Improve periodic sync reliability and make it optional (#8647)

* Improve recordings sync reliability

* Cleanup

* Formatting

* Make logs consistent

* Make syncing optional
This commit is contained in:
Nicolas Mowen
2023-11-18 05:06:00 -07:00
committed by GitHub
parent 9ac40cd953
commit 2da99c2308
5 changed files with 55 additions and 37 deletions

View File

@@ -31,13 +31,12 @@ def remove_empty_directories(directory: str) -> None:
def sync_recordings(limited: bool) -> None:
"""Check the db for stale recordings entries that don't exist in the filesystem."""
def delete_db_entries_without_file(files_on_disk: list[str]) -> bool:
def delete_db_entries_without_file(check_timestamp: float) -> bool:
"""Delete db entries where file was deleted outside of frigate."""
if limited:
recordings = Recordings.select(Recordings.id, Recordings.path).where(
Recordings.start_time
>= (datetime.datetime.now() - datetime.timedelta(hours=36)).timestamp()
Recordings.start_time >= check_timestamp
)
else:
# get all recordings in the db
@@ -50,9 +49,16 @@ def sync_recordings(limited: bool) -> None:
for page in range(num_pages):
for recording in recordings.paginate(page, page_size):
if recording.path not in files_on_disk:
if not os.path.exists(recording.path):
recordings_to_delete.add(recording.id)
if len(recordings_to_delete) == 0:
return True
logger.info(
f"Deleting {len(recordings_to_delete)} recording DB entries with missing files"
)
# convert back to list of dictionaries for insertion
recordings_to_delete = [
{"id": recording_id} for recording_id in recordings_to_delete
@@ -64,10 +70,6 @@ def sync_recordings(limited: bool) -> None:
)
return False
logger.debug(
f"Deleting {len(recordings_to_delete)} recording DB entries with missing files"
)
# create a temporary table for deletion
RecordingsToDelete.create_table(temporary=True)
@@ -95,38 +97,51 @@ def sync_recordings(limited: bool) -> None:
if not Recordings.select().where(Recordings.path == file).exists():
files_to_delete.append(file)
if len(files_to_delete) == 0:
return True
logger.info(
f"Deleting {len(files_to_delete)} recordings files with missing DB entries"
)
if float(len(files_to_delete)) / max(1, len(files_on_disk)) > 0.5:
logger.debug(
f"Deleting {(float(len(files_to_delete)) / len(files_on_disk)):2f}% of recordings DB entries, could be due to configuration error. Aborting..."
)
return
return False
for file in files_to_delete:
os.unlink(file)
return True
logger.debug("Start sync recordings.")
if limited:
# get recording files from last 36 hours
hour_check = f"{RECORD_DIR}/{(datetime.datetime.now().astimezone(datetime.timezone.utc) - datetime.timedelta(hours=36)).strftime('%Y-%m-%d/%H')}"
files_on_disk = {
os.path.join(root, file)
for root, _, files in os.walk(RECORD_DIR)
for file in files
if root > hour_check
}
else:
# get all recordings files on disk and put them in a set
files_on_disk = {
os.path.join(root, file)
for root, _, files in os.walk(RECORD_DIR)
for file in files
}
db_success = delete_db_entries_without_file(files_on_disk)
# start checking on the hour 36 hours ago
check_point = datetime.datetime.now().replace(
minute=0, second=0, microsecond=0
).astimezone(datetime.timezone.utc) - datetime.timedelta(hours=36)
db_success = delete_db_entries_without_file(check_point.timestamp())
# only try to cleanup files if db cleanup was successful
if db_success:
if limited:
# get recording files from last 36 hours
hour_check = f"{RECORD_DIR}/{check_point.strftime('%Y-%m-%d/%H')}"
files_on_disk = {
os.path.join(root, file)
for root, _, files in os.walk(RECORD_DIR)
for file in files
if root > hour_check
}
else:
# get all recordings files on disk and put them in a set
files_on_disk = {
os.path.join(root, file)
for root, _, files in os.walk(RECORD_DIR)
for file in files
}
delete_files_without_db_entry(files_on_disk)
logger.debug("End sync recordings.")