search

aws / sagemaker-tensorflow-serving-container

A TensorFlow Serving solution for use in SageMaker. This repo is now deprecated.
Apache License 2.0
174 stars 101 forks source link

expose gunicorn logging #219

Closed mseth10 closed 2 years ago

mseth10 commented 2 years ago

Issue #, if available: Expose option to set gunicorn logging level. Helpful for debugging gunicorn related errors.

Description of changes: Changes tested in https://github.com/aws/deep-learning-containers/pull/1713

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

sagemaker-bot commented 2 years ago

AWS CodeBuild CI Report

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

satishpasumarthi commented 2 years ago

nit: Let's highlight this option in the README.md file so that our customers are aware of this for debugging?

mseth10 commented 2 years ago

nit: Let's highlight this option in the README.md file so that our customers are aware of this for debugging?

Is there any particular section where we talk about different environment variables? If not, do you want me to add something like "Now you can use the environment variable SAGEMAKER_GUNICORN_LOGLEVEL to set the logging level for Gunicorn." in this section https://github.com/aws/sagemaker-tensorflow-serving-container#deploying-to-multi-model-endpoint @satishpasumarthi

satishpasumarthi commented 2 years ago

Yeah. That would be better. Let's create a section for it if not present !