AWX: Add termination_grace_period_seconds

roles/installer/files/pre-stop/termination-env

@@ -0,0 +1,66 @@
+# file, which when exists, indicates that `master` script has successfully
+# completed pre-stop script execution
+marker_file="${PRE_STOP_MARKER_FILE:-/var/lib/pre-stop/.termination_marker}"
+
+# file which the running `master` script continuously updates (mtime) to
+# indicate it's still running. this file is then read by `watcher`s to
+# understand if they still have to wait for `termination_marker`
+heartbeat_file="${PRE_STOP_HEARTBEAT_FILE:-/var/lib/pre-stop/.heartbeat}"
+
+# file which:
+#   * `watcher`s create when they bail out because they didn't see the
+#   `heartbeat_file` to be updated within `$heartbeat_failed_threshold`;
+#   * `master` creates when its handler command fails;
+# when scripts see such file, they also give up
+bailout_file="${PRE_STOP_BAILOUT_FILE:-/var/lib/pre-stop/.bailout}"
+heartbeat_threshold="${PRE_STOP_HEARTBEAT_THRESHOLD:-60}"
+
+# where the scripts' stdout/stderr are streamed
+stdout="${PRE_STOP_STDOUT:-/proc/1/fd/1}"
+stderr="${PRE_STOP_STDERR:-/proc/1/fd/2}"
+
+# command the `master` script executes, which when successfully finishes,
+# causes the script to create the `marker_file`
+handler="${PRE_STOP_HANDLER:-bash -c \"PYTHONUNBUFFERED=x awx-manage disable_instance --wait --retry=inf\"}"
+
+log_prefix="${PRE_STOP_LOG_PREFIX:-preStop.exec}"
+[[ -n ${PRE_STOP_LOG_ROLE} ]] && log_prefix="${log_prefix}] [$PRE_STOP_LOG_ROLE"
+
+# interval at which `watcher`s check for `marker_file` presence
+recheck_sleep="${PRE_STOP_RECHECK_SLEEP:-1}"
+# interval at which `watcher`s report into $stdout that they are still watching
+report_every="${PRE_STOP_REPORT_EVERY:-30}"
+
+function log {
+  printf "[%s] $1\n" "$log_prefix" "${@:2}"
+}
+
+function parameters_string {
+  for param in "$@"; do
+    printf "%s=\"%s\"\n" "$param" "${!param}"
+  done | paste -s -d ' '
+}
+
+function check_bailout {
+  if [[ -f $bailout_file ]]; then
+    log "\"%s\" file has been detected, accepting bail out signal and failing the hook script" \
+      "$bailout_file"
+    exit 1
+  fi
+}
+
+function check_heartbeat {
+  if [[ -f $heartbeat_file ]]; then
+    delta=$(( $(date +%s) - $(stat -c %Y "$heartbeat_file") ))
+  else
+    delta=$(( $(date +%s) - $1 ))
+  fi
+
+  if [[ $delta -gt $heartbeat_threshold ]]; then
+    log "The heartbeat file hasn't been updated since %ss, which is above the threshold of %ds, assuming the master is not operating and failing the hook script" \
+      $delta
+      $heartbeat_threshold
+    touch "$bailout_file"
+    exit 1
+  fi
+}

roles/installer/files/pre-stop/termination-master

@@ -0,0 +1,50 @@
+#/usr/bin/env bash
+
+PRE_STOP_LOG_ROLE="${PRE_STOP_LOG_ROLE:-master}"
+source $(dirname "$0")/termination-env
+
+{
+
+log "The hook has started: %s" \
+  "$(parameters_string \
+    "marker_file" \
+    "heartbeat_file" \
+    "bailout_file" \
+    "handler" \
+  )"
+
+touch "$heartbeat_file"
+
+set -o pipefail
+eval "$handler" 2>&1 | while IFS= read -r line; do
+  # we check the files here and break early, but overall script termination
+  # happens later - as we need to distinguish between files detection and
+  # command failure, while bash doesn't offer a simple way to do this here
+  # inside the loop (`exit` does not terminate the script)
+  [[ -f $bailout_file ]] && break
+  [[ -f $marker_file ]] && break
+
+  log "[handler] %s" "$line"
+  touch "$heartbeat_file"
+done
+ec=$?
+set +o pipefail
+
+# process various cases in specific order
+check_bailout
+
+if [[ -f $marker_file ]]; then
+  log "Done! The marker file has been detected, assuming some other instance of the script has run to completion"
+  exit 0
+elif [[ $ec -ne 0 ]]; then
+  log "The handler has failed with \"%d\" exit code, failing the hook script too" \
+    $ec
+  # signal others to bail out
+  touch "$bailout_file"
+  exit $ec
+else
+  log "Done! Generating the marker file allowing to proceed to termination"
+  touch "$marker_file"
+fi
+
+} > "$stdout" 2> "$stderr"

roles/installer/files/pre-stop/termination-waiter

@@ -0,0 +1,33 @@
+#/usr/bin/env bash
+
+PRE_STOP_LOG_ROLE="${PRE_STOP_LOG_ROLE:-waiter}"
+source $(dirname "$0")/termination-env
+
+{
+
+log "The hook has started: %s" \
+  "$(parameters_string \
+    "marker_file" \
+    "heartbeat_file" \
+    "bailout_file" \
+    "recheck_sleep" \
+    "report_every" \
+  )"
+
+n=0
+checks_started=$(date +%s)
+
+while ! [[ -f $marker_file ]]; do
+  check_bailout
+  check_heartbeat $checks_started
+
+  if [[ $(($n % $report_every)) -eq 0 ]]; then
+    log "Waiting for the marker file to be accessible..."
+  fi
+  n=$(($n + 1))
+  sleep $recheck_sleep
+done
+
+log "The marker file found, exiting to proceed to termination"
+
+} > "$stdout" 2> "$stderr"

roles/installer/tasks/resources_configuration.yml

@@ -208,6 +208,7 @@
     wait: yes
   loop:
     - 'configmaps/config'
+    - 'configmaps/pre_stop_scripts'
     - 'secrets/app_credentials'
     - 'rbac/service_account'
     - 'storage/persistent'

roles/installer/templates/configmaps/pre_stop_scripts.yaml.j2

@@ -0,0 +1,16 @@
+{% if termination_grace_period_seconds is defined %}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: '{{ ansible_operator_meta.name }}-{{ deployment_type }}-pre-stop-scripts'
+  namespace: '{{ ansible_operator_meta.namespace }}'
+  labels:
+    {{ lookup("template", "../common/templates/labels/common.yaml.j2") | indent(width=4) | trim }}
+data:
+  termination-master: |
+    {{ lookup("file", "files/pre-stop/termination-master") | indent(width=4) | trim }}
+  termination-waiter: |
+    {{ lookup("file", "files/pre-stop/termination-waiter") | indent(width=4) | trim }}
+  termination-env: |
+    {{ lookup("file", "files/pre-stop/termination-env") | indent(width=4) | trim }}
+{% endif %}

roles/installer/templates/deployments/deployment.yaml.j2

@@ -23,6 +23,7 @@ spec:
       annotations:
 {% for template in [
     "configmaps/config",
+    "configmaps/pre_stop_scripts",
     "secrets/app_credentials",
     "storage/persistent",
   ] %}
@@ -139,6 +140,23 @@ spec:
               mountPath: "/var/run/redis"
             - name: "{{ ansible_operator_meta.name }}-redis-data"
               mountPath: "/data"
+{% if termination_grace_period_seconds is defined %}
+            - name: pre-stop-data
+              mountPath: /var/lib/pre-stop
+            - name: pre-stop-scripts
+              mountPath: /var/lib/pre-stop/scripts
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                - bash
+                - -c
+                # redis image doesn't support writing to `/proc/1/fd/*`
+                - >
+                  PRE_STOP_STDOUT=/dev/stdout
+                  PRE_STOP_STDERR=/dev/stderr
+                  /var/lib/pre-stop/scripts/termination-waiter
+{% endif %}
           resources: {{ redis_resource_requirements }}
         - image: '{{ _image }}'
           name: '{{ ansible_operator_meta.name }}-web'
@@ -226,6 +244,18 @@ spec:
 {% endif %}
 {% if web_extra_volume_mounts -%}
             {{ web_extra_volume_mounts | indent(width=12, first=True) }}
+{% endif %}
+{% if termination_grace_period_seconds is defined %}
+            - name: pre-stop-data
+              mountPath: /var/lib/pre-stop
+            - name: pre-stop-scripts
+              mountPath: /var/lib/pre-stop/scripts
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                - bash
+                - /var/lib/pre-stop/scripts/termination-waiter
 {% endif %}
           env:
             - name: MY_POD_NAMESPACE
@@ -308,6 +338,18 @@ spec:
 {% endif %}
 {% if task_extra_volume_mounts -%}
             {{ task_extra_volume_mounts | indent(width=12, first=True) }}
+{% endif %}
+{% if termination_grace_period_seconds is defined %}
+            - name: pre-stop-data
+              mountPath: /var/lib/pre-stop
+            - name: pre-stop-scripts
+              mountPath: /var/lib/pre-stop/scripts
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                - bash
+                - /var/lib/pre-stop/scripts/termination-master
 {% endif %}
           env:
             - name: SUPERVISOR_WEB_CONFIG_PATH
@@ -377,6 +419,18 @@ spec:
               mountPath: "/var/lib/awx/projects"
 {% if ee_extra_volume_mounts -%}
             {{ ee_extra_volume_mounts | indent(width=12, first=True) }}
+{% endif %}
+{% if termination_grace_period_seconds is defined %}
+            - name: pre-stop-data
+              mountPath: /var/lib/pre-stop
+            - name: pre-stop-scripts
+              mountPath: /var/lib/pre-stop/scripts
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                - bash
+                - /var/lib/pre-stop/scripts/termination-waiter
 {% endif %}
           env:
 {% if development_mode | bool %}
@@ -412,6 +466,9 @@ spec:
 {% if security_context_settings|length %}
         {{ security_context_settings | to_nice_yaml | indent(8) }}
 {% endif %}
+{% endif %}
+{% if termination_grace_period_seconds is defined %}
+      terminationGracePeriodSeconds: {{ termination_grace_period_seconds }}
 {% endif %}
       volumes:
 {% if bundle_ca_crt %}
@@ -441,6 +498,14 @@ spec:
             items:
               - key: ldap-ca.crt
                 path: 'ldap-ca.crt'
+{% endif %}
+{% if termination_grace_period_seconds is defined %}
+        - name: pre-stop-data
+          emptyDir: {}
+        - name: pre-stop-scripts
+          configMap:
+            name: '{{ ansible_operator_meta.name }}-{{ deployment_type }}-pre-stop-scripts'
+            defaultMode: 0775
 {% endif %}
         - name: "{{ ansible_operator_meta.name }}-application-credentials"
           secret: