Finding performance problems: profiling or logging?
All Pythons are slow, but some are faster than others
The best way to find performance bottlenecks: observing production
CI for performance: Reliable benchmarking in noisy environments
How vectorization speeds up your Python code
Invasive procedures: Python affordances for performance measurement
Speeding up software with faster hardware: tradeoffs and alternatives
The hidden performance overhead of Python C extensions
Creating a better flamegraph visualization
The limits of Python vectorization as a performance technique
If your software is running slowly in production, do you need profiling or logging?