Award Abstract # 1743363
CloudLab Phase II: Community Infrastructure To Expand the Frontiers of Cloud Computing Research

NSF Org: CNS
Division Of Computer and Network Systems
Recipient: UNIVERSITY OF UTAH
Initial Amendment Date: July 24, 2017
Latest Amendment Date: November 19, 2021
Award Number: 1743363
Award Instrument: Cooperative Agreement
Program Manager: Deepankar Medhi
dmedhi@nsf.gov
 (703)292-2935
CNS
 Division Of Computer and Network Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: October 1, 2017
End Date: September 30, 2022 (Estimated)
Total Intended Award Amount: $9,688,325.00
Total Awarded Amount to Date: $9,688,325.00
Funds Obligated to Date: FY 2017 = $5,833,587.00
FY 2018 = $2,558,508.00

FY 2019 = $1,296,230.00
History of Investigator:
  • Robert Ricci (Principal Investigator)
    ricci@cs.utah.edu
  • Kuang-Ching Wang (Co-Principal Investigator)
  • Aditya Akella (Co-Principal Investigator)
  • Michael Zink (Co-Principal Investigator)
  • Glenn Ricart (Co-Principal Investigator)
Recipient Sponsored Research Office: University of Utah
201 PRESIDENTS CIR
SALT LAKE CITY
UT  US  84112-9049
(801)581-6903
Sponsor Congressional District: 01
Primary Place of Performance: University of Utah
50 CENTRAL CAMPUS DR
SALT LAKE CITY
UT  US  84112-9205
Primary Place of Performance
Congressional District:
01
Unique Entity Identifier (UEI): LL8GLEVH6MG3
Parent UEI:
NSF Program(s): CISE Research Resources
Primary Program Source: 01001718DB NSF RESEARCH & RELATED ACTIVIT
01001819DB NSF RESEARCH & RELATED ACTIVIT

01001920DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 8002
Program Element Code(s): 289000
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

This project seeks to extend the capabilities and capacity of the Cloudlab compute cloud in the second phase of the NSFCloud program. Since CloudLab began service in mid-2015, this experimental research infrastructure has become a critical experimental resource for the computer science research community. CloudLab has served over 2,000 users in over 39,000 experiments spanning more than 400 projects, with experimenters coming from nearly every state. The Cloudlab project continues to increase its support of computing for the domain science research communities, and support of technology transfers to commercial cloud technology providers and users.

The proposed Phase II activity seeks to expand the testbed capacity and capabilities through 11 enumerated hardware and software extensions to satisfy the growing needs of leading computer science systems researchers. The three major areas of new technology investments are in 1) new cloud networking technology, 2) support for new cloud architectures, and 3) increased programmability in cloud network data planes.

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.

Duplyakin, D and Ricci, R and Maricq, M and Wong, G and Duerig, J and Eide, E and Stoller, L and Hibler, M and Johnson, D and Webb, K and Akella, A and Wang, K and Ricart, G and Landweber, L and Elliott, C and Zink, M and Cecchet, E and Kar, S and and Mis "The Design and Operation of CloudLab" The Design and Operation of CloudLab , 2019 Citation Details
Duplyakin, Dmitry and Uta, Alexandru and Maricq, Aleksander and Ricci, Robert "In Datacenter Performance, The Only Constant Is Change" Proceedings of the Twentieth IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid , 2020 Citation Details
Duplyakin, Dmitry and Uta, Alexandru and Maricq, Aleksander and Ricci, Robert "On Studying CPU Performance of CloudLab Hardware" Proceedings of the Worksop on Midscale Education and Research Infrastructure and Tools (MERIT) , 2019 https://doi.org/10.1109/ICNP.2019.8888128 Citation Details
Maricq, A and Duplyakin, D and Jimenez, I and Maltzahn, C and Stutsman, R and Ricci, R "Taming Performance Variability" Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI ?18) , 2018 Citation Details
Uta, Alexandru and Custura, Alexandru and Duplyakin, Dmitry and Jimenez, Ivo and Rellermeyer, Jan and Maltzahn, Carlos and Ricci, Robert and Iosup, Alexandru "Is Big Data Performance Reproducible in Modern Cloud Networks?" Proceedings of the Seventeenth USENIX Symposium on Networked Systems Design and Implementation (NSDI) , 2029 Citation Details

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.

This project continues and expands the popular CloudLab facility, first funded under grant CNS-1419199, by addressing specific categories of user needs: (1) Adding capabilities to support research on the frontiers of cloud computing. For example, common requests from CloudLab users include deep control over switching infrastructure, programmable network interfaces and other user-programmable accelerators, and advanced monitoring capabilities. (2) Adding significant capacity to the CloudLab facility to alleviate concerns around research infrastructure availability during periods of high demand. (3) Evolving CloudLab as a platform for building community resources. Here, the project facilitated sub-communities within the large CloudLab user community to self-organize and share resources; supported richer environments for describing complex, evolving experiments; and provided a world-class set of tools to further repeatable research within the Computer Science community. (4) CloudLab has turned out to be an attractive platform for enabling the future of cyberinfrastructure for science. The project supported other CI projects by partnering with the NSF PAWR program and actively assisting other NSF projects such as CyVerse.


Intellectual merit: Because the research done by CloudLab's is a primary "result" from the platform, the project personnel have put more effort into automating the way that we find published research that uses the platform. For instance, the project implemented a system that uses the Scopus scientific publication database to automate finding these publications. This system does two searches: one for "CloudLab" in the text of papers and citations to the main CloudLab papers; and another that searches for users in our database. To make sure that the right users have been found, the portal shows the user one of the publications found for "them" and asks for confirmation.


Broader impact: CloudLab has revolutionized how computer systems research is performed. Every major computer systems conference, including OSDI, SOSP, NSDI, and SIGCOMM, includes several papers whose empirical results have used CloudLab infrastructure as their primary testbed. CloudLab has also played a significant role in supporting education, by providing compute resources to support courses taught across the world, notably in helping develop and scale large popular courses, such as “Big Data Systems” at UT Austin and UW Madison. Likewise, CloudLab has played an important role in helping with experimental research on standing up large compute to aid in the analysis of large datasets in domain science applications. 



 


Last Modified: 02/12/2023
Modified by: Aditya Akella

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

Print this page

Back to Top of page