mirror of
https://github.com/eunomia-bpf/bpf-developer-tutorial.git
synced 2026-02-03 10:14:44 +08:00
53ed115589
Implement a complete Python stack profiler that demonstrates how to: - Walk CPython interpreter frame structures from eBPF - Extract Python function names, filenames, and line numbers - Combine native C stacks with Python interpreter stacks - Profile Python applications with minimal overhead Key features: - Python internal struct definitions (PyFrameObject, PyCodeObject, PyThreadState) - String reading for both PyUnicodeObject and PyBytesObject - Frame walking with configurable stack depth - Both human-readable and flamegraph-compatible output formats - Command-line options for PID filtering and sampling frequency Files added: - python-stack.bpf.c: eBPF program for capturing Python stacks - python-stack.c: Userspace program for printing results - python-stack.h: Python internal structure definitions - test_program.py: Python test workload - run_test.sh: Automated test script - README.md: Comprehensive tutorial documentation - Makefile: Build configuration - .gitignore: Ignore build artifacts This tutorial serves as an educational foundation for understanding: 1. How to read userspace memory from eBPF 2. CPython internals and frame management 3. Sampling-based profiling techniques 4. Combining kernel and userspace observability Note: Current implementation demonstrates concepts but requires additional work for production use (thread state discovery, multi-version support, symbol resolution). 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
47 lines
1.1 KiB
Python
Executable File
47 lines
1.1 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
Simple Python test program to demonstrate stack profiling
|
|
This simulates a typical workload with multiple function calls
|
|
"""
|
|
|
|
import time
|
|
import sys
|
|
|
|
def expensive_computation(n):
|
|
"""Simulate CPU-intensive work"""
|
|
result = 0
|
|
for i in range(n):
|
|
result += i ** 2
|
|
return result
|
|
|
|
def process_data(iterations):
|
|
"""Process data with nested function calls"""
|
|
results = []
|
|
for i in range(iterations):
|
|
value = expensive_computation(10000)
|
|
results.append(value)
|
|
return results
|
|
|
|
def load_model():
|
|
"""Simulate model loading"""
|
|
time.sleep(0.1)
|
|
data = process_data(50)
|
|
return sum(data)
|
|
|
|
def main():
|
|
"""Main function that orchestrates the workload"""
|
|
print("Python test program starting...")
|
|
print(f"PID: {__import__('os').getpid()}")
|
|
print("Running CPU-intensive workload...")
|
|
|
|
# Run for a while to allow profiling
|
|
for iteration in range(100):
|
|
result = load_model()
|
|
if iteration % 10 == 0:
|
|
print(f"Iteration {iteration}: result = {result}")
|
|
|
|
print("Test program completed.")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|