Skip to content

Set parameter process waiting to False #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 20, 2018
Merged

Set parameter process waiting to False #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
19da785
Add wait to run-ps
mvsusp Nov 20, 2018
e546b60
Set wait to False
mvsusp Nov 20, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/sagemaker_tensorflow_container/training.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,8 @@ def _env_vars_with_tf_config(env, ps_task):

def _run_ps(env):
env_vars = _env_vars_with_tf_config(env, ps_task=True)
framework.entry_point.run(env.module_dir, env.user_entry_point, env.to_cmd_args(), env_vars)
framework.entry_point.run(env.module_dir, env.user_entry_point,
env.to_cmd_args(), env_vars, wait=False)


def _run_worker(env):
Expand Down
38 changes: 25 additions & 13 deletions test/unit/test_training.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,8 @@ def test_train_distributed_master(run, distributed_training_env):

run.assert_any_call('s3://my/bucket', 'script_name',
distributed_training_env.to_cmd_args(),
{'TF_CONFIG': ps_tf_config})
{'TF_CONFIG': ps_tf_config},
wait=False)

master_tf_config = '{"cluster": {' \
'"master": ["host1:2222"], ' \
Expand All @@ -107,8 +108,7 @@ def test_train_distributed_master(run, distributed_training_env):

run.assert_called_with('s3://my/bucket', 'script_name',
distributed_training_env.to_cmd_args(),
{
'TF_CONFIG': master_tf_config})
{'TF_CONFIG': master_tf_config})


@patch('subprocess.check_call')
Expand All @@ -131,7 +131,7 @@ def test_train_distributed_worker(run,

run.assert_any_call('s3://my/bucket', 'script_name',
distributed_training_env.to_cmd_args(),
{'TF_CONFIG': ps_tf_config})
{'TF_CONFIG': ps_tf_config}, wait=False)

master_tf_config = '{"cluster": {' \
'"master": ["host1:2222"], ' \
Expand Down Expand Up @@ -176,18 +176,30 @@ def test_run_ps(env_vars_with_tf_config, run, distributed_training_env):

run.assert_called_once_with(distributed_training_env.module_dir,
distributed_training_env.user_entry_point,
distributed_training_env.to_cmd_args(), env_vars_with_tf_config())
distributed_training_env.to_cmd_args(), env_vars_with_tf_config(),
wait=False)


def test_build_tf_config():
assert training._build_tf_config(HOST_LIST, HOST1) == \
{'cluster': CLUSTER_WITH_PS, 'environment': 'cloud', 'task': MASTER_TASK}
assert training._build_tf_config(HOST_LIST, HOST1, ps_task=True) == \
{'cluster': CLUSTER_WITH_PS, 'environment': 'cloud', 'task': PS_TASK_1}
assert training._build_tf_config(HOST_LIST, HOST2) == \
{'cluster': CLUSTER_WITH_PS, 'environment': 'cloud', 'task': WORKER_TASK}
assert training._build_tf_config(HOST_LIST, HOST2, ps_task=True) == \
{'cluster': CLUSTER_WITH_PS, 'environment': 'cloud', 'task': PS_TASK_2}
assert training._build_tf_config(HOST_LIST, HOST1) == {
'cluster': CLUSTER_WITH_PS,
'environment': 'cloud',
'task': MASTER_TASK
}
assert training._build_tf_config(HOST_LIST, HOST1, ps_task=True) == {
'cluster': CLUSTER_WITH_PS,
'environment': 'cloud',
'task': PS_TASK_1
}
assert training._build_tf_config(HOST_LIST, HOST2) == {
'cluster': CLUSTER_WITH_PS,
'environment': 'cloud',
'task': WORKER_TASK
}
assert training._build_tf_config(HOST_LIST, HOST2, ps_task=True) == {
'cluster': CLUSTER_WITH_PS,
'environment': 'cloud',
'task': PS_TASK_2}


def test_build_tf_config_error():
Expand Down