• ShareChat hit a billion features per second, then it had to make it 10x cheaper “Great system…now please make it 10 times cheaper.” That’s not exactly what the ShareChat team wanted to hear after completing a major engineering feat: scaling a real-time feature store 1000X without scaling their database (ScyllaDB). • To scale from supporting 1 million features per second to 1 billion features per second, the team has already. • - Redesigned their database schema to store all features together as protocol buffers and optimized tile configurations (reduced required rows from 2B to 73M/sec) - Switched their database compaction strategy from incremental to leveled (doubled database capacity) - Forked caching and gRPC libraries to eliminate mutex contention and connection bottlenecks - Applied object pooling and garbage collector tuning to reduce memory allocation overhead You can read about those performance optimizations in Scaling an ML Feature Store From 1M to 1B Features per Second. • But ShareChat - an Indian leader in a globally competitive social media market - is always looking to optimize. • After reaching this scalability milestone, the team received a follow-up challenge: reducing the feature store’s costs by 10X (without compromising performance, of course). • Staff Software Engineer at ShareChat, and Ivan Burmistrov, then Principal Software Engineer at ShareChat, shared how they approached this new challenge in a keynote at Monster Scale Summit 2025.

Article Summaries:

  • ShareChat hit a billion features per second, then it had to make it 10x cheaper “Great system…now please make it 10 times cheaper.” That’s not exactly what the ShareChat team wanted to hear after completing a major engineering feat: scaling a real-time feature store 1000X without scaling their database (ScyllaDB). To scale from supporting 1 million features per second to 1 billion features per second, the team has already. - Redesigned their database schema to store all features together as protocol buffers and optimized tile configurations (reduced required rows from 2B to 73M/sec) - Switched

Sources: