Add script for cleaning up the cache

Pungi would by default only ever add files to the cache. That would
eventually result in essentially a mirror of the Koji volume.

This patch adds a helper cleanup script. When called, it goes through
files in the cache and deletes anything that is not hardlinked from
elsewhere and with mtime not updated recently.

Cleaning up files that hardlinked from some compose would not save any
space anyway. The mtime check should account for cases like subpackage
being downloaded but not included in any compose. This would avoid it
from being downloaded over and over again.

When a compose fails or is aborted, there can be a stale lock file left
behind in the cache. This script cleans that up too.

Signed-off-by: Lubomír Sedlář <lsedlar@redhat.com>

pungi/scripts/cache_cleanup.py

@@ -0,0 +1,63 @@
+import argparse
+import os
+import re
+import time
+
+from pungi.util import format_size
+
+
+LOCK_RE = re.compile(r".*\.lock(\|[A-Za-z0-9]+)*$")
+
+
+def should_be_cleaned_up(path, st, threshold):
+    if st.st_nlink == 1 and st.st_mtime < threshold:
+        # No other instances, older than limit
+        return True
+
+    if LOCK_RE.match(path) and st.st_mtime < threshold:
+        # Suspiciously old lock
+        return True
+
+    return False
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("CACHE_DIR")
+    parser.add_argument("-n", "--dry-run", action="store_true")
+    parser.add_argument("--verbose", action="store_true")
+    parser.add_argument(
+        "--max-age",
+        help="how old files should be considered for deletion",
+        default=7,
+        type=int,
+    )
+
+    args = parser.parse_args()
+
+    topdir = os.path.abspath(args.CACHE_DIR)
+    max_age = args.max_age * 24 * 3600
+
+    cleaned_up = 0
+
+    threshold = time.time() - max_age
+    for dirpath, dirnames, filenames in os.walk(topdir):
+        for f in filenames:
+            filepath = os.path.join(dirpath, f)
+            st = os.stat(filepath)
+            if should_be_cleaned_up(filepath, st, threshold):
+                if args.verbose:
+                    print("RM %s" % filepath)
+                cleaned_up += st.st_size
+                if not args.dry_run:
+                    os.remove(filepath)
+        if not dirnames and not filenames:
+            if args.verbose:
+                print("RMDIR %s" % dirpath)
+            if not args.dry_run:
+                os.rmdir(dirpath)
+
+    if args.dry_run:
+        print("Would reclaim %s bytes." % format_size(cleaned_up))
+    else:
+        print("Reclaimed %s bytes." % format_size(cleaned_up))

setup.py

@@ -41,6 +41,7 @@ setup(
             "pungi-gather = pungi.scripts.pungi_gather:cli_main",
             "pungi-config-dump = pungi.scripts.config_dump:cli_main",
             "pungi-config-validate = pungi.scripts.config_validate:cli_main",
+            "pungi-cache-cleanup = pungi.scripts.cache_cleanup:main",
         ]
     },
     scripts=["contrib/yum-dnf-compare/pungi-compare-depsolving"],