Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

repo-compress: use chunkindex rather than repository.list() #8398

Merged
merged 1 commit into from
Sep 19, 2024
Merged

repo-compress: use chunkindex rather than repository.list() #8398

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 13 additions & 19 deletions src/borg/archiver/repo_compress_cmd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,26 +14,20 @@
logger = create_logger()


def find_chunks(repository, repo_objs, stats, ctype, clevel, olevel):
def find_chunks(repository, repo_objs, cache, stats, ctype, clevel, olevel):
"""find chunks that need processing (usually: recompression)."""
recompress_ids = []
compr_keys = stats["compr_keys"] = set()
compr_wanted = ctype, clevel, olevel
marker = None
while True:
result = repository.list(limit=LIST_SCAN_LIMIT, marker=marker)
if not result:
break
marker = result[-1][0]
chunk_ids = [id for id, _ in result]
for id, chunk_no_data in zip(chunk_ids, repository.get_many(chunk_ids, read_data=False)):
meta = repo_objs.parse_meta(id, chunk_no_data, ro_type=ROBJ_DONTCARE)
compr_found = meta["ctype"], meta["clevel"], meta.get("olevel", -1)
if compr_found != compr_wanted:
recompress_ids.append(id)
compr_keys.add(compr_found)
stats[compr_found] += 1
stats["checked_count"] += 1
for id, _ in cache.chunks.iteritems():
chunk_no_data = repository.get(id, read_data=False)
meta = repo_objs.parse_meta(id, chunk_no_data, ro_type=ROBJ_DONTCARE)
compr_found = meta["ctype"], meta["clevel"], meta.get("olevel", -1)
if compr_found != compr_wanted:
recompress_ids.append(id)
compr_keys.add(compr_found)
stats[compr_found] += 1
stats["checked_count"] += 1
return recompress_ids


Expand Down Expand Up @@ -88,8 +82,8 @@ def format_compression_spec(ctype, clevel, olevel):


class RepoCompressMixIn:
@with_repository(cache=False, manifest=True, compatibility=(Manifest.Operation.CHECK,))
def do_repo_compress(self, args, repository, manifest):
@with_repository(cache=True, manifest=True, compatibility=(Manifest.Operation.CHECK,))
def do_repo_compress(self, args, repository, manifest, cache):
"""Repository (re-)compression"""

def get_csettings(c):
Expand All @@ -110,7 +104,7 @@ def get_csettings(c):

stats_find = defaultdict(int)
stats_process = defaultdict(int)
recompress_ids = find_chunks(repository, repo_objs, stats_find, ctype, clevel, olevel)
recompress_ids = find_chunks(repository, repo_objs, cache, stats_find, ctype, clevel, olevel)
recompress_candidate_count = len(recompress_ids)
chunks_limit = min(1000, max(100, recompress_candidate_count // 1000))

Expand Down
Loading