Estimate repair storage needs live without relying on journal history

operations/gemini_backup_repair.py

@@ -178,6 +178,61 @@ printf '%s\\0' "$LOCKFILE" "$WORKDIR" "$STAGING_ROOT" "$ARCHIVE_DIR" "$MIN_FREE_
     return fields[:6], fields[6:]
 
 
+def snapshot_budget(file_stats, database_sizes):
+    total = 0
+    for size, count in file_stats:
+        if size < 0 or count < 0:
+            raise ValueError('Invalid file statistics')
+        total += size + count * 8192
+    for size in database_sizes:
+        if size < 0:
+            raise ValueError('Invalid database size')
+        total += size * 3 + 67108864
+    return total * 12 // 10 + 67108864
+
+
+def estimate_budget():
+    # Same dry-run exclusions, file metadata, SQL expansion and growth allowance
+    # as installed lib/space.sh. No cleanup, write, service stop or journal needed.
+    script = r'''set -e
+LIB_DIR=/usr/local/lib/app-backup
+source "$1"
+CONFIG_FILE=$2
+load_config
+build_plan
+guard_workspaces
+for i in "${!LABELS[@]}"; do
+  check_source_path "${SOURCES[i]}"
+  exclusions "${LABELS[i]}"
+  stats=$(rsync -aHAX --dry-run --stats --numeric-ids "${EXCLUDES[@]}" -- "${SOURCES[i]}/" "$STAGING_ROOT/.space-estimate/" 8>&- 9>&-)
+  bytes=$(awk '/^Total file size:/ {gsub(/,/, "", $4); print $4}' <<< "$stats")
+  count=$(awk '/^Number of files:/ {gsub(/,/, "", $4); print $4}' <<< "$stats")
+  [[ $bytes =~ ^[0-9]+$ && $count =~ ^[0-9]+$ ]] || exit 1
+  printf 'F %s %s\n' "$bytes" "$count"
+done
+for i in "${!DB_NAMES[@]}"; do
+  secure_file "${DB_CNFS[i]}"
+  size=$("$DB_CLIENT_BIN" --defaults-extra-file="${DB_CNFS[i]}" --database="${DB_NAMES[i]}" --batch --skip-column-names --execute='SELECT COALESCE(SUM(data_length+index_length),0) FROM information_schema.tables WHERE table_schema=DATABASE()')
+  [[ $size =~ ^[0-9]+$ ]] || exit 1
+  printf 'D %s\n' "$size"
+done
+'''
+    result = subprocess.run(['bash', '-c', script, 'estimate', str(COMMON), str(CONFIG)],
+                            check=True, capture_output=True, text=True, pass_fds=(9,), timeout=900)
+    files, databases = [], []
+    for line in result.stdout.splitlines():
+        if re.fullmatch(r'F [0-9]+ [0-9]+', line):
+            _, size, count = line.split()
+            files.append((int(size), int(count)))
+        elif re.fullmatch(r'D [0-9]+', line):
+            databases.append(int(line.split()[1]))
+        else:
+            raise RuntimeError('Unexpected source estimation output')
+    if not files:
+        raise RuntimeError('No source file estimates')
+    return snapshot_budget(files, databases)
+
+
 def free(path):
     v = os.statvfs(path)
     return v.f_bavail * v.f_frsize
@@ -233,15 +288,10 @@ def main():
             private_dir(path)
         if STAGING.stat().st_dev == archives.stat().st_dev or PRESERVED.stat().st_dev == archives.stat().st_dev:
             raise SystemExit('Required separate filesystems are absent')
-        # The unchanged real estimator is run again below before activating config.
-        journal = subprocess.run(['journalctl', '-u', 'app-backup.service', '--since', '2026-10-18',
-                                  '--no-pager', '-o', 'cat'], check=True, capture_output=True, text=True)
-        budgets = re.findall(r'Estimated snapshot budget: ([0-9]+) bytes', journal.stdout)
-        if not budgets:
-            raise SystemExit('No observed snapshot budget; inspect before relocation')
-        budget = int(budgets[-1])
+        budget = estimate_budget()
+        print('Live snapshot budget: ' + str(budget) + ' bytes', flush=True)
         if free(STAGING) < budget + reserve:
-            raise SystemExit('Staging filesystem lacks observed budget plus unchanged reserve')
+            raise SystemExit('Staging filesystem lacks live budget plus unchanged reserve')
         original = CONFIG.read_bytes()
         saved = STATE / 'app-backup.conf.before'
         if not saved.exists():
@@ -265,7 +315,7 @@ def main():
                              budget + reserve + 10 * GIB, reserve + 2 * GIB)
         json_atomic(STATE / 'relocation-plan.json', {
             'staging': str(STAGING), 'active_archives': str(archives),
-            'preservation_root': str(PRESERVED), 'observed_snapshot_budget': budget,
+            'preservation_root': str(PRESERVED), 'live_snapshot_budget': budget,
             'moves': [{'source': str(p), 'allocated_bytes': n} for p, n in moves]})
         for src, amount in moves:
             if free(PRESERVED) < amount + reserve + 2 * GIB: