OK S3: Building the System Ourselves
summary
Overview of Odnoklassniki’s in-house distributed, fault-tolerant object storage systems (one-blob-storage and one-cold-storage) used to store and process nearly an exabyte of binary media (video, photos, music). Describes the architecture, operational experience and engineering choices for building and running these large-scale storage services.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 4:24System requirements
- 6:50Infrastructure and storage
- 11:29Design and features
- 20:13Functional requirements
- 23:26Schema and transactions
- 30:49Lifecycle and scheduler
- 32:55Authentication and API
- 34:41Performance optimizations
- 43:15Results and use cases
- 44:38Q&A
related talks
50mA Homegrown S3 Server: Challenges of Building Stable Storage
01h 01mOK S3
44mInside S3
47mA Distributed, Scalable and Highly Reliable Data Storage System
29mData @Scale Seattle - Kestutis Patiejunas
39mStorage Technologies for Large-Scale Projects
49mSharding: from scratch to Yandex Disk
36mStorage Wars