Profiling PyPy using the Firefox profiler user interface | PyPy

[utterances-bot]

Profiling PyPy using the Firefox profiler user interface | PyPy

https://www.pypy.org/posts/2024/05/vmprof-firefox-converter.html

[mattip]

Summarizing the steps to recreate the flame graph here:

• Download the test text file
• Copy the second script into a file

import collections, sys
counts = collections.Counter()
remaining = ''
while True:
    chunk = remaining + sys.stdin.read(64*1024)
    if not chunk:
        break
    last_lf = chunk.rfind('\n')  # process to last LF character
    if last_lf == -1:
        remaining = ''
    else:
        remaining = chunk[last_lf+1:]
        chunk = chunk[:last_lf]
    counts.update(chunk.lower().split())

for word, count in counts.most_common():
    print(word, count)

• pip install vmprof flask_cors
• clone the converter repo, since it is not yet pip-installable git clone https://github.com/Cskorpion/vmprof-firefox-converter
• run the test cd vmprof-firefox-converter; python -m vmprofconvert -run test_vmprof.py < ~/Downloads/kjvbible.txt
• when the browser opens, click on "1/3 tracks" and change it to "show all tracks"
• then click on the "Thread 0" track