Skip to content

increase docker-compose timeout to 120 and ping interval to 5 #525

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.

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 7 commits into from
Dec 8, 2018
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
6 changes: 3 additions & 3 deletions src/sagemaker/local/entities.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
logger.setLevel(logging.WARNING)

_UNUSED_ARN = 'local:arn-does-not-matter'
HEALTH_CHECK_TIMEOUT_LIMIT = 30
HEALTH_CHECK_TIMEOUT_LIMIT = 120


class _LocalTrainingJob(object):
Expand Down Expand Up @@ -405,7 +405,7 @@ def _wait_for_serving_container(serving_port):

endpoint_url = 'http://localhost:%s/ping' % serving_port
while True:
i += 1
i += 5
if i >= HEALTH_CHECK_TIMEOUT_LIMIT:
raise RuntimeError('Giving up, endpoint didn\'t launch correctly')

Expand All @@ -416,7 +416,7 @@ def _wait_for_serving_container(serving_port):
else:
return

time.sleep(1)
time.sleep(5)


def _perform_request(endpoint_url, pool_manager=None):
Expand Down
6 changes: 6 additions & 0 deletions src/sagemaker/local/image.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,9 @@

CONTAINER_PREFIX = 'algo'
DOCKER_COMPOSE_FILENAME = 'docker-compose.yaml'
DOCKER_COMPOSE_HTTP_TIMEOUT_ENV = 'COMPOSE_HTTP_TIMEOUT'
DOCKER_COMPOSE_HTTP_TIMEOUT = '120'


# Environment variables to be set during training
REGION_ENV_NAME = 'AWS_REGION'
Expand Down Expand Up @@ -359,6 +362,9 @@ def _generate_compose_file(self, command, additional_volumes=None, additional_en
additional_env_var_list = ['{}={}'.format(k, v) for k, v in additional_env_vars.items()]
environment.extend(additional_env_var_list)

if os.environ.get(DOCKER_COMPOSE_HTTP_TIMEOUT_ENV) is None:
os.environ[DOCKER_COMPOSE_HTTP_TIMEOUT_ENV] = DOCKER_COMPOSE_HTTP_TIMEOUT

if command == 'train':
optml_dirs = {'output', 'output/data', 'input'}

Expand Down