Accelerating Query Performance in CrateDB
summary
Shows concrete tactics and measured wins: use EXPLAIN ANALYZE to see Lucene-time breakdowns, prefer partition filters to avoid hitting 250 shards, and replace nested‑loop joins with hash joins for equijoins. Reports real numbers (19s → 6s after common table expressions, then 200ms after rewrites), explains partitioning (12 months × 3 shards → 72 primaries), and recommends running OPTIMIZE to merge segments and clustered into/partition by month to reduce shard fan‑out.
AI-written summary · about
chapters (7)
- 0:00CrateDB introduction
- 3:37When to use distributed DB
- 8:15Performance issues in distributed DB
- 14:23Query plans in CrateDB
- 15:48Data distribution with partitions
- 24:07Optimizing queries with examples
- 36:34Recap and closing
related talks
23mWhen ms matter: Maximizing query performance in CrateDB
16mExploring Query Optimization: How a few lines of code can save hours of time- 16mExploring Query Optimization: How a few lines of code can save hours of time
49mIt’s Not Always About the Index: The Hidden Secrets of Query Performance
42mTips & Tricks to Keep Your Queries under 100ms with ClickHouse®
30mPerformance: Tips & Tricks to Optimize the Speed of Your Mission-Critical Database
41mTips and Tricks to Scale Elasticsearch for 1M RPMs and Beyond
50mImproving Postgres' Efficiency