Remove functionality associated with unused historical stats tables

changelog.d/9721.removal

@@ -0,0 +1 @@
+Remove functionality associated with the unused `room_stats_historical` and `user_stats_historical` tables.

docs/room_and_user_statistics.md

@@ -1,9 +1,9 @@
 Room and User Statistics
 ========================
 
-Synapse maintains room and user statistics (as well as a cache of room state),
-in various tables. These can be used for administrative purposes but are also
-used when generating the public room directory.
+Synapse maintains room and user statistics in various tables. These can be used
+for administrative purposes but are also used when generating the public room
+directory.
 
 
 # Synapse Developer Documentation
@@ -15,48 +15,8 @@ used when generating the public room directory.
 * **subject**: Something we are tracking stats about – currently a room or user.
 * **current row**: An entry for a subject in the appropriate current statistics
     table. Each subject can have only one.
-* **historical row**: An entry for a subject in the appropriate historical
-    statistics table. Each subject can have any number of these.
 
 ### Overview
 
-Stats are maintained as time series. There are two kinds of column:
-
-* absolute columns – where the value is correct for the time given by `end_ts`
-    in the stats row. (Imagine a line graph for these values)
-    * They can also be thought of as 'gauges' in Prometheus, if you are familiar.
-* per-slice columns – where the value corresponds to how many of the occurrences
-    occurred within the time slice given by `(end_ts − bucket_size)…end_ts`
-    or `start_ts…end_ts`. (Imagine a histogram for these values)
-
-Stats are maintained in two tables (for each type): current and historical.
-
-Current stats correspond to the present values. Each subject can only have one
-entry.
-
-Historical stats correspond to values in the past. Subjects may have multiple
-entries.
-
-## Concepts around the management of stats
-
-### Current rows
-
-Current rows contain the most up-to-date statistics for a room.
-They only contain absolute columns
-
-### Historical rows
-
-Historical rows can always be considered to be valid for the time slice and
-end time specified.
-
-* historical rows will not exist for every time slice – they will be omitted
-    if there were no changes. In this case, the following assumptions can be
-    made to interpolate/recreate missing rows:
-    - absolute fields have the same values as in the preceding row
-    - per-slice fields are zero (`0`)
-* historical rows will not be retained forever – rows older than a configurable
-    time will be purged.
-
-#### Purge
-
-The purging of historical rows is not yet implemented.
+Stats correspond to the present values. Current rows contain the most up-to-date
+statistics for a room. Each subject can only have one entry.

docs/sample_config.yaml

@@ -2652,11 +2652,6 @@ stats:
   #
   #enabled: false
 
-  # The size of each timeslice in the room_stats_historical and
-  # user_stats_historical tables, as a time period. Defaults to "1d".
-  #
-  #bucket_size: 1h
-
 
 # Server Notices room configuration
 #

synapse/config/stats.py

@@ -38,13 +38,9 @@ class StatsConfig(Config):
 
     def read_config(self, config, **kwargs):
         self.stats_enabled = True
-        self.stats_bucket_size = 86400 * 1000
         stats_config = config.get("stats", None)
         if stats_config:
             self.stats_enabled = stats_config.get("enabled", self.stats_enabled)
-            self.stats_bucket_size = self.parse_duration(
-                stats_config.get("bucket_size", "1d")
-            )
         if not self.stats_enabled:
             logger.warning(ROOM_STATS_DISABLED_WARN)
 
@@ -59,9 +55,4 @@ def generate_config_section(self, config_dir_path, server_name, **kwargs):
           # correctly.
           #
           #enabled: false
-
-          # The size of each timeslice in the room_stats_historical and
-          # user_stats_historical tables, as a time period. Defaults to "1d".
-          #
-          #bucket_size: 1h
         """

synapse/handlers/stats.py

@@ -45,7 +45,6 @@ def __init__(self, hs: "HomeServer"):
         self.clock = hs.get_clock()
         self.notifier = hs.get_notifier()
         self.is_mine_id = hs.is_mine_id
-        self.stats_bucket_size = hs.config.stats_bucket_size
 
         self.stats_enabled = hs.config.stats_enabled
 
@@ -106,20 +105,6 @@ async def _unsafe_process(self) -> None:
                 room_deltas = {}
                 user_deltas = {}
 
-            # Then count deltas for total_events and total_event_bytes.
-            (
-                room_count,
-                user_count,
-            ) = await self.store.get_changes_room_total_events_and_bytes(
-                self.pos, max_pos
-            )
-
-            for room_id, fields in room_count.items():
-                room_deltas.setdefault(room_id, Counter()).update(fields)
-
-            for user_id, fields in user_count.items():
-                user_deltas.setdefault(user_id, Counter()).update(fields)
-
             logger.debug("room_deltas: %s", room_deltas)
             logger.debug("user_deltas: %s", user_deltas)
 
@@ -181,12 +166,10 @@ async def _handle_deltas(
 
             event_content = {}  # type: JsonDict
 
-            sender = None
             if event_id is not None:
                 event = await self.store.get_event(event_id, allow_none=True)
                 if event:
                     event_content = event.content or {}
-                    sender = event.sender
 
             # All the values in this dict are deltas (RELATIVE changes)
             room_stats_delta = room_to_stats_deltas.setdefault(room_id, Counter())
@@ -244,12 +227,6 @@ async def _handle_deltas(
                     room_stats_delta["joined_members"] += 1
                 elif membership == Membership.INVITE:
                     room_stats_delta["invited_members"] += 1
-
-                    if sender and self.is_mine_id(sender):
-                        user_to_stats_deltas.setdefault(sender, Counter())[
-                            "invites_sent"
-                        ] += 1
-
                 elif membership == Membership.LEAVE:
                     room_stats_delta["left_members"] += 1
                 elif membership == Membership.BAN:
@@ -279,10 +256,6 @@ async def _handle_deltas(
                 room_state["is_federatable"] = (
                     event_content.get("m.federate", True) is True
                 )
-                if sender and self.is_mine_id(sender):
-                    user_to_stats_deltas.setdefault(sender, Counter())[
-                        "rooms_created"
-                    ] += 1
             elif typ == EventTypes.JoinRules:
                 room_state["join_rules"] = event_content.get("join_rule")
             elif typ == EventTypes.RoomHistoryVisibility:

synapse/storage/databases/main/purge_events.py

@@ -392,7 +392,6 @@ def _purge_room_txn(self, txn, room_id: str) -> List[int]:
             "room_memberships",
             "room_stats_state",
             "room_stats_current",
-            "room_stats_historical",
             "room_stats_earliest_token",
             "rooms",
             "stream_ordering_to_exterm",