下载 20 MB 文件后,paramiko 挂在 get 上

问题描述 投票:0回答:5

我需要 python sftp 客户端从 sftp 服务器下载文件。我开始使用Paramiko。 KB 大小的小文件效果很好,但是当我尝试下载 600 MB 的文件时,它会在下载 20 MB 的文件后无限期挂起。无法弄清楚问题是什么。增加窗口大小也没有解决。任何帮助将不胜感激!

host = config.getsafe(section, "host")
username = config.getsafe(section, "username")
port = config.getsafe(section, "port")
remote_dir = config.getsafe(section, "remote_dir")
download_dir = config.getsafe(section, "download_dir")
archive_dir = config.getsafe(section, "archive_dir") if config.has_option(section, "archive_dir") else None
password = config.getsafe(section, "password") if config.has_option(section, "password") else None
file_pattern = config.getsafe(section, "file_pattern") if config.has_option(section, "file_pattern") else "*"
passphrase = config.getsafe(section, "passphrase") if config.has_option(section, "passphrase") else None
gnupg_home = config.getsafe(section, "gnupg_home") if config.has_option(section, "gnupg_home") else None

ssh = paramiko.SSHClient()
ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
ssh.connect(hostname=host, port=int(port), username=username, password=password)

sftp = ssh.open_sftp()
sftp.sshclient = ssh

sftp.get("/SFTP/PL_DEV/test.dat", "C:/import/download/test.dat")
python-3.x ssh paramiko
5个回答
9
投票

我做了两件事来解决类似的问题:

  1. 增加窗口大小你说你也尝试过;对我来说,这有助于将大小从几十 MB 增加到半 GB,但仅此而已

  2. 有效禁用重新加密 – 这可能会产生安全隐患,但帮助我从奇怪的 Windows sftp 服务器获取超过 GB 的文件

    with paramiko.Transport((_SFTP['host'], 22)) as transport:
        # SFTP FIXES
        transport.default_window_size=paramiko.common.MAX_WINDOW_SIZE
        transport.packetizer.REKEY_BYTES = pow(2, 40)  # 1TB max, this is a security degradation!
        transport.packetizer.REKEY_PACKETS = pow(2, 40)  # 1TB max, this is a security degradation!
        # / SFTP FIXES
    
        transport.connect(username=_SFTP['user'], password=_SFTP['password'])
            with paramiko.SFTPClient.from_transport(transport) as sftp:
                listdir = sftp.listdir()
                # ...
                sftp.get(remotepath=filename, localpath=localpath)
    

1
投票

增加default_max_packet_size和default_window_size如下对我有用:

client = paramiko.SSHClient()
client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
client.load_system_host_keys()

client.connect(hostname, username=username, password=password, port=port)
tr = client.get_transport()
tr.default_max_packet_size = 100000000
tr.default_window_size = 100000000
sftp = client.open_sftp()
sftp.get(remote_file, local_filepath)

client.close()

1
投票

使用最新的paramiko 2.4.2,我有类似的问题。就我而言,几天前,我们的供应商将其 SFTP 提供商从

Globalscape
(SSH-2.0-1.82_sshlib Globalscape) 切换到
Cerberus
(SSH-2.0-CerberusFTPServer_10.0)。从那时起,paramiko 就无法下载~450MB 的文件了。

症状如下: 下载速度极慢。下载20~30MB后,总是出错:

Server connection dropped msg.

这是日志(Globalscape)-成功下载:

"paramiko.transport", "DEBUG", "starting thread (client mode): 0x160096d8"
"paramiko.transport", "DEBUG", "Local version/idstring: SSH-2.0-paramiko_2.4.1"
"paramiko.transport", "DEBUG", "Remote version/idstring: SSH-2.0-1.82_sshlib Globalscape"
"paramiko.transport", "INFO", "Connected (version 2.0, client 1.82_sshlib)"
"paramiko.transport", "DEBUG", "kex algos:['diffie-hellman-group14-sha1', 'diffie-hellman-group-exchange-sha1', 'diffie-hellman-group1-sha1'] server key:['ssh-rsa'] client encrypt:['twofish256-cbc', 'twofish-cbc', 'twofish128-cbc', 'blowfish-cbc', '3des-cbc', 'arcfour', 'cast128-cbc', 'aes256-cbc', 'aes128-cbc', 'aes256-ctr', 'aes128-ctr'] server encrypt:['twofish256-cbc', 'twofish-cbc', 'twofish128-cbc', 'blowfish-cbc', '3des-cbc', 'arcfour', 'cast128-cbc', 'aes256-cbc', 'aes128-cbc', 'aes256-ctr', 'aes128-ctr'] client mac:['hmac-sha1', 'hmac-md5', 'hmac-sha1-96', 'hmac-md5-96'] server mac:['hmac-sha1', 'hmac-md5', 'hmac-sha1-96', 'hmac-md5-96'] client compress:['zlib', 'none'] server compress:['zlib', 'none'] client lang:[''] server lang:[''] kex follows?False"
"paramiko.transport", "DEBUG", "HostKey agreed: ssh-rsa"
"paramiko.transport", "DEBUG", "Cipher agreed: aes128-ctr"
"paramiko.transport", "DEBUG", "MAC agreed: hmac-sha1"
"paramiko.transport", "DEBUG", "Compression agreed: none"
"paramiko.transport", "DEBUG", "Got server p (2048 bits)"
"paramiko.transport", "DEBUG", "kex engine KexGex specified hash_algo <built-in function openssl_sha1>"
"paramiko.transport", "DEBUG", "Switch to new keys ..."
"paramiko.transport", "DEBUG", "Attempting public-key auth..."
"paramiko.transport", "DEBUG", "userauth is OK"
"paramiko.transport", "INFO", "Auth banner: b'Welcome to the our Secure FTP Server'"
"paramiko.transport", "INFO", "Authentication (publickey) successful!"
"paramiko.transport", "DEBUG", "[chan 0] Max packet in: 32768 bytes"
"paramiko.transport", "DEBUG", "[chan 0] Max packet out: 35840 bytes"
"paramiko.transport", "DEBUG", "Secsh channel 0 opened."
"paramiko.transport", "DEBUG", "[chan 0] Sesch channel 0 request ok"
"paramiko.transport.sftp", "INFO", "[chan 0] Opened sftp connection (server version 3)"
"paramiko.transport.sftp", "DEBUG", "[chan 0] stat(b'data.csv')"
"paramiko.transport.sftp", "DEBUG", "[chan 0] open(b'data.csv', 'rb')"
"paramiko.transport.sftp", "DEBUG", "[chan 0] open(b'data.csv', 'rb') -> 31"
"paramiko.transport.sftp", "DEBUG", "[chan 0] close(31)"
"paramiko.transport.sftp", "INFO", "[chan 0] sftp session closed."
"paramiko.transport", "DEBUG", "[chan 0] EOF sent (0)"
"paramiko.transport", "DEBUG", "EOF in transport thread"

这是日志(Cerberus)-下载失败:

"paramiko.transport", "DEBUG", "starting thread (client mode): 0x119706d8"
"paramiko.transport", "DEBUG", "Local version/idstring: SSH-2.0-paramiko_2.4.1"
"paramiko.transport", "DEBUG", "Remote version/idstring: SSH-2.0-CerberusFTPServer_10.0"
"paramiko.transport", "INFO", "Connected (version 2.0, client CerberusFTPServer_10.0)"
"paramiko.transport", "DEBUG", "kex algos:['ecdh-sha2-nistp256', 'ecdh-sha2-nistp384', 'ecdh-sha2-nistp521', 'diffie-hellman-group-exchange-sha256', 'diffie-hellman-group-exchange-sha1', 'diffie-hellman-group14-sha1', 'diffie-hellman-group1-sha1'] server key:['ssh-rsa'] client encrypt:['aes128-ctr', 'aes128-cbc', 'aes192-ctr', 'aes192-cbc', 'aes256-ctr', 'aes256-cbc', '3des-cbc'] server encrypt:['aes128-ctr', 'aes128-cbc', 'aes192-ctr', 'aes192-cbc', 'aes256-ctr', 'aes256-cbc', '3des-cbc'] client mac:['hmac-sha1', 'hmac-sha1-96', 'hmac-sha2-256', 'hmac-sha2-256-96', 'hmac-sha2-512', 'hmac-sha2-512-96', 'hmac-ripemd160', '[email protected]', 'hmac-md5'] server mac:['hmac-sha1', 'hmac-sha1-96', 'hmac-sha2-256', 'hmac-sha2-256-96', 'hmac-sha2-512', 'hmac-sha2-512-96', 'hmac-ripemd160', '[email protected]', 'hmac-md5'] client compress:['none'] server compress:['none'] client lang:['en-US'] server lang:['en-US'] kex follows?False"
"paramiko.transport", "DEBUG", "Kex agreed: ecdh-sha2-nistp256"
"paramiko.transport", "DEBUG", "HostKey agreed: ssh-rsa"
"paramiko.transport", "DEBUG", "Cipher agreed: aes128-ctr"
"paramiko.transport", "DEBUG", "MAC agreed: hmac-sha2-256"
"paramiko.transport", "DEBUG", "Compression agreed: none"
"paramiko.transport", "DEBUG", "kex engine KexNistp256 specified hash_algo <built-in function openssl_sha256>"
"paramiko.transport", "DEBUG", "Switch to new keys ..."
"paramiko.transport", "DEBUG", "Attempting public-key auth..."
"paramiko.transport", "DEBUG", "userauth is OK"
"paramiko.transport", "INFO", "Authentication (publickey) successful!"
"paramiko.transport", "DEBUG", "[chan 0] Max packet in: 32768 bytes"
"paramiko.transport", "DEBUG", "[chan 0] Max packet out: 32768 bytes"
"paramiko.transport", "DEBUG", "Secsh channel 0 opened."
"paramiko.transport", "DEBUG", "[chan 0] Sesch channel 0 request ok"
"paramiko.transport.sftp", "INFO", "[chan 0] Opened sftp connection (server version 3)"
"paramiko.transport.sftp", "DEBUG", "[chan 0] stat(b'data.csv')"
"paramiko.transport.sftp", "DEBUG", "[chan 0] open(b'data.csv', 'rb')"
"paramiko.transport.sftp", "DEBUG", "[chan 0] open(b'data.csv', 'rb') -> 7b45394343333830462d383832352d343436342d393831302d4444373838314237303433367d"
"paramiko.transport", "DEBUG", "EOF in transport thread"

添加

transport.default_window_size = paramiko.common.MAX_WINDOW_SIZE

对我有用(至少现在是这样)。不确定如果文件大小从 ~450MB 增加到 >>0.5GB 会发生什么。


0
投票

我已经为这个问题绞尽脑汁有一段时间了,在提出了大约四个不同的建议并将它们混合在一起之后,这是我为我工作的方法:

首先(连接到您的 sftp 并循环浏览符合您请求的文件列表):

def getzipfiles(directory):
    # configuration file collection used to build my 
    # custom classlib.dataconnection json files
    configfilename = [fname for fname in configfiles if 'verifty_get' in fname]
    sftp_get = Configs.get_sftp_settings(configfilename[0])

    print("got here")
    try:
        cnopts = pysftp.CnOpts()
        cnopts.hostkeys = None #debug in dev (set your hostkeys!!!)
        sftpconn_get = pysftp.Connection(sftp_get.hostname,
                                         username=sftp_get.username,
                                         password=sftp_get.password,
                                         cnopts=cnopts)

        filelist = sftpconn_get.listdir()
        sftpconn_get.close()

        for filename in filelist:
            matchval = re.search(r'D*********_(?P<date>\d{8})_(?P<time>(\d{2}-?){3}.\d{1,8}).zip', filename, re.I)
            if matchval:
                getlargezipfiles(directory, filename)

    except:
        e = sys.exc_info()
        sftp_exception = e
        print("SFTP listdir failed, exception: {}".format(e))

第二(传入要保存文件的目录,以及文件名)

def getlargezipfiles(directory, filename):
    configfilename = [fname for fname in configfiles if 'verifty_get' in fname]
    sftp_get = Configs.get_sftp_settings(configfilename[0])

    MAX_RETRIES = 2

    port = 22
    sftp_file = filename
    local_file = "{}{}".format(directory,filename)
    ssh_conn = sftp_client = None
    start_time = time.time()

    for retry in range(MAX_RETRIES):
        try:
            ssh_conn = paramiko.Transport((sftp_get.hostname, port))
            ssh_conn.packetizer.REKEY_BYTES = pow(2, 40)  # 1TB max, this is a security degradation!
            ssh_conn.packetizer.REKEY_PACKETS = pow(2, 40)  # 1TB max, this is a security degradation!
            ssh_conn.default_window_size = paramiko.common.MAX_WINDOW_SIZE
            ssh_conn.connect(username=sftp_get.username, password=sftp_get.password)
            sftp_client = paramiko.SFTPClient.from_transport(ssh_conn)
            filesize = sftp_client.stat(sftp_file).st_size
            sftp_client.get_channel().in_window_size = 2097152
            sftp_client.get_channel().out_window_size = 2097152
            sftp_client.get_channel().in_max_packet_size = 2097152
            sftp_client.get_channel().out_max_packet_size = 2097152

            print("Getting {} size [{}] at {}".format(sftp_file, filesize, datetime.now()))
            sftp_client.get(sftp_file, local_file)
            
            break
        except (EOFError, paramiko.ssh_exception.SSHException, OSError) as x:
            retry += 1
            print("%s %s - > retrying %s..." % (type(x), x, retry))
            time.sleep(abs(retry) * 10)
            # back off in steps of 10, 20.. seconds
        finally:
            if hasattr(sftp_client, "close") and callable(sftp_client.close):
                sftp_client.close()
            if hasattr(ssh_conn, "close") and callable(ssh_conn.close):
                ssh_conn.close()

    print("Loading File %s Took %d seconds " % (sftp_file, time.time() - start_time))

0
投票

非常感谢您的回答。我有这个库挂在我身上,我有点惊讶,因为我只是期望 get() 能够工作,仅仅添加这两行也解决了我的问题:

 try:
        # Create an SSH client instance
        client = paramiko.SSHClient()
        # Set AutoAddPolicy (not recommended for production)
        client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
        client.load_system_host_keys()

        client.connect( hostname=host, port=port, username=username,
                   password= password, look_for_keys= False, compress=True
                 )
        transport = client.get_transport()
        transport.default_window_size = paramiko.common.MAX_WINDOW_SIZE

        sftp_client = client.open_sftp()
        return sftp_client
    except Exception as ex:
        print(f"Error connecting to SFTP server: {ex}")
        return None  
© www.soinside.com 2019 - 2024. All rights reserved.