 24–28 February 2018, pp. 504–517. IEEE Computer Society (2018). https://doi.org/10.1109/HPCA.2018.00050
Nguyen, D.T., Zhou, G., Xing, G.: Poster: towards reducing smartphone application delay through read/write isolation. In: Campbell, A.T., Kotz, D., Cox, L.P., Mao, Z.M. (eds.) The 12th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2014, Bretton Woods, NH, USA, 16–19 June 2014, p. 378. ACM (2014). https://doi.org/10.1145/2594368.2601458
Wang, X., Li, J., Li, J., Yan, H.: Multilevel similarity model for high-resolution remote sensing image registration. Inf. Sci. 505 (2019). https://doi.org/10.1016/j.ins.2019.07.023
Wu, C., et al.: Maximizing I/O throughput and minimizing performance variation via reinforcement learning based I/O merging for SSDs. IEEE Trans. Comput. 69(1), 72–86 (2020). https://doi.org/10.1109/TC.2019.2938956
Wu, F., Lu, Z., Zhou, Y., He, X., Tan, Z., Xie, C.: OSPADA: one-shot programming aware data allocation policy to improve 3D NAND flash read performance. In: 36th IEEE International Conference on Computer Design, ICCD 2018, Orlando, FL, USA, 7–10 October 2018, pp. 51–58. IEEE Computer Society (2018). https://doi.org/10.1109/ICCD.2018.00018
Xie, W., Chen, Y.: A cache management scheme for hiding garbage collection latency in flash-based solid state drives. In: 2015 IEEE International Conference on Cluster Computing, CLUSTER 2015, Chicago, IL, USA, 8–11 September 2015, pp. 486–487. IEEE Computer Society (2015). https://doi.org/10.1109/CLUSTER.2015.75
Yan, S., et al.: Tiny-tail flash: near-perfect elimination of garbage collection tail latencies in NAND SSDs. TOS 13(3), 22:1–22:26 (2017). https://doi.org/10.1145/3121133
Zhu, Z., Han, G., Jia, G., Shu, L.: Modified DenseNet for automatic fabric defect detection with edge computing for minimizing latency. IEEE Internet Things J. 7(10), 9623–9636 (2020)
Zhu, Z., Tan, L., Li, Y., Ji, C.: PHDFS: optimizing i/o performance of HDFS in deep learning cloud computing platform. J. Syst. Arch. 109, 101810 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, Z., Wu, C., Ji, C., Wang, X. (2020). Machine Learning Assisted OSP Approach for Improved QoS Performance on 3D Charge-Trap Based SSDs. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12488. Springer, Cham. https://doi.org/10.1007/978-3-030-62463-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-62463-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62462-0
Online ISBN: 978-3-030-62463-7
eBook Packages: Computer ScienceComputer Science (R0)