-
Notifications
You must be signed in to change notification settings - Fork 560
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
Memory leak on compressed predict requests with oatpp #1316
Comments
More info on that : we managed to reproduce this issues with the above Python scripts, but not with curl. So after testing more with @YaYaB, we had a strong intuition that it has something to do with the HTTP serving. We also tested to send gzip-compressed queries, asking for uncompressed responses, and no memory leak was noticed. So really looks like it's something related to GZIP compression. |
Actualy it is even not related to tensorrt but even with classical caffe predictions with or without gpu |
@rguilmont @YaYaB gzip/deflate encryption is handled by https://github.com/oatpp/oatpp-zlib from within https://github.com/oatpp/oatpp. The components are simply added here: https://github.com/jolibrain/deepdetect/blob/master/src/http/app_component.hpp#L114 Running valgrind on @lganzzzo Hi, the Libz init memory reported by valgrind:
|
Hey @beniz , Your code looks good. Most probably it's on oatpp side. |
Hi @lganzzzo how are things ? Do you have any fresh lead on this by any chance ? I've seen issues with libz a long time ago, this could still be outside oatpp. |
Hey @beniz , Yes, at this point it looks like a It might take a while |
Thanks a lot guys. FYI we've mitigated this gzip issue by setting an Envoy proxy in front of deepdetect, taking care of compression and decompression of requests. |
Configuration
23bd913ac180b56eddbf90c71d1f2e8bc2310c54
Your question / the problem you're facing:
When using the last versions of DeDe (0.18.0 and 0.17.0 at least) I have noticed that there was a memory leak (similar to #1260). I thought that it was fixed but using the following test it does not seem to be.
Tests are made using a 1080Ti gpu fyi.
Error message (if any) / steps to reproduce the problem:
First I run a container using the following image
CALL
LOG
Then I create a service using an nsfw model
CALL
LOG
Then I launch many predictions with a fixed batche size using the script called
dd_test.py
that is pasted belowCALL
LOG
Now if you check the evolution of the RAM used we observe an increase (1644Mo at the beginning to 2095Mo after 5 minutes
).
The text was updated successfully, but these errors were encountered: