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

local tests are failing with connection refused #226

Open rbavery opened 1 year ago

rbavery commented 1 year ago

Describe the bug I cloned the repo and tried to run a test with tox. After long wait times, this test resulted all in failures with connection refused errors.

----------------------------------------------------------- Captured stdout teardown ------------------------------------------------------------
model_volume_5
----------------------------------------------------------- Captured stderr teardown ------------------------------------------------------------
Error: No such container: sagemaker-tensorflow-serving-test
============================================================ short test summary info ============================================================
FAILED test/integration/local/test_pre_post_processing.py::test_predict_json[1] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_zero_content[1] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_large_input[1] - requests.exceptions.ConnectionError: HTTPConnectionPool(host=...
FAILED test/integration/local/test_pre_post_processing.py::test_csv_input[1] - requests.exceptions.ConnectionError: HTTPConnectionPool(host='l...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_specific_versions[1] - requests.exceptions.ConnectionError: HTTPConnec...
FAILED test/integration/local/test_pre_post_processing.py::test_unsupported_content_type[1] - requests.exceptions.ConnectionError: HTTPConnect...
FAILED test/integration/local/test_pre_post_processing.py::test_ping_service[1] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_json[2] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_zero_content[2] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_large_input[2] - requests.exceptions.ConnectionError: HTTPConnectionPool(host=...
FAILED test/integration/local/test_pre_post_processing.py::test_csv_input[2] - requests.exceptions.ConnectionError: HTTPConnectionPool(host='l...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_specific_versions[2] - requests.exceptions.ConnectionError: HTTPConnec...
FAILED test/integration/local/test_pre_post_processing.py::test_unsupported_content_type[2] - requests.exceptions.ConnectionError: HTTPConnect...
FAILED test/integration/local/test_pre_post_processing.py::test_ping_service[2] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_json[3] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_zero_content[3] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_large_input[3] - requests.exceptions.ConnectionError: HTTPConnectionPool(host=...
FAILED test/integration/local/test_pre_post_processing.py::test_csv_input[3] - requests.exceptions.ConnectionError: HTTPConnectionPool(host='l...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_specific_versions[3] - requests.exceptions.ConnectionError: HTTPConnec...
FAILED test/integration/local/test_pre_post_processing.py::test_unsupported_content_type[3] - requests.exceptions.ConnectionError: HTTPConnect...
FAILED test/integration/local/test_pre_post_processing.py::test_ping_service[3] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_json[4] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_zero_content[4] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_large_input[4] - requests.exceptions.ConnectionError: HTTPConnectionPool(host=...
FAILED test/integration/local/test_pre_post_processing.py::test_csv_input[4] - requests.exceptions.ConnectionError: HTTPConnectionPool(host='l...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_specific_versions[4] - requests.exceptions.ConnectionError: HTTPConnec...
FAILED test/integration/local/test_pre_post_processing.py::test_unsupported_content_type[4] - requests.exceptions.ConnectionError: HTTPConnect...
FAILED test/integration/local/test_pre_post_processing.py::test_ping_service[4] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_json[5] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_zero_content[5] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
FAILED test/integration/local/test_pre_post_processing.py::test_large_input[5] - requests.exceptions.ConnectionError: HTTPConnectionPool(host=...
FAILED test/integration/local/test_pre_post_processing.py::test_csv_input[5] - requests.exceptions.ConnectionError: HTTPConnectionPool(host='l...
FAILED test/integration/local/test_pre_post_processing.py::test_predict_specific_versions[5] - requests.exceptions.ConnectionError: HTTPConnec...
FAILED test/integration/local/test_pre_post_processing.py::test_unsupported_content_type[5] - requests.exceptions.ConnectionError: HTTPConnect...
FAILED test/integration/local/test_pre_post_processing.py::test_ping_service[5] - requests.exceptions.ConnectionError: HTTPConnectionPool(host...
======================================================== 35 failed in 605.63s (0:10:05) =========================================================
ERROR: InvocationError for command /home/rave/sagemaker-tensorflow-serving-container/.tox/py36/bin/python -m pytest test/integration/local/test_pre_post_processing.py --framework-version 1.14 (exited with code 1)
E           urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='localhost', port=8080): Max retries exceeded with url: /ping (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fde268ed250>: Failed to establish a new connection: [Errno 111] Connection refused'))

To reproduce git clone https://github.com/aws/sagemaker-tensorflow-serving-container/

tox -e py36 -- test/integration/local/test_pre_post_processing.py --framework-version 1.14

Expected behavior the tests would pass

System information I'm using the most recent commit on master and running tests that build and run the docker containers in this repo without any changes.

Additional context I'm trying to debug a problem with these containers that is causing 400 errors in CloudWatch and application x-image errors even though my custom inference.py script supports application x-image