I used nginx to build mlflow server with its proxy_pass and integrated simple HTTP auth in nginx. However, when I ran the experiment for a while, the mlflow client met this exception. And I have no idea how to fix it.
Here is the error messages:
Traceback (most recent call last):
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connection.py", line 159, in _new_conn
(self._dns_host, self.port), self.timeout, **extra_kw)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/util/connection.py", line 80, in create_connection
raise err
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/util/connection.py", line 70, in create_connection
sock.connect(sa)
TimeoutError: [Errno 60] Operation timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connectionpool.py", line 354, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1239, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1285, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1234, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1026, in _send_output
self.send(msg)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 964, in send
self.connect()
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connection.py", line 181, in connect
conn = self._new_conn()
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connection.py", line 168, in _new_conn
self, "Failed to establish a new connection: %s" % e)
urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x1280a8438>: Failed to establish a new connection: [Errno 60] Operation timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/requests/adapters.py", line 449, in send
timeout=timeout
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/connectionpool.py", line 638, in urlopen
_stacktrace=sys.exc_info()[2])
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/urllib3/util/retry.py", line 398, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host=<host_ip>, port=<port>): Max retries exceeded with url: /api/2.0/mlflow/experiments/get-by-name?experiment_name=<exp_name> (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x1280a8438>: Failed to establish a new connection: [Errno 60] Operation timed out',))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "tmp_experiment_entry.py", line 4, in <module>
mlflow.set_experiment(<exp_name>)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/tracking/fluent.py", line 47, in set_experiment
experiment = client.get_experiment_by_name(experiment_name)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/tracking/client.py", line 151, in get_experiment_by_name
return self._tracking_client.get_experiment_by_name(name)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/tracking/_tracking_service/client.py", line 114, in get_experiment_by_name
return self.store.get_experiment_by_name(name)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/store/tracking/rest_store.py", line 219, in get_experiment_by_name
response_proto = self._call_endpoint(GetExperimentByName, req_body)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/store/tracking/rest_store.py", line 32, in _call_endpoint
return call_endpoint(self.get_host_creds(), endpoint, method, json_body, response_proto)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/utils/rest_utils.py", line 133, in call_endpoint
host_creds=host_creds, endpoint=endpoint, method=method, params=json_body)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/utils/rest_utils.py", line 70, in http_request
url=url, headers=headers, verify=verify, **kwargs)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mlflow/utils/rest_utils.py", line 51, in request_with_ratelimit_retries
response = requests.request(**kwargs)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/requests/api.py", line 60, in request
return session.request(method=method, url=url, **kwargs)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/requests/sessions.py", line 533, in request
resp = self.send(prep, **send_kwargs)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/requests/sessions.py", line 646, in send
r = adapter.send(request, **kwargs)
File "/usr/local/opt/python/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/requests/adapters.py", line 516, in send
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPConnectionPool(host=<host_ip>, port=<port>): Max retries exceeded with url: /api/2.0/mlflow/experiments/get-by-name?experiment_name=<exp_name> (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x1280a8438>: Failed to establish a new connection: [Errno 60] Operation timed out',))
In the client, I use mlflow log by the following format and log_params, log_metrics in main function
with mlflow.start_run():
main(params)
