如何在Python中找到S3多部分上传失败的地方

Question

我正在实现一个cron作业，该作业将向S3 Bucket上传一个大的每日备份文件。它大多数时候都有效，但每隔一段时间，我就会检查bucket，文件大小明显小于实际大小。

它应该大约是50GB，但上次出现时，它显示为34GB。我的主要问题是我不确定该尝试/捕捉什么错误。

我仍然在学习Python，对我来说太枯燥了。

from progress import ProgressPercentage  # class file progress.py
from slack import *  # function file for Slack notifications
import random
import glob
import os
import boto3
import botocore
from boto3.s3.transfer import TransferConfig
bucket = "my-s3-backup"
s3 = boto3.resource('s3')
# Grabbing the last file, and removing the full path from the string
pattern = "/path/to/backup/file/xb_*"
files = list(filter(os.path.isfile, glob.glob(pattern)))
files.sort(key=lambda x: os.path.getmtime(x))
file_to_upload = files[-1]
file_name = file_to_upload.replace('/path/to/backup/file/', '')
key_path = 'physical_db_backups/' + file_name
# Multipart upload function
def multi_part_upload():
config = TransferConfig(multipart_threshold=1024 * 25,
max_concurrency=10,
multipart_chunksize=1024 * 25,
use_threads=True)
try:
s3.meta.client.upload_file(file_to_upload, bucket, key_path, Config=config,
Callback=ProgressPercentage(file_to_upload))
# Custom Slack notification to inform completion
sendslacksuccess("Physical Backup to S3 Complete:n" + file_name)
except botocore.exceptions.ClientError as error:

# Custom Slack notification to inform of failure
sendslackerror("Physical Backup to S3 Failed:n" + file_name + "nError: " + error)

if __name__ == '__main__':
multi_part_upload()

如果脚本不是"；失败；但它并没有上传完整的文件大小，我想在这里捕捉什么异常？我应该在某个地方记录输出吗？

我正在查看Botocore异常文档。我只是不确定用这个try/catch做什么。

供参考，这里是文件大小的差异：

aws s3 ls --summarize --human-readable --recursive s3://my-s3-backup/physical_db_backups/

2022-05-07 14:31:28   50.7 GiB physical_db_backups/xb_202205070101.xb.zst
2022-05-08 12:48:07   50.8 GiB physical_db_backups/xb_202205080101.xb.zst
2022-05-09 01:30:04   34.2 GiB physical_db_backups/xb_202205090101.xb.zst <--- WRONG

Answer 1

好吧，因为我是个白痴，没有意识到文件还没有完成，所以我做了一些更改。

1. 我编辑了cron以便稍后启动。

2. 我已经创建了逻辑来确定备份脚本是否正在运行。

3. 我可能会进行额外的检查以确保文件存在，但目前这是一个经过测试的工作POC。

   from progress import ProgressPercentage  # class file progress.py
   from slack import *  # function file for Slack notifications
   import random
   from time import sleep
   import psutil
   import glob
   import os
   import boto3
   import botocore
   from boto3.s3.transfer import TransferConfig
   import logging
   bucket = "fsn-s3-backup"
   s3 = boto3.resource('s3')
   pattern = "/path/to/backup/file/xb_*"
   files = list(filter(os.path.isfile, glob.glob(pattern)))
   files.sort(key=lambda x: os.path.getmtime(x))
   file_to_upload = files[-1]
   file_name = file_to_upload.replace('/path/to/backup/file/', '')
   key_path = 'physical_db_backups/' + file_name
   logging.basicConfig(filename='/var/log/s3-backup.log', format='%(asctime)s - %(levelname)s - %(message)s', datefmt='%m/%d/%Y %I:%M:%S %p', filemode='a')
   logger = logging.getLogger()
   logger.setLevel(logging.INFO)
   
   def multi_part_upload():
   config = TransferConfig(multipart_threshold=1024 * 25,
   max_concurrency=10,
   multipart_chunksize=1024 * 25,
   use_threads=True)
   try:
   s3.meta.client.upload_file(file_to_upload, bucket, key_path, Config=config,
   Callback=ProgressPercentage(file_to_upload),
   ExtraArgs={'ContentType': 'application/zstd'})
   logger.info("Physical Backup to S3 Complete")
   sendslacksuccess("Physical Backup to S3 Complete:n" + file_name)
   except botocore.exceptions.ClientError as error:
   logger.error("Physical Backup to S3 Failed: " + error)
   sendslackerror("Physical Backup to S3 Failed:n" + file_name + "nError: " + error)
   
   def checkIfProcessRunning(processName):
   for proc in psutil.process_iter():
   cmdline = proc.cmdline()
   if processName in cmdline:
   return True
   return False
   
   if __name__ == '__main__':
   backuprunning = True
   while backuprunning:
   logger.info("Checking if backup shell script is running")
   if checkIfProcessRunning('/path/to/physical_backup.sh'):
   logger.info("Backup shell script still running. Sleeping for 60s")
   sleep(60)
   else:
   backuprunning = False
   logger.info("Beginning multipart upload")
   multi_part_upload()