Abstract
Hybrid Shingled Magnetic Recording (H-SMR) drives are the most recently developed SMR drives, which allow dynamic conversion of the recording format between Conventional Magnetic Recording (CMR) and SMR on a single disk drive. We identify the unique opportunities of H-SMR drives to manage the tradeoffs between performance and capacity, including the possibility of adjusting the SMR area capacity based on storage usage and the flexibility of dynamic data swapping between the CMR area and SMR area.
We design and implement FluidSMR, an adaptive management scheme for hybrid SMR Drives, to fully utilize H-SMR drives under different workloads and capacity usages. FluidSMR has a two-phase allocation scheme to support a growing usage of the H-SMR drive. The scheme can intelligently determine the sizes of the CMR and the SMR space in an H-SMR drive based on the dynamic changing of workloads. Moreover, FluidSMR uses a cache in the CMR region, managed by a proposed loop-back log policy, to reduce the overhead of updates to the SMR region.
Evaluations using enterprise traces demonstrate that FluidSMR outperforms baseline schemes in various workloads by decreasing the average I/O latency and effectively reducing/controlling the performance impact of the format conversion between CMR and SMR.
- [1] . 2015. Skylight—A window on shingled disk operation. ACM Trans. Stor. 11, 4, Article
16 (Oct. 2015), 28 pages. https://doi.org/10.1145/2821511Google Scholar - [2] . 2011. Data management and layout for shingled magnetic recording. IEEE Trans. Magn. 47, 10 (2011), 3691–3697.Google Scholar
Cross Ref
- [3] . 2010. Design issues for a shingled write disk system. In Proceedings of the IEEE Conference on Mass Storage Systems and Technologies (MSST'10).Google Scholar
Digital Library
- [4] . 2013. LinkBench: A database benchmark based on the Facebook social graph. In Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data. 1185–1196.Google Scholar
Digital Library
- [5] . 1970. Space/time trade-offs in hash coding with allowable errors. Commun. ACM 13, 7 (1970), 422–426.Google Scholar
Digital Library
- [6] . [n.d.]. Realms API. Retrieved from http://www.t10.org/cgi-bin/ac.pl?t=d&f=17-158r1.pdf.Google Scholar
- [7] . 2008. The disksim Simulation Environment Version 4.0 Reference Manual (cmu-pdl-08-101). Parallel Data Laboratory (2008), 26.Google Scholar
- [8] . 2020. Characterizing, modeling, and benchmarking RocksDB key-value workloads at Facebook. In Proceedings of the 18th USENIX Conference on File and Storage Technologies
(FAST'20) . 209–223.Google ScholarDigital Library
- [9] . 2019. TDDFS: A tier-aware data deduplication-based file system. ACM Trans. Stor. 15, 1 (2019), 1–26.Google Scholar
Digital Library
- [10] . 2010. Indirection systems for shingled-recording disk drives. In Proceedings of the IEEE Conference on Mass Storage Systems and Technologies (MSST'10).Google Scholar
Digital Library
- [11] . 2011. Hystor: Making the best use of solid state drives in high performance storage systems. In Proceedings of the International Conference on Supercomputing.
ACM , 22–32.Google ScholarDigital Library
- [12] . 1997.
Computational geometry . In Computational Geometry. Springer, 1–17.Google ScholarCross Ref
- [13] . 2018. Extending Magic Pocket Innovation with the First Petabyte Scale SMR Drive Deployment. Retrieved November 2019 from https://blogs.dropbox.com/tech/2018/06/extending-magic-pocket-innovation-with-the-first-petabyte-scale-smr-drive-deployment/.Google Scholar
- [14] . 2018. CDBB: An NVRAM-based burst buffer coordination system for parallel file systems. In Proceedings of the High Performance Computing Symposium.
Society for Computer Simulation International , 1.Google Scholar - [15] . [n.d.]. Flex Overview. Retrieved from http://t13.org/Documents/UploadedDocuments/docs2018/f17156r0-Flex_Overview.pdf.Google Scholar
- [16] . 2018. Flex dynamic recording. USENIX ;login: 43, 1 (2018).Google Scholar
- [17] . 2016. Write management for interlaced magnetic recording devices.
US Patent 9,508,362. Google Scholar - [18] . 2017. Interlaced magnetic recording.
US Patent 9,728,206. Google Scholar - [19] . 2018. Chewanalyzer: Workload-aware data management across differentiated storage pools. In Proceedings of the IEEE 26th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems
(MASCOTS'18) .IEEE , 94–101.Google ScholarCross Ref
- [20] . [n.d.]. Dynamic Hybrid-SMR: An OCP Proposal to Improve Data Center Disk Drives. Retrieved from https://blog.google/products/google-cloud/dynamic-hybrid-smr-ocp-proposal-improve-data-center-disk-drives/.Google Scholar
- [21] . 2011. Cost effective storage using extent based dynamic tiering. In Proceedings of the USENIX Conference on File and Storage TechnologiesFAST, Vol. 11. 20–20.Google Scholar
- [22] . 2019. Track-based translation layers for interlaced magnetic recording. In Proceedings of the USENIX Annual Technical Conference
(USENIX ATC'19) . 821–832.Google Scholar - [23] . 2012. Data handling algorithms for autonomous shingled magnetic recording hdds. IEEE Trans. Magn. 48, 5 (2012), 1777–1781.Google Scholar
Cross Ref
- [24] . 2014. Novel address mappings for shingled write disks. In Proceedings of the HotStorage'14.Google Scholar
- [25] . 2017. SMaRT: An approach to shingled magnetic recording translation. In Proceedings of the 15th USENIX Conference on File and Storage Technologies
(FAST'17) .Google Scholar - [26] . 2015. Information Technology—Zoned Block Commands (ZBC). Retrieved from http://www.t10.org/drafts.htm.Google Scholar
- [27] . [n.d.]. Zoned-device ATA Command Set (ZAC) working draft.Google Scholar
- [28] . 2014. HiSMRfs: A high performance file system for shingled storage array. In Proceedings of the 30th Symposium on Mass Storage Systems and Technologies
(MSST'14) . 1–6. https://doi.org/10.1109/MSST.2014.6855539Google ScholarCross Ref
- [29] . 2015. Caveat-scriptor: Write anywhere shingled disks. In Proceedings of the ACM Workshop on Hot Topics in Storage and File Systems (HotStorage'15).Google Scholar
- [30] . 2011. HybridStore: A cost-efficient, high-performance storage system combining SSDs and HDDs. In Proceedings of the IEEE 19th Annual International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems.
IEEE , 227–236.Google ScholarDigital Library
- [31] . 2010. FASTer FTL for enterprise-class flash memory SSDs. In Proceedings of the International Workshop on Storage Network Architecture and Parallel I/Os
(SNAPI'10) .IEEE , 3–12.Google ScholarDigital Library
- [32] . 2012. H-SWD: Incorporating hot data identification into shingled write disks. In Proceedings of the 20th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems
(MASCOTS'12) .Google ScholarDigital Library
- [33] . 2017. SMORE: A Cold Data Object Store for SMR Drives (Extended Version). arXiv:1705.09701. Retrieved from https://arxiv.org/abs/1705.09701.Google Scholar
- [34] . 2017. SMORE: A cold data object store for SMR drives. In Proceedings of the 33rd International Conference on Massive Storage Systems and Technology
(MSST'17) .Google Scholar - [35] . 2016. ZEA, A data management approach for SMR. In Proceedings of the 8th USENIX Workshop on Hot Topics in Storage and File Systems
(HotStorage'16) .Google ScholarDigital Library
- [36] . 2014. A new parity-based migration method to expand RAID-5. IEEE Trans. Parallel Distrib. Syst. 25, 8 (2014), 1945–1954.Google Scholar
Cross Ref
- [37] . 2008. Write off-loading: Practical power management for enterprise storage. ACM Trans. Stor. 4, 3 (2008), 10.Google Scholar
Digital Library
- [38] . 2012. H-SWD: A novel shingled write disk scheme based on hot and cold data identification. In Proceedings of the USENIX Conference on File and Storage Technologies (FAST'12).Google Scholar
- [39] . 2015. SMRDB: Key-value data store for shingled magnetic recording disks. In Proceedings of the 8th ACM International Systems and Storage Conference.
ACM , 18.Google ScholarDigital Library
- [40] . 2014. Flushing out pdflush. Retrieved from https://lwn.net/Articles/326552/.Google Scholar
- [41] . 1994. An introduction to disk drive modeling. Computer 27, 3 (1994), 17–28.Google Scholar
Digital Library
- [42] . [n.d.]. New Flex Dynamic Recording Method Redefines the Data Center Hard Drive. Retrieved from https://blog.seagate.com/intelligent/new-flex-dynamic-recording-method-redefines-data-center-hard-drive/.Google Scholar
- [43] . 2012. Hybrid aggregates: Combining SSDs and HDDs in a single storage pool. ACM SIGOPS Operat. Syst. Rev. 46, 3 (2012), 50–56.Google Scholar
Digital Library
- [44] . 2017. Flex Device Interface. Retrieved March 2020 from http://t13.org/Documents/Uploaded Documents/docs2018/f18101r0-Flex_Device_Interface.pdf.Google Scholar
- [45] . 2017. Larger, cheaper, but faster: SSD-SMR hybrid storage boosted by a new SMR-oriented cache framework. In Proceedings of the IEEE Symposium Mass Storage Systems and Technology
(MSST'17) .Google Scholar - [46] . [n.d.]. Dynamic Hybrid SMR. Retrieved from https://blog.westerndigital.com/dynamic-hybrid-smr/.Google Scholar
- [47] . 1996. The HP AutoRAID hierarchical storage system. ACM Trans. Comput. Syst. 14, 1 (1996), 108–136.Google Scholar
Digital Library
- [48] . 2012. GSR: A global stripe-based redistribution approach to accelerate RAID-5 scaling. In Proceedings of the 41st International Conference on Parallel Processing.
IEEE , 460–469.Google ScholarDigital Library
- [49] . 2012. SDM: A stripe-based data migration scheme to improve the scalability of RAID-6. In Proceedings of the IEEE International Conference on Cluster Computing.
IEEE , 284–292.Google ScholarDigital Library
- [50] . 2015. Code 5-6: An efficient MDS array coding scheme to accelerate online RAID level migration. In Proceedings of the 44th International Conference on Parallel Processing.
IEEE , 450–459.Google ScholarDigital Library
- [51] . 2017. Performance evaluation of host aware shingled magnetic recording (HA-SMR) drives. IEEE Trans. Comput. 66, 11 (2017), 1932–1945.Google Scholar
Digital Library
- [52] . 2019. ZoneAlloy: Elastic data and space management for hybrid SMR drives. In Proceedings of the 11th USENIX Workshop on Hot Topics in Storage and File Systems
(HotStorage'19) .Google Scholar - [53] . 2020. Tracklace: Data management for interlaced magnetic recording. IEEE Transactions on Computers 70, 3 (2020), 347–358.Google Scholar
Digital Library
- [54] . 2016. Evaluating host aware SMR drives. In Proceedings of the 8th USENIX Workshop on Hot Topics in Storage and File Systems
(HotStorage'16) .Google ScholarDigital Library
- [55] . 2018. Data management design for interlaced magnetic recording. In Proceedings of the 10th USENIX Workshop on Hot Topics in Storage and File Systems
(HotStorage'18) .Google ScholarDigital Library
- [56] . 2016. HS-BAS: A hybrid storage system based on band awareness of Shingled Write Disk. In Proceedings of the IEEE 34th International Conference on Computer Design
(ICCD'16) .IEEE , 64–71.Google ScholarCross Ref
- [57] . 2019. ZoneTier: A zone-based storage tiering and caching co-design to integrate SSDs with SMR drives. ACM Trans. Stor. 15, 3 (2019), 19.Google Scholar
- [58] . 2017. Virtual persistent cache: Remedy the long latency behavior of host-aware shingled magnetic recording drives. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design
(ICCAD'17) .IEEE , 17–24.Google ScholarCross Ref
- [59] . 2018. On improving the write responsiveness for host-aware SMR drives. IEEE Trans. Comput. 68, 1 (2018), 111–124.Google Scholar
Digital Library
- [60] . 2019. GearDB: A GC-free key-value store on HM-SMR drives with gear compaction. In Proceedings of the 17th USENIX Conference on File and Storage Technologies
(FAST'19) . 159–171.Google Scholar - [61] . 2020. Idler: I/O workload controlling for better responsiveness on host-aware shingled magnetic recording drives. IEEE Trans. Comput. (2020), 1–1. https://doi.org/10.1109/TC.2020.2966194Google Scholar
- [62] . 2007. SLAS: An efficient approach to scaling round-robin striped volumes. ACM Trans. Stor. 3, 1 (2007), 3–es.Google Scholar
Digital Library
- [63] . 2009. ALV: A new data redistribution approach to RAID-5 scaling. IEEE Trans. Comput. 59, 3 (2009), 345–357.Google Scholar
Digital Library
- [64] . 2011. Fastscale: Accelerate raid scaling by minimizing data migration. In Proceedings of the USENIX Conference on File and Storage Technologies
(FAST'11) . 149–161.Google Scholar
Index Terms
FluidSMR: Adaptive Management for Hybrid SMR Drives
Recommendations
Evaluating host aware SMR drives
HotStorage'16: Proceedings of the 8th USENIX Conference on Hot Topics in Storage and File SystemsShingled Magnetic Recording (SMR) technology increases the areal density of hard disk drives. Among the three types of SMR drives on the market today, Host Aware SMR (HA-SMR) drives look the most promising. In this paper, we carry out evaluation to ...
Adaptive SDRE based nonlinear sensorless speed control for PMSM drives
ACC'09: Proceedings of the 2009 conference on American Control ConferenceField orientation or vector control is an advanced technique used for the development of high-performance permanent magnet synchronous motor (PMSM) drives. In this paper, a field-oriented adaptive nonlinear control for PMSM drives is presented for ...
Fault diagnosis and management system for switched reluctance motor drives
An effective detection and diagnosis of faults is desirable for online condition monitoring, assessment, product quality assurance and improved operational efficiency of Switched Reluctance Motor (SRM) drives. The proposed fault diagnosis and management ...






Comments