Abstract
Since little has been reported in the literature concerning enterprise storage system file-level request scheduling, we do not have enough knowledge about how various scheduling factors affect performance. Moreover, we are in lack of a good understanding on how to enhance request scheduling to adapt to the changing characteristics of workloads and hardware resources. To answer these questions, we first build a request scheduler prototype based on WAFL®, a mainstream file system running on numerous enterprise storage systems worldwide. Next, we use the prototype to quantitatively measure the impact of various scheduling configurations on performance on a NetApp®'s enterprise-class storage system. Several observations have been made. For example, we discover that in order to improve performance, the priority of write requests and non-preempted restarted requests should be boosted in some workloads. Inspired by these observations, we further propose two scheduling enhancement heuristics called SORD (size-oriented request dispatching) and QATS (queue-depth aware time slicing). Finally, we evaluate them by conducting a wide range of experiments using workloads generated by SPC-1 and SFS2014 on both HDD-based and all-flash platforms. Experimental results show that the combination of the two can noticeably reduce average request latency under some workloads.
- 2015. Bandwidth (Computing). Retrieved Sept. 11, 2015 from https://en.wikipedia.org/wiki/Bandwidth_(computing).Google Scholar
- 2015. {NetApp FAS8080 EX Datasheet. Retrieved Sept. 11, 2015 from http://www.netapp.com/us/media/ds-3580.pdf.Google Scholar
- 2015. P320h HHHL PCIe Enterprise SSD. Retrieved Oct. 19, 2015 from https://www.micron.com/∼/media/documents/products/product-flyer/brief_p320h_hhhl.pdf.Google Scholar
- 2015. SPEC SFS 2014 Benchmark. Retrieved Sept. 11, 2015 from https://www.spec.org/sfs2014/.Google Scholar
- 2015. ZFS at OpenSolaris community. Retrieved Sept. 11, 2015 from http://opensolaris.org/os/community/zfs/.Google Scholar
- Parag Agrawal, Daniel Kifer, and Christopher Olston. 2008. Scheduling shared scans of large data files. Proceedings of the VLDB Endowment 1, 1 (2008), 958--969. Google Scholar
Digital Library
- Giridhar Appaji Nag Yasa and P. C. Nagesh. 2012. Space savings and design considerations in variable length deduplication. ACM SIGOPS Operating Systems Review 46, 3 (2012), 57--64. Google Scholar
Digital Library
- Alexandros Batsakis, Randal Burns, Arkady Kanevsky, James Lentini, and Thomas Talpey. 2009. CA-NFS: A congestion-aware network file system. ACM Transactions on Storage (TOS) 5, 4 (2009), 15. Google Scholar
Digital Library
- Ellie Berriman, Paul Feresten, and Shawn Kung. 2015. IDC worldwide quarterly enterprise storage systems tracker.Google Scholar
- David Boutcher and Abhishek Chandra. 2010. Does virtualization make disk scheduling passé? ACM SIGOPS Operating Systems Review 44, 1 (2010), 20--24. Google Scholar
Digital Library
- John Bruno, Jose Brustoloni, Eran Gabber, Banu Özden, and Abraham Silberschatz. 1999. Disk scheduling with quality of service guarantees. In Proceedings of the IEEE International Conference on Multimedia Computing and Systems, 1999, Vol. 2. IEEE, 400--405. Google Scholar
Digital Library
- Shenze Chen, John A. Stankovic, James F. Kurose, and Don Towsley. 1991. Performance evaluation of two new disk scheduling algorithms for real-time systems. Real-Time Systems 3, 3 (1991), 307--336.Google Scholar
Cross Ref
- Storage Performance Council. 2017. PC Benchmark 1 (SPC-1) Specification - Revision 3.1. http://www.storageperformance.org/specs/SPC1_v310.pdf.Google Scholar
- Matthew Curtis-Maury, Vinay Devadas, Vania Fang, and Aditya Kulkarni. 2016. To waffinity and beyond: A scalable architecture for incremental parallelization of file system code. In Proceedings of the12th USENIX Symposium on Operating Systems Design and Implementation (OSDI’16). USENIX Association, 419--434. Google Scholar
Digital Library
- Scott Dawkins, Kaladhar Voruganti, and John D. Strunk. 2012. Systems research and innovation in data ONTAP. ACM SIGOPS Operating Systems Review 46, 3 (2012), 1--3. Google Scholar
Digital Library
- John K. Edwards, Daniel Ellard, Craig Everhart, Robert Fair, Eric Hamilton, Andy Kahn, Arkady Kanevsky, James Lentini, Ashish Prakash, Keith A Smith, and others. 2008. FlexVol: Flexible, efficient file volume virtualization in WAFL. In Proceedings of the USENIX 2008 Annual Technical Conference on Annual Technical Conference. USENIX Association, 129--142. Google Scholar
Digital Library
- EMC. 2015. EMC Isilon OneFS: A Technical Overview. https://www.emc.com/collateral/hardware/white-papers/h10719-isilon-onefs-technical-overview-wp.pdf.Google Scholar
- Binny S. Gill and Dharmendra S. Modha. 2005. Wow: Wise ordering for writes-combining spatial and temporal locality in non-volatile caches. In Proceedings of the 4th Conference on USENIX Conference on File and Storage Technologies-Volume 4. USENIX Association, 10--10. Google Scholar
Digital Library
- Anoop Gupta, Andrew Tucker, and Shigeru Urushibara. 1991. The impact of operating system scheduling policies and synchronization methods of performance of parallel applications. In ACM SIGMETRICS Performance Evaluation Review, Vol. 19. ACM, 120--132. Google Scholar
Digital Library
- Dave Hitz and others. 1994. File system design for an NFS file server appliance. In USENIX Winter, Vol. 94. Google Scholar
Digital Library
- Sitaram Iyer and Peter Druschel. 2001. Anticipatory scheduling: A disk scheduling framework to overcome deceptive idleness in synchronous I/O. In ACM SIGOPS Operating Systems Review, Vol. 35. ACM, 117--130. Google Scholar
Digital Library
- Jaeho Kim, Yongseok Oh, Eunsam Kim, Jongmoo Choi, Donghee Lee, and Sam H. Noh. 2009. Disk schedulers for solid state drivers. In Proceedings of the 7th ACM International Conference on Embedded Software. ACM, 295--304. Google Scholar
Digital Library
- Youngjae Kim, Scott Atchley, Geoffroy R. Vallée, and Galen M. Shipman. 2015. LADS: Optimizing data transfers using layout-aware data scheduling. In Proceedings of the 13th USENIX Conference on File and Storage Technologies. USENIX Association, 67--80. Google Scholar
Digital Library
- Andrew W. Leung, Shankar Pasupathy, Garth R. Goodson, and Ethan L. Miller. 2008. Measurement and analysis of large-scale network file system workloads. In Proceedings of the USENIX Annual Technical Conference, Vol. 1. 5--2. Google Scholar
Digital Library
- Peter Macko, Margo I. Seltzer, and Keith A. Smith. 2010. Tracking back references in a write-anywhere file system. In Proceedings of FAST. 15--28. Google Scholar
Digital Library
- Marshall Kirk McKusick and George V. Neville-Neil. 2004. Thread scheduling in FreeBSD 5.2. Queue 2, 7 (2004), 58--64. Google Scholar
Digital Library
- Hugo Patterson, Stephen Manley, Mike Federwisch, Dave Hitz, Steve Kleiman, and Shane Owara. 2002. SnapMirror®: File system based asynchronous mirroring for disaster recovery. In Proceedings of the 1st USENIX Conference on File and Storage Technologies. USENIX Association, 9--9. Google Scholar
Digital Library
- Anna Povzner, Tim Kaldewey, Scott Brandt, Richard Golding, Theodore M. Wong, and Carlos Maltzahn. 2008. Efficient guaranteed disk request scheduling with fahrrad. In ACM SIGOPS Operating Systems Review, Vol. 42. ACM, 13--25. Google Scholar
Digital Library
- AL Reddy and Jim Wyllie. 1993. Disk scheduling in a multimedia I/O system. In Proceedings of the 1st ACM International Conference on Multimedia. ACM, 225--233. Google Scholar
Digital Library
- Ohad Rodeh. 2008. B-trees, shadowing, and clones. ACM Transactions on Storage (TOS) 3, 4 (2008), 2. Google Scholar
Digital Library
- Y. Rompogiannakis, Guido Nerjes, Peter Muth, Michael Paterakis, Peter Triantafillou, and Gerhard Weikum. 1998. Disk scheduling for mixed-media workloads in a multimedia server. In Proceedings of the 6th ACM International Conference on Multimedia. ACM, 297--302. Google Scholar
Digital Library
- Prashant J. Shenoy and Harrick M. Vin. 1998. Cello: A disk scheduling framework for next generation operating systems. In ACM SIGMETRICS Performance Evaluation Review, Vol. 26. ACM, 44--55. Google Scholar
Digital Library
- Alexander Thomasian. 2011. Survey and analysis of disk scheduling methods. ACM SIGARCH Computer Architecture News 39, 2 (2011), 8--25. Google Scholar
Digital Library
- Avishay Traeger, Erez Zadok, Nikolai Joukov, and Charles P. Wright. 2008. A nine year study of file system and storage benchmarking. ACM Transactions on Storage (TOS) 4, 2 (2008), 5. Google Scholar
Digital Library
- Yuehai Xu and Song Jiang. 2011. A scheduling framework that makes any disk schedulers non-work-conserving solely based on request characteristics. In Proceedings of FAST. 119--132. Google Scholar
Digital Library
- Chang-Woo Yang, Adam Wierman, Sanjay Shakkottai, and Mor Harchol-Balter. 2006. Tail asymptotics for policies favoring short jobs in a many-flows regime. ACM SIGMETRICS Performance Evaluation Review 34, 1 (2006), 97--108. Google Scholar
Digital Library
- Matei Zaharia, Dhruba Borthakur, Joydeep Sen Sarma, Khaled Elmeleegy, Scott Shenker, and Ion Stoica. 2010. Delay scheduling: A simple technique for achieving locality and fairness in cluster scheduling. In Proceedings of the 5th European Conference on Computer Systems. ACM, 265--278. Google Scholar
Digital Library
Index Terms
Empirical Evaluation and Enhancement of Enterprise Storage System Request Scheduling
Recommendations
LSM-tree managed storage for large-scale key-value store
SoCC '17: Proceedings of the 2017 Symposium on Cloud ComputingKey-value stores are increasingly adopting LSM-trees as their enabling data structure in the backend storage, and persisting their clustered data through a file system. A file system is expected to not only provide file/directory abstraction to organize ...
Parallelism-Aware Request Scheduling for MEMS-based Storage Devices
MASCOTS '06: Proceedings of the 14th IEEE International Symposium on Modeling, Analysis, and SimulationMEMS-based storage is being developed as a new storage media. Due to its attractive features such as high-bandwidth, low-power consumption, and low cost, MEMS storage is anticipated to be used for a wide range of applications. However, MEMS storage has ...






Comments