def assertCanRunJob(self, resource_group, location, cluster_id, job_name,
container_settings, timeout_sec):
create_custom_job(self.client,
resource_group.name,
location,
cluster_id,
job_name,
1,
'echo hello | tee $AZ_BATCHAI_OUTPUT_OUTPUTS/hi.txt',
container=container_settings)
# Verify if the job finishes reasonably fast.
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job_name,
timeout_sec),
models.ExecutionState.succeeded)
# Verify if output files and standard output files are available and contain expected greeting.
assert_job_files_are(self, self.client, resource_group.name, job_name,
'OUTPUTS', {u'hi.txt': u'hello\n'})
assert_job_files_are(self, self.client, resource_group.name, job_name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'hello\n',
u'stderr.txt': ''
})
def test_password_less_ssh_in_container(self, resource_group, location,
cluster):
"""Tests if password-less ssh is configured in containers."""
job = create_custom_job(
self.client,
resource_group.name,
location,
cluster.id,
'job',
2,
'ssh 10.0.0.5 echo done && ssh 10.0.0.5 echo done',
container=models.ContainerSettings(
image_source_registry=models.ImageSourceRegistry(
image='ubuntu')))
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job.name, MINUTE),
models.ExecutionState.succeeded)
job = self.client.jobs.get(resource_group.name, job.name)
assert_job_files_are(
self, self.client, resource_group.name, job.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'done\ndone\n',
u'stderr.txt': re.compile('Permanently added.*')
})
self.client.jobs.delete(resource_group.name, job.name).result()
self.assertRaises(
CloudError,
lambda: self.client.jobs.get(resource_group.name, job.name))
def test_job_preparation_container(self, resource_group, location,
cluster):
"""Tests job preparation execution for a job running in a container."""
# create a job with job preparation which populates input data in $AZ_BATCHAI_INPUT_INPUT/hi.txt
job = create_custom_job(
self.client,
resource_group.name,
location,
cluster.id,
'job',
1,
'cat $AZ_BATCHAI_INPUT_INPUT/hi.txt',
'mkdir -p $AZ_BATCHAI_INPUT_INPUT && echo hello | tee $AZ_BATCHAI_INPUT_INPUT/hi.txt',
container=models.ContainerSettings(
image_source_registry=models.ImageSourceRegistry(
image='ubuntu')))
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job.name, MINUTE),
models.ExecutionState.succeeded)
assert_job_files_are(
self, self.client, resource_group.name, job.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'hello\n',
u'stderr.txt': u'',
u'stdout-job_prep.txt': u'hello\n',
u'stderr-job_prep.txt': u''
})
self.client.jobs.delete(resource_group.name, job.name).result()
self.assertRaises(
CloudError,
lambda: self.client.jobs.get(resource_group.name, job.name))
def test_job_environment_variables_and_secrets(self, resource_group,
location, cluster):
"""Tests if it's possible to mount external file systems for a job."""
job_name = 'job'
job = self.client.jobs.create(
resource_group.name,
job_name,
parameters=models.JobCreateParameters(
location=location,
cluster=models.ResourceId(id=cluster.id),
node_count=1,
std_out_err_path_prefix='$AZ_BATCHAI_MOUNT_ROOT/{0}'.format(
AZURE_FILES_MOUNTING_PATH),
environment_variables=[
models.EnvironmentVariable(name='VARIABLE', value='VALUE')
],
secrets=[
models.EnvironmentVariableWithSecretValue(
name='SECRET_VARIABLE', value='SECRET')
],
# Check that the job preparation has access to env variables and secrets.
job_preparation=models.JobPreparation(
command_line='echo $VARIABLE $SECRET_VARIABLE'),
# Check that the job has access to env variables and secrets.
custom_toolkit_settings=models.CustomToolkitSettings(
command_line='echo $VARIABLE $SECRET_VARIABLE'))).result(
) # type: models.Job
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job.name, MINUTE),
models.ExecutionState.succeeded)
# Check that environment variables are reported by the server.
self.assertEqual(len(job.environment_variables), 1)
self.assertEqual(job.environment_variables[0].name, 'VARIABLE')
self.assertEqual(job.environment_variables[0].value, 'VALUE')
# Check that secrets are reported back by server, but value is not reported.
self.assertEqual(len(job.secrets), 1)
self.assertEqual(job.secrets[0].name, 'SECRET_VARIABLE')
self.assertIsNone(job.secrets[0].value)
# Check that job and job prep had access to the env variables and secrets.
assert_job_files_are(
self, self.client, resource_group.name, job.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'VALUE SECRET\n',
u'stderr.txt': u'',
u'stdout-job_prep.txt': u'VALUE SECRET\n',
u'stderr-job_prep.txt': u''
})
def test_job_creation_and_deletion(self, resource_group, location, cluster,
storage_account, storage_account_key):
"""Tests simple scenario for a job - submit, check results, delete."""
job = create_custom_job(
self.client,
resource_group.name,
location,
cluster.id,
'job',
1,
'echo hi | tee {0}/hi.txt'.format(JOB_OUTPUT_DIRECTORY_PATH_ENV),
container=models.ContainerSettings(
image_source_registry=models.ImageSourceRegistry(
image='ubuntu'))) # type: models.Job
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job.name, MINUTE),
models.ExecutionState.succeeded)
# Check standard job output
assert_job_files_are(self, self.client, resource_group.name, job.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'hi\n',
u'stderr.txt': u''
})
# Check job's output
assert_job_files_are(self, self.client, resource_group.name, job.name,
JOB_OUTPUT_DIRECTORY_ID, {u'hi.txt': u'hi\n'})
# Check that we can access the output files directly in storage using path segment returned by the server
assert_file_in_file_share(
self, storage_account.name, storage_account_key,
job.job_output_directory_path_segment + '/' +
STDOUTERR_FOLDER_NAME, 'stdout.txt', u'hi\n')
self.client.jobs.delete(resource_group.name, job.name).result()
self.assertRaises(
CloudError,
lambda: self.client.jobs.get(resource_group.name, job.name))
def test_file_server(self, resource_group, location, storage_account,
storage_account_key):
"""Tests file server functionality
1. Create file server
2. Create two clusters with this file server
3. Check that the file server is mounted:
a. submit tasks (one from host and another from container) on the first cluster to write data to nfs
b. submit a task on the second cluster to read the data from nfs
"""
server = create_file_server(
self.client, location, resource_group.name,
self.file_server_name) # type: models.FileServer
cluster1 = create_cluster(
self.client,
location,
resource_group.name,
'cluster1',
'STANDARD_D1',
1,
storage_account.name,
storage_account_key,
file_servers=[
models.FileServerReference(
file_server=models.ResourceId(id=server.id),
relative_mount_path='nfs',
mount_options="rw")
])
cluster2 = create_cluster(
self.client,
location,
resource_group.name,
'cluster2',
'STANDARD_D1',
1,
storage_account.name,
storage_account_key,
file_servers=[
models.FileServerReference(
file_server=models.ResourceId(id=server.id),
relative_mount_path='nfs',
mount_options="rw")
])
# Verify the file server is reported.
assert_existing_file_servers_are(self, self.client,
resource_group.name,
[self.file_server_name])
# Verify the file server become available in a reasonable time
self.assertTrue(
wait_for_file_server(self.is_live, self.client,
resource_group.name, self.file_server_name,
_FILE_SERVER_CREATION_TIMEOUT_SEC))
# Verify the remote login information and private ip are reported
server = self.client.file_servers.get(
resource_group.name,
self.file_server_name) # type: models.FileServer
self.assertRegexpMatches(server.mount_settings.file_server_public_ip,
RE_ID_ADDRESS)
self.assertRegexpMatches(server.mount_settings.file_server_internal_ip,
RE_ID_ADDRESS)
# Verify the clusters allocated nodes successfully
self.assertEqual(
wait_for_nodes(self.is_live, self.client, resource_group.name,
'cluster1', 1, NODE_STARTUP_TIMEOUT_SEC), 1)
self.assertEqual(
wait_for_nodes(self.is_live, self.client, resource_group.name,
'cluster2', 1, NODE_STARTUP_TIMEOUT_SEC), 1)
# Execute publishing tasks on the first cluster
job1 = create_custom_job(
self.client, resource_group.name, location, cluster1.id,
'host_publisher', 1,
'echo hi from host > $AZ_BATCHAI_MOUNT_ROOT/nfs/host.txt')
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job1.name, MINUTE),
models.ExecutionState.succeeded)
job2 = create_custom_job(
self.client,
resource_group.name,
location,
cluster1.id,
'container_publisher',
1,
'echo hi from container >> $AZ_BATCHAI_MOUNT_ROOT/nfs/container.txt',
container=models.ContainerSettings(
image_source_registry=models.ImageSourceRegistry(
image="ubuntu")))
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job2.name, MINUTE),
models.ExecutionState.succeeded)
# Execute consumer task on the second cluster
job3 = create_custom_job(
self.client, resource_group.name, location, cluster2.id,
'consumer', 1, 'cat $AZ_BATCHAI_MOUNT_ROOT/nfs/host.txt; '
'cat $AZ_BATCHAI_MOUNT_ROOT/nfs/container.txt')
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job3.name, MINUTE),
models.ExecutionState.succeeded)
# Verify the data
assert_job_files_are(
self, self.client, resource_group.name, job3.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'hi from host\nhi from container\n',
u'stderr.txt': ''
})
# Delete clusters
self.client.clusters.delete(resource_group.name, 'cluster1').result()
self.client.clusters.delete(resource_group.name, 'cluster2').result()
# Test deletion
self.client.file_servers.delete(resource_group.name,
self.file_server_name).result()
assert_existing_file_servers_are(self, self.client,
resource_group.name, [])
def test_job_level_mounting(self, resource_group, location, cluster,
storage_account, storage_account_key):
"""Tests if it's possible to mount external file systems for a job."""
job_name = 'job'
# Create file share and container to mount on the job level
if storage_account.name != FAKE_STORAGE.name:
files = FileService(storage_account.name, storage_account_key)
files.create_share('jobshare', fail_on_exist=False)
blobs = BlockBlobService(storage_account.name, storage_account_key)
blobs.create_container('jobcontainer', fail_on_exist=False)
job = self.client.jobs.create(
resource_group.name,
job_name,
parameters=models.JobCreateParameters(
location=location,
cluster=models.ResourceId(id=cluster.id),
node_count=1,
mount_volumes=models.
MountVolumes(azure_file_shares=[
models.AzureFileShareReference(
account_name=storage_account.name,
azure_file_url='https://{0}.file.core.windows.net/{1}'.
format(storage_account.name, 'jobshare'),
relative_mount_path='job_afs',
credentials=models.AzureStorageCredentialsInfo(
account_key=storage_account_key),
)
],
azure_blob_file_systems=[
models.AzureBlobFileSystemReference(
account_name=storage_account.name,
container_name='jobcontainer',
relative_mount_path='job_bfs',
credentials=models.
AzureStorageCredentialsInfo(
account_key=storage_account_key),
)
]),
# Put standard output on cluster level AFS to check that the job has access to it.
std_out_err_path_prefix='$AZ_BATCHAI_MOUNT_ROOT/{0}'.format(
AZURE_FILES_MOUNTING_PATH),
# Create two output directories on job level AFS and blobfuse.
output_directories=[
models.OutputDirectory(
id='OUTPUT1',
path_prefix='$AZ_BATCHAI_JOB_MOUNT_ROOT/job_afs'),
models.OutputDirectory(
id='OUTPUT2',
path_prefix='$AZ_BATCHAI_JOB_MOUNT_ROOT/job_bfs')
],
# Check that the job preparation has access to job level file systems.
job_preparation=models.JobPreparation(
command_line=
'echo afs > $AZ_BATCHAI_OUTPUT_OUTPUT1/prep_afs.txt; '
'echo bfs > $AZ_BATCHAI_OUTPUT_OUTPUT2/prep_bfs.txt; '
'echo done'),
# Check that the job has access to job
custom_toolkit_settings=models.CustomToolkitSettings(
command_line=
'echo afs > $AZ_BATCHAI_OUTPUT_OUTPUT1/job_afs.txt; '
'echo bfs > $AZ_BATCHAI_OUTPUT_OUTPUT2/job_bfs.txt; '
'mkdir $AZ_BATCHAI_OUTPUT_OUTPUT1/afs; '
'echo afs > $AZ_BATCHAI_OUTPUT_OUTPUT1/afs/job_afs.txt; '
'mkdir $AZ_BATCHAI_OUTPUT_OUTPUT2/bfs; '
'echo bfs > $AZ_BATCHAI_OUTPUT_OUTPUT2/bfs/job_bfs.txt; '
'echo done'))).result()
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, job.name, MINUTE),
models.ExecutionState.succeeded)
job = self.client.jobs.get(resource_group.name, job.name)
# Assert job and job prep standard output is populated on cluster level filesystem
assert_job_files_are(
self, self.client, resource_group.name, job.name,
STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'done\n',
u'stderr.txt': u'',
u'stdout-job_prep.txt': u'done\n',
u'stderr-job_prep.txt': u''
})
# Assert files are generated on job level AFS
assert_job_files_are(self, self.client, resource_group.name, job.name,
'OUTPUT1', {
u'job_afs.txt': u'afs\n',
u'prep_afs.txt': u'afs\n',
u'afs': None
})
# Assert files are generated on job level blobfuse
assert_job_files_are(self, self.client, resource_group.name, job.name,
'OUTPUT2', {
u'job_bfs.txt': u'bfs\n',
u'prep_bfs.txt': u'bfs\n',
u'bfs': None
})
# Assert subfolders are available via API
assert_job_files_in_path_are(self, self.client, resource_group.name,
job.name, 'OUTPUT1', 'afs',
{u'job_afs.txt': u'afs\n'})
assert_job_files_in_path_are(self, self.client, resource_group.name,
job.name, 'OUTPUT2', 'bfs',
{u'job_bfs.txt': u'bfs\n'})
# Assert that we can access the output files created on job level mount volumes directly in storage using path
# segment returned by the server.
if storage_account.name != FAKE_STORAGE.name:
files = FileService(storage_account.name, storage_account_key)
self.assertTrue(
files.exists(
'jobshare', job.job_output_directory_path_segment + '/' +
OUTPUT_DIRECTORIES_FOLDER_NAME, 'job_afs.txt'))
blobs = BlockBlobService(storage_account.name, storage_account_key)
self.assertTrue(
blobs.exists(
'jobcontainer', job.job_output_directory_path_segment +
'/' + OUTPUT_DIRECTORIES_FOLDER_NAME + '/job_bfs.txt'))
# After the job is done the filesystems should be unmounted automatically, check this by submitting a new job.
checker = self.client.jobs.create(
resource_group.name,
'checker',
parameters=models.JobCreateParameters(
location=location,
cluster=models.ResourceId(id=cluster.id),
node_count=1,
std_out_err_path_prefix='$AZ_BATCHAI_MOUNT_ROOT/{0}'.format(
AZURE_FILES_MOUNTING_PATH),
custom_toolkit_settings=models.CustomToolkitSettings(
command_line='echo job; df | grep -E "job_bfs|job_afs"'))
).result()
# Check the job failed because there are not job level mount volumes anymore
self.assertEqual(
wait_for_job_completion(self.is_live, self.client,
resource_group.name, checker.name, MINUTE),
models.ExecutionState.failed)
# Check that the cluster level AFS was still mounted
assert_job_files_are(self, self.client, resource_group.name,
checker.name, STANDARD_OUTPUT_DIRECTORY_ID, {
u'stdout.txt': u'job\n',
u'stderr.txt': u''
})