-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
make pending timeout customizable #1268
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -249,7 +249,10 @@ def main(argv=None): | |
parser.add_argument('--tensorboard-image', type=str, default='tensorflow/tensorflow:1.12.0') | ||
parser.add_argument('--timeout-hours', type=int, | ||
default=200, | ||
help='Time in hours to wait for the Job submitted by arena to complete') | ||
help='Time in minutes to wait for the Job submitted by arena to complete') | ||
parser.add_argument('--pending-timeout-minutes', type=int, | ||
default=360, | ||
help='Time in hours to wait for the Job submitted by arena from pending to running') | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The var says --pending-timeout-minutes, whereas the descriptions says hours? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Thank you for spotting it! Fix it. |
||
# parser.add_argument('--command', type=str) | ||
parser.add_argument('--output-dir', type=str, default='') | ||
parser.add_argument('--output-data', type=str, default='None') | ||
|
@@ -321,7 +324,8 @@ def main(argv=None): | |
|
||
# wait for job done | ||
# _wait_job_done(fullname, job_type, datetime.timedelta(minutes=timeout_hours)) | ||
_wait_job_running(fullname, job_type, datetime.timedelta(minutes=30)) | ||
pending_timeout_minutes = args.pending_timeout_minutes | ||
_wait_job_running(fullname, job_type, datetime.timedelta(minutes=pending_timeout_minutes)) | ||
|
||
rc = _job_logging(fullname, job_type) | ||
logging.info("rc: {0}".format(rc)) | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -29,7 +29,7 @@ def estimator_op(name, image, command, | |
evaluator=False, evaluator_cpu_limit=0, evaluator_memory_limit=0, | ||
env=[], data=[], sync_source=None, | ||
metrics=['Train-accuracy:PERCENTAGE'], | ||
arena_image='cheyang/arena_launcher:v0.5', | ||
arena_image='cheyang/arena_launcher:v0.6', | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Should these images be moved to a more neutral docker registry name? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I agree with your suggestions. I'd like to move it to a neutral docker registry name. I will keep it in mind and try to find. Thanks. |
||
timeout_hours=240): | ||
|
||
"""This function submits Distributed TFJob in Estimator mode. | ||
|
@@ -62,7 +62,7 @@ def parameter_servers_op(name, image, command, env, data, sync_source, annotatio | |
tensorboard, | ||
worker_port, ps_port, | ||
metrics=['Train-accuracy:PERCENTAGE'], | ||
arena_image='cheyang/arena_launcher:v0.5', | ||
arena_image='cheyang/arena_launcher:v0.6', | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. See above |
||
timeout_hours=240): | ||
|
||
"""This function submits Distributed TFJob in Parameter Servers mode. | ||
|
@@ -97,7 +97,7 @@ def distributed_tf_op(name, image, command, env=[], data=[], sync_source=None, | |
ps_port=22224, | ||
tensorboard=False, | ||
metrics=['Train-accuracy:PERCENTAGE'], | ||
arena_image='cheyang/arena_launcher:v0.5', | ||
arena_image='cheyang/arena_launcher:v0.6', | ||
timeout_hours=240): | ||
"""This function submits Distributed TFJob in Distributed mode. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It should be hours, right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, because training always takes more than 1 hour.