-
-
Notifications
You must be signed in to change notification settings - Fork 388
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Question: interpretation of results #107
Comments
Hi!
If you have suggestions on how to make this more clear, please let me know! |
Hm, strange. The program ran for 5 mins on one input, 10 mins on the other and still had these swings. It turned out to be accidentally quadratic. One string concatenation was profiled to generate net 1.9GB of allocations :o I think for now a simple listing in the Readme will help, gonna send a PR. |
Sounds like a success story! I'd greatly appreciate it if you could write it up here (with whatever details you feel comfortable including): https://github.com/emeryberger/scalene/issues/58 I am surprised there are such large swings for such substantial allocations. If you can share your code (privately is fine), I'd like to see what's going on. Thanks! |
It was half a success story maybe, as I also used py-spy and my problem needed a flamegraph I think, to nail down who was calling a certain function so often it made up 90% of all activity. Just looking at memory allocation numbers sent me down the wrong path at first, until I understood why a string concatenation generated 1.9GB of memory traffic. You can replay my findings by |
Hi!
I'm trying to profile a program and drill down into the underlying library (
--profile-all --reduced-profile
) and am somewhat stumped by the results.The text was updated successfully, but these errors were encountered: