diff options
Diffstat (limited to 'roles/openshift_master/tasks/main.yml')
| -rw-r--r-- | roles/openshift_master/tasks/main.yml | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml index ce2f96723..1a59717c7 100644 --- a/roles/openshift_master/tasks/main.yml +++ b/roles/openshift_master/tasks/main.yml @@ -168,10 +168,21 @@ - include: set_loopback_context.yml when: openshift.common.version_gte_3_2_or_1_2 +# TODO: Master startup can fail when ec2 transparently reallocates the block +# storage, causing etcd writes to temporarily fail. Retry failures blindly just +# once to allow time for this transient condition to to resolve and for systemd +# to restart the master (which will eventually succeed). +# +# https://github.com/coreos/etcd/issues/3864 +# https://github.com/openshift/origin/issues/6065 +# https://github.com/openshift/origin/issues/6447 - name: Start and enable master service: name={{ openshift.common.service_type }}-master enabled=yes state=started when: not openshift_master_ha | bool register: start_result + until: not start_result | failed + retries: 1 + delay: 60 notify: Verify API Server - name: Check for non-HA master service presence @@ -202,6 +213,9 @@ state: started when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and inventory_hostname == openshift_master_hosts[0] register: start_result + until: not start_result | failed + retries: 1 + delay: 60 - set_fact: master_api_service_status_changed: "{{ start_result | changed }}" @@ -218,6 +232,9 @@ state: started when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and inventory_hostname != openshift_master_hosts[0] register: start_result + until: not start_result | failed + retries: 1 + delay: 60 - set_fact: master_api_service_status_changed: "{{ start_result | changed }}" @@ -251,6 +268,9 @@ state: started when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and inventory_hostname == openshift_master_hosts[0] register: start_result + until: not start_result | failed + retries: 1 + delay: 60 - pause: seconds: 15 @@ -263,6 +283,9 @@ state: started when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and inventory_hostname != openshift_master_hosts[0] register: start_result + until: not start_result | failed + retries: 1 + delay: 60 - set_fact: master_controllers_service_status_changed: "{{ start_result | changed }}" |