tests: investigate import empty_dir failure

[efiop]

#45

=================================== FAILURES ===================================
_______________________ TestImport.test_import_empty_dir _______________________
[gw0] linux -- Python 3.9.18 /opt/hostedtoolcache/Python/3.9.18/x64/bin/python

self = <dvc_gs.tests.test_dvc.TestImport object at 0x7f403314a850>
tmp_dir = PosixTmpDir('/tmp/pytest-of-runner/pytest-0/popen-gw0/test_import_empty_dir0')
dvc = Repo: '/tmp/pytest-of-runner/pytest-0/popen-gw0/test_import_empty_dir0'
workspace = FakeGCP: 'gs://pytest-servers-imfnca/', is_object_storage = True

    def test_import_empty_dir(self, tmp_dir, dvc, workspace, is_object_storage):
        # prefix based storage services (e.g s3) doesn't have the real concept
        # of directories. So instead we create an empty file that ends with a
        # trailing slash in order to actually support this operation
        if is_object_storage:
            contents: Union[str, Dict[str, str]] = ""
        else:
            contents = {}
    
        workspace.gen({"empty_dir/": contents})
    
>       dvc.imp_url("remote://workspace/empty_dir/")

/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/testing/workspace_tests.py:82: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/repo/__init__.py:61: in wrapper
    return f(repo, *args, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/repo/scm_context.py:151: in run
    return method(repo, *args, **kw)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/repo/imp_url.py:85: in imp_url
    stage.run(jobs=jobs, no_download=no_download)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/funcy/decorators.py:47: in wrapper
    return deco(call, *dargs, **dkwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/stage/decorators.py:43: in rwlocked
    return call()
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/funcy/decorators.py:68: in __call__
    return self._func(*self._args, **self._kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/stage/__init__.py:600: in run
    self._sync_import(dry, force, kwargs.get("jobs", None), no_download)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/funcy/decorators.py:47: in wrapper
    return deco(call, *dargs, **dkwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/stage/decorators.py:43: in rwlocked
    return call()
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/funcy/decorators.py:68: in __call__
    return self._func(*self._args, **self._kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/stage/__init__.py:637: in _sync_import
    sync_import(self, dry, force, jobs, no_download)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/stage/imports.py:62: in sync_import
    stage.deps[0].download(
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/dependency/base.py:50: in download
    fs_download(self.fs, self.fs_path, to.fs_path, jobs=jobs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc/fs/__init__.py:77: in download
    generic.copy(
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/generic.py:93: in copy
    return _get(
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/generic.py:211: in _get
    return _get_one(from_paths[0], to_paths[0])
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/generic.py:201: in _get_one
    return get_file(
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/callbacks.py:70: in func
    return wrapped(path1, path2, **kw)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/callbacks.py:42: in wrapped
    res = fn(*args, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/dvc_objects/fs/base.py:556: in get_file
    self.fs.get_file(from_info, to_info, callback=callback, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/fsspec/asyn.py:118: in wrapper
    return sync(self.loop, func, *args, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/fsspec/asyn.py:103: in sync
    raise return_result
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/fsspec/asyn.py:56: in _runner
    result[0] = await coro
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/core.py:1494: in _get_file
    await self._get_file_request(u2, lpath, callback=callback, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/decorator.py:221: in fun
    return await caller(func, *(extras + args), **kw)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/retry.py:146: in retry_request
    raise e
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/retry.py:122: in retry_request
    return await func(*args, **kwargs)
/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/core.py:1467: in _get_file_request
    r.raise_for_status()
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <ClientResponse(http://localhost:54355/download/storage/v1/b/pytest-servers-imfnca/o/empty_dir?alt=media) [404 Not Fou...charset=utf-8', 'X-Content-Type-Options': 'nosniff', 'Date': 'Fri, 22 Sep 2023 16:11:26 GMT', 'Content-Length': '10')>


    def raise_for_status(self) -> None:
        if not self.ok:
            # reason should always be not None for a started response
            assert self.reason is not None
            self.release()
>           raise ClientResponseError(
                self.request_info,
                self.history,
                status=self.status,
                message=self.reason,
                headers=self.headers,
            )
E           aiohttp.client_exceptions.ClientResponseError: 404, message='Not Found', url=URL('http://localhost:54355/download/storage/v1/b/pytest-servers-imfnca/o/empty_dir?alt=media')

/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/aiohttp/client_reqrep.py:1005: ClientResponseError
------------------------------ Captured log setup ------------------------------
DEBUG    gcsfs:core.py:436 GET: b/pytest-servers-imfnca, (), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:core.py:436 POST: b, (), None
----------------------------- Captured stdout call -----------------------------
Importing 'remote://workspace/empty_dir/' -> 'empty_dir'
----------------------------- Captured stderr call -----------------------------
WARNING: 'remote://workspace/empty_dir/' is empty.
------------------------------ Captured log call -------------------------------
DEBUG    urllib3.util.retry:retry.py:351 Converted retries value: 3 -> Retry(total=3, connect=None, read=None, redirect=None, status=None)
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (1): localhost:54355
DEBUG    urllib3.connectionpool:connectionpool.py:473 http://localhost:54355 "POST /upload/storage/v1/b/pytest-servers-imfnca/o?uploadType=multipart HTTP/1.1" 200 502
DEBUG    google.auth._default:_default.py:255 Checking None for explicit credentials as part of auth process...
DEBUG    google.auth._default:_default.py:228 Checking Cloud SDK credentials as part of auth process...
DEBUG    google.auth._default:_default.py:234 Cloud SDK credentials not found on disk; not using them
DEBUG    google.auth.transport._http_client:_http_client.py:102 Making request: GET http://169.254.169.254
WARNING  google.auth._default:_default.py:338 Authentication failed using Compute Engine authentication due to unavailable metadata server.
DEBUG    gcsfs.credentials:credentials.py:238 Connection with method "google_default" failed
Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 232, in connect
    self.connect(method=meth)
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 249, in connect
    self.__getattribute__("_connect_" + method)()
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 77, in _connect_google_default
    credentials, project = gauth.default(scopes=[self.scope])
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/_default.py", line 691, in default
    raise exceptions.DefaultCredentialsError(_CLOUD_SDK_MISSING_CREDENTIALS)
google.auth.exceptions.DefaultCredentialsError: Your default credentials were not found. To set up Application Default Credentials, see https://cloud.google.com/docs/authentication/external/set-up-adc for more information.
DEBUG    gcsfs.credentials:credentials.py:238 Connection with method "cache" failed
Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 232, in connect
    self.connect(method=meth)
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 249, in connect
    self.__getattribute__("_connect_" + method)()
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 104, in _connect_cache
    raise ValueError("No cached tokens")
ValueError: No cached tokens
DEBUG    google.auth.transport.requests:requests.py:185 Making request: GET http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (1): metadata.google.internal:80
WARNING  google.auth.compute_engine._metadata:_metadata.py:205 Compute Engine Metadata server unavailable on attempt 1 of 5. Reason: HTTPConnectionPool(host='metadata.google.internal', port=80): Max retries exceeded with url: /computeMetadata/v1/instance/service-accounts/default/?recursive=true (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f40187580a0>: Failed to establish a new connection: [Errno -2] Name or service not known'))
DEBUG    google.auth.transport.requests:requests.py:185 Making request: GET http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (2): metadata.google.internal:80
WARNING  google.auth.compute_engine._metadata:_metadata.py:205 Compute Engine Metadata server unavailable on attempt 2 of 5. Reason: HTTPConnectionPool(host='metadata.google.internal', port=80): Max retries exceeded with url: /computeMetadata/v1/instance/service-accounts/default/?recursive=true (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f40186f8670>: Failed to establish a new connection: [Errno -2] Name or service not known'))
DEBUG    google.auth.transport.requests:requests.py:185 Making request: GET http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (3): metadata.google.internal:80
WARNING  google.auth.compute_engine._metadata:_metadata.py:205 Compute Engine Metadata server unavailable on attempt 3 of 5. Reason: HTTPConnectionPool(host='metadata.google.internal', port=80): Max retries exceeded with url: /computeMetadata/v1/instance/service-accounts/default/?recursive=true (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f401875[110](https://github.com/iterative/dvc-gs/actions/runs/6276583341/job/17046587833?pr=45#step:7:111)0>: Failed to establish a new connection: [Errno -2] Name or service not known'))
DEBUG    google.auth.transport.requests:requests.py:185 Making request: GET http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (4): metadata.google.internal:80
WARNING  google.auth.compute_engine._metadata:_metadata.py:205 Compute Engine Metadata server unavailable on attempt 4 of 5. Reason: HTTPConnectionPool(host='metadata.google.internal', port=80): Max retries exceeded with url: /computeMetadata/v1/instance/service-accounts/default/?recursive=true (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f401870c3d0>: Failed to establish a new connection: [Errno -2] Name or service not known'))
DEBUG    google.auth.transport.requests:requests.py:185 Making request: GET http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true
DEBUG    urllib3.connectionpool:connectionpool.py:245 Starting new HTTP connection (5): metadata.google.internal:80
WARNING  google.auth.compute_engine._metadata:_metadata.py:205 Compute Engine Metadata server unavailable on attempt 5 of 5. Reason: HTTPConnectionPool(host='metadata.google.internal', port=80): Max retries exceeded with url: /computeMetadata/v1/instance/service-accounts/default/?recursive=true (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f401870c130>: Failed to establish a new connection: [Errno -2] Name or service not known'))
DEBUG    gcsfs.credentials:credentials.py:238 Connection with method "cloud" failed
Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/compute_engine/credentials.py", line [113](https://github.com/iterative/dvc-gs/actions/runs/6276583341/job/17046587833?pr=45#step:7:114), in refresh
    self._retrieve_info(request)
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/compute_engine/credentials.py", line 86, in _retrieve_info
    info = _metadata.get_service_account_info(
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/compute_engine/_metadata.py", line 285, in get_service_account_info
    return get(request, path, params={"recursive": "true"})
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/compute_engine/_metadata.py", line 214, in get
    raise exceptions.TransportError(
google.auth.exceptions.TransportError: Failed to retrieve http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true from the Google Compute Engine metadata service. Compute Engine Metadata server unavailable

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 97, in _connect_cloud
    self.credentials.refresh(req)
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/google/auth/compute_engine/credentials.py", line [119](https://github.com/iterative/dvc-gs/actions/runs/6276583341/job/17046587833?pr=45#step:7:120), in refresh
    raise new_exc from caught_exc
google.auth.exceptions.RefreshError: Failed to retrieve http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true from the Google Compute Engine metadata service. Compute Engine Metadata server unavailable

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 232, in connect
    self.connect(method=meth)
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 249, in connect
    self.__getattribute__("_connect_" + method)()
  File "/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/gcsfs/credentials.py", line 99, in _connect_cloud
    raise ValueError("Invalid gcloud credentials") from error
ValueError: Invalid gcloud credentials
DEBUG    gcsfs.credentials:credentials.py:233 Connected with method anon
INFO     dvc.stage.imports:imports.py:50 Importing 'remote://workspace/empty_dir/' -> 'empty_dir'
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
WARNING  dvc.output:output.py:717 'remote://workspace/empty_dir/' is empty.
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o/{}, ('pytest-servers-imfnca', 'empty_dir'), None
DEBUG    gcsfs:core.py:436 GET: b/{}/o, ('pytest-servers-imfnca',), None
DEBUG    gcsfs:retry.py:[145](https://github.com/iterative/dvc-gs/actions/runs/6276583341/job/17046587833?pr=45#step:7:146) Request returned 404, no retries.
=========================== short test summary info ============================
XPASS dvc_gs/tests/test_dvc.py::TestRemote::test_pull_00_prefix 
XPASS dvc_gs/tests/test_dvc.py::TestRemote::test_pull_no_00_prefix 
XPASS dvc_gs/tests/test_dvc.py::TestRemote::test_stage_cache_push_pull 
FAILED dvc_gs/tests/test_dvc.py::TestImport::test_import_empty_dir - aiohttp....
=================== 1 failed, 32 passed, 3 xpassed in 11.88s ===================