ray exec and ray attach commands (#2560)

ray exec CLUSTER CMD [--screen] [--start] [--stop]
ray attach CLUSTER [--start]

Example:
ray exec sgd.yaml 'source activate tensorflow_p27 && cd ~/ray/python/ray/rllib && ./train.py --run=PPO --env=CartPole-v0' --screen --start --stop

This will in one command create a cluster and run the command on it in a screen session. The screen can later be attached to via ray attach. After the command finishes, the cluster workers will be terminated and the head node stopped.
This commit is contained in:
Eric Liang
2018-08-15 14:31:50 -07:00
committed by GitHub
parent 53f9755594
commit 079c4e482a
10 changed files with 322 additions and 75 deletions
+4 -4
View File
@@ -316,8 +316,8 @@ class Monitor(object):
if ip:
self.load_metrics.update(ip, static_resources, dynamic_resources)
else:
print("Warning: could not find ip for client {}."
.format(client_id))
print("Warning: could not find ip for client {} in {}.".format(
client_id, self.local_scheduler_id_to_ip_map))
def xray_heartbeat_handler(self, unused_channel, data):
"""Handle an xray heartbeat message from Redis."""
@@ -342,8 +342,8 @@ class Monitor(object):
if ip:
self.load_metrics.update(ip, static_resources, dynamic_resources)
else:
print("Warning: could not find ip for client {}."
.format(client_id))
print("Warning: could not find ip for client {} in {}.".format(
client_id, self.local_scheduler_id_to_ip_map))
def plasma_manager_heartbeat_handler(self, unused_channel, data):
"""Handle a plasma manager heartbeat from Redis.