Deferred runtime pipelining for contentious multicore software transactions

Shuai Mu, Sebastian Angel, Dennis Shasha

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

Abstract

DRP is a new concurrency control protocol for software transactional memory that achieves high throughput, even for skewed workloads that exhibit high contention. DRP builds on prior works that chop transactions into pieces to expose more concurrency opportunities, but unlike these works, DRP performs no static analyses and supports arbitrary workloads. DRP achieves a high degree of concurrency across most workloads and guarantees deadlock freedom, strict serializability, and opacity. We incorporate DRP into the software transactional objects library STO [18] and find that DRP improves STO’s throughput on several STAMP benchmarks by up to 3.6×. Additionally, an in-memory multicore database implemented with our modified variant of STO outperforms databases that use OCC or transaction chopping for concurrency control. Specifically, DRP achieves 6.6× higher throughput than OCC when contention is high. Compared to transaction chopping, DRP achieves 3.3× higher throughput when contention is medium or low. Furthermore, our implementation achieves comparable performance to OCC and transaction chopping at other contention levels.

Original languageEnglish (US)
Title of host publicationProceedings of the 14th EuroSys Conference 2019
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450362818
DOIs
StatePublished - Mar 25 2019
Event14th European Conference on Computer Systems, EuroSys 2019 - Dresden, Germany
Duration: Mar 25 2019Mar 28 2019

Publication series

NameProceedings of the 14th EuroSys Conference 2019

Conference

Conference14th European Conference on Computer Systems, EuroSys 2019
CountryGermany
CityDresden
Period3/25/193/28/19

Fingerprint

Throughput
Concurrency control
Data storage equipment
Opacity
Network protocols

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Mu, S., Angel, S., & Shasha, D. (2019). Deferred runtime pipelining for contentious multicore software transactions. In Proceedings of the 14th EuroSys Conference 2019 [3303966] (Proceedings of the 14th EuroSys Conference 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3302424.3303966

Deferred runtime pipelining for contentious multicore software transactions. / Mu, Shuai; Angel, Sebastian; Shasha, Dennis.

Proceedings of the 14th EuroSys Conference 2019. Association for Computing Machinery, Inc, 2019. 3303966 (Proceedings of the 14th EuroSys Conference 2019).

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

Mu, S, Angel, S & Shasha, D 2019, Deferred runtime pipelining for contentious multicore software transactions. in Proceedings of the 14th EuroSys Conference 2019., 3303966, Proceedings of the 14th EuroSys Conference 2019, Association for Computing Machinery, Inc, 14th European Conference on Computer Systems, EuroSys 2019, Dresden, Germany, 3/25/19. https://doi.org/10.1145/3302424.3303966
Mu S, Angel S, Shasha D. Deferred runtime pipelining for contentious multicore software transactions. In Proceedings of the 14th EuroSys Conference 2019. Association for Computing Machinery, Inc. 2019. 3303966. (Proceedings of the 14th EuroSys Conference 2019). https://doi.org/10.1145/3302424.3303966
Mu, Shuai ; Angel, Sebastian ; Shasha, Dennis. / Deferred runtime pipelining for contentious multicore software transactions. Proceedings of the 14th EuroSys Conference 2019. Association for Computing Machinery, Inc, 2019. (Proceedings of the 14th EuroSys Conference 2019).
@inproceedings{aaa0415090f148b8af60ca120d44f9a0,
title = "Deferred runtime pipelining for contentious multicore software transactions",
abstract = "DRP is a new concurrency control protocol for software transactional memory that achieves high throughput, even for skewed workloads that exhibit high contention. DRP builds on prior works that chop transactions into pieces to expose more concurrency opportunities, but unlike these works, DRP performs no static analyses and supports arbitrary workloads. DRP achieves a high degree of concurrency across most workloads and guarantees deadlock freedom, strict serializability, and opacity. We incorporate DRP into the software transactional objects library STO [18] and find that DRP improves STO’s throughput on several STAMP benchmarks by up to 3.6×. Additionally, an in-memory multicore database implemented with our modified variant of STO outperforms databases that use OCC or transaction chopping for concurrency control. Specifically, DRP achieves 6.6× higher throughput than OCC when contention is high. Compared to transaction chopping, DRP achieves 3.3× higher throughput when contention is medium or low. Furthermore, our implementation achieves comparable performance to OCC and transaction chopping at other contention levels.",
author = "Shuai Mu and Sebastian Angel and Dennis Shasha",
year = "2019",
month = "3",
day = "25",
doi = "10.1145/3302424.3303966",
language = "English (US)",
series = "Proceedings of the 14th EuroSys Conference 2019",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of the 14th EuroSys Conference 2019",

}

TY - GEN

T1 - Deferred runtime pipelining for contentious multicore software transactions

AU - Mu, Shuai

AU - Angel, Sebastian

AU - Shasha, Dennis

PY - 2019/3/25

Y1 - 2019/3/25

N2 - DRP is a new concurrency control protocol for software transactional memory that achieves high throughput, even for skewed workloads that exhibit high contention. DRP builds on prior works that chop transactions into pieces to expose more concurrency opportunities, but unlike these works, DRP performs no static analyses and supports arbitrary workloads. DRP achieves a high degree of concurrency across most workloads and guarantees deadlock freedom, strict serializability, and opacity. We incorporate DRP into the software transactional objects library STO [18] and find that DRP improves STO’s throughput on several STAMP benchmarks by up to 3.6×. Additionally, an in-memory multicore database implemented with our modified variant of STO outperforms databases that use OCC or transaction chopping for concurrency control. Specifically, DRP achieves 6.6× higher throughput than OCC when contention is high. Compared to transaction chopping, DRP achieves 3.3× higher throughput when contention is medium or low. Furthermore, our implementation achieves comparable performance to OCC and transaction chopping at other contention levels.

AB - DRP is a new concurrency control protocol for software transactional memory that achieves high throughput, even for skewed workloads that exhibit high contention. DRP builds on prior works that chop transactions into pieces to expose more concurrency opportunities, but unlike these works, DRP performs no static analyses and supports arbitrary workloads. DRP achieves a high degree of concurrency across most workloads and guarantees deadlock freedom, strict serializability, and opacity. We incorporate DRP into the software transactional objects library STO [18] and find that DRP improves STO’s throughput on several STAMP benchmarks by up to 3.6×. Additionally, an in-memory multicore database implemented with our modified variant of STO outperforms databases that use OCC or transaction chopping for concurrency control. Specifically, DRP achieves 6.6× higher throughput than OCC when contention is high. Compared to transaction chopping, DRP achieves 3.3× higher throughput when contention is medium or low. Furthermore, our implementation achieves comparable performance to OCC and transaction chopping at other contention levels.

UR - http://www.scopus.com/inward/record.url?scp=85063867954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063867954&partnerID=8YFLogxK

U2 - 10.1145/3302424.3303966

DO - 10.1145/3302424.3303966

M3 - Conference contribution

T3 - Proceedings of the 14th EuroSys Conference 2019

BT - Proceedings of the 14th EuroSys Conference 2019

PB - Association for Computing Machinery, Inc

ER -