fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-09-17 13:58:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add a simple annotations cache to the server (#1220)

Browse Source 
Reading the user annotations had a performance problem.
The same file was read over and over.  Now, the last set of user
annotations are cached.
This commit is contained in:
bmccandless
2020-03-12 20:06:44 -07:00
committed by GitHub
parent f28bd52d79
commit bbfd2e5ac5
1 changed files with 22 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
server/common/annotations.py
View File

@@ -92,6 +92,10 @@ class AnnotationsLocalFile(Annotations):
# lock used to protect label file write ops
self.label_lock = threading.RLock()
# cache the most recent annotations
self.last_fname = None
self.last_labels = None
def is_safe_collection_name(self, name):
"""
return true if this is a safe collection name
@@ -114,10 +118,20 @@ class AnnotationsLocalFile(Annotations):
def read_labels(self, data_adaptor):
fname = self._get_filename(data_adaptor)
if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
return pd.read_csv(fname, dtype="category", index_col=0, header=0, comment="#", keep_default_na=False)
else:
return pd.DataFrame()
with self.label_lock:
if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
# returned the cached labels if possible, otherwise read them from the file
if fname == self.last_fname:
return self.last_labels
else:
labels = pd.read_csv(fname, dtype="category",
index_col=0, header=0, comment="#", keep_default_na=False)
# update the cache
self.last_fname = fname
self.last_labels = labels
return labels
else:
return pd.DataFrame()
def write_labels(self, df, data_adaptor):
# update our internal state and save it. Multi-threading often enabled,
@@ -142,6 +156,10 @@ class AnnotationsLocalFile(Annotations):
else:
open(fname, "w").close()
# update the cache
self.last_fname = fname
self.last_labels = df
def _get_userid(self):
if self.CXGUID not in session:
session[self.CXGUID] = uuid4().hex