TraceTracker

Hardware/software co-evaluation for large-scale I/O workload reconstruction

Miryeong Kwon, Jie Zhang, Gyuyoung Park, Wonil Choi, David Donofrio, John Shalf, Mahmut Kandemir, Myoungsoo Jung

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

3 Citations (Scopus)

Abstract

Block traces are widely used for system studies, model verifications, and design analyses in both industry and academia. While such traces include detailed block access patterns, existing trace-driven research unfortunately often fails to find true-north due to a lack of runtime contexts such as user idle periods and system delays, which are fundamentally linked to the characteristics of target storage hardware. In this work, we propose TraceTracker, a novel hardware/software co-evaluation method that allows users to reuse a broad range of the existing block traces by keeping most their execution contexts and user scenarios while adjusting them with new system information. Specifically, our TraceTracker's software evaluation model can infer CPU burst times and user idle periods from old storage traces, whereas its hardware evaluation method remasters the storage traces by interoperating the inferred time information, and updates all inter-arrival times by making them aware of the target storage system. We apply the proposed co-evaluation model to 577 traces, which were collected by servers from different institutions and locations a decade ago, and revive the traces on a high-performance flash-based storage array. The evaluation results reveal that the accuracy of the execution contexts reconstructed by TraceTracker is on average 99% and 96% with regard to the frequency of idle operations and the total idle periods, respectively.

Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages87-96
Number of pages10
ISBN (Electronic)9781538612323
DOIs
Publication statusPublished - 2017 Dec 5
Event2017 IEEE International Symposium on Workload Characterization, IISWC 2017 - Seattle, United States
Duration: 2017 Oct 12017 Oct 3

Publication series

NameProceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
Volume2017-January

Other

Other2017 IEEE International Symposium on Workload Characterization, IISWC 2017
CountryUnited States
CitySeattle
Period17/10/117/10/3

Fingerprint

Hardware
Program processors
Information systems
Servers
Workload
Evaluation
Software
Industry
Evaluation method
Evaluation model

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Information Systems and Management

Cite this

Kwon, M., Zhang, J., Park, G., Choi, W., Donofrio, D., Shalf, J., ... Jung, M. (2017). TraceTracker: Hardware/software co-evaluation for large-scale I/O workload reconstruction. In Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017 (pp. 87-96). (Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IISWC.2017.8167759
Kwon, Miryeong ; Zhang, Jie ; Park, Gyuyoung ; Choi, Wonil ; Donofrio, David ; Shalf, John ; Kandemir, Mahmut ; Jung, Myoungsoo. / TraceTracker : Hardware/software co-evaluation for large-scale I/O workload reconstruction. Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 87-96 (Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017).
@inproceedings{31d881256df6483989e8e20637848897,
title = "TraceTracker: Hardware/software co-evaluation for large-scale I/O workload reconstruction",
abstract = "Block traces are widely used for system studies, model verifications, and design analyses in both industry and academia. While such traces include detailed block access patterns, existing trace-driven research unfortunately often fails to find true-north due to a lack of runtime contexts such as user idle periods and system delays, which are fundamentally linked to the characteristics of target storage hardware. In this work, we propose TraceTracker, a novel hardware/software co-evaluation method that allows users to reuse a broad range of the existing block traces by keeping most their execution contexts and user scenarios while adjusting them with new system information. Specifically, our TraceTracker's software evaluation model can infer CPU burst times and user idle periods from old storage traces, whereas its hardware evaluation method remasters the storage traces by interoperating the inferred time information, and updates all inter-arrival times by making them aware of the target storage system. We apply the proposed co-evaluation model to 577 traces, which were collected by servers from different institutions and locations a decade ago, and revive the traces on a high-performance flash-based storage array. The evaluation results reveal that the accuracy of the execution contexts reconstructed by TraceTracker is on average 99{\%} and 96{\%} with regard to the frequency of idle operations and the total idle periods, respectively.",
author = "Miryeong Kwon and Jie Zhang and Gyuyoung Park and Wonil Choi and David Donofrio and John Shalf and Mahmut Kandemir and Myoungsoo Jung",
year = "2017",
month = "12",
day = "5",
doi = "10.1109/IISWC.2017.8167759",
language = "English",
series = "Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "87--96",
booktitle = "Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017",
address = "United States",

}

Kwon, M, Zhang, J, Park, G, Choi, W, Donofrio, D, Shalf, J, Kandemir, M & Jung, M 2017, TraceTracker: Hardware/software co-evaluation for large-scale I/O workload reconstruction. in Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017. Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 87-96, 2017 IEEE International Symposium on Workload Characterization, IISWC 2017, Seattle, United States, 17/10/1. https://doi.org/10.1109/IISWC.2017.8167759

TraceTracker : Hardware/software co-evaluation for large-scale I/O workload reconstruction. / Kwon, Miryeong; Zhang, Jie; Park, Gyuyoung; Choi, Wonil; Donofrio, David; Shalf, John; Kandemir, Mahmut; Jung, Myoungsoo.

Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 87-96 (Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017; Vol. 2017-January).

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

TY - GEN

T1 - TraceTracker

T2 - Hardware/software co-evaluation for large-scale I/O workload reconstruction

AU - Kwon, Miryeong

AU - Zhang, Jie

AU - Park, Gyuyoung

AU - Choi, Wonil

AU - Donofrio, David

AU - Shalf, John

AU - Kandemir, Mahmut

AU - Jung, Myoungsoo

PY - 2017/12/5

Y1 - 2017/12/5

N2 - Block traces are widely used for system studies, model verifications, and design analyses in both industry and academia. While such traces include detailed block access patterns, existing trace-driven research unfortunately often fails to find true-north due to a lack of runtime contexts such as user idle periods and system delays, which are fundamentally linked to the characteristics of target storage hardware. In this work, we propose TraceTracker, a novel hardware/software co-evaluation method that allows users to reuse a broad range of the existing block traces by keeping most their execution contexts and user scenarios while adjusting them with new system information. Specifically, our TraceTracker's software evaluation model can infer CPU burst times and user idle periods from old storage traces, whereas its hardware evaluation method remasters the storage traces by interoperating the inferred time information, and updates all inter-arrival times by making them aware of the target storage system. We apply the proposed co-evaluation model to 577 traces, which were collected by servers from different institutions and locations a decade ago, and revive the traces on a high-performance flash-based storage array. The evaluation results reveal that the accuracy of the execution contexts reconstructed by TraceTracker is on average 99% and 96% with regard to the frequency of idle operations and the total idle periods, respectively.

AB - Block traces are widely used for system studies, model verifications, and design analyses in both industry and academia. While such traces include detailed block access patterns, existing trace-driven research unfortunately often fails to find true-north due to a lack of runtime contexts such as user idle periods and system delays, which are fundamentally linked to the characteristics of target storage hardware. In this work, we propose TraceTracker, a novel hardware/software co-evaluation method that allows users to reuse a broad range of the existing block traces by keeping most their execution contexts and user scenarios while adjusting them with new system information. Specifically, our TraceTracker's software evaluation model can infer CPU burst times and user idle periods from old storage traces, whereas its hardware evaluation method remasters the storage traces by interoperating the inferred time information, and updates all inter-arrival times by making them aware of the target storage system. We apply the proposed co-evaluation model to 577 traces, which were collected by servers from different institutions and locations a decade ago, and revive the traces on a high-performance flash-based storage array. The evaluation results reveal that the accuracy of the execution contexts reconstructed by TraceTracker is on average 99% and 96% with regard to the frequency of idle operations and the total idle periods, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85046466212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046466212&partnerID=8YFLogxK

U2 - 10.1109/IISWC.2017.8167759

DO - 10.1109/IISWC.2017.8167759

M3 - Conference contribution

T3 - Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017

SP - 87

EP - 96

BT - Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kwon M, Zhang J, Park G, Choi W, Donofrio D, Shalf J et al. TraceTracker: Hardware/software co-evaluation for large-scale I/O workload reconstruction. In Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 87-96. (Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017). https://doi.org/10.1109/IISWC.2017.8167759