Everything Everywhere at Once: Tracing under High Load with 10k Backends
summary
Describes expanding distributed tracing to meet VKontakte’s needs in a very high-load environment with around 10,000 backends. Covers collecting cross-service interaction data for requests, and evaluates existing trace storage/visualization tools such as Jaeger and Sentry while discussing how tracing was adapted and scaled for this infrastructure.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 5:33Standard tracing problems
- 11:26Alternative solutions
- 18:13Integration with tech
- 23:14New tracing system
- 31:04Data storage and indexing
- 35:21Results and performance
- 39:22Q&A
related talks
45mMastering Distributed Tracing: Insights from Building a Platform from Scratch
51mHow We Do Tracing at the Scale of Thousands of Services and Millions of Spans per Second
30mRunning Highly Scalable Tracing, Logging, Monitoring & Metric System in Production
34mReduce Complexity with Distributing Tracing
49mDistributed Tracing: How the Pros Debug Concurrent and Distributed Systems
32mA Picture is Worth 1,000 Traces
24mDistributed Tracing : New DevOps Foundation.
28mTracing the Journey into Distributed Tracing