Yandex.Metrica and a Non‑standard ClickHouse
summary
Yandex.Metrica’s analytics team describes running a heavily customized ClickHouse deployment they adopted in 2014, explaining why ClickHouse was chosen and how they modified and operated it for large-scale web analytics. The talk covers specific operational experience, custom extensions and tuning of ClickHouse to meet Metrica’s data ingestion, storage and query-performance requirements.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 3:22ClickHouse compute cloud
- 10:23Cloud manager and balancing
- 20:38Event insert timings
- 28:57ClickHouse as key-value store
- 35:29Summary
- 36:16Q&A
related talks
22mClickHouse as Time-Series Storage for Graphite
31mHow ClickHouse® Inspired Us to Build a High Performance Time Series Database
51mTheory and practice of using ClickHouse in real applications
53mClickHouse capabilities for advanced developers
59mEffective Use of ClickHouse
51mWhat You Need to Know About ClickHouse Architecture
49mSolving real business cases with ClickHouse
26mO11y in One: Exploring ClickHouse as a Unified Telemetry Database