Integration of burst buffer in high-level parallel I/O library for exa-scale computing era

Kaiyuan Hou, Reda Al-Bahrani, Esteban Rangel, Ankit Agrawal, Robert Latham, Robert Ross, Alok Nidhi Choudhary, Wei-Keng Liao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While the computing power of supercomputers continues to improve at an astonishing rate, companion I/O systems are struggling to keep up in performance. To mitigate the performance gap, several supercomputing systems have been configured to incorporate burst buffers into their I/O stack; the exact role of which, however, still remains unclear. In this paper, we examine the features of burst buffers and study their impact on application I/O performance. Our goal is to demonstrate that burst buffers can be utilized by parallel I/O libraries to significantly improve performance. To this end, we developed an I/O driver in PnetCDF that uses a log-based format to store individual I/O requests on the burst buffer-later to be flushed to the parallel file system as one request. We evaluated our implementation by running standard I/O benchmarks on Cori, a Cray XC40 supercomputer at NERSC with a centralized burst buffer system, and Theta, a Cray XC40 supercomputer at ALCF with locally available SSDs. Our results show that IO aggregation is a promising role for burst buffers in high-level I/O libraries.

Original languageEnglish (US)
Title of host publicationProceedings of PDSW-DISCS 2018
Subtitle of host publication3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-12
Number of pages12
ISBN (Electronic)9781728101927
DOIs
StatePublished - Feb 8 2019
Event3rd IEEE/ACM Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, PDSW-DISCS 2018 - Dallas, United States
Duration: Nov 12 2018 → …

Publication series

NameProceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference3rd IEEE/ACM Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, PDSW-DISCS 2018
CountryUnited States
CityDallas
Period11/12/18 → …

Fingerprint

Supercomputers
Computer systems
Agglomeration

Keywords

  • Exa-scale
  • Log
  • burst-buffer

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Hou, K., Al-Bahrani, R., Rangel, E., Agrawal, A., Latham, R., Ross, R., ... Liao, W-K. (2019). Integration of burst buffer in high-level parallel I/O library for exa-scale computing era. In Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 1-12). [8638428] (Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PDSW-DISCS.2018.000-1
Hou, Kaiyuan ; Al-Bahrani, Reda ; Rangel, Esteban ; Agrawal, Ankit ; Latham, Robert ; Ross, Robert ; Choudhary, Alok Nidhi ; Liao, Wei-Keng. / Integration of burst buffer in high-level parallel I/O library for exa-scale computing era. Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1-12 (Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis).
@inproceedings{0dc7f2cdd82d43e494441c66c77931fd,
title = "Integration of burst buffer in high-level parallel I/O library for exa-scale computing era",
abstract = "While the computing power of supercomputers continues to improve at an astonishing rate, companion I/O systems are struggling to keep up in performance. To mitigate the performance gap, several supercomputing systems have been configured to incorporate burst buffers into their I/O stack; the exact role of which, however, still remains unclear. In this paper, we examine the features of burst buffers and study their impact on application I/O performance. Our goal is to demonstrate that burst buffers can be utilized by parallel I/O libraries to significantly improve performance. To this end, we developed an I/O driver in PnetCDF that uses a log-based format to store individual I/O requests on the burst buffer-later to be flushed to the parallel file system as one request. We evaluated our implementation by running standard I/O benchmarks on Cori, a Cray XC40 supercomputer at NERSC with a centralized burst buffer system, and Theta, a Cray XC40 supercomputer at ALCF with locally available SSDs. Our results show that IO aggregation is a promising role for burst buffers in high-level I/O libraries.",
keywords = "Exa-scale, Log, burst-buffer",
author = "Kaiyuan Hou and Reda Al-Bahrani and Esteban Rangel and Ankit Agrawal and Robert Latham and Robert Ross and Choudhary, {Alok Nidhi} and Wei-Keng Liao",
year = "2019",
month = "2",
day = "8",
doi = "10.1109/PDSW-DISCS.2018.000-1",
language = "English (US)",
series = "Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--12",
booktitle = "Proceedings of PDSW-DISCS 2018",
address = "United States",

}

Hou, K, Al-Bahrani, R, Rangel, E, Agrawal, A, Latham, R, Ross, R, Choudhary, AN & Liao, W-K 2019, Integration of burst buffer in high-level parallel I/O library for exa-scale computing era. in Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis., 8638428, Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 1-12, 3rd IEEE/ACM Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, PDSW-DISCS 2018, Dallas, United States, 11/12/18. https://doi.org/10.1109/PDSW-DISCS.2018.000-1

Integration of burst buffer in high-level parallel I/O library for exa-scale computing era. / Hou, Kaiyuan; Al-Bahrani, Reda; Rangel, Esteban; Agrawal, Ankit; Latham, Robert; Ross, Robert; Choudhary, Alok Nidhi; Liao, Wei-Keng.

Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1-12 8638428 (Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Integration of burst buffer in high-level parallel I/O library for exa-scale computing era

AU - Hou, Kaiyuan

AU - Al-Bahrani, Reda

AU - Rangel, Esteban

AU - Agrawal, Ankit

AU - Latham, Robert

AU - Ross, Robert

AU - Choudhary, Alok Nidhi

AU - Liao, Wei-Keng

PY - 2019/2/8

Y1 - 2019/2/8

N2 - While the computing power of supercomputers continues to improve at an astonishing rate, companion I/O systems are struggling to keep up in performance. To mitigate the performance gap, several supercomputing systems have been configured to incorporate burst buffers into their I/O stack; the exact role of which, however, still remains unclear. In this paper, we examine the features of burst buffers and study their impact on application I/O performance. Our goal is to demonstrate that burst buffers can be utilized by parallel I/O libraries to significantly improve performance. To this end, we developed an I/O driver in PnetCDF that uses a log-based format to store individual I/O requests on the burst buffer-later to be flushed to the parallel file system as one request. We evaluated our implementation by running standard I/O benchmarks on Cori, a Cray XC40 supercomputer at NERSC with a centralized burst buffer system, and Theta, a Cray XC40 supercomputer at ALCF with locally available SSDs. Our results show that IO aggregation is a promising role for burst buffers in high-level I/O libraries.

AB - While the computing power of supercomputers continues to improve at an astonishing rate, companion I/O systems are struggling to keep up in performance. To mitigate the performance gap, several supercomputing systems have been configured to incorporate burst buffers into their I/O stack; the exact role of which, however, still remains unclear. In this paper, we examine the features of burst buffers and study their impact on application I/O performance. Our goal is to demonstrate that burst buffers can be utilized by parallel I/O libraries to significantly improve performance. To this end, we developed an I/O driver in PnetCDF that uses a log-based format to store individual I/O requests on the burst buffer-later to be flushed to the parallel file system as one request. We evaluated our implementation by running standard I/O benchmarks on Cori, a Cray XC40 supercomputer at NERSC with a centralized burst buffer system, and Theta, a Cray XC40 supercomputer at ALCF with locally available SSDs. Our results show that IO aggregation is a promising role for burst buffers in high-level I/O libraries.

KW - Exa-scale

KW - Log

KW - burst-buffer

UR - http://www.scopus.com/inward/record.url?scp=85063039350&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063039350&partnerID=8YFLogxK

U2 - 10.1109/PDSW-DISCS.2018.000-1

DO - 10.1109/PDSW-DISCS.2018.000-1

M3 - Conference contribution

T3 - Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 1

EP - 12

BT - Proceedings of PDSW-DISCS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hou K, Al-Bahrani R, Rangel E, Agrawal A, Latham R, Ross R et al. Integration of burst buffer in high-level parallel I/O library for exa-scale computing era. In Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1-12. 8638428. (Proceedings of PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage and Data Intensive Scalable Computing Systems, Held in conjunction with SC 2018: The International Conference for High Performance Computing, Networking, Storage and Analysis). https://doi.org/10.1109/PDSW-DISCS.2018.000-1