From 44fd1fa1fc68738effed7e1719ac714a076a681a Mon Sep 17 00:00:00 2001 From: Johnathan Kupferer Date: Wed, 22 Jan 2025 16:54:10 -0500 Subject: [PATCH] Add retries for ocp4_workload_habana_gaudi_gpu_setup --- .../tasks/habana_gaudi_operator.yml | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/ansible/roles_ocp_workloads/ocp4_workload_habana_gaudi_gpu_setup/tasks/habana_gaudi_operator.yml b/ansible/roles_ocp_workloads/ocp4_workload_habana_gaudi_gpu_setup/tasks/habana_gaudi_operator.yml index b43218afb57..9e5a73a3b15 100644 --- a/ansible/roles_ocp_workloads/ocp4_workload_habana_gaudi_gpu_setup/tasks/habana_gaudi_operator.yml +++ b/ansible/roles_ocp_workloads/ocp4_workload_habana_gaudi_gpu_setup/tasks/habana_gaudi_operator.yml @@ -5,6 +5,9 @@ api_version: v1 kind: Namespace name: "{{ habana_gaudi_operator_namespace }}" + register: r_habana_gpu_operator_namespace + until: r_habana_gpu_operator_namespace is successful + retries: 10 delay: 5 - name: Create Habana Gaudi GPU operatorgroup @@ -12,6 +15,7 @@ state: present definition: "{{ lookup('template', 'habana-gaudi/habana_gaudi_operatorgroup.yaml.j2') | from_yaml }}" register: operatorgroup_result + until: operatorgroup_result is successful retries: 25 delay: 5 @@ -20,6 +24,7 @@ state: present definition: "{{ lookup('template', 'habana-gaudi/habana_gaudi_sub.yaml.j2') | from_yaml }}" register: subscription_result + until: subscription_result is successful retries: 50 delay: 5 @@ -32,4 +37,6 @@ state: present definition: "{{ lookup('template', 'habana-gaudi/habana_gpu_deviceconfig.yaml.j2') | from_yaml }}" register: devconfig_result - delay: 5 \ No newline at end of file + until: devconfig_result is successful + retries: 30 + delay: 5