Unsuccessful task submission to an existing ray cluster

Ray Clusters
1

How severe does this issue affect your experience of using Ray?

  • High: It blocks me to complete my task.

I’m using AZURE, I deployed a small test cluster via the example-full.yaml file ；

After deploying the cluster I tried to submit my task using ray submit；

then I encountered a connection timeout error (I deployed the above small ray cluster on a GUI-less ubuntu, from which I submitted the task to the cluster), here are some detailed pictures：

Head Nod 0
Head Nod 0920×324 33.4 KB

(I set the number of cpu’s provided by the head nod to 0 as per the documentation hints and after deployment I got a ray cluster with only one head nod at the moment.)

Ray submit
Ray submit820×126 3.74 KB

(The series of pythons I want to run on the ray cluster are in the /home/chou/123 folder)

Failed Connected
Failed Connected1246×537 133 KB

(I ran a ping test from chou-ubuntu to the public ip of the head nod and found that the connection could not be established)
headnod net
headnod net1637×585 75.8 KB

4

Hello everyone, this problem has been solved, not the reason of the firewall, with ray address designation has a relationship, I can not specify the deep reason, and I will summarize after I get clear and accurate knowledge from ray documents.