How We Built a Shared Bus of Dynamic Resources at Yandex
summary
Describes Yandex’s design for a shared dynamic-resource bus that allows updating a resource’s implementation inside a container without restarting the process. Covers the architecture and operational approach used to provide a convenient, reliable, and scalable system for rolling resource updates in minutes.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 5:24Traditional solutions problems
- 14:59Data storage and transactions
- 20:54Rolling out to pods
- 23:25Complex rollout scenarios
- 28:20Automation and rollbacks
- 31:34Q&A
related talks
46mManaging Resources as a Product
50mHow We Built a Distributed Queue Service at Yandex
48mInternal Cloud at Yandex — From Prototype to Platform
47mHow We Balance Load Inside Yandex Messenger
51mYandex Database: Distributed Queries in the Clouds
41mYARN Resource Management and Dynamic Max
41mClouds of Cocaine
21mPreparing Yandex search data — the library and processes we built