AI BriefingNetflix's High-Throughput Graph Abstraction: Part I
Key point
Netflix built an OLTP-optimized Graph Abstraction that handles 10 million operations per second.
Details
Netflix's graph use cases are broadly divided into two categories.
OLAP (Online Analytical Processing) aims at algorithmic exploration and in-depth analysis of large-scale datasets. It leverages standard models and languages such as RDF, SPARQL, Gremlin, openCypher, and SQL, focusing on precise analysis rather than high throughput.
OLTP (Online Transactional Processing) requires millisecond-level response times and extremely high throughput of up to millions of operations per second. To achieve this performance, trade-offs such as accepting eventual consistency or limiting query complexity and traversal depth are employed.
Netflix's Graph Abstraction was designed specifically for this OLTP use case. Currently, this system handles approximately 10 million operations per second across more than 650 environments.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Slater – A Low-Memory graphdb for Read-Intensive Graphs
MySQL 3 minutes vs ClickHouse 0.3 seconds, the same query