upstream/borgbackup
1
0
Fork 0
mirror of https://github.com/borgbackup/borg.git synced 2026-07-06 16:57:30 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

compact: show deduplication and compression factors, fixes #9856

Browse source
This commit is contained in:
Thomas Waldmann 2026-07-05 20:14:51 +02:00
parent 10df5a898b
commit 2b2ceaeb2c
No known key found for this signature in database
GPG key ID: 243ACFA951F78E01
1 changed files with 11 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
src/borg/archiver/compact_cmd.py
View file

@ -114,11 +114,12 @@ class ArchiveGarbageCollector:
def analyze_archives(self) -> tuple[set, int, int, int]:
"""Iterate over all items in all archives, create the dicts id -> size of all used chunks."""
def use_it(id):
def use_it(id, size=0):
entry = self.chunks.get(id)
if entry is not None:
# the chunk is in the repo, mark it used.
self.chunks[id] = entry._replace(flags=entry.flags | ChunkIndex.F_USED)
new_size = size if entry.size == 0 and size != 0 else entry.size
self.chunks[id] = entry._replace(flags=entry.flags | ChunkIndex.F_USED, size=new_size)
else:
# with --stats: we do NOT have this chunk in the repository!
# without --stats: we do not have this chunk or the chunks index is incomplete.
@ -148,7 +149,7 @@ class ArchiveGarbageCollector:
if "chunks" in item:
for id, size in item.chunks:
total_size += size # original, uncompressed file content size
use_it(id)
use_it(id, size)
pi.show(i + 1) # report after each archive, so the last one lands on 100%
pi.finish()
return missing_chunks, total_files, total_size, num_archives
@ -173,17 +174,24 @@ class ArchiveGarbageCollector:
self.compact_packs()
repo_size_after = self.repository_size
deduplicated_size = sum(entry.size for id, entry in self.chunks.iteritems() if entry.flags & ChunkIndex.F_USED)
count = len(self.chunks)
logger.info(f"Overall statistics, considering all {self.archives_count} archives in this repository:")
logger.info(
f"Source data size was {format_file_size(self.total_size, precision=0, iec=self.iec)} "
f"in {self.total_files} files."
)
logger.info(f"Deduplicated size is {format_file_size(deduplicated_size, precision=0, iec=self.iec)}.")
dedup_factor = deduplicated_size / self.total_size if self.total_size else 1.0
logger.info(f"Deduplication factor is {dedup_factor:.2f}.")
if self.stats:
logger.info(
f"Repository size is {format_file_size(repo_size_after, precision=0, iec=self.iec)} "
f"in {count} objects."
)
comp_factor = repo_size_after / deduplicated_size if deduplicated_size else 1.0
logger.info(f"Compression factor is {comp_factor:.2f}.")
if not self.dry_run: # nothing was deleted on a dry run, so before == after
logger.info(
f"Compaction saved "