在磁盘安装完成后的Google Cloud Platform(GCP)中,我无法ssh到我的实例 .
细节:
在Windows 7 PC上通过google cloud sdk shell cmd windows我在 C:\>
运行以下命令:
python "C:\Users\user's name\path\to\py\create_instance_working.py" --name inst-test2 --zone us-central1-a direct-to
pic-1234 cc-test1
运行 create_instance_working.py
,看起来像这样:
import argparse
import os
import time
import googleapiclient.discovery
from six.moves import input
# [START list_instances]
def list_instances(compute, project, zone):
result = compute.instances().list(project=project, zone=zone).execute()
return result['items']
# [END list_instances]
# [START create_instance]
def create_instance(compute, project, zone, name, bucket):
image_response = compute.images().getFromFamily(
project='direct-topic-1234', family='theFam').execute()
source_disk_image = image_response['selfLink']
machine_type = "projects/direct-topic-1234/zones/us-central1-a/machineTypes/n1-standard-4"
startup_script = open(
os.path.join(
os.path.dirname(__file__), 'startup-script_working.sh'), 'r').read()
print(machine_type)
config = {
'name': name,
'machineType': machine_type,
'disks': [
{
'boot': True,
'autoDelete': True,
'initializeParams': {
'sourceImage': source_disk_image,
'diskSizeGb': '15',
}
}, {
"deviceName": "disk-2",
"index": 1,
"interface": "SCSI",
"kind": "compute#attachedDisk",
"mode": "READ_WRITE",
"source": "projects/direct-topic-1234/zones/us-central1-a/disks/disk-2",
"type": "PERSISTENT"
}
],
'networkInterfaces': [{
'network': 'global/networks/default',
'accessConfigs': [
{'type': 'ONE_TO_ONE_NAT', 'name': 'External NAT'}
]
}],
"serviceAccounts": [
{
"email": "123456789-compute@developer.gserviceaccount.com",
"scopes": [
"https://www.googleapis.com/auth/devstorage.read_only",
"https://www.googleapis.com/auth/logging.write",
"https://www.googleapis.com/auth/monitoring.write",
"https://www.googleapis.com/auth/servicecontrol",
"https://www.googleapis.com/auth/service.management.readonly",
"https://www.googleapis.com/auth/trace.append"
]
}
],
'metadata': {
'items': [{
'key': 'startup-script',
'value': startup_script
}, {
'key': 'bucket',
'value': bucket
}]
}
}
return compute.instances().insert(
project=project,
zone=zone,
body=config).execute()
# [END create_instance]
# [START delete_instance]
def delete_instance(compute, project, zone, name):
return compute.instances().delete(
project=project,
zone=zone,
instance=name).execute()
# [END delete_instance]
# [START wait_for_operation]
def wait_for_operation(compute, project, zone, operation):
print('Waiting for operation to finish...')
while True:
result = compute.zoneOperations().get(
project=project,
zone=zone,
operation=operation).execute()
if result['status'] == 'DONE':
print("done.")
if 'error' in result:
raise Exception(result['error'])
return result
time.sleep(1)
# [END wait_for_operation]
# [START run]
def main(project, bucket, zone, instance_name, wait=True):
compute = googleapiclient.discovery.build('compute', 'v1')
print('Creating instance.')
operation = create_instance(compute, project, zone, instance_name, bucket)
wait_for_operation(compute, project, zone, operation['name'])
instances = list_instances(compute, project, zone)
print('Instances in project %s and zone %s:' % (project, zone))
for instance in instances:
print(' - ' + instance['name'])
print("""
Instance created.
It will take a minute or two for the instance to complete work.
Check this URL: http://storage.googleapis.com/{}/output.png
Once the image is uploaded press enter to delete the instance.
""".format(bucket))
# if wait:
# input()
#
# print('Deleting instance.')
#
# operation = delete_instance(compute, project, zone, instance_name)
# wait_for_operation(compute, project, zone, operation['name'])
print('all done with instance.')
if __name__ == '__main__':
print('in here 3')
main('direct-topic-1234', 'cc-test1', 'us-central1-a', 'inst-test1')
print('in here 4')
# [END run]
它调用一个如下所示的启动脚本( startup-script_working.sh
):
sudo mkfs.ext4 -m 0 -F -E lazy_itable_init=0,lazy_journal_init=0,discard /dev/sdb
sudo mount -o discard,defaults /dev/sdb /var
sudo chmod a+w /var
sudo cp /etc/fstab /etc/fstab.backup
echo UUID=`sudo blkid -s UUID -o value /dev/sdb` /var ext4 discard,defaults,nofail 0 2 | sudo tee -a /etc/fstab
两者都改编自:
在GCP控制台中,当我看到实例绿灯时,我立即单击实例 ssh
按钮并成功连接到实例 . 但是,如果我继续打开与实例的新ssh连接,它们都会工作,直到我在 /var
上的挂载完成 . 通过在ssh连接(通常是第一个)中通过以下方式查找它时,我看到挂载是完整的: df -h
. 我可以看到 /dev/sdb 197G 60M 197G 1% /var
. 在尝试失败之前,挂载没有出现 . 但是在它出现后,没有什么可以扼杀它 . 在控制台中尝试了 >_
按钮(shell) gcloud compute ssh [instance name]
. 用 [user name]@[external IP]
试过腻子 .
我已经尝试过等待5分钟ssh到实例(挂载将在那时完成),这也不起作用 .
IMPORTANT: 如果我注释掉所有启动脚本行,我可以无限期地连接,没有SSH问题 . 我尝试过创建一个新磁盘并附加它 .
所以它似乎是导致ssh问题的磁盘装载 .
早期的ssh连接继续运行得很好,即使我不能创建一个新的连接 .
当ssh连接失败时,我在ssh窗口中看到:“Connection Failed
与SSH服务器通信时发生错误 . 检查服务器和网络配置 . “
会有什么想法导致这种情况?
实例是Linux发行版SUSE 12
我的安装说明来自这里:
https://cloud.google.com/compute/docs/disks/add-persistent-disk
如果有一个好方法可以避免有用的情况(请提供),但我真的想知道我做错了什么 .
我是GCP的新手,通常是 Cloud ,python,ssh和Linux . (这个问题中的所有内容都是新的!)
如果我注释掉启动脚本行,按照描述运行所有内容,ssh到保险,手动运行启动脚本命令,我没有错误,需要仍然测试我之后是否创建另一个ssh连接 . 我们这样做并报告回来 .
1 回答
挂载在
/var
上,其中包含与ssh
(以及其他内容)相关的数据,因此可以使/var
的系统看到空白磁盘 . 必须在其他地方保留数据(cp -ar
),将mount挂载到var,然后再移回数据 .我之前的回答是错的 .