Difference between revisions of "Setting up a new node in the cluster"

From Collective Computational Unit
Jump to navigation Jump to search
m
m
Line 1: Line 1:
 
== Preparing the node ==
 
== Preparing the node ==
  
Create new user "kubernetes" with groups docker and sudo.
+
* Create new user "kubernetes" with groups docker and sudo.
 
+
* Follow the steps to install docker, nvidia-docker2 and make nvidia-docker the default runtime on the node.
== Docker ==
+
* Follow instructions [[Initializing_the_Kubernetes_cluster|on this page]] to install Kubernetes and pre-requisites.
 
 
* follow the steps to install docker, nvidia-docker2 and make nvidia-docker the default runtime on the node.
 
 
 
== Kubernetes ==
 
 
 
Follow instructions [[Initializing_the_Kubernetes_cluster|on this page]] to install Kubernetes and pre-requisites.
 
  
 
== Spin up the slave node ==
 
== Spin up the slave node ==

Revision as of 16:29, 17 June 2019

Preparing the node

  • Create new user "kubernetes" with groups docker and sudo.
  • Follow the steps to install docker, nvidia-docker2 and make nvidia-docker the default runtime on the node.
  • Follow instructions on this page to install Kubernetes and pre-requisites.

Spin up the slave node

On the master node:

> cd init
> ./show_join_command.sh

Copy the output into a new file "join_cluster.sh" in the init directory of the slave.

On the slave:

> cd init
> chmod +x join_cluster.sh
> sudo ./join_cluster.sh