aDFS: An Almost Depth-First-Search Distributed Graph-Querying System
summary
aDFS is a distributed graph query engine that executes pattern matching with an almost depth-first exploration, uses non-blocking dispatch of remote intermediates, and enforces a fine‑grained flow control to cap runtime memory. On eight machines it produces 9.3 trillion matches on a Twitter query in under 20 minutes (~8 billion matches/sec). Against Neo4J, GraphFrames, G-Miner, Fractal, Peregrine and BiGJoin it completes queries those systems cannot and runs orders of magnitude faster while keeping memory bounded.
AI-written summary · about
chapters (8)
- 0:00Intro
- 0:20Graphs and Graph Queries
- 2:20Complexities in Graph-Query Execution
- 4:38aDFS Design Principles
- 7:12From a PGQL Query to an aDFS Execution Plan
- 8:13Asynchronous DFS/BFS Traversals
- 11:34Schemaless Graphs and Queries
- 13:33Conclusions & Future Work
related talks
32mGraph Databases, and Dungeons and Dragons
01h 00mGraph Mastery to AI
26mGraph Databases will change your (freakin') life
52mEnhance your work with graph database
54mDistributed Graph DBMSs — The Future for Analytics on Big Data?
49mModern Graph Databases
34mApache AGE
41mCypher-based Graph Pattern Matching in Apache Flink