Instance-Optimized Data Layouts for Cloud Analytics Workloads
Summary: Introducing MTO, an instance-optimized data-layout framework that jointly blocks across all tables in multi-table cloud workloads (star/snowflake schemas) to maximize block skipping. Leveraging sideways information from joins, it beats single-table layouts, with up to 93% fewer blocks accessed and 75% faster end-to-end queries on a commercial service. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jialin Ding (Massachusetts Institute of Technology)
- 2. Umar Farooq Minhas (Microsoft)
- 3. Badrish Chandramouli (Microsoft)
- 4. Chi Wang (Microsoft)
- 5. Yinan Li (Microsoft)
- 6. Ying Li (Microsoft)
- 7. Donald Kossmann (Microsoft)
- 8. Johannes Gehrke (Microsoft)
- 9. Tim Kraska (Massachusetts Institute of Technology)
BibTeX Citation
@inproceedings{ding_sigmod21,
title = {{Instance-Optimized Data Layouts for Cloud Analytics Workloads}},
author = {Ding, Jialin and Minhas, Umar Farooq and Chandramouli, Badrish and Wang, Chi and Li, Yinan and Li, Ying and Kossmann, Donald and Gehrke, Johannes and Kraska, Tim},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3457270},
url = {https://dl.acm.org/doi/10.1145/3448016.3457270},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 27 of 27 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 37 of 37 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,866 | Optimal Column Layout for Hybrid Workloads | 2019 | VLDB |
| 2 | 12,191 | A Partitioning Framework for Aggressive Data Skipping | 2014 | VLDB |
| 3 | 3,578 | Advanced Join Strategies for Large-Scale Distributed Computation | 2014 | VLDB |
| 4 | 6,640 | Understanding Insights into the Basic Structure and Essential Issues of Table Placement Methods in Clusters | 2013 | VLDB |
| 5 | 2,344 | Towards Cost-Optimal Query Processing in the Cloud | 2021 | VLDB |
| 6 | 10,672 | Optimizing Block Skipping for High-Dimensional Data with Learned Adaptive Curve | 2025 | SIGMOD |
| 7 | 7,660 | Pruning in Snowflake: Working Smarter, Not Harder | 2025 | SIGMOD |
| 8 | 1,135 | Qd-tree: Learning Data Layouts for Big Data Analytics | 2020 | SIGMOD |
| 9 | 4,742 | Continuous Cloud-Scale Query Optimization and Processing | 2013 | VLDB |
| 10 | 3,106 | Skipping-oriented Partitioning for Columnar Layouts | 2017 | VLDB |