Freeze HA scoring and document reported production failover

scripts/plan-promotion-cleanup.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+"""Print (never execute) exact cleanup commands from a supplied CIB snapshot."""
+import argparse
+from pathlib import Path
+import shlex
+import sys
+import xml.etree.ElementTree as ET
+
+
+def plan(path, clone_id, preferred_node):
+    root = ET.parse(path).getroot()
+    clones = [c for c in root.findall('./configuration/resources/clone') if c.get('id') == clone_id]
+    if len(clones) != 1:
+        raise ValueError('Expected exactly one clone with the supplied ID')
+    for meta in clones[0].findall('meta_attributes'):
+        if meta.get('id-ref') or meta.find('rule') is not None:
+            raise ValueError('Clone metadata uses references/rules; inspect manually')
+    matches = []
+    for location in root.findall('./configuration/constraints/rsc_location'):
+        if location.get('rsc') != clone_id:
+            continue
+        for rule in location.findall('rule'):
+            children = list(rule)
+            if (rule.get('role') == 'Promoted' and rule.get('score') == '200'
+                    and len(children) == 1 and children[0].tag == 'expression'
+                    and children[0].get('attribute') == '#uname'
+                    and children[0].get('operation') == 'eq'
+                    and children[0].get('value') == preferred_node):
+                # Preserve unrelated rules if the location has more than one.
+                target = location.get('id') if len(list(location)) == 1 else rule.get('id')
+                if not target:
+                    raise ValueError('Matching constraint/rule lacks an ID')
+                matches.append(target)
+    if len(matches) != 1:
+        raise ValueError('Expected exactly one simple Promoted/200/#uname preference; inspect the full CIB manually')
+    target_roles = [p.get('value') for m in clones[0].findall('meta_attributes')
+                    for p in m.findall('nvpair') if p.get('name') == 'target-role']
+    if target_roles != ['Promoted']:
+        raise ValueError('Expected one direct clone target-role=Promoted; inspect inheritance/rules manually')
+    # target-role=Promoted is an intentional production invariant, not a
+    # temporary node preference. Never remove or rewrite it here.
+    return [shlex.join(['sudo', 'pcs', 'constraint', 'remove', matches[0]])]
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('cib', type=Path)
+    parser.add_argument('--clone', required=True)
+    parser.add_argument('--preferred-node', required=True)
+    parser.add_argument('--lab-validated', action='store_true', help='operator acknowledgement that this candidate passed lab validation')
+    args = parser.parse_args()
+    if not args.lab_validated:
+        parser.error('No rollout commands emitted: lab validation must be completed and acknowledged first')
+    try:
+        commands = plan(args.cib, args.clone, args.preferred_node)
+    except (ValueError, ET.ParseError, OSError) as error:
+        print('No commands emitted:', error, file=sys.stderr)
+        return 1
+    print('# Review against the current CIB before running. No commands have been executed.')
+    print('\n'.join(commands))
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())