[英]How to change permission recursively to folder with AWS s3 or AWS s3api
我正在尝试向 s3 中的现有帐户授予权限。
该存储桶归该账户所有,但数据是从另一个账户的存储桶复制的。
当我尝试使用以下命令授予权限时:
aws s3api put-object-acl --bucket <bucket_name> --key <folder_name> --profile <original_account_profile> --grant-full-control emailaddress=<destination_account_email>
我收到错误:
An error occurred (NoSuchKey) when calling the PutObjectAcl operation: The specified key does not exist.
而如果我在单个文件上执行该命令,则该命令会成功。
我怎样才能使它适用于一个完整的文件夹?
这只能通过使用管道来实现。 试试——
aws s3 ls s3://bucket/path/ --recursive | awk '{cmd="aws s3api put-object-acl --acl bucket-owner-full-control --bucket bucket --key "$4; system(cmd)}'
您需要为每个对象单独运行该命令。
您可以使用以下方法缩短该过程:
aws s3 cp --acl bucket-owner-full-control --metadata Key=Value --profile <original_account_profile> s3://bucket/path s3://bucket/path
也就是说,您将文件复制到自身,但添加了向存储桶所有者授予权限的 ACL。
如果您有子目录,则添加--recursive
。
其他答案没问题,但最快的方法是使用带有选项--metadata-directive REPLACE
的aws s3 cp
命令,如下所示:
aws s3 cp --recursive --acl bucket-owner-full-control s3://bucket/folder s3://bucket/folder --metadata-directive REPLACE
这给出了介于 50Mib/s 和 80Mib/s 之间的速度。
John R 的评论中的答案,建议使用“虚拟”选项,例如--storage-class STANDARD
。 虽然这有效,但只给了我 5Mib/s 和 11mb/s 之间的复制速度。
尝试此操作的灵感来自 AWS 关于该主题的支持文章: https : //aws.amazon.com/premiumsupport/knowledge-center/s3-object-change-anonymous-ownership/
注意:如果您的某些对象遇到“访问被拒绝”,这可能是因为您将 AWS 凭证用于存储桶拥有账户,而您需要对从中复制文件的账户使用凭证。
使用python递归设置权限
#!/usr/bin/env python
import boto3
import sys
client = boto3.client('s3')
BUCKET='enter-bucket-name'
def process_s3_objects(prefix):
"""Get a list of all keys in an S3 bucket."""
kwargs = {'Bucket': BUCKET, 'Prefix': prefix}
failures = []
while_true = True
while while_true:
resp = client.list_objects_v2(**kwargs)
for obj in resp['Contents']:
try:
print(obj['Key'])
set_acl(obj['Key'])
kwargs['ContinuationToken'] = resp['NextContinuationToken']
except KeyError:
while_true = False
except Exception:
failures.append(obj["Key"])
continue
print "failures :", failures
def set_acl(key):
client.put_object_acl(
GrantFullControl="id=%s" % get_account_canonical_id,
Bucket=BUCKET,
Key=key
)
def get_account_canonical_id():
return client.list_buckets()["Owner"]["ID"]
process_s3_objects(sys.argv[1])
这是我的powershell
唯一解决方案。
aws s3 ls s3://BUCKET/ --recursive | %{ "aws s3api put-object-acl --bucket BUCKET --key "+$_.ToString().substring(30)+" --acl bucket-owner-full-control" }
我使用这个 Linux Bash shell oneliner 递归地更改 ACL:
aws s3 ls s3://bucket --recursive | cut -c 32- | xargs -n 1 -d '\n' -- aws s3api put-object-acl --acl public-read --bucket bukcet --key
即使文件名包含 () 字符,它也能工作。
我在一个相当大的存储桶中获取日志对象的所有权时遇到了类似的问题。 对象总数 - 3,290,956 总大小 1.4 TB。
我能够找到的解决方案对于这么多对象来说太慢了。 我最终编写了一些代码,这些代码能够比
aws s3 cp
您将需要安装要求:
pip install pathos boto3 click
#!/usr/bin/env python3
import logging
import os
import sys
import boto3
import botocore
import click
from time import time
from botocore.config import Config
from pathos.pools import ThreadPool as Pool
logger = logging.getLogger(__name__)
streamformater = logging.Formatter("[*] %(levelname)s: %(asctime)s: %(message)s")
logstreamhandler = logging.StreamHandler()
logstreamhandler.setFormatter(streamformater)
def _set_log_level(ctx, param, value):
if value:
ctx.ensure_object(dict)
ctx.obj["log_level"] = value
logger.setLevel(value)
if value <= 20:
logger.info(f"Logger set to {logging.getLevelName(logger.getEffectiveLevel())}")
return value
@click.group(chain=False)
@click.version_option(version='0.1.0')
@click.pass_context
def cli(ctx):
"""
Take object ownership of S3 bucket objects.
"""
ctx.ensure_object(dict)
ctx.obj["aws_config"] = Config(
retries={
'max_attempts': 10,
'mode': 'standard'
}
)
@cli.command("own")
@click.argument("bucket", type=click.STRING)
@click.argument("prefix", type=click.STRING, default="/")
@click.option("--profile", type=click.STRING, default="default", envvar="AWS_DEFAULT_PROFILE", help="Configuration profile from ~/.aws/{credentials,config}")
@click.option("--region", type=click.STRING, default="us-east-1", envvar="AWS_DEFAULT_REGION", help="AWS region")
@click.option("--threads", "-t", type=click.INT, default=40, help="Threads to use")
@click.option("--loglevel", "log_level", hidden=True, flag_value=logging.INFO, callback=_set_log_level, expose_value=False, is_eager=True, default=True)
@click.option("--verbose", "-v", "log_level", flag_value=logging.DEBUG, callback=_set_log_level, expose_value=False, is_eager=True, help="Increase log_level")
@click.pass_context
def command_own(ctx, *args, **kwargs):
ctx.obj.update(kwargs)
profile_name = ctx.obj.get("profile")
region = ctx.obj.get("region")
bucket = ctx.obj.get("bucket")
prefix = ctx.obj.get("prefix").lstrip("/")
threads = ctx.obj.get("threads")
pool = Pool(nodes=threads)
logger.addHandler(logstreamhandler)
logger.info(f"Getting ownership of all objects in s3://{bucket}/{prefix}")
start = time()
try:
SESSION: boto3.Session = boto3.session.Session(profile_name=profile_name)
except botocore.exceptions.ProfileNotFound as e:
logger.warning(f"Profile {profile_name} was not found.")
logger.warning(f"Falling back to environment variables for AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN")
AWS_ACCESS_KEY_ID = os.environ.get("AWS_ACCESS_KEY_ID", "")
AWS_SECRET_ACCESS_KEY = os.environ.get("AWS_SECRET_ACCESS_KEY", "")
AWS_SESSION_TOKEN = os.environ.get("AWS_SESSION_TOKEN", "")
if AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY:
if AWS_SESSION_TOKEN:
SESSION: boto3.Session = boto3.session.Session(aws_access_key_id=AWS_ACCESS_KEY_ID, aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
aws_session_token=AWS_SESSION_TOKEN)
else:
SESSION: boto3.Session = boto3.session.Session(aws_access_key_id=AWS_ACCESS_KEY_ID, aws_secret_access_key=AWS_SECRET_ACCESS_KEY)
else:
logger.error("Unable to find AWS credentials.")
sys.exit(1)
s3c = SESSION.client('s3', config=ctx.obj["aws_config"])
def bucket_keys(Bucket, Prefix='', StartAfter='', Delimiter='/'):
Prefix = Prefix[1:] if Prefix.startswith(Delimiter) else Prefix
if not StartAfter:
del StartAfter
if Prefix.endswith(Delimiter):
StartAfter = Prefix
del Delimiter
for page in s3c.get_paginator('list_objects_v2').paginate(Bucket=Bucket, Prefix=Prefix):
for content in page.get('Contents', ()):
yield content['Key']
def worker(key):
logger.info(f"Processing: {key}")
s3c.copy_object(Bucket=bucket, Key=key,
CopySource={'Bucket': bucket, 'Key': key},
ACL='bucket-owner-full-control',
StorageClass="STANDARD"
)
object_keys = bucket_keys(bucket, prefix)
pool.map(worker, object_keys)
end = time()
logger.info(f"Completed for {end - start:.2f} seconds.")
if __name__ == '__main__':
cli()
用法:
get_object_ownership.py own -v my-big-aws-logs-bucket /prefix
上面提到的存储桶使用 40 个线程处理了大约 7 个小时。
[*] 信息:2021-08-05 19:53:55,542:已完成 25320.45 秒。
在同一数据子集上使用 AWS cli 与此工具进行更多速度比较:
aws s3 cp --recursive --acl bucket-owner-full-control --metadata-directive 53.59s 用户 7.24s 系统 20% cpu 5:02.42 总计
对比
[*] 信息:2021-08-06 09:07:43,506:完成 49.09 秒。
这样python代码效率更高,否则需要更长的时间。
import boto3
import sys
client = boto3.client('s3')
BUCKET='mybucket'
def process_s3_objects(prefix):
"""Get a list of all keys in an S3 bucket."""
kwargs = {'Bucket': BUCKET, 'Prefix': prefix}
failures = []
while_true = True
while while_true:
resp = client.list_objects_v2(**kwargs)
for obj in resp['Contents']:
try:
set_acl(obj['Key'])
except KeyError:
while_true = False
except Exception:
failures.append(obj["Key"])
continue
kwargs['ContinuationToken'] = resp['NextContinuationToken']
print ("failures :"+ failures)
def set_acl(key):
print(key)
client.put_object_acl(
ACL='bucket-owner-full-control',
Bucket=BUCKET,
Key=key
)
def get_account_canonical_id():
return client.list_buckets()["Owner"]["ID"]
process_s3_objects(sys.argv[1])
aws s3api put-object-acl --bucket bucketname_example_3636 --key bigdirectories2_noglacier/bkpy_workspace_sda4.tar --acl bucket-owner-full-control
aws s3 ls s3://bucketname_example_3636 --recursive > listfile.txt
sed 's/^(.*)$/aws s3api put-object-acl --bucket bucketname_example_3636 --key \\1 --acl bucket-owner-full-control/g' listfile.txt > listfile_v2.txt;
sed '1 i\\#!/bin/bash' listfile_v2.txt > listfile_v3.txt;
cp listfile_v3.txt listfile_v3.sh;
chmod u+x listfile_v3.sh;
listfile_v3.sh;
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.