From bc371acb3effe1c51b938161e3430c1ca36e476a Mon Sep 17 00:00:00 2001
From: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
Date: Wed, 6 Nov 2024 11:05:44 -0600
Subject: [PATCH] Cleanup batching (#14836)

* Implement batching for event cleanup

* remove import

* add debug logging
---
 frigate/events/cleanup.py | 42 +++++++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/frigate/events/cleanup.py b/frigate/events/cleanup.py
index 7d3e7c4561..8ae38b5340 100644
--- a/frigate/events/cleanup.py
+++ b/frigate/events/cleanup.py
@@ -21,6 +21,9 @@ class EventCleanupType(str, Enum):
     snapshots = "snapshots"
 
 
+CHUNK_SIZE = 50
+
+
 class EventCleanup(threading.Thread):
     def __init__(
         self, config: FrigateConfig, stop_event: MpEvent, db: SqliteVecQueueDatabase
@@ -107,6 +110,7 @@ def expire(self, media_type: EventCleanupType) -> list[str]:
                 .namedtuples()
                 .iterator()
             )
+            logger.debug(f"{len(expired_events)} events can be expired")
             # delete the media from disk
             for expired in expired_events:
                 media_name = f"{expired.camera}-{expired.id}"
@@ -125,13 +129,34 @@ def expire(self, media_type: EventCleanupType) -> list[str]:
                     logger.warning(f"Unable to delete event images: {e}")
 
             # update the clips attribute for the db entry
-            update_query = Event.update(update_params).where(
+            query = Event.select(Event.id).where(
                 Event.camera.not_in(self.camera_keys),
                 Event.start_time < expire_after,
                 Event.label == event.label,
                 Event.retain_indefinitely == False,
             )
-            update_query.execute()
+
+            events_to_update = []
+
+            for batch in query.iterator():
+                events_to_update.extend([event.id for event in batch])
+                if len(events_to_update) >= CHUNK_SIZE:
+                    logger.debug(
+                        f"Updating {update_params} for {len(events_to_update)} events"
+                    )
+                    Event.update(update_params).where(
+                        Event.id << events_to_update
+                    ).execute()
+                    events_to_update = []
+
+            # Update any remaining events
+            if events_to_update:
+                logger.debug(
+                    f"Updating clips/snapshots attribute for {len(events_to_update)} events"
+                )
+                Event.update(update_params).where(
+                    Event.id << events_to_update
+                ).execute()
 
         events_to_update = []
 
@@ -196,7 +221,11 @@ def expire(self, media_type: EventCleanupType) -> list[str]:
                             logger.warning(f"Unable to delete event images: {e}")
 
         # update the clips attribute for the db entry
-        Event.update(update_params).where(Event.id << events_to_update).execute()
+        for i in range(0, len(events_to_update), CHUNK_SIZE):
+            batch = events_to_update[i : i + CHUNK_SIZE]
+            logger.debug(f"Updating {update_params} for {len(batch)} events")
+            Event.update(update_params).where(Event.id << batch).execute()
+
         return events_to_update
 
     def run(self) -> None:
@@ -222,10 +251,11 @@ def run(self) -> None:
                 .iterator()
             )
             events_to_delete = [e.id for e in events]
+            logger.debug(f"Found {len(events_to_delete)} events that can be expired")
             if len(events_to_delete) > 0:
-                chunk_size = 50
-                for i in range(0, len(events_to_delete), chunk_size):
-                    chunk = events_to_delete[i : i + chunk_size]
+                for i in range(0, len(events_to_delete), CHUNK_SIZE):
+                    chunk = events_to_delete[i : i + CHUNK_SIZE]
+                    logger.debug(f"Deleting {len(chunk)} events from the database")
                     Event.delete().where(Event.id << chunk).execute()
 
                     if self.config.semantic_search.enabled: