Fix recover-quorum play executed when quorum is already here

kubernetes-sigs · Jul 10, 2020 · 15c3271 · 15c3271
1 parent ef90bb3
commit 15c3271
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 3 deletions.
diff --git a/roles/recover_control_plane/etcd/tasks/main.yml b/roles/recover_control_plane/etcd/tasks/main.yml
@@ -20,9 +20,10 @@
   when:
     - groups['broken_etcd']
 
+# When there is an error, everything is printed in stderr_lines, even "is healthy" messages.
 - name: Set has_quorum fact
   set_fact:
-    has_quorum: "{{ etcd_endpoint_health.stdout_lines | select('match', '.*is healthy.*') | list | length >= etcd_endpoint_health.stderr_lines | select('match', '.*is unhealthy.*') | list | length }}"
+    has_quorum: "{{ etcd_endpoint_health.stderr_lines | select('match', '.*is healthy.*') | list | length >= etcd_endpoint_health.stderr_lines | select('match', '.*is unhealthy.*') | list | length }}"
 
 - include_tasks: recover_lost_quorum.yml
   when:

diff --git a/roles/recover_control_plane/etcd/tasks/recover_lost_quorum.yml b/roles/recover_control_plane/etcd/tasks/recover_lost_quorum.yml
@@ -1,7 +1,11 @@
 ---
 - name: Save etcd snapshot
-  shell: "{{ bin_dir }}/etcdctl --cacert {{ etcd_cert_dir }}/ca.pem --cert {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem --key {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem snapshot save /tmp/snapshot.db"
+  shell: "{{ bin_dir }}/etcdctl snapshot save /tmp/snapshot.db"
   environment:
+    - ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    - ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+    - ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
+    - ETCDCTL_ENDPOINTS: "{{ etcd_access_addresses.split(',') | first }}"
     - ETCDCTL_API: 3
   when: etcd_snapshot is not defined
 
@@ -22,8 +26,12 @@
     state: absent
 
 - name: Restore etcd snapshot
-  shell: "{{ bin_dir }}/etcdctl --cacert {{ etcd_cert_dir }}/ca.pem --cert {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem --key {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem snapshot restore /tmp/snapshot.db --name {{ etcd_member_name }} --initial-cluster {{ etcd_member_name }}={{ etcd_peer_url }} --initial-cluster-token k8s_etcd --initial-advertise-peer-urls {{ etcd_peer_url }} --data-dir {{ etcd_data_dir }}"
+  shell: "{{ bin_dir }}/etcdctl snapshot restore /tmp/snapshot.db --name {{ etcd_member_name }} --initial-cluster {{ etcd_member_name }}={{ etcd_peer_url }} --initial-cluster-token k8s_etcd --initial-advertise-peer-urls {{ etcd_peer_url }} --data-dir {{ etcd_data_dir }}"
   environment:
+    - ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    - ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+    - ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
+    - ETCDCTL_ENDPOINTS: "{{ etcd_access_addresses }}"
     - ETCDCTL_API: 3
 
 - name: Remove etcd snapshot