Profilers are lying hobbitses
Day 1 / 15:30 / Track 1 / Lang: ENEverybody hates a lying hobbit... But are profilers broken or are we naive in our expectations?
In this talk we will re-visit some broken assumptions and try and get to grips with the limitations of our tools. We'll cover:
- Fiction of instruction level profiling
- Skid & PEBS
- Safepoint bias, theory and practice
- JMC blindspots, theory and practice
- Honest-Profiler vs. Async-Profiler
- Profilers vs. Inlining and Inlining vs. Programmer
- Profilers vs. Multi-threading
Nitsan Wakart, TTNR Labs
nitsanwA coder with a pedantic passion for performance. His work has spanned army intelligence systems, dot.com era startups, financial institutions and innovative product companies. Also a blogger and active Open Source developer (importantly JCTools but a modest contributor to RxJava/Netty/Akka and others as well). When not plotting world domination, Nitsan enjoys pinnacoladas and getting caught in the rain.