DBScholar

Back to papers

A Top-Down Approach to Achieving Performance Predictability in Database Systems

Summary: Top-down study of performance predictability across MySQL, PostgreSQL, and VoltDB using TProfiler identifies key latency-variance sources. Proposes Variance-Aware Transaction Scheduling (VATS) and a lazy buffer-pool policy, yielding up to 5.6x variance reduction and 6.3x 99th percentile latency, with VATS adopted in MySQL/MariaDB. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
h75664b9b9ce75554
Venue
SIGMOD
Year
2017
Pagerank
6.3369302e-05
Overall Rank
4,932 | 66.95%
DOI
10.1145/3035918.3064016

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{huang_sigmod17,
        title = {{A Top-Down Approach to Achieving Performance Predictability in Database Systems}},
        author = {Huang, Jiamin and Mozafari, Barzan and Schoenebeck, Grant and Wenisch, Thomas F.},
        series = {{SIGMOD} '17},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3035918.3064016},
        url = {https://dl.acm.org/doi/10.1145/3035918.3064016},
        year = {2017}
}

Incoming Citations (Sorted by Pagerank)

Showing 11 of 11 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 26 of 26 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
157 OLTP Through the Looking Glass, and What We Found There 2008 SIGMOD 0.00028244257
236 OLTP-Bench: An Extensible Testbed for Benchmarking Relational Databases 2014 VLDB 0.00023639649
390 QPipe: A Simultaneously Pipelined Relational Query Engine 2005 SIGMOD 0.00019232929
447 Staring into the Abyss: An Evaluation of Concurrency Control with One Thousand Cores 2015 VLDB 0.00018126139
613 Scalable Logging through Emerging Non-Volatile Memory 2014 VLDB 0.00015527424
670 SharedDB: Killing One Thousand Queries With One Stone 2012 VLDB 0.00014929358
707 Main-Memory Scan Sharing For Multi-Core CPUs 2008 VLDB 0.00014613324
757 DBSherlock: A Performance Diagnostic Tool for Transactional Databases 2016 SIGMOD 0.00014202187
859 Storage Management in the NVRAM Era 2014 VLDB 0.00013384817
865 Let’s Talk About Storage & Recovery Methods for Non-Volatile Memory Database Systems 2015 SIGMOD 0.00013346121
1,029 A Scalable, Predictable Join Operator for Highly Concurrent Data Warehouses 2009 VLDB 0.00012380835
1,043 The DataPath System: A Data-Centric Analytic Processing Engine for Large Data Warehouses 2010 SIGMOD 0.00012325755
1,124 Least Expected Cost Query Optimization: An Exercise in Utility 1999 PODS 0.00011898749
1,127 FlashLogging: Exploiting Flash Devices for Synchronous Logging Performance 2009 SIGMOD 0.00011887959
1,345 SQLVM: Performance Isolation in Multi-Tenant Relational Database-as-a-Service 2013 CIDR 0.00010952015
1,926 Predictable Performance for Unpredictable Workloads 2009 VLDB 9.3500398e-05
1,940 Performance and Resource Modeling in Highly-Concurrent OLTP Workloads 2013 SIGMOD 9.3179491e-05
2,018 PIQL: Success-Tolerant Query Processing in the Cloud 2012 VLDB 9.1687512e-05
3,005 Sharing Buffer Pool Memory in Multi-Tenant Relational Database-as-a-Service 2015 VLDB 7.7460817e-05
3,406 Variance Aware Optimization of Parameterized Queries 2010 SIGMOD 7.3151509e-05
3,864 Making Updates Disk-I/O Friendly Using SSDs 2013 VLDB 6.9461754e-05
4,091 DBSeer: Resource and Performance Prediction for Building a Next Generation Database Cloud 2013 CIDR 6.7959748e-05
4,338 Generalized Scale Independence Through Incremental Precomputation 2013 SIGMOD 6.6413964e-05
5,324 CliffGuard: A Principled Framework for Finding Robust Database Designs 2015 SIGMOD 6.1645235e-05
5,695 Recovery Architectures for Multiprocessor Database Machines 1985 SIGMOD 6.0174981e-05
9,195 DBSeer: Pain-free Database Administration through Workload Intelligence 2015 VLDB 5.1958544e-05
Previous Page 1 / 1 Next

Semantically Similar Papers