RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows

Subedi, Pradeep; Davis, Philip E.; Parashar, Manish

doi:10.1109/cluster48925.2021.00021

Title: RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows

Abstract

While in-situ workflow formulations have addressed some of the data-related challenges associated with extreme-scale scientific workflows, these workflows involve complex interactions and different modes of data exchange. In the context of increasing system complexity, such workflows present significant resource management challenges, requiring complex cost-performance tradeoffs. This paper presents RISE, an intelligent staging-based data management middleware, which builds on the DataSpaces framework and performs intelligent scheduling of data management operations to reduce I/O contention. In RISE, data are always written immediately to local buffers to reduce the effect of the transfer impact upon application performance. RISE identifies applications’ data access patterns and moves data towards data consumers only when the network is expected to be idle, reducing the impact of asynchronous background data movement upon critical data read/write requests. Here, we experimentally demonstrate that RISE can take advantage of staging nodes to offload data during writes without degrading application data movement performance.

Authors:

Subedi, Pradeep ^[1]; Davis, Philip E. ^[1]; Parashar, Manish ^[1]

Univ. of Utah, Salt Lake City, UT (United States)

Publication Date:: 2021-09-01

Research Org.:: Rutgers Univ., Piscataway, NJ (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR). Scientific Discovery through Advanced Computing (SciDAC)

OSTI Identifier:: 1907691

Grant/Contract Number:: SC0021326; AC05-00OR22725

Resource Type:: Journal Article: Accepted Manuscript

Journal Name:: Proceedings - IEEE International Conference on Cluster Computing (Online)

Additional Journal Information:: Journal Volume: 2021; Conference: 2021 IEEE International Conference on Cluster Computing (CLUSTER), Portland, OR (United States), 7-10 Sep 2021; Journal ID: ISSN 2168-9253

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; Extreme Scale Data Staging; Machine Learning; Data Management; High Performance Computing

Citation Formats


                    Subedi, Pradeep, Davis, Philip E., and Parashar, Manish. RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows.  United States: N. p., 2021. 
        Web.  doi:10.1109/cluster48925.2021.00021.

Copy to clipboard


                    Subedi, Pradeep, Davis, Philip E., & Parashar, Manish. RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows.  United States.  https://doi.org/10.1109/cluster48925.2021.00021

Copy to clipboard


                    Subedi, Pradeep, Davis, Philip E., and Parashar, Manish. 2021.  
        "RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows".  United States.  https://doi.org/10.1109/cluster48925.2021.00021.  https://www.osti.gov/servlets/purl/1907691.

Copy to clipboard


                    
@article{osti_1907691,

  title        = {RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows},

  author       = {Subedi, Pradeep and Davis, Philip E. and Parashar, Manish},

  abstractNote = {While in-situ workflow formulations have addressed some of the data-related challenges associated with extreme-scale scientific workflows, these workflows involve complex interactions and different modes of data exchange. In the context of increasing system complexity, such workflows present significant resource management challenges, requiring complex cost-performance tradeoffs. This paper presents RISE, an intelligent staging-based data management middleware, which builds on the DataSpaces framework and performs intelligent scheduling of data management operations to reduce I/O contention. In RISE, data are always written immediately to local buffers to reduce the effect of the transfer impact upon application performance. RISE identifies applications’ data access patterns and moves data towards data consumers only when the network is expected to be idle, reducing the impact of asynchronous background data movement upon critical data read/write requests. Here, we experimentally demonstrate that RISE can take advantage of staging nodes to offload data during writes without degrading application data movement performance.},

  doi          = {10.1109/cluster48925.2021.00021},

  url          = {https://www.osti.gov/biblio/1907691},
  journal      = {Proceedings - IEEE International Conference on Cluster Computing (Online)},

  issn         = {2168-9253},

  number       = ,

  volume       = 2021,

  place        = {United States},

  year         = {2021},

  month        = {9}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/cluster48925.2021.00021

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

In-memory staging and data-centric task placement for coupled scientific simulation workflows: In-memory staging and data-centric task placement for coupled scientific simulation workflows
journal, April 2017

Zhang, Fan; Jin, Tong; Sun, Qian
Concurrency and Computation: Practice and Experience, Vol. 29, Issue 12
https://doi.org/10.1002/cpe.4147

Dual space analysis of turbulent combustion particle data
conference, March 2011

Wei, Jishang; Yu, Hongfeng; Grout, Ray W.
2011 IEEE Pacific Visualization Symposium
https://doi.org/10.1109/PACIFICVIS.2011.5742377

Opportunities for Nonvolatile Memory Systems in Extreme-Scale High-Performance Computing
journal, March 2015

Vetter, Jeffrey S.; Mittal, Sparsh
Computing in Science & Engineering, Vol. 17, Issue 2
https://doi.org/10.1109/MCSE.2015.4

DeStager: feature guided in-situ data management in distributed deep memory hierarchies
journal, August 2018

Zhang, Xuechen; Zheng, Fang; Nguyen, Bao
Distributed and Parallel Databases, Vol. 37, Issue 1
https://doi.org/10.1007/s10619-018-7235-3

DataSpaces: an interaction and coordination framework for coupled simulation workflows
journal, February 2011

Docan, Ciprian; Parashar, Manish; Klasky, Scott
Cluster Computing, Vol. 15, Issue 2
https://doi.org/10.1007/s10586-011-0162-y

ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing: ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing
journal, October 2014

Docan, Ciprian; Zhang, Fan; Jin, Tong
Concurrency and Computation: Practice and Experience, Vol. 27, Issue 14
https://doi.org/10.1002/cpe.3407

Omnisc'IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction
conference, November 2014

Dorier, Matthieu; Ibrahim, Shadi; Antoniu, Gabriel
SC14: International Conference for High Performance Computing, Networking, Storage and Analysis
https://doi.org/10.1109/SC.2014.56

Addressing data resiliency for staging based scientific workflows
conference, November 2019

Duan, Shaohua; Subedi, Pradeep; Davis, Philip E.
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
https://doi.org/10.1145/3295500.3356158

Scalable Data Resilience for In-memory Data Staging
conference, May 2018

Duan, Shaohua; Subedi, Pradeep; Teranishi, Keita
2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
https://doi.org/10.1109/IPDPS.2018.00021

Computing Just What You Need: Online Data Analysis and Reduction at Extreme Scales
conference, December 2017

Foster, Ian
2017 IEEE 24th International Conference on High Performance Computing (HiPC)
https://doi.org/10.1109/HiPC.2017.00042

ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management
journal, July 2020

Godoy, William F.; Podhorszki, Norbert; Wang, Ruonan
SoftwareX, Vol. 12
https://doi.org/10.1016/j.softx.2020.100561

Exploring Data Staging Across Deep Memory Hierarchies for Coupled Data Intensive Simulation Workflows
conference, May 2015

Jin, Tong; Zhang, Fan; Sun, Qian
2015 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
https://doi.org/10.1109/IPDPS.2015.50

Full-f gyrokinetic particle simulation of centrally heated global ITG turbulence from magnetic axis to edge pedestal top in a realistic tokamak geometry
journal, September 2009

Ku, S.; Chang, C. S.; Diamond, P. H.
Nuclear Fusion, Vol. 49, Issue 11
https://doi.org/10.1088/0029-5515/49/11/115021

Lynx: a learning linux prefetching mechanism for SSD performance model
conference, August 2016

Laga, Arezki; Boukhobza, Jalil; Koskas, Michel
2016 5th Non-Volatile Memory Systems and Applications Symposium (NVMSA)
https://doi.org/10.1109/NVMSA.2016.7547186

Leveraging Machine Learning for Anticipatory Data Delivery in Extreme Scale In-situ Workflows
conference, September 2019

Subedi, Pradeep; Davis, Philip E.; Parashar, Manish
2019 IEEE International Conference on Cluster Computing (CLUSTER)
https://doi.org/10.1109/CLUSTER.2019.8891003

Terascale direct numerical simulations of turbulent combustion using S3D
journal, January 2009

Chen, J. H.; Choudhary, A.; de Supinski, B.
Computational Science & Discovery, Vol. 2, Issue 1
https://doi.org/10.1088/1749-4699/2/1/015001

Stacker: An Autonomic Data Movement Engine for Extreme-Scale Data Staging-Based In-Situ Workflows
conference, November 2018

Subedi, Pradeep; Davis, Philip; Duan, Shaohua
SC18: International Conference for High Performance Computing, Networking, Storage and Analysis
https://doi.org/10.1109/SC.2018.00076

Flexpath: Type-Based Publish/Subscribe System for Large-Scale Science Analytics
conference, May 2014

Dayal, Jai; Bratcher, Drew; Eisenhauer, Greg
2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)
https://doi.org/10.1109/CCGrid.2014.104

Adaptive data placement for staging-based coupled scientific workflows
conference, January 2015

Sun, Qian; Parashar, Manish; Jin, Tong
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '15
https://doi.org/10.1145/2807591.2807669

Practical prefetching via data compression
conference, January 1993

Curewitz, Kenneth M.; Krishnan, P.; Vitter, Jeffrey Scott
Proceedings of the 1993 ACM SIGMOD international conference on Management of data - SIGMOD '93
https://doi.org/10.1145/170035.170077

The future of scientific workflows
journal, April 2017

Deelman, Ewa; Peterka, Tom; Altintas, Ilkay
The International Journal of High Performance Computing Applications, Vol. 32, Issue 1
https://doi.org/10.1177/1094342017704893

Combining in-situ and in-transit processing to enable extreme-scale scientific analysis
conference, November 2012

Bennett, Janine C.; Abbasi, Hasan; Bremer, Peer-Timo
2012 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, 2012 International Conference for High Performance Computing, Networking, Storage and Analysis
https://doi.org/10.1109/SC.2012.31

Moving the Code to the Data - Dynamic Code Deployment Using ActiveSpaces
conference, May 2011

Docan, Ciprian; Parashar, Manish; Cummings, Julian
Distributed Processing Symposium (IPDPS), 2011 IEEE International Parallel & Distributed Processing Symposium
https://doi.org/10.1109/IPDPS.2011.120

DataStager: scalable data staging services for petascale applications
journal, June 2010

Abbasi, Hasan; Wolf, Matthew; Eisenhauer, Greg
Cluster Computing, Vol. 13, Issue 3
https://doi.org/10.1007/s10586-010-0135-6

Scientific workflow management and the Kepler system
journal, January 2006

Ludäscher, Bertram; Altintas, Ilkay; Berkley, Chad
Concurrency and Computation: Practice and Experience, Vol. 18, Issue 10
https://doi.org/10.1002/cpe.994

Identifying Hierarchical Structure in Sequences: A linear-time algorithm
journal, September 1997

Nevill-Manning, C. G.; Witten, I. H.
Journal of Artificial Intelligence Research, Vol. 7
https://doi.org/10.1613/jair.374

In Situ Visualization at Extreme Scale: Challenges and Opportunities
journal, November 2009

Kwan-Liu Ma,
IEEE Computer Graphics and Applications, Vol. 29, Issue 6
https://doi.org/10.1109/MCG.2009.120

Taverna: a tool for the composition and enactment of bioinformatics workflows
journal, June 2004

Oinn, T.; Addis, M.; Ferris, J.
Bioinformatics, Vol. 20, Issue 17
https://doi.org/10.1093/bioinformatics/bth361

Mercury: Enabling remote procedure call for high-performance computing
conference, September 2013

Soumagne, Jerome; Kimpe, Dries; Zounmevo, Judicael
2013 IEEE International Conference on Cluster Computing (CLUSTER)
https://doi.org/10.1109/CLUSTER.2013.6702617

Mochi: Composing Data Services for High-Performance Computing Environments
journal, January 2020

Ross, Robert B.; Amvrosiadis, George; Carns, Philip
Journal of Computer Science and Technology, Vol. 35, Issue 1
https://doi.org/10.1007/s11390-020-9802-0

Similar records in OSTI.GOV collections:

In-Staging Data Placement for Asynchronous Coupling of Task-Based Scientific Workflows, In: 2016 Second International Workshop on Extreme Scale Programming Models and Middlewar (ESPM2)

Conference Sun, Qian; Romanus, Melissa; Jin, Tong; ... - PROCEEDINGS OF SECOND INTERNATIONAL WORKSHOP ON EXTREME SCALE PROGRAMMING MODELS AND MIDDLEWARE (ESPM2 2016)

Coupled application workflows composed of applications implemented using task-based models present new coupling and data exchange challenges, due to the asynchronous interaction and coupling behaviors between tasks of the component applications. In this paper, we present an adaptive data placement approach that addresses these challenges by dynamically adjusting to the asynchronous coupling patterns. Specifically, it places data across a set of staging cores/nodes with an awareness of the application-specific data locality requirements and the runtime task executions at these staging cores/nodes, with the goal of reducing end-to-end execution time and data movement overhead of the workflow. We experimentally demonstrate themore »« less
https://doi.org/10.1109/ESPM2.2016.12
CoREC: Scalable and Resilient In-memory Data Staging for In-situ Workflows

Journal Article Duan, Shaohua; Subedi, Pradeep; Davis, Philip; ... - ACM Transactions on Parallel Computing

The dramatic increase in the scale of current and planned high-end HPC systems is leading new challenges, such as the growing costs of data movement and IO, and the reduced mean time between failures (MTBF) of system components. In-situ workflows, i.e., executing the entire application workflows on the HPC system, have emerged as an attractive approach to address data-related challenges by moving computations closer to the data, and staging-based frameworks have been effectively used to support in-situ workflows at scale. However, the resilience of these staging-based solutions has not been addressed, and they remain susceptible to expensive data failures. Furthermore,more »« less
https://doi.org/10.1145/3391448

Full Text Available
Combining In-situ and In-transit Processing to Enable Extreme-Scale Scientific Analysis

Conference Bennett, Janine; Abbasi, Hasan; Bremer, Peer-Timo; ...

With the onset of extreme-scale computing, I/O constraints make it increasingly difficult for scientists to save a sufficient amount of raw simulation data to persistent storage. One potential solution is to change the data analysis pipeline from a post-process centric to a concurrent approach based on either in-situ or in-transit processing. In this context computations are considered in-situ if they utilize the primary compute resources, while in-transit processing refers to offloading computations toa set of secondary resources using asynchronous data transfers. In this paper we explore the design and implementation of three common analysis techniques typically performed on large-scale scientificmore »« less
https://doi.org/10.1109/SC.2012.31

Full Text Available
DataSpaces: an interaction and coordination framework for coupled simulation workflows

Journal Article Docan, Ciprian; Parashar, Manish; Klasky, Scott - Cluster Computing

Emerging high-performance distributed computing environments are enabling new end-to-end formulations in science and engineering that involve multiple interacting processes and data-intensive application workflows. For example, current fusion simulation efforts are exploring coupled models and codes that simultaneously simulate separate application processes, such as the core and the edge turbulence. These components run on different high performance computing resources, need to interact at runtime with each other and with services for data monitoring, data analysis and visualization, and data archiving. As a result, they require efficient and scalable support for dynamic and flexible couplings and interactions, which remains a challenge. Thismore »« less
https://doi.org/10.1007/s10586-011-0162-y
Optimizing the Energy Usage and Cognitive Value of Extreme-Scale Data-Analysis Approaches

Technical Report Samsel, Francesca

Scientific discovery at the extreme scale is a unique technical challenge, requiring the reduction of massive amounts of data into compact analysis products that capture key scientific insights. This analysis process needs to occur under extreme-scale computational constraints including minimizing 1) data movement, 2) energy usage and 3) storage usage. Put simply, extreme-scale computing platforms are to achieve a three orders-of-magnitude increase in computational performance while consuming only two times the electrical power of current platforms. Data movement costs will dominate energy usage at this scale, so the HPC community expects extreme scale analysis algorithms will be utilized to reducemore »« less
https://doi.org/10.2172/1503679

Full Text Available

Similar Records

Title: RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows

Abstract

Citation Formats

In-memory staging and data-centric task placement for coupled scientific simulation workflows: In-memory staging and data-centric task placement for coupled scientific simulation workflows journal, April 2017

Dual space analysis of turbulent combustion particle data conference, March 2011

Opportunities for Nonvolatile Memory Systems in Extreme-Scale High-Performance Computing journal, March 2015

DeStager: feature guided in-situ data management in distributed deep memory hierarchies journal, August 2018

DataSpaces: an interaction and coordination framework for coupled simulation workflows journal, February 2011

ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing: ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing journal, October 2014

Omnisc'IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction conference, November 2014

Addressing data resiliency for staging based scientific workflows conference, November 2019

Scalable Data Resilience for In-memory Data Staging conference, May 2018

Computing Just What You Need: Online Data Analysis and Reduction at Extreme Scales conference, December 2017

ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management journal, July 2020

Exploring Data Staging Across Deep Memory Hierarchies for Coupled Data Intensive Simulation Workflows conference, May 2015

Full-f gyrokinetic particle simulation of centrally heated global ITG turbulence from magnetic axis to edge pedestal top in a realistic tokamak geometry journal, September 2009

Lynx: a learning linux prefetching mechanism for SSD performance model conference, August 2016

Leveraging Machine Learning for Anticipatory Data Delivery in Extreme Scale In-situ Workflows conference, September 2019

Terascale direct numerical simulations of turbulent combustion using S3D journal, January 2009

Stacker: An Autonomic Data Movement Engine for Extreme-Scale Data Staging-Based In-Situ Workflows conference, November 2018

Flexpath: Type-Based Publish/Subscribe System for Large-Scale Science Analytics conference, May 2014

Adaptive data placement for staging-based coupled scientific workflows conference, January 2015

Practical prefetching via data compression conference, January 1993

The future of scientific workflows journal, April 2017

Combining in-situ and in-transit processing to enable extreme-scale scientific analysis conference, November 2012

Moving the Code to the Data - Dynamic Code Deployment Using ActiveSpaces conference, May 2011

DataStager: scalable data staging services for petascale applications journal, June 2010

Scientific workflow management and the Kepler system journal, January 2006

Identifying Hierarchical Structure in Sequences: A linear-time algorithm journal, September 1997

In Situ Visualization at Extreme Scale: Challenges and Opportunities journal, November 2009

Taverna: a tool for the composition and enactment of bioinformatics workflows journal, June 2004

Mercury: Enabling remote procedure call for high-performance computing conference, September 2013

Mochi: Composing Data Services for High-Performance Computing Environments journal, January 2020

In-memory staging and data-centric task placement for coupled scientific simulation workflows: In-memory staging and data-centric task placement for coupled scientific simulation workflows
journal, April 2017

Dual space analysis of turbulent combustion particle data
conference, March 2011

Opportunities for Nonvolatile Memory Systems in Extreme-Scale High-Performance Computing
journal, March 2015

DeStager: feature guided in-situ data management in distributed deep memory hierarchies
journal, August 2018

DataSpaces: an interaction and coordination framework for coupled simulation workflows
journal, February 2011

ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing: ActiveSpaces: Exploring dynamic code deployment for extreme scale data processing
journal, October 2014

Omnisc'IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction
conference, November 2014

Addressing data resiliency for staging based scientific workflows
conference, November 2019

Scalable Data Resilience for In-memory Data Staging
conference, May 2018

Computing Just What You Need: Online Data Analysis and Reduction at Extreme Scales
conference, December 2017

ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management
journal, July 2020

Exploring Data Staging Across Deep Memory Hierarchies for Coupled Data Intensive Simulation Workflows
conference, May 2015

Full-f gyrokinetic particle simulation of centrally heated global ITG turbulence from magnetic axis to edge pedestal top in a realistic tokamak geometry
journal, September 2009

Lynx: a learning linux prefetching mechanism for SSD performance model
conference, August 2016

Leveraging Machine Learning for Anticipatory Data Delivery in Extreme Scale In-situ Workflows
conference, September 2019

Terascale direct numerical simulations of turbulent combustion using S3D
journal, January 2009

Stacker: An Autonomic Data Movement Engine for Extreme-Scale Data Staging-Based In-Situ Workflows
conference, November 2018

Flexpath: Type-Based Publish/Subscribe System for Large-Scale Science Analytics
conference, May 2014

Adaptive data placement for staging-based coupled scientific workflows
conference, January 2015

Practical prefetching via data compression
conference, January 1993

The future of scientific workflows
journal, April 2017

Combining in-situ and in-transit processing to enable extreme-scale scientific analysis
conference, November 2012

Moving the Code to the Data - Dynamic Code Deployment Using ActiveSpaces
conference, May 2011

DataStager: scalable data staging services for petascale applications
journal, June 2010

Scientific workflow management and the Kepler system
journal, January 2006

Identifying Hierarchical Structure in Sequences: A linear-time algorithm
journal, September 1997

In Situ Visualization at Extreme Scale: Challenges and Opportunities
journal, November 2009

Taverna: a tool for the composition and enactment of bioinformatics workflows
journal, June 2004

Mercury: Enabling remote procedure call for high-performance computing
conference, September 2013

Mochi: Composing Data Services for High-Performance Computing Environments
journal, January 2020