skip to main content
10.1145/3599691.3603400acmconferencesArticle/Chapter ViewAbstractPublication PageshotstorageConference Proceedingsconference-collections
research-article
Public Access

Do we still need IO schedulers for low-latency disks?

Published: 10 July 2023 Publication History

Abstract

The performance of recent data storage devices has significantly improved over previous generations, with lower latency, greater throughput, and greater parallelism. Since we now have Ultra-Low Latency (ULL) data storage devices capable of providing data in less than 10 microseconds, in this paper we question the need for IO schedulers for better performance and energy efficiency. Specifically, we measure the latency costs of Linux IO scheduling algorithms and investigate their impact on overall performance and energy efficiency using a ULL storage device, a power meter, and various IO workloads. Our observations indicate that IO schedulers for ULL storage either do not help or significantly increase request latencies while also negatively impacting throughput and energy efficiency. Although we recognize the value of IO schedulers for slower devices or for other metrics such as fairness and QoS, we believe that IO schedulers have become unnecessary for ULL devices to improve performance or energy efficiency.

References

[1]
2016. mq-deadline multiqueue I/O scheduler. https://github.eom/torvalds/linux/blob/master/block/mq-deadline.c.
[2]
2017. Kyber multiqueue I/O scheduler. https://patchwork.kernel.org/patch/9672023/.
[3]
2017. Samsung SZ985 Z-NAND SSD. https://www.samsung.com/us/labs/pdfs/collateral/Samsung_Z-NAND_Technology_Brief_v5.pdf.
[4]
2018. Product Brief: Intel Optane SSD DC P4800X Series. https://www.intel.com/content/dam/www/public/us/en/documents/product-briefs/optane-ssd-dc-p4800x-brief.pdf.
[5]
2019. NVM Express Base Specification, rev. 1.4. https://nvmexpress.org/wp-content/uploads/NVM-Express-1_4-2019.06.10-Ratified.pdf.
[6]
2022. RocksDB Performance Benchmarking with db_bench. https://github.com/facebook/rocksdb/wiki/Benchmarking-tools.
[7]
2023. Multi-Queue Block IO Queueing Mechanism (blk-mq). https://docs.kernel.org/block/blk-mq.html.
[8]
Jens Axboe. 2019. Efficient IO through io_uring. https://kernel.dk/io_uring.pdf.
[9]
Matias Bjørling, Jens Axboe, David Nellans, and Philippe Bonnet. 2013. Linux Block IO: Introducing Multi-queue SSD Access on Multi-core Systems. In Proceedings of the 6th International Systems and Storage Conference (Haifa, Israel) (SYSTOR '13). ACM, New York, NY, USA, Article 22, 10 pages.
[10]
Budget Fair Queueing 2022. Budget Fair Queueing (BFQ) Storage-I/O Scheduler. http://algo.ing.unimo.it/people/paolo/disk_sched/.
[11]
F. T. Hady, A. Foong, B. Veal, and D. Williams. 2017. Platform Storage Performance With 3D XPoint Technology. Proc. IEEE 105, 9 (Sept 2017), 1822--1833.
[12]
Logan Hall, Bryan Harris, Erica Tomes, and Nihat Altiparmak. 2017. Big Data Aware Virtual Machine Placement in Cloud Data Centers. In 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT 2017) (Austin, Texas, USA) (BDCAT '17). ACM, New York, NY, USA, 209--218.
[13]
Mohammad Hedayati, Kai Shen, Michael L. Scott, and Mike Marty. 2019. Multi-Queue Fair Queuing. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA, 301-314. http://www.usenix.org/conference/atc19/presentation/hedayati-queue
[14]
Michael Larabel. 2020. Linux 5.6 I/O Scheduler Benchmarks: None, Kyber, BFQ, MQ-Deadline. https://www.phoronix.com/review/linux-56-nvme.
[15]
Gyusun Lee, Seokha Shin, Wonsuk Song, Tae Jun Ham, Jae W. Lee, and Jinkyu Jeong. 2019. Asynchronous I/O Stack: A Low-latency Kernel I/O Stack for Ultra-Low Latency SSDs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA, 603--616. https://www.usenix.org/conference/atc19/presentation/lee-gyusun
[16]
Geraldo F. Oliveira, Saugata Ghose, Juan Gómez-Luna, Amirali Boroumand, Alexis Savery, Sonny Rao, Salman Qazi, Gwendal Grignou, Rahul Thakur, Eric Shiu, and Onur Mutlu. 2021. Extending Memory Capacity in Consumer Devices with Emerging Non-Volatile Memory: An Experimental Study. ArXiv abs/2111.02325 (2021).
[17]
Onset Computer Corporation 2017. HOBO® Plug Load Logger (UX120-018) Manual. Onset Computer Corporation. https://www.onsetcomp.com/sites/default/files/resources-documents/17838-E%20MAN-UX120-018.pdf
[18]
Amy Tai, Igor Smolyar, Michael Wei, and Dan Tsafrir. 2021. Optimizing Storage Performance with Calibrated Interrupts. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, 129--145. https://www.usenix.org/conference/osdi21/presentation/tai
[19]
Toby J. Teorey and Tad B. Pinkerton. 1972. A Comparative Analysis of Disk Scheduling Policies. In Communications of the ACM. 177--184.
[20]
Paolo Valente and Arianna Avanzini. 2015. Evolution of the BFQ Storage-I/O scheduler. In 2015 Mobile Systems Technologies Workshop (MST). IEEE, 15--20.
[21]
Jiwon Woo, Minwoo Ahn, Gyusun Lee, and Jinkyu Jeong. 2021. D2FQ: Device-Direct Fair Queueing for NVMe SSDs. In 19th USENIX Conference on File and Storage Technologies (FAST '21). USENIX Association, 403--415. https://www.usenix.org/conference/fast21/presentation/woo
[22]
Bruce L. Worthington, Gregory R. Ganger, and Yale N. Patt. 1994. Scheduling Algorithms for Modern Disk Drives. In SIGMETRICS. 241--252.
[23]
Jisoo Yang, Dave B. Minturn, and Frank Hady. 2012. When Poll is Better than Interrupt. In Proceedings of the 10th USENIX Conference on File and Storage Technologies (San Jose, CA) (FAST '12). USENIX Association, USA, 3.
[24]
Suli Yang, Tyler Harter, Nishant Agrawal, Salini Selvaraj Kowsalya, Anand Krishnamurthy, Samer Al-Kiswany, Rini T Kaushik, Andrea C Arpaci-Dusseau, and Remzi H Arpaci-Dusseau. 2015. Split-level I/O scheduling. In Proceedings of the 25th Symposium on Operating Systems Principles. ACM, 474--489.

Cited By

View all
  • (2024)I/O in a flashProceedings of the 22nd USENIX Conference on File and Storage Technologies10.5555/3650697.3650708(177-192)Online publication date: 27-Feb-2024
  • (2024)Can Storage Devices be Power Adaptive?Proceedings of the 16th ACM Workshop on Hot Topics in Storage and File Systems10.1145/3655038.3665945(47-54)Online publication date: 8-Jul-2024
  • (2024)LightFS: A Lightweight Host-CSD Coordinated File System Optimizing for Heavy Small File AccessesIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2024.344301043:11(3527-3538)Online publication date: Nov-2024

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
HotStorage '23: Proceedings of the 15th ACM Workshop on Hot Topics in Storage and File Systems
July 2023
131 pages
ISBN:9798400702242
DOI:10.1145/3599691
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

In-Cooperation

  • USENIX

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 July 2023

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. IO scheduler
  2. ultra-low latency storage
  3. energy efficiency

Qualifiers

  • Research-article

Funding Sources

Conference

HotStorage '23
Sponsor:

Acceptance Rates

Overall Acceptance Rate 34 of 87 submissions, 39%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)312
  • Downloads (Last 6 weeks)48
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)I/O in a flashProceedings of the 22nd USENIX Conference on File and Storage Technologies10.5555/3650697.3650708(177-192)Online publication date: 27-Feb-2024
  • (2024)Can Storage Devices be Power Adaptive?Proceedings of the 16th ACM Workshop on Hot Topics in Storage and File Systems10.1145/3655038.3665945(47-54)Online publication date: 8-Jul-2024
  • (2024)LightFS: A Lightweight Host-CSD Coordinated File System Optimizing for Heavy Small File AccessesIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2024.344301043:11(3527-3538)Online publication date: Nov-2024

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media