Skip to content
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

"/s2i/bin/assemble: line 59: 10 Killed" when using S2I to build PyTorch container #180

Closed
isaacmg opened this issue Jul 5, 2018 · 5 comments

Comments

@isaacmg
Copy link

isaacmg commented Jul 5, 2018

So I fixed my previous network error by expanding the pip timeout. However now I'm getting an error with respect to assemble.

---> Installing application source...
---> Installing dependencies ...
Collecting torch (from -r requirements.txt (line 1))
Downloading https://files.pythonhosted.org/packages/69/43/380514bd9663f1bf708abeb359b8b48d3fabb1c8e95bb3427a980a064c57/torch-0.4.0-cp36-cp36m-manylinux1_x86_64.whl (484.0MB)
/s2i/bin/assemble: line 59:    10 Killed                  pip install -r requirements.txt
Build failed
ERROR: An error occurred: non-zero (13) exit code from seldonio/seldon-core-s2i-python3

Does anyone know why this error is happening? My requirements.txt only contains torch, torchvision, and Pillow. It runs fine outside of S2I.

@ukclivecox
Copy link
Contributor

can you set the loglevel on s2i to get more info?

 --loglevel int32   Set the level of log output (0-5)

@isaacmg
Copy link
Author

isaacmg commented Jul 6, 2018

Here are the closest lines on log level 5. It honestly looks like it is still timing out which I find hard to believe as I tested on a 25mb/s connection.

I0705 22:21:13.646220   15331 sti.go:681] Collecting torch (from torchvision->-r requirements.txt (line 1))
I0705 22:21:13.968231   15331 sti.go:681] Downloading https://files.pythonhosted.org/packages/69/43/380514bd9663f1bf708abeb359b8b48d3fabb1c8e95bb3427a980a064c57/torch-0.4.0-cp36-cp36m-manylinux1_x86_64.whl (484.0MB)
I0705 22:41:36.917202   15331 sti.go:685] /s2i/bin/assemble: line 59:    10 Killed                  pip install -r requirements.txt
I0705 22:41:37.194192   15331 docker.go:1055] Waiting for container "50ab180a9b79a9502f5081c5135155386d29f4d04caa16c3c192b8521c0f4dcd" to stop ...
I0705 22:41:37.982898   15331 docker.go:991] Removing container "50ab180a9b79a9502f5081c5135155386d29f4d04caa16c3c192b8521c0f4dcd" ...
I0705 22:41:38.128674   15331 docker.go:1001] Removed container "50ab180a9b79a9502f5081c5135155386d29f4d04caa16c3c192b8521c0f4dcd"
I0705 22:41:38.131249   15331 cleanup.go:33] Removing temporary directory /var/folders/sf/1hd0wxfd7cd5s6yg32l745h40000gn/T/s2i737762660
I0705 22:41:38.131268   15331 fs.go:278] Removing directory '/var/folders/sf/1hd0wxfd7cd5s6yg32l745h40000gn/T/s2i737762660'
I0705 22:41:38.139097   15331 build.go:156] Build failed
E0705 22:41:38.139123   15331 errors.go:276] An error occurred: non-zero (13) exit code from seldonio/seldon-core-s2i-python3```

@ukclivecox
Copy link
Contributor

It could be a memory issue. is there a limit on memory that your local Docker can use?
Can you increase what is available or try the build on a machine with more resources?
If these don't help I suggest posting an issue on Source2Image project : https://github.com/openshift/source-to-image/issues

@johnugeorge
Copy link

I had the same issue. When I tried to give more memory to Docker, it worked. I gave 8G memory to Docker and image was built successfully.

@isaacmg
Copy link
Author

isaacmg commented Jul 8, 2018

Thanks for the help. As you said it was a memory issue. I doubled the size of my VM and it successfully built the image.

@isaacmg isaacmg closed this as completed Jul 8, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants