In [5]:

path = 'gs://gresearch/neuralgcm/03_04_2024/neural_gcm_stochastic_1_4_deg_v0.pkl'

with gs_open_default(path) as f:
  print(len(f.read()))  # fails

ERROR:gcsfs:_request out of retries on exception: ("Failed to retrieve http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true from the Google Compute Engine metadata service. Status: 404 Response:\nb''", <google.auth.transport.requests._Response object at 0x7b0a4dd37e20>)
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py", line 128, in refresh
    self._retrieve_info(request)
  File "/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py", line 101, in _retrieve_info
    info = _metadata.get_service_account_info(
  File "/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/_metadata.py", line 323, in get_service_account_info
    return get(request, path, params={"recursive": "true"})
  File "/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/_metadata.py", line 248, 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. Status: 404 Response:\nb''", <google.auth.transport.requests._Response object at 0x7b0a4dd37e20>)

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

Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/gcsfs/retry.py", line 123, in retry_request
    return await func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/gcsfs/core.py", line 421, in _request
    headers=self._get_headers(headers),
  File "/usr/local/lib/python3.10/dist-packages/gcsfs/core.py", line 400, in _get_headers
    self.credentials.apply(out)
  File "/usr/local/lib/python3.10/dist-packages/gcsfs/credentials.py", line 187, in apply
    self.maybe_refresh()
  File "/usr/local/lib/python3.10/dist-packages/gcsfs/credentials.py", line 182, in maybe_refresh
    self.credentials.refresh(req)
  File "/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py", line 134, 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. Status: 404 Response:\nb''", <google.auth.transport.requests._Response object at 0x7b0a4dd37e20>)

---------------------------------------------------------------------------
TransportError                            Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py in refresh(self, request)
    127         try:
--> 128             self._retrieve_info(request)
    129             self.token, self.expiry = _metadata.get_service_account_token(

/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py in _retrieve_info(self, request)
    100         """
--> 101         info = _metadata.get_service_account_info(
    102             request, service_account=self._service_account_email

/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/_metadata.py in get_service_account_info(request, service_account)
    322     # for more on the use of 'recursive'.
--> 323     return get(request, path, params={"recursive": "true"})
    324 

/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/_metadata.py in get(request, path, root, params, recursive, retry_count, headers, return_none_for_not_found_error)
    247 
--> 248     raise exceptions.TransportError(
    249         "Failed to retrieve {} from the Google Compute Engine "

TransportError: ("Failed to retrieve http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true from the Google Compute Engine metadata service. Status: 404 Response:\nb''", <google.auth.transport.requests._Response object at 0x7b0a4dd37e20>)

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

RefreshError                              Traceback (most recent call last)
<ipython-input-5-7478255724ae> in <cell line: 1>()
----> 1 with gs_open_default(path) as f:
      2   print(len(f.read()))

<ipython-input-3-0131ff1af10c> in gs_open_default(path)
      7 def gs_open_default(path):
      8   fs = gcsfs.GCSFileSystem()
----> 9   return fs.open(path, 'rb')

/usr/local/lib/python3.10/dist-packages/fsspec/spec.py in open(self, path, mode, block_size, cache_options, compression, **kwargs)
   1291         else:
   1292             ac = kwargs.pop("autocommit", not self._intrans)
-> 1293             f = self._open(
   1294                 path,
   1295                 mode=mode,

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _open(self, path, mode, block_size, cache_options, acl, consistency, metadata, autocommit, fixed_key_metadata, generation, **kwargs)
   1514             block_size = self.default_block_size
   1515         const = consistency or self.consistency
-> 1516         return GCSFile(
   1517             self,
   1518             path,

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in __init__(self, gcsfs, path, mode, block_size, autocommit, cache_type, cache_options, acl, consistency, metadata, content_type, timeout, fixed_key_metadata, generation, **kwargs)
   1673             raise OSError("Attempt to open a bucket")
   1674         self.generation = _coalesce_generation(generation, path_generation)
-> 1675         super().__init__(
   1676             gcsfs,
   1677             path,

/usr/local/lib/python3.10/dist-packages/fsspec/spec.py in __init__(self, fs, path, mode, block_size, autocommit, cache_type, cache_options, size, **kwargs)
   1649                 self.size = size
   1650             else:
-> 1651                 self.size = self.details["size"]
   1652             self.cache = caches[cache_type](
   1653                 self.blocksize, self._fetch_range, self.size, **cache_options

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in details(self)
   1709     def details(self):
   1710         if self._details is None:
-> 1711             self._details = self.fs.info(self.path, generation=self.generation)
   1712         return self._details
   1713 

/usr/local/lib/python3.10/dist-packages/fsspec/asyn.py in wrapper(*args, **kwargs)
    116     def wrapper(*args, **kwargs):
    117         self = obj or args[0]
--> 118         return sync(self.loop, func, *args, **kwargs)
    119 
    120     return wrapper

/usr/local/lib/python3.10/dist-packages/fsspec/asyn.py in sync(loop, func, timeout, *args, **kwargs)
    101         raise FSTimeoutError from return_result
    102     elif isinstance(return_result, BaseException):
--> 103         raise return_result
    104     else:
    105         return return_result

/usr/local/lib/python3.10/dist-packages/fsspec/asyn.py in _runner(event, coro, result, timeout)
     54         coro = asyncio.wait_for(coro, timeout=timeout)
     55     try:
---> 56         result[0] = await coro
     57     except Exception as ex:
     58         result[0] = ex

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _info(self, path, generation, **kwargs)
    957         # Check exact file path
    958         try:
--> 959             exact = await self._get_object(path)
    960             # this condition finds a "placeholder" - still need to check if it's a directory
    961             if exact["size"] or not exact["name"].endswith("/"):

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _get_object(self, path)
    514         # fall back to a bucket list + filter to object name (storage.objects.list).
    515         try:
--> 516             res = await self._call(
    517                 "GET", "b/{}/o/{}", bucket, key, json_out=True, generation=generation
    518             )

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _call(self, method, path, json_out, info_out, *args, **kwargs)
    435     ):
    436         logger.debug(f"{method.upper()}: {path}, {args}, {kwargs.get('headers')}")
--> 437         status, headers, info, contents = await self._request(
    438             method, path, *args, **kwargs
    439         )

<decorator-gen-119> in _request(self, method, path, headers, json, data, *args, **kwargs)

/usr/local/lib/python3.10/dist-packages/gcsfs/retry.py in retry_request(func, retries, *args, **kwargs)
    151             if retry == retries - 1:
    152                 logger.exception(f"{func.__name__} out of retries on exception: {e}")
--> 153                 raise e
    154             if is_retriable(e):
    155                 logger.debug(f"{func.__name__} retrying after exception: {e}")

/usr/local/lib/python3.10/dist-packages/gcsfs/retry.py in retry_request(func, retries, *args, **kwargs)
    121             if retry > 0:
    122                 await asyncio.sleep(min(random.random() + 2 ** (retry - 1), 32))
--> 123             return await func(*args, **kwargs)
    124         except (
    125             HttpError,

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _request(self, method, path, headers, json, data, *args, **kwargs)
    419             params=self._get_params(kwargs),
    420             json=json,
--> 421             headers=self._get_headers(headers),
    422             data=data,
    423             timeout=self.requests_timeout,

/usr/local/lib/python3.10/dist-packages/gcsfs/core.py in _get_headers(self, headers)
    398         if "User-Agent" not in out:
    399             out["User-Agent"] = "python-gcsfs/" + version
--> 400         self.credentials.apply(out)
    401         return out
    402 

/usr/local/lib/python3.10/dist-packages/gcsfs/credentials.py in apply(self, out)
    185     def apply(self, out):
    186         """Insert credential headers in-place to a dictionary"""
--> 187         self.maybe_refresh()
    188         if self.credentials is not None:
    189             self.credentials.apply(out)

/usr/local/lib/python3.10/dist-packages/gcsfs/credentials.py in maybe_refresh(self)
    180                     return  # repeat to avoid race (but don't want lock in common case)
    181                 logger.debug("GCS refresh")
--> 182                 self.credentials.refresh(req)
    183                 self.apply(self.heads)
    184 

/usr/local/lib/python3.10/dist-packages/google/auth/compute_engine/credentials.py in refresh(self, request)
    132         except exceptions.TransportError as caught_exc:
    133             new_exc = exceptions.RefreshError(caught_exc)
--> 134             raise new_exc from caught_exc
    135 
    136     @property

RefreshError: ("Failed to retrieve http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/?recursive=true from the Google Compute Engine metadata service. Status: 404 Response:\nb''", <google.auth.transport.requests._Response object at 0x7b0a4dd37e20>)