Hi Folks, Occasionally When I Clone A Job And Enqueue It, Instead Of Being Processed By The Expected Queue, A New Queue (With Some Id That Looks Like An Hash) Is Created Instead, And The Experiment Hangs In A "Pending" State. When This Happens, If I Abor

Unanswered

and in the logs of the K8s Glue I see an exception occurred:

` No tasks in queue 54d3edb05a89462faaf51e1c878cf2c7
No tasks in Queues, sleeping for 5.0 seconds
No tasks in queue 54d3edb05a89462faaf51e1c878cf2c7
No tasks in Queues, sleeping for 5.0 seconds
FATAL ERROR:
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 710, in urlopen
chunked=chunked,
File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/usr/local/lib/python3.6/dist-packages/urllib3/connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "/usr/lib/python3.6/http/client.py", line 1285, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1331, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1280, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1085, in _send_output
self.send(chunk)
File "/usr/lib/python3.6/http/client.py", line 1006, in send
self.sock.sendall(data)
File "/usr/lib/python3.6/ssl.py", line 975, in sendall
v = self.send(byte_view[count:])
File "/usr/lib/python3.6/ssl.py", line 944, in send
return self._sslobj.write(data)
File "/usr/lib/python3.6/ssl.py", line 642, in write
return self._sslobj.write(data)
ConnectionResetError: [Errno 104] Connection reset by peer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/requests/adapters.py", line 449, in send
timeout=timeout
File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 786, in urlopen
method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2]
File "/usr/local/lib/python3.6/dist-packages/urllib3/util/retry.py", line 550, in increment
raise six.reraise(type(error), error, _stacktrace)
File "/usr/local/lib/python3.6/dist-packages/urllib3/packages/six.py", line 769, in reraise
raise value.with_traceback(tb)
File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 710, in urlopen
chunked=chunked,
File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/usr/local/lib/python3.6/dist-packages/urllib3/connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "/usr/lib/python3.6/http/client.py", line 1285, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1331, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1280, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/usr/lib/python3.6/http/client.py", line 1085, in _send_output
self.send(chunk)
File "/usr/lib/python3.6/http/client.py", line 1006, in send
self.sock.sendall(data)
File "/usr/lib/python3.6/ssl.py", line 975, in sendall
v = self.send(byte_view[count:])
File "/usr/lib/python3.6/ssl.py", line 944, in send
return self._sslobj.write(data)
File "/usr/lib/python3.6/ssl.py", line 642, in write
return self._sslobj.write(data)
urllib3.exceptions.ProtocolError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/commands/worker.py", line 1449, in daemon
gpu_queues=dynamic_gpus,
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/glue/k8s.py", line 774, in run_tasks_loop
level="INFO",
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/commands/events.py", line 99, in send_log_events
return self.send_events(list_events=log_events, session=session)
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/commands/events.py", line 58, in send_events
sent_events += send_packet(lines)
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/commands/events.py", line 32, in send_packet
'add_batch', data=jsonlines, headers={'Content-type': 'application/json-lines'}, session=session
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/commands/base.py", line 127, in post
return session.post(service=self.service, action=endpoint, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/session.py", line 300, in post
json=json or kwargs)
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/session.py", line 308, in _manual_request
json=json or kwargs)
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/backend_api/session/session.py", line 363, in send_request
json=json,
File "/usr/local/lib/python3.6/dist-packages/clearml_agent/backend_api/session/session.py", line 291, in _send_request
method, url, headers=headers, auth=auth, data=data, json=json, timeout=timeout)
File "/usr/local/lib/python3.6/dist-packages/requests/sessions.py", line 542, in request
resp = self.send(prep, **send_kwargs)
File "/usr/local/lib/python3.6/dist-packages/requests/sessions.py", line 655, in send
r = adapter.send(request, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/requests/adapters.py", line 498, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer')) `

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					SarcasticSquirrel56
				
					0
					 × 1

158 Views

0 Answers

2 years ago

one year ago