Back to Devoured - June 08, 2026
DEVOURED
Dynamic Repartitioning for Time Series Workloads

Dynamic Repartitioning for Time Series Workloads

Data Netflix
Netflix engineers implemented dynamic partition splitting in Cassandra to prevent performance bottlenecks in high-volume time-series workloads like viewing history and metrics.
What: The system automatically detects hot or oversized partitions at runtime and splits them into smaller segments, maintaining backward compatibility with existing queries while avoiding manual data re-sharding.
Decoder
  • Wide partition: A partition in Cassandra that contains a massive number of rows, causing performance degradation due to high memory usage during read/write operations.
Original article

Netflix built dynamic partition splitting in Cassandra to handle wide partitions in high-volume time-series workloads like viewing history, metrics, and events. Rather than relying on static buckets or manual fixes, the system detects hot or oversized partitions at runtime and automatically splits them into smaller pieces while preserving query compatibility and data consistency.

Explore all 68 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi