Award Abstract # 1562837
CSR: Medium: Collaborative Research: NVM-enabled Host-side Caches

NSF Org: CNS
Division Of Computer and Network Systems
Recipient: ARIZONA STATE UNIVERSITY
Initial Amendment Date: April 22, 2016
Latest Amendment Date: April 22, 2016
Award Number: 1562837
Award Instrument: Standard Grant
Program Manager: Marilyn McClure
mmcclure@nsf.gov
 (703)292-5197
CNS
 Division Of Computer and Network Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: June 1, 2016
End Date: May 31, 2021 (Estimated)
Total Intended Award Amount: $304,251.00
Total Awarded Amount to Date: $304,251.00
Funds Obligated to Date: FY 2016 = $304,251.00
History of Investigator:
  • Ming Zhao (Principal Investigator)
    mingzhao@asu.edu
Recipient Sponsored Research Office: Arizona State University
660 S MILL AVENUE STE 204
TEMPE
AZ  US  85281-3670
(480)965-5479
Sponsor Congressional District: 04
Primary Place of Performance: Arizona State University
PO BOX 878809
Tempe
AZ  US  85287-8809
Primary Place of Performance
Congressional District:
04
Unique Entity Identifier (UEI): NTLHJXM55KZ6
Parent UEI:
NSF Program(s): Special Projects - CNS,
CSR-Computer Systems Research
Primary Program Source: 01001617DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 7924, 9251
Program Element Code(s): 171400, 735400
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

Non-volatile memory (NVM) is a transformative technology that is dramatically changing how data storage systems of the
future are built. This technology allows an unprecedented combination of performance and persistence into a single
device. This project will develop a suite of storage caching techniques for this transformative technology along four
complementary dimensions.

The first two usage dimensions address the selective use of NVM as host-side read caches for persistently stored data
as well as using their persistence properties explicitly by developing fault-tolerant write caching solutions. The
latter two develop advanced techniques for delivering storage quality of service (QoS) using NVM caches and building caching
algorithms that are aware of data reduction techniques, such as deduplication and compression, for the NVM layer. Together, these contributions have the potential to transform enterprise data center storage stacks by readily adopting the best properties of current and future NVM technology. The expected performance benefits apply to a broad spectrum of computer systems and applications.

Educational activities will include the involvement of undergraduate students and incorporation of the project's research findings into coursework. Planned outreach activities will focus on recruitment of under-represented students from minority groups in computer science for participation in the project. Transition of the new technologies to practice through open source distribution of the Linux operating system and KVM hypervisor code implementing the innovations are successful expectations.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

(Showing: 1 - 10 of 27)
Chen, Yitao and Biookaghazadeh, Saman and Zhao, Ming "Exploring the capabilities of mobile devices in supporting deep learning" 4th ACM/IEEE Symposium on Edge Computing , 2019
Debadatta Mishra and Puru Kulkarni and Raju Rangaswami "StepAhead: Rethinking File System NamespaceTranslations" Proceedings of the Asia-Pacific Workshop on Systems (APSys) , 2016
Debadatta Mishra and Puru Kulkarni and Raju Rangaswami "Synergy: A Hypervisor Managed Holistic Caching System" IEEE Transactions on Cloud Computing , 2017 , p.99
Debadatta Mishra and Puru Kulkarni and Raju Rangaswami "Synergy: A Hypervisor Managed Holistic Caching System" IEEE Transactions on Cloud Computing , 2017
Fu, Jianyu and Lu, Youyou and Shu, Jiwu and Liu, Guangming and Zhao, Ming "COWCache: effective flash caching for Copy-on-Write virtual disks" Cluster Computing , 2019
Giuseppe Vietri and Liana Rodriguez and Wendy Aleman Martinez, Steven Lyons, Jason Liu, Raju Rangaswami, Ming Zhao,Giri Narasimhan "Driving Cache Replacement with ML-based LeCaR" Proceedings of HotStorage 2018 , 2018
Liu, Yubo and Li, Hongbo and Lu, Yutong and Chen, Zhiguang and Xiao, Nong and Zhao, Ming "HasFS: optimizing file system consistency mechanism on NVM-based hybrid storage architecture" Cluster Computing , 2019
Liu, Yubo and Li, Hongbo and Lu, Yutong and Chen, Zhiguang and Zhao, Ming "An Efficient and Flexible Metadata Management Layer for Local File Systems" 2019 IEEE 37th International Conference on Computer Design (ICCD) , 2019
L. V. Rodriguez, F. Yusuf, S. Lyons, E. Paz, R. Rangaswami, J. Liu, M. Zhao, G. Narasimhan "Learning Cache Replacement with Cacheus" 19th USENIX Conference on File and Storage Technologies (FAST) , 2021
Mario Conseugra and Wendy Martinez and Giri Narasimhan and Raju Rangaswami and Leo Shao and Giuseppe Vietri "Analyzing adaptive cache replacement strategies" arXiv:1503.07624 , 2017
Mario Conseugra and Wendy Martinez and Giri Narasimhan and Raju Rangaswami and Leo Shao and GiuseppeVietri "Analyzing adaptive cache replacement strategies" arXiv:1503.07624 , 2017
(Showing: 1 - 10 of 27)

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

Non-volatile memory (NVM) is a transformative technology that is dramatically changing how data storage systems of the future are built. This technology allows an unprecedented combination of performance and persistence into a single device. This project has developed a suite of storage caching techniques for this transformative technology along four complementary dimensions.

The first two usage dimensions has addressed the selective use of NVM as host-side read caches for persistently stored data as well as using their persistence properties explicitly by developing fault-tolerant write caching solutions. The latter two has developed advanced techniques for delivering storage quality of service (QoS) using NVM caches and building caching algorithms that are aware of data reduction techniques, such as deduplication and compression, for the NVM layer. Together, these contributions help transform enterprise data center storage stacks by readily adopting the best properties of current and future NVM technology. The performance benefits apply to a broad spectrum of computer systems and applications.

Educational activities include the involvement of undergraduate students and incorporation of the project's research findings into coursework. The outreach activities have focused on recruitment of under-represented students from minority groups in computer science for participation in the project. Transition of the new technologies to practice through open-source distribution of the Linux operating system and KVM hypervisor code implementing the innovations are successful expectations.

The project has produced many important results. For example, CloudCache provides on-demand cache management based on a new cache demand model (reuse working set), which can satisfy VMs’ dynamic cache demands while minimizing space wastage and device wear-out; CacheDedup is the first deduplication solution optimized for caches which provides integrated cache and deduplication management and novel duplication-aware cache replacement algorithms; and Cacheus is a new class of fully adaptive, machine-learned caching algorithms that utilize a combination of experts designed carefully to address newly identified workload primitive types such as scan and churn.

The results of this project have generated broader impacts in several key aspects. First, the findings of the project have improved the content of various courses at ASU in the areas of Cloud Computing and Operating Systems, at the undergraduate, masters, and Ph.D. levels. The project has also been a source of undergraduate research experience and encouraged many of the participants to pursue graduate studies. Second, the project has provided critical systems software solutions for efficiently managing host-side caches within the modern datacenter including bare-bones and virtualized servers and storage. These solutions can significantly improve datacenter resource usage efficiency and workload performance guarantees. Third, research artifacts of the project have been broadly disseminated, including many publications, open-source software, and trace data. Finally, the project has developed important research underpinnings for making the infrastructure for cloud and big-data systems better performing and more robust at a lower cost. Fundamentally, the caching contributions benefit the datacenters by significantly reducing the hardware requirements to run workloads. This directly addresses both cost and energy footprints within datacenters. The contributions of the project also enable performance guarantees in workloads and significant efficiencies in cache resource usage within such environments that directly translate into cost-savings for the datacenter operators and better end-user experience.


Last Modified: 09/29/2021
Modified by: Ming Zhao

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page