Implementing OLAP: how we built columnar storage in YDB

on YouTube ↗52m

" summary

YDB is an OLTP platform and the talk explains how columnar storage was implemented on top of it to support OLAP workloads. It describes the technologies used within YDB (transactional engine and existing database infrastructure) and the approach of adding a column-oriented layer to handle analytical queries alongside fast transactional processing.

AI-written summary · about

" chapters (11)

1. 0:00Introduction
2. 2:15Why columnar tables
3. 6:30Architecture and design
4. 16:29Data storage format
5. 20:20Data scan algorithm
6. 25:00Index optimization
7. 33:15Experiments and results
8. 38:37Summary and outlook
9. 41:08ClickHouse comparison
10. 45:02JOIN support
11. 49:15Q&A

" related talks

• 01h 00mColumnar DBMS: The Magic of Data Compression and Super-Fast QueriesVladislav Buyval · HighLoad++ Genesis 2025
• 58mUnderstanding Big Data for Software EngineersDavid Ostrovsky · NDC Oslo 2023
• 51mYandex Database: Distributed Queries in the CloudsSergey Puchin · Backend Conf 2019 (РИТ++)
• 01h 27mYugabyteDB YSQL DevelopmentSeth Luersen · Distributed SQL Summit 2022
• 26mColumnar Storage: Redefining Data Management for the Modern EraZoe Steinkamp · Voxxed Days Thessaloniki 2024
• 44mYDB Java SDK: The Battle for PerformanceAleksandr Gorshenin · JPoint 2023
• 27mIntroduction to YugabyteDB – Design and ArchitectureKarthik Ranganathan · Distributed SQL Summit Asia 2021
• 47mAnatomy of a Distributed SQL Database - YugabyteDBFranck Pachot · Devoxx France 2022