orphan disk search update

inc/orphan-disks.py

@@ -3,6 +3,7 @@
 import argparse
 import csv
 import json
+import math
 from pathlib import Path
 import re
 import subprocess
@@ -146,7 +147,7 @@ def scan(root=Path('/etc/pve/nodes'), get=api):
             for volume in disks:
                 result = classify(volume, name, shared, refs, bool(errors))
                 if result:
-                    rows.append(dict(zip(FIELDS, [label, sid, volume['volid'], volume.get('size', 0), *result])))
+                    rows.append(dict(zip(FIELDS, [label, sid, volume['volid'], volume.get('size'), *result])))
     # Detect migrations/config changes during this non-atomic inventory.
     _, after_errors, after = references(root, nodes, guests)
     if after != before or after_errors:
@@ -156,6 +157,19 @@ def scan(root=Path('/etc/pve/nodes'), get=api):
     return rows, warnings, coverage
 
 
+def format_size(size_bytes):
+    try:
+        size = float(size_bytes)
+    except (TypeError, ValueError):
+        return 'Unknown'
+    if not math.isfinite(size) or size < 0:
+        return 'Unknown'
+    for unit in ('B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB'):
+        if size < 1024 or unit == 'PiB':
+            return f'{size:.2f} {unit}'
+        size /= 1024
+
+
 def render(rows, warnings, coverage):
     print('\nCluster orphaned / unused disk report (read-only)')
     print('Coverage: ' + ('INCOMPLETE / NEEDS REVIEW' if warnings else 'all discovered disk storage scanned'))
@@ -169,8 +183,8 @@ def render(rows, warnings, coverage):
         if group != (row['node'], row['storage']):
             group = (row['node'], row['storage'])
             print(f'\n{group[0]} / {group[1]}')
-        size = float(row['size_bytes'] or 0) / (1024 ** 3)
-        print(f"  {row['volume']}  {size:.2f} GiB  {row['status']}\n    {row['detail']}")
+        size = format_size(row['size_bytes'])
+        print(f"  {row['volume']}  Disk size: {size}  {row['status']}\n    {row['detail']}")
     print(f'\n{len(rows)} volume(s) reported.')
     if not rows:
         print('No unreferenced or unused volumes found in the successfully scanned storage.')
@@ -179,10 +193,11 @@ def render(rows, warnings, coverage):
 def export_csv(path, rows, warnings):
     # Exclusive creation avoids overwriting existing files, including symlink targets.
     with open(path, 'x', newline='') as handle:
-        writer = csv.DictWriter(handle, fieldnames=FIELDS + ['coverage_warnings'])
+        writer = csv.DictWriter(handle, fieldnames=FIELDS + ['disk_size', 'coverage_warnings'])
         writer.writeheader()
         for row in rows:
-            writer.writerow(dict(row, coverage_warnings='; '.join(warnings)))
+            writer.writerow(dict(row, disk_size=format_size(row['size_bytes']),
+                                 coverage_warnings='; '.join(warnings)))
         if warnings and not rows:
             writer.writerow({'status': 'Incomplete scan', 'coverage_warnings': '; '.join(warnings)})