Intro: Dragonfly
summary
Project Dragonfly is an open source P2P image and file distribution system that claims to cut bandwidth and keep average download cost flat at scale by using a supernode + dfget P2P architecture, block-level deduplication and block-level dynamic compression, plus CDN sync and a memory-backed file system. Deployed inside Alibaba since 2015 with 1.5 billion downloads/month and shown to push data to tens of thousands of nodes in 30 seconds, it reports ~3x faster deploys versus native pulls; roadmap adds Go refactor, plugin scaling, multi-cloud and stronger encryption.
AI-written summary · about
chapters (23)
- 0:00Introduction
- 3:32Milestones
- 7:33Status of Dragonfly
- 9:29Dragonfly Community
- 13:24Supernode Architecture
- 14:44Dispersity Theory
- 16:24Proximity
- 19:24Compression Benefits
- 20:24Size Limiter
- 21:24Storage Manager
- 23:24Memory File System
- 24:24Use Case
- 25:24Demo
- 27:24Data Comparison
- 28:24Security
- 29:24Scaling
- 30:24decentralization
- 31:24repositories
- 32:24registry
- 33:24Supernode
- 34:24Mass Transfer
- 35:24Super Moves
- 36:24Dragonfly Support
related talks
27mDragonfly: Make Image Distribution Efficiently and Safely in Cloud Native
34mDeep Dive: Dragonfly
29mAccelerates Image Distribution In Multi-Cluster With Dragonfly
31mThe New Evolution of Image Distribution System Dragonfly
36mDragonfly: Intro, Updates and AI Model Distribution in the Practice of...
19mDragonfly 2.0 — Bring a breakthrough Leap to the Domain of Cloud Native File...
29mPull Once, Scale Everywhere: Fixing Image Pull Bottlenecks With Dragonfly
48mDropbox’s Traffic Infrastructure