summaryrefslogtreecommitdiffstats
path: root/roles/openshift_master/tasks
diff options
context:
space:
mode:
authorScott Dodson <sdodson@redhat.com>2016-10-10 09:41:19 -0400
committerGitHub <noreply@github.com>2016-10-10 09:41:19 -0400
commita37dc403f19d9b0cd772d4f876732834f8c7fd4b (patch)
tree8ea07e846259b6bf3f7415149942707ee2346b49 /roles/openshift_master/tasks
parente5f2d1d43bc12b9bee353dab6a74ae7b79ec2de0 (diff)
parent1bc6d4390661fe18bebbc020b2c7b25972e80b41 (diff)
downloadopenshift-a37dc403f19d9b0cd772d4f876732834f8c7fd4b.tar.gz
openshift-a37dc403f19d9b0cd772d4f876732834f8c7fd4b.tar.bz2
openshift-a37dc403f19d9b0cd772d4f876732834f8c7fd4b.tar.xz
openshift-a37dc403f19d9b0cd772d4f876732834f8c7fd4b.zip
Merge pull request #2572 from ironcladlou/master-retries
Retry failed master startup once
Diffstat (limited to 'roles/openshift_master/tasks')
-rw-r--r--roles/openshift_master/tasks/main.yml11
1 files changed, 11 insertions, 0 deletions
diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml
index ce2f96723..645871ab4 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