Not sensitive to temporary S3 credentials expiring

[jrbourbeau]

I tried to download some granules in a Python session that had been up for a while (over an hour)

files = earthaccess.download(granules, "test_data")

and got this error due to the temporary S3 credentials that earthaccess was using being expired (full traceback further below):

PermissionError: The provided token has expired.

Full traceback:

---------------------------------------------------------------------------
ClientError                               Traceback (most recent call last)
File /opt/coiled/env/lib/python3.11/site-packages/s3fs/core.py:706, in S3FileSystem._lsdir(self, path, refresh, max_items, delimiter, prefix, versions)
    705 files = []
--> 706 async for c in self._iterdir(
    707     bucket,
    708     max_items=max_items,
    709     delimiter=delimiter,
    710     prefix=prefix,
    711     versions=versions,
    712 ):
    713     if c["type"] == "directory":

File /opt/coiled/env/lib/python3.11/site-packages/s3fs/core.py:756, in S3FileSystem._iterdir(self, bucket, max_items, delimiter, prefix, versions)
    749 it = pag.paginate(
    750     Bucket=bucket,
    751     Prefix=prefix,
   (...)
    754     **self.req_kw,
    755 )
--> 756 async for i in it:
    757     for l in i.get("CommonPrefixes", []):

File /opt/coiled/env/lib/python3.11/site-packages/aiobotocore/paginate.py:30, in AioPageIterator.__anext__(self)
     29 while True:
---> 30     response = await self._make_request(current_kwargs)
     31     parsed = self._extract_parsed_response(response)

File /opt/coiled/env/lib/python3.11/site-packages/aiobotocore/client.py:383, in AioBaseClient._make_api_call(self, operation_name, api_params)
    382     error_class = self.exceptions.from_code(error_code)
--> 383     raise error_class(parsed_response, operation_name)
    384 else:

ClientError: An error occurred (ExpiredToken) when calling the ListObjectsV2 operation: The provided token has expired.

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

PermissionError                           Traceback (most recent call last)
Cell In[29], line 1
----> 1 files = earthaccess.download(granules, "test_data")
      2 print(f"{files = }")

File /opt/coiled/env/lib/python3.11/site-packages/earthaccess/api.py:176, in download(granules, local_path, provider, threads)
    174     granules = [granules]
    175 try:
--> 176     results = earthaccess.__store__.get(granules, local_path, provider, threads)
    177 except AttributeError as err:
    178     print(err)

File /opt/coiled/env/lib/python3.11/site-packages/earthaccess/store.py:463, in Store.get(self, granules, local_path, provider, threads)
    457     local_path = os.path.join(
    458         ".",
    459         "data",
    460         f"{datetime.datetime.today().strftime('%Y-%m-%d')}-{uuid4().hex[:6]}",
    461     )
    462 if len(granules):
--> 463     files = self._get(granules, local_path, provider, threads)
    464     return files
    465 else:

File /opt/coiled/env/lib/python3.11/site-packages/multimethod/__init__.py:315, in multimethod.__call__(self, *args, **kwargs)
    313 func = self[tuple(func(arg) for func, arg in zip(self.type_checkers, args))]
    314 try:
--> 315     return func(*args, **kwargs)
    316 except TypeError as ex:
    317     raise DispatchError(f"Function {func.__code__}") from ex

File /opt/coiled/env/lib/python3.11/site-packages/earthaccess/store.py:564, in Store._get_granules(self, granules, local_path, provider, threads)
    562 # TODO: make this async
    563 for file in data_links:
--> 564     s3_fs.get(file, local_path)
    565     file_name = os.path.join(local_path, os.path.basename(file))
    566     print(f"Downloaded: {file_name}")

File /opt/coiled/env/lib/python3.11/site-packages/fsspec/asyn.py:118, in sync_wrapper.<locals>.wrapper(*args, **kwargs)
    115 @functools.wraps(func)
    116 def wrapper(*args, **kwargs):
    117     self = obj or args[0]
--> 118     return sync(self.loop, func, *args, **kwargs)

File /opt/coiled/env/lib/python3.11/site-packages/fsspec/asyn.py:103, 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

File /opt/coiled/env/lib/python3.11/site-packages/fsspec/asyn.py:56, 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

File /opt/coiled/env/lib/python3.11/site-packages/fsspec/asyn.py:609, in AsyncFileSystem._get(self, rpath, lpath, recursive, callback, maxdepth, **kwargs)
    604 rpaths = await self._expand_path(
    605     rpath, recursive=recursive, maxdepth=maxdepth
    606 )
    607 if source_is_str and (not recursive or maxdepth is not None):
    608     # Non-recursive glob does not copy directories
--> 609     rpaths = [
    610         p for p in rpaths if not (trailing_sep(p) or await self._isdir(p))
    611     ]
    612     if not rpaths:
    613         return

File /opt/coiled/env/lib/python3.11/site-packages/fsspec/asyn.py:610, in <listcomp>(.0)
    604 rpaths = await self._expand_path(
    605     rpath, recursive=recursive, maxdepth=maxdepth
    606 )
    607 if source_is_str and (not recursive or maxdepth is not None):
    608     # Non-recursive glob does not copy directories
    609     rpaths = [
--> 610         p for p in rpaths if not (trailing_sep(p) or await self._isdir(p))
    611     ]
    612     if not rpaths:
    613         return

File /opt/coiled/env/lib/python3.11/site-packages/s3fs/core.py:1411, in S3FileSystem._isdir(self, path)
   1409 # This only returns things within the path and NOT the path object itself
   1410 try:
-> 1411     return bool(await self._lsdir(path))
   1412 except FileNotFoundError:
   1413     return False

File /opt/coiled/env/lib/python3.11/site-packages/s3fs/core.py:719, in S3FileSystem._lsdir(self, path, refresh, max_items, delimiter, prefix, versions)
    717     files += dirs
    718 except ClientError as e:
--> 719     raise translate_boto_error(e)
    721 if delimiter and files and not versions:
    722     self.dircache[path] = files

PermissionError: The provided token has expired.

IIUC this has to do with me adding this @lru_cache a while ago for performance reasons without thinking about how these credentials can expire:

earthaccess/earthaccess/store.py

Line 185 in 7db2e59

@lru_cache

I'd still like to having caching around getting new S3 credentials since it can be pretty slow (several seconds) but the top-level @lru_cache we have now isn't the right approach to caching.