Group Chats on Odnoklassniki
summary
Describes how Odnoklassniki/TamTam handles extremely high messaging load (about 50M MAU and over 10 billion events per day) and the engineering challenges of reliably and quickly delivering messages. Covers the messenger’s architecture and operational approaches to make message delivery performant and fault-tolerant at that scale.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 3:19Current messenger infra
- 6:52Chat history storage problem
- 10:28Hot and cold data solution
- 13:39Scaling group chats
- 19:01Parallel processing issues
- 23:19Actor and queue solution
- 26:31Read and protocol optimization
- 28:39Summary and results
- 30:08Q&A
related talks
36mTammy: a modular Matrix messenger
30mRebuilding Facebook Chat
16mMessaging @Scale
53mMessaging: The fine line between awesome and awful
44mThe live ops power panel
01h 01mMessaging: The fine line between awesome and awful
01h 18mThe future of chat
44mFrom Telegram to Odnoklassniki: Secrets of Embedding Apps Anywhere
