Python 使Boto3上传呼叫阻塞（单线程）
编辑：我最初的假设被证明部分错误。我在这里添加了一个冗长的答案，请其他人进行压力测试和纠正Python 使Boto3上传呼叫阻塞（单线程）,python,boto3,Python,Boto3,编辑：我最初的假设被证明部分错误。我在这里添加了一个冗长的答案，请其他人进行压力测试和纠正 我正在寻找一种以单线程方式利用Boto3 S3API来模拟线程安全键值存储的方法。简而言之，我想使用调用线程而不是新线程来上传 据我所知，Boto3（或.upload_file（））中方法的默认行为是将任务启动到新线程，并立即返回None 从： 这是一个托管传输，必要时将在多个线程中执行多部分上载 （如果我对这一点的理解一开始是错误的，那么对其进行更正也会很有帮助。这在Boto3 1.9.134中。）
我正在寻找一种以单线程方式利用Boto3 S3API来模拟线程安全键值存储的方法。简而言之，我想使用调用线程而不是新线程来上传 据我所知，Boto3（或
.upload_file（）Nonebufdef key_exists_in_bucket(bucket_obj, key: str) -> bool:
try:
bucket_obj.Object(key).load()
except botocore.exceptions.ClientError:
return False
else:
return True
键\u exists\u in_bucket（）Falsebucket.upload\u fileobj（）use\u threads希望这对您有用。测试方法是否阻塞：
我自己对这种行为进行了经验测试。首先，我生成了一个100MB的文件，其中包含：
dd if=/dev/zero of=100mb.txt bs=100M count=1
import boto3
import time
import io
file = open('100mb.txt', 'rb')
buf = io.BytesIO(file.read())
bucket = boto3.resource('s3').Bucket('testbucket')
start = time.time()
print("starting to upload...")
bucket.upload_fileobj(buf, '100mb')
print("finished uploading")
end = time.time()
print("time: {}".format(end-start))
开始上传100mb.txt文件
已完成上载文件100mb.txt。时间：46.35254502296448
已完成上载文件200mb.txt。时间：61.70564889907837 使用会话进行测试：
如果希望上传方法按调用顺序完成，则需要这样做 代码： 输出： 开始上传文件200mb.txt
开始上传100mb.txt文件
已完成上载文件200mb.txt。时间：46.62478971481323
已完成上载文件100mb.txt。时间：50.5159502941895 我找到的一些资源：
-这里有一个关于方法是阻塞还是非阻塞的问题。这不是结论性的，但其中可能包含相关信息。
-GitHub有一个开放平台，允许boto3中的同步传输。
-还有一些工具，如和专门用于允许从s3和其他aws服务异步下载和上传 关于我以前的回答：
您可以在boto3中阅读有关文件传输配置的信息。特别是： 传输操作使用线程来实现并发性。线程使用 可以通过将“使用线程”属性设置为False来禁用 最初我认为这与并发执行的多个传输有关。但是，在使用TransferConfig时读取参数max_concurrency中的注释说明，并发性不是指多个传输，而是指
“将请求执行传输的线程数”。所以它是用来加速传输的。use_threads属性仅用于允许多部分传输中的并发性。我认为，由于这个问题的答案和答案似乎都存在直接冲突，因此最好直接找到源代码 总结
默认情况下使用多个线程（10）boto3- 但是，它不是异步的，因为它在返回之前等待（加入）这些线程，而不是使用“触发并忘记”技术
- 因此，通过这种方式，如果您试图从多个客户端与一个s3存储桶通信，那么读/写线程安全就已经就位
细节 我在这里努力解决的一个方面是，多（子线程）并不意味着顶级方法本身是非阻塞的：如果调用线程开始上传到多个子线程，但随后等待这些线程完成并返回，我敢说这仍然是一个阻塞调用。另一方面，如果方法调用在
asyncio线程x.join（）import io
import pdb
import boto3
# From dd if=/dev/zero of=100mb.txt bs=50M count=1
buf = io.BytesIO(open('100mb.txt', 'rb').read())
bucket = boto3.resource('s3').Bucket('test-threads')
pdb.run("bucket.upload_fileobj(buf, '100mb')")
pdb。上传\u文件
import boto3
import time
import io
from boto3.s3.transfer import TransferConfig
import threading
config = TransferConfig(use_threads=False)
bucket = boto3.resource('s3').Bucket('testbucket')
def upload(filename):
file = open(filename, 'rb')
buf = io.BytesIO(file.read())
start = time.time()
print("starting to upload file {}".format(filename))
bucket.upload_fileobj(buf,filename,Config=config)
end = time.time()
print("finished uploading file {}. time: {}".format(filename,end-start))
x1 = threading.Thread(target=upload, args=('200mb.txt',))
x2 = threading.Thread(target=upload, args=('100mb.txt',))
x1.start()
time.sleep(2)
x2.start()
import boto3
import time
import io
from boto3.s3.transfer import TransferConfig
import threading
config = TransferConfig(use_threads=False)
session = boto3.session.Session()
s3 = session.resource('s3')
bucket = s3.Bucket('testbucket')
def upload(filename):
file = open(filename, 'rb')
buf = io.BytesIO(file.read())
start = time.time()
print("starting to upload file {}".format(filename))
bucket.upload_fileobj(buf,filename)
end = time.time()
print("finished uploading file {}. time: {}".format(filename,end-start))
x1 = threading.Thread(target=upload, args=('200mb.txt',))
x2 = threading.Thread(target=upload, args=('100mb.txt',))
x1.start()
time.sleep(2)
x2.start()
import io
import pdb
import boto3
# From dd if=/dev/zero of=100mb.txt bs=50M count=1
buf = io.BytesIO(open('100mb.txt', 'rb').read())
bucket = boto3.resource('s3').Bucket('test-threads')
pdb.run("bucket.upload_fileobj(buf, '100mb')")
(Pdb) s
--Call--
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/boto3/s3/inject.py(542)bucket_upload_fileobj()
-> def bucket_upload_fileobj(self, Fileobj, Key, ExtraArgs=None,
(Pdb) s
(Pdb) l
574
575 :type Config: boto3.s3.transfer.TransferConfig
576 :param Config: The transfer configuration to be used when performing the
577 upload.
578 """
579 -> return self.meta.client.upload_fileobj(
580 Fileobj=Fileobj, Bucket=self.name, Key=Key, ExtraArgs=ExtraArgs,
581 Callback=Callback, Config=Config)
582
583
584
(Pdb) l 531
526
527 subscribers = None
528 if Callback is not None:
529 subscribers = [ProgressCallbackInvoker(Callback)]
530
531 config = Config
532 if config is None:
533 config = TransferConfig()
534
535 with create_transfer_manager(self, config) as manager:
536 future = manager.upload(
(Pdb) unt 534
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/boto3/s3/inject.py(535)upload_fileobj()
-> with create_transfer_manager(self, config) as manager:
(Pdb) config
<boto3.s3.transfer.TransferConfig object at 0x7f1790dc0cc0>
(Pdb) config.use_threads
True
(Pdb) config.max_concurrency
10
# https://github.com/boto/s3transfer/blob/2aead638c8385d8ae0b1756b2de17e8fad45fffa/s3transfer/manager.py#L223
# The executor responsible for making S3 API transfer requests
self._request_executor = BoundedExecutor(
max_size=self._config.max_request_queue_size,
max_num_threads=self._config.max_request_concurrency,
tag_semaphores={
IN_MEMORY_UPLOAD_TAG: TaskSemaphore(
self._config.max_in_memory_upload_chunks),
IN_MEMORY_DOWNLOAD_TAG: SlidingWindowSemaphore(
self._config.max_in_memory_download_chunks)
},
executor_cls=executor_cls
)
(Pdb) n
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/boto3/s3/inject.py(536)upload_fileobj()
-> future = manager.upload(
(Pdb) manager
<s3transfer.manager.TransferManager object at 0x7f178db437f0>
(Pdb) manager._config
<boto3.s3.transfer.TransferConfig object at 0x7f1790dc0cc0>
(Pdb) manager._config.use_threads
True
(Pdb) manager._config.max_concurrency
10
(Pdb) l 290, 303
290 -> if extra_args is None:
291 extra_args = {}
292 if subscribers is None:
293 subscribers = []
294 self._validate_all_known_args(extra_args, self.ALLOWED_UPLOAD_ARGS)
295 call_args = CallArgs(
296 fileobj=fileobj, bucket=bucket, key=key, extra_args=extra_args,
297 subscribers=subscribers
298 )
299 extra_main_kwargs = {}
300 if self._bandwidth_limiter:
301 extra_main_kwargs['bandwidth_limiter'] = self._bandwidth_limiter
302 return self._submit_transfer(
303 call_args, UploadSubmissionTask, extra_main_kwargs)
(Pdb) unt 301
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/s3transfer/manager.py(302)upload()
-> return self._submit_transfer(
(Pdb) extra_main_kwargs
{}
(Pdb) UploadSubmissionTask
<class 's3transfer.upload.UploadSubmissionTask'>
(Pdb) call_args
<s3transfer.utils.CallArgs object at 0x7f178db5a5f8>
(Pdb) l 300, 5
300 if self._bandwidth_limiter:
301 extra_main_kwargs['bandwidth_limiter'] = self._bandwidth_limiter
302 -> return self._submit_transfer(
303 call_args, UploadSubmissionTask, extra_main_kwargs)
304
305 def download(self, bucket, key, fileobj, extra_args=None,
(Pdb) s
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/s3transfer/manager.py(303)upload()
-> call_args, UploadSubmissionTask, extra_main_kwargs)
(Pdb) s
--Call--
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/s3transfer/manager.py(438)_submit_transfer()
-> def _submit_transfer(self, call_args, submission_task_cls,
(Pdb) s
> /home/ubuntu/envs/py372/lib/python3.7/site-packages/s3transfer/manager.py(440)_submit_transfer()
-> if not extra_main_kwargs:
(Pdb) l 440, 10
440 -> if not extra_main_kwargs:
441 extra_main_kwargs = {}
442
443 # Create a TransferFuture to return back to the user
444 transfer_future, components = self._get_future_with_components(
445 call_args)
446
447 # Add any provided done callbacks to the created transfer future
448 # to be invoked on the transfer future being complete.
449 for callback in get_callbacks(transfer_future, 'done'):
450 components['coordinator'].add_done_callback(callback)
(Pdb) l
444 transfer_future, components = self._get_future_with_components(
445 call_args)
446
447 # Add any provided done callbacks to the created transfer future
448 # to be invoked on the transfer future being complete.
449 -> for callback in get_callbacks(transfer_future, 'done'):
450 components['coordinator'].add_done_callback(callback)
451
452 # Get the main kwargs needed to instantiate the submission task
453 main_kwargs = self._get_submission_task_main_kwargs(
454 transfer_future, extra_main_kwargs)
(Pdb) transfer_future
<s3transfer.futures.TransferFuture object at 0x7f178db5a780>
class TransferCoordinator(object):
"""A helper class for managing TransferFuture"""
def __init__(self, transfer_id=None):
self.transfer_id = transfer_id
self._status = 'not-started'
self._result = None
self._exception = None
self._associated_futures = set()
self._failure_cleanups = []
self._done_callbacks = []
self._done_event = threading.Event() # < ------ !!!!!!
class BoundedExecutor(object):
EXECUTOR_CLS = futures.ThreadPoolExecutor
# ...
def __init__(self, max_size, max_num_threads, tag_semaphores=None,
executor_cls=None):
self._max_num_threads = max_num_threads
if executor_cls is None:
executor_cls = self.EXECUTOR_CLS
self._executor = executor_cls(max_workers=self._max_num_threads)
from concurrent import futures
_executor = futures.ThreadPoolExecutor(max_workers=10)
# https://github.com/boto/s3transfer/blob/2aead638c8385d8ae0b1756b2de17e8fad45fffa/s3transfer/futures.py#L249
def result(self):
self._done_event.wait(MAXINT)
# Once done waiting, raise an exception if present or return the
# final result.
if self._exception:
raise self._exception
return self._result
>>> import boto3
>>> import time
>>> import io
>>>
>>> buf = io.BytesIO(open('100mb.txt', 'rb').read())
>>>
>>> bucket = boto3.resource('s3').Bucket('test-threads')
>>> start = time.time()
>>> print("starting to upload...")
starting to upload...
>>> bucket.upload_fileobj(buf, '100mb')
>>> print("finished uploading")
finished uploading
>>> end = time.time()
>>> print("time: {}".format(end-start))
time: 2.6030001640319824
def get_bufsize(buf, chunk=1024) -> int:
start = buf.tell()
try:
size = 0
while True:
out = buf.read(chunk)
if out:
size += chunk
else:
break
return size
finally:
buf.seek(start)
import os
import sys
import threading
import time
class ProgressPercentage(object):
def __init__(self, filename, buf):
self._filename = filename
self._size = float(get_bufsize(buf))
self._seen_so_far = 0
self._lock = threading.Lock()
self.start = None
def __call__(self, bytes_amount):
with self._lock:
if not self.start:
self.start = time.monotonic()
self._seen_so_far += bytes_amount
percentage = (self._seen_so_far / self._size) * 100
sys.stdout.write(
"\r%s %s of %s (%.2f%% done, %.2fs elapsed\n" % (
self._filename, self._seen_so_far, self._size,
percentage, time.monotonic() - self.start))
# Use sys.stdout.flush() to update on one line
# sys.stdout.flush()
In [19]: import io
...:
...: from boto3.session import Session
...:
...: s3 = Session().resource("s3")
...: bucket = s3.Bucket("test-threads")
...: buf = io.BytesIO(open('100mb.txt', 'rb').read())
...:
...: bucket.upload_fileobj(buf, 'mykey', Callback=ProgressPercentage("mykey", buf))
mykey 262144 of 104857600.0 (0.25% done, 0.00s elapsed
mykey 524288 of 104857600.0 (0.50% done, 0.00s elapsed
mykey 786432 of 104857600.0 (0.75% done, 0.01s elapsed
mykey 1048576 of 104857600.0 (1.00% done, 0.01s elapsed
mykey 1310720 of 104857600.0 (1.25% done, 0.01s elapsed
mykey 1572864 of 104857600.0 (1.50% done, 0.02s elapsed