Merge pull request #6859 from abutcher/bz1536217

Automatic merge from submit-queue.

Bug 1536217: Need to validate etcd serving certs before 3.9 upgrade

2 files changed, 46 insertions, 0 deletions

diff --git a/playbooks/common/openshift-cluster/upgrades/pre/verify_cluster.yml b/playbooks/common/openshift-cluster/upgrades/pre/verify_cluster.yml
index 693ab2d96..5ee8a9d78 100644
--- a/playbooks/common/openshift-cluster/upgrades/pre/verify_cluster.yml
+++ b/playbooks/common/openshift-cluster/upgrades/pre/verify_cluster.yml
@@ -92,3 +92,25 @@
         state: started
         enabled: yes
       with_items: "{{ master_services }}"
+
+# Until openshift-ansible is determining which host is the CA host we
+# must (unfortunately) ensure that the first host in the etcd group is
+# the etcd CA host.
+# https://bugzilla.redhat.com/show_bug.cgi?id=1469358
+- name: Verify we can proceed on first etcd
+  hosts: oo_first_etcd
+  gather_facts: no
+  tasks:
+  - name: Ensure CA exists on first etcd
+    stat:
+      path: /etc/etcd/generated_certs
+    register: __etcd_ca_stat
+
+  - fail:
+      msg: >
+        In order to correct an etcd certificate signing problem
+        upgrading may require re-generating etcd certificates. Please
+        ensure that the /etc/etcd/generated_certs directory exists on
+        the first host defined in your [etcd] group.
+    when:
+    - not __etcd_ca_stat.stat.exists | bool
diff --git a/playbooks/common/openshift-cluster/upgrades/upgrade_control_plane.yml b/playbooks/common/openshift-cluster/upgrades/upgrade_control_plane.yml
index 080372c81..a10fd4bee 100644
--- a/playbooks/common/openshift-cluster/upgrades/upgrade_control_plane.yml
+++ b/playbooks/common/openshift-cluster/upgrades/upgrade_control_plane.yml
@@ -2,6 +2,30 @@
 ###############################################################################
 # Upgrade Masters
 ###############################################################################
+
+# Prior to 3.6, openshift-ansible created etcd serving certificates
+# without a SubjectAlternativeName entry for the system hostname. The
+# SAN list in Go 1.8 is now (correctly) authoritative and since
+# openshift-ansible configures masters to talk to etcd hostnames
+# rather than IP addresses, we must correct etcd certificates.
+#
+# This play examines the etcd serving certificate SANs on each etcd
+# host and records whether or not the system hostname is missing.
+- name: Examine etcd serving certificate SAN
+  hosts: oo_etcd_to_config
+  tasks:
+  - slurp:
+      src: /etc/etcd/server.crt
+    register: etcd_serving_cert
+  - set_fact:
+      __etcd_cert_lacks_hostname: "{{ (openshift.common.hostname not in (etcd_serving_cert.content | b64decode | lib_utils_oo_parse_certificate_san)) | bool }}"
+
+# Redeploy etcd certificates when hostnames were missing from etcd
+# serving certificate SANs.
+- import_playbook: ../../../openshift-etcd/redeploy-certificates.yml
+  when:
+  - true in hostvars | lib_utils_oo_select_keys(groups['oo_etcd_to_config']) | lib_utils_oo_collect('__etcd_cert_lacks_hostname') | default([false])
+
 - name: Backup and upgrade etcd
   import_playbook: ../../../openshift-etcd/private/upgrade_main.yml