Skip to content

dvc: properly collect used cache #504

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

Merged
merged 2 commits into from
Mar 3, 2018
Merged

dvc: properly collect used cache #504

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d80b7da
cloud: makedirs: catch exception instead of checking in advance
efiop Mar 3, 2018
f814269
dvc: properly collect used cache
efiop Mar 3, 2018
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
5 changes: 4 additions & 1 deletion dvc/cloud/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,8 +125,11 @@ def _push(self, path):

def _makedirs(self, fname):
dname = os.path.dirname(fname)
if not os.path.exists(dname):
try:
os.makedirs(dname)
except OSError as e:
if e.errno != os.errno.EEXIST:
raise

def _pull_key(self, key, path):
""" Cloud-specific method of pulling keys """
Expand Down
20 changes: 14 additions & 6 deletions dvc/project.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,14 +159,22 @@ def checkout(self):
for stage in self.stages():
stage.checkout()

def _used_cache(self):
def _used_cache(self, collect_dir=False):
clist = []
for stage in self.stages():
for out in stage.outs:
if not out.use_cache:
continue
if out.cache not in clist:
if not os.path.isdir(out.cache) and \
out.cache not in clist:
clist.append(out.cache)
if os.path.isdir(out.cache):
dir_cache = out.dir_cache()
clist.extend(dir_cache.values())
if collect_dir:
clist.extend([os.path.join(out.cache, f) for f in dir_cache.keys()])
else:
clist.append(out.cache)
return clist

def _remove_cache_file(self, cache):
Expand All @@ -188,22 +196,22 @@ def _remove_cache(self, cache):
os.rmdir(cache)

def gc(self):
clist = self._used_cache()
clist = self._used_cache(collect_dir=False)
for cache in self.cache.all():
if cache in clist:
continue
self._remove_cache(cache)
self.logger.info(u'\'{}\' was removed'.format(self.to_dvc_path(cache)))

def push(self, jobs=1):
self.cloud.push(self._used_cache(), jobs)
self.cloud.push(self._used_cache(collect_dir=True), jobs)

def pull(self, jobs=1):
self.cloud.pull(self._used_cache(), jobs)
self.cloud.pull(self._used_cache(collect_dir=False), jobs)
self.checkout()

def status(self, jobs=1):
return self.cloud.status(self._used_cache(), jobs)
return self.cloud.status(self._used_cache(collect_dir=True), jobs)

def graph(self):
G = nx.DiGraph()
Expand Down
9 changes: 7 additions & 2 deletions tests/test_gc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,8 @@ class TestGC(TestDvc):
def setUp(self):
super(TestGC, self).setUp()

stage = self.dvc.add(self.FOO)
self.dvc.add(self.FOO)
self.dvc.add(self.DATA_DIR)
self.good_cache = self.dvc.cache.all()

self.bad_cache = []
Expand All @@ -26,6 +27,11 @@ def setUp(self):
self.create(path, i)
self.bad_cache.append(path)

path = os.path.join(self.dvc.cache.cache_dir, '45', '6', 'data')
os.mkdir(os.path.dirname(path))
self.create(path, 'md5: "123"')
self.bad_cache.append(path)

def test_api(self):
self.dvc.gc()
self._test_gc()
Expand All @@ -41,4 +47,3 @@ def _test_gc(self):

for c in self.good_cache:
self.assertTrue(os.path.exists(c))
self.assertTrue(os.path.isfile(c))