in cookbooks/aws-parallelcluster-slurm/libraries/emit_chef_error_event.rb [54:82]
def get_error_info(node, failures)
{
"datetime" => DateTime.now,
"version" => 0,
"cluster-name" => node["cluster"]["cluster_name"],
"scheduler" => node["cluster"]["scheduler"],
"node-role" => "ComputeFleet",
"level" => "ERROR",
"instance-id" => node["ec2"]["instance_id"],
"event-type" => "chef-recipe-exception",
"message" => "Chef recipe exception",
"component" => get_component(node.override_runlist),
"compute" => {
"name" => node["cluster"]["slurm_nodename"],
"instance-id" => node["ec2"]["instance_id"],
"instance-type" => node["ec2"]["instance_type"],
"availability-zone" => node["ec2"]["availability_zone"],
"address" => node["ipaddress"],
"hostname" => node["ec2"]["hostname"],
"queue-name" => node["cluster"]["scheduler_queue_name"],
"compute-resource" => node["cluster"]["scheduler_compute_resource_name"],
"node-type" => get_node_type(node["cluster"]["slurm_nodename"]),
},
"detail" => {
"failures" => failures,
},
}
end