서브메뉴
검색
Workload Adaptations for Contended Main-Memory Multicore Transactions- [electronic resource]
Workload Adaptations for Contended Main-Memory Multicore Transactions- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214095923
- ISBN
- 9798379604837
- DDC
- 004
- 서명/저자
- Workload Adaptations for Contended Main-Memory Multicore Transactions - [electronic resource]
- 발행사항
- [S.l.]: : Harvard University., 2022
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2022
- 형태사항
- 1 online resource(120 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
- 주기사항
- Advisor: Kohler, Eddie.
- 학위논문주기
- Thesis (Ph.D.)--Harvard University, 2022.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약Database transactions guarantee atomicity for complex queries. Recent work in main-memory multicore transaction processing systems have achieved high transaction processing throughput, especially for uncontended workloads. Many systems achieve high performance by implementing new concurrency control (CC) protocols. Notably, variants of optimistic concurrency control (OCC), such as single-version concurrency control (1VCC) and multi-version concurrency control (MVCC) can perform well even under contention. In this work, I present MSTO, an MVCC system implemented to evaluate CC performance without the impact of basis factors. Experimental results show that while MVCC does outperform over 1VCC in some scenarios, 1VCC is far more resilient to collapse at high contention than previously believed. 1VCC even outperforms MVCC on many high-contention workloads. I then introduce an optimization to reduce write-write conflicts between transactions, deferred updates. In conjunction with the static timestamp splitting optimization that reduces read-write conflicts, deferred updates can be very effective at improving transactional throughput for all CC protocols, including TPC-C throughputs of 5.68x for 1VCC and 4.72x for MVCC compared to their baselines. Finally, I present and evaluate adaptive timestamp splitting, which changes each record's partitioning strategy to accommodate workloads with heterogeneous access patterns. On workloads where 1VCC with deferred updates and adaptive timestamp splitting records the highest throughput, it commits up to 3.98x as many transactions as 1VCC with deferred updates and static timestamp splitting, and up to 4.43x as many transactions as baseline 1VCC. Not all workloads benefit from adaptive timestamp splitting, as baseline MVCC records greater throughput at very high contention.
- 일반주제명
- Computer science.
- 일반주제명
- Engineering.
- 기타저자
- Harvard University Engineering and Applied Sciences - Computer Science
- 기본자료저록
- Dissertations Abstracts International. 84-12B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2022 us |||||||||||||||c||eng d■001000016931128
■00520240214095923
■006m o d
■007cr#unu||||||||
■020 ▼a9798379604837
■035 ▼a(MiAaPQ)AAI29261819
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aQian, William Luo.▼0(orcid)0000-0002-0856-2134
■24510▼aWorkload Adaptations for Contended Main-Memory Multicore Transactions▼h[electronic resource]
■260 ▼a[S.l.]:▼bHarvard University. ▼c2022
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2022
■300 ▼a1 online resource(120 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 84-12, Section: B.
■500 ▼aAdvisor: Kohler, Eddie.
■5021 ▼aThesis (Ph.D.)--Harvard University, 2022.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aDatabase transactions guarantee atomicity for complex queries. Recent work in main-memory multicore transaction processing systems have achieved high transaction processing throughput, especially for uncontended workloads. Many systems achieve high performance by implementing new concurrency control (CC) protocols. Notably, variants of optimistic concurrency control (OCC), such as single-version concurrency control (1VCC) and multi-version concurrency control (MVCC) can perform well even under contention. In this work, I present MSTO, an MVCC system implemented to evaluate CC performance without the impact of basis factors. Experimental results show that while MVCC does outperform over 1VCC in some scenarios, 1VCC is far more resilient to collapse at high contention than previously believed. 1VCC even outperforms MVCC on many high-contention workloads. I then introduce an optimization to reduce write-write conflicts between transactions, deferred updates. In conjunction with the static timestamp splitting optimization that reduces read-write conflicts, deferred updates can be very effective at improving transactional throughput for all CC protocols, including TPC-C throughputs of 5.68x for 1VCC and 4.72x for MVCC compared to their baselines. Finally, I present and evaluate adaptive timestamp splitting, which changes each record's partitioning strategy to accommodate workloads with heterogeneous access patterns. On workloads where 1VCC with deferred updates and adaptive timestamp splitting records the highest throughput, it commits up to 3.98x as many transactions as 1VCC with deferred updates and static timestamp splitting, and up to 4.43x as many transactions as baseline 1VCC. Not all workloads benefit from adaptive timestamp splitting, as baseline MVCC records greater throughput at very high contention.
■590 ▼aSchool code: 0084.
■650 4▼aComputer science.
■650 4▼aEngineering.
■653 ▼aDatabase transactions
■653 ▼aTransaction processing
■653 ▼aOptimistic concurrency control
■653 ▼aTimestamp splitting
■690 ▼a0984
■690 ▼a0537
■71020▼aHarvard University▼bEngineering and Applied Sciences - Computer Science.
■7730 ▼tDissertations Abstracts International▼g84-12B.
■773 ▼tDissertation Abstract International
■790 ▼a0084
■791 ▼aPh.D.
■792 ▼a2022
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931128▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
