tests/installed: Make reboot task less racy

This took a whole lot of experimentation.  I hit upon the idea
of doing a `systemctl stop sshd` to avoid the situation where we
might ssh back into the system while it's in the process of shutting
down.

Ultimately the other fix is disabling `ControlMaster`; see
for example: https://github.com/ansible/ansible/issues/17935

Closes: #1548
Approved by: cgwalters

diff --git a/tests/installed/playbook-run.sh b/tests/installed/playbook-run.sh
index 3136899fa5d4385b77595f975fa6b1b07aa8c287..37572bd42144bd7b902f68fdb0acd7adc45cbd82 100755 (executable)
--- a/tests/installed/playbook-run.sh
+++ b/tests/installed/playbook-run.sh
@@ -32,4 +32,6 @@ rpm -q standard-test-roles
 
 export ANSIBLE_INVENTORY=${ANSIBLE_INVENTORY:-$(test -e inventory && echo inventory || echo /usr/share/ansible/inventory)}
 ls -al /dev/kvm
+# Sadly having this on makes the reboot playbook break
+export ANSIBLE_SSH_ARGS='-o ControlMaster=no'
 exec ansible-playbook --tags=atomic "$@"

diff --git a/tests/installed/tasks/reboot.yml b/tests/installed/tasks/reboot.yml
index fd07710273a5ed5d0fef2e844ea99fbffcd2b110..a5d0cbecf7d30cb64c6c926c4e45651507daafe1 100644 (file)
--- a/tests/installed/tasks/reboot.yml
+++ b/tests/installed/tasks/reboot.yml
@@ -33,34 +33,35 @@
   command: cat /proc/sys/kernel/random/boot_id
   register: orig_bootid
 
+# Stop sshd (thus preventing new connections) and kill our current user's
+# connection so that we can't race to get back in to the system while it's
+# shutting down
 - name: restart hosts
   when: (not skip_shutdown is defined) or (not skip_shutdown)
-  shell: sleep 3 && shutdown -r now
+  shell: |
+    systemctl stop sshd
+    systemd-run --on-active=5 systemctl reboot
   async: 1
   poll: 0
   ignore_errors: true
 
-# NB: The following tasks use local actions, so we need to explicitly ensure
-# that they don't use sudo, which may require a password, and is not necessary
-# anyway.
+# NB: The wait_for is executed locally and doesn't require privs, so avoid sudo
+- debug:
+    msg: "Waiting for reboot: {{ ansible_date_time.iso8601 }}"
+- wait_for_connection:
+    delay: 5
+    timeout: 120
+    search_regex: "OpenSSH"
+- debug:
+    msg: "SSH port is up {{ ansible_date_time.iso8601 }}"
 
-- name: wait for hosts to come back up
-  local_action:
-    wait_for host={{ real_ansible_host }}
-    port={{ real_ansible_port | default('22') }}
-    state=started
-    delay=30
-    timeout={{ timeout }}
-    search_regex="OpenSSH"
-  become: false
-
-# I'm not sure the retries are even necessary, but I'm keeping them in
-- name: Wait until bootid changes
+- name: Assert that the bootid changed
   command: cat /proc/sys/kernel/random/boot_id
   register: new_bootid
   until: new_bootid.stdout != orig_bootid.stdout
-  retries: 6
-  delay: 10
+- assert:
+    that:
+      - new_bootid.stdout != orig_bootid.stdout
 
 # provide an empty iterator when a list is not provided
 # http://docs.ansible.com/ansible/playbooks_conditionals.html#loops-and-conditionals