Break down monthly active users by appservice_id (#7030)

* Break down monthly active users by appservice_id and emit via prometheus.

Co-authored-by: Brendan Abolivier <babolivier@matrix.org>

2 files changed, 44 insertions, 1 deletions

diff --git a/synapse/app/homeserver.py b/synapse/app/homeserver.py
index c2a334a2b0..e0fdddfdc9 100644
--- a/synapse/app/homeserver.py
+++ b/synapse/app/homeserver.py
@@ -298,6 +298,11 @@ class SynapseHomeServer(HomeServer):
 
 # Gauges to expose monthly active user control metrics
 current_mau_gauge = Gauge("synapse_admin_mau:current", "Current MAU")
+current_mau_by_service_gauge = Gauge(
+    "synapse_admin_mau_current_mau_by_service",
+    "Current MAU by service",
+    ["app_service"],
+)
 max_mau_gauge = Gauge("synapse_admin_mau:max", "MAU Limit")
 registered_reserved_users_mau_gauge = Gauge(
     "synapse_admin_mau:registered_reserved_users",
@@ -585,12 +590,20 @@ def run(hs):
     @defer.inlineCallbacks
     def generate_monthly_active_users():
         current_mau_count = 0
+        current_mau_count_by_service = {}
         reserved_users = ()
         store = hs.get_datastore()
         if hs.config.limit_usage_by_mau or hs.config.mau_stats_only:
             current_mau_count = yield store.get_monthly_active_count()
+            current_mau_count_by_service = (
+                yield store.get_monthly_active_count_by_service()
+            )
             reserved_users = yield store.get_registered_reserved_users()
         current_mau_gauge.set(float(current_mau_count))
+
+        for app_service, count in current_mau_count_by_service.items():
+            current_mau_by_service_gauge.labels(app_service).set(float(count))
+
         registered_reserved_users_mau_gauge.set(float(len(reserved_users)))
         max_mau_gauge.set(float(hs.config.max_mau_value))
 
diff --git a/synapse/storage/data_stores/main/monthly_active_users.py b/synapse/storage/data_stores/main/monthly_active_users.py
index 1507a14e09..925bc5691b 100644
--- a/synapse/storage/data_stores/main/monthly_active_users.py
+++ b/synapse/storage/data_stores/main/monthly_active_users.py
@@ -43,13 +43,40 @@ class MonthlyActiveUsersWorkerStore(SQLBaseStore):
 
         def _count_users(txn):
             sql = "SELECT COALESCE(count(*), 0) FROM monthly_active_users"
-
             txn.execute(sql)
             (count,) = txn.fetchone()
             return count
 
         return self.db.runInteraction("count_users", _count_users)
 
+    @cached(num_args=0)
+    def get_monthly_active_count_by_service(self):
+        """Generates current count of monthly active users broken down by service.
+        A service is typically an appservice but also includes native matrix users.
+        Since the `monthly_active_users` table is populated from the `user_ips` table
+        `config.track_appservice_user_ips` must be set to `true` for this
+        method to return anything other than native matrix users.
+
+        Returns:
+            Deferred[dict]: dict that includes a mapping between app_service_id
+                and the number of occurrences.
+
+        """
+
+        def _count_users_by_service(txn):
+            sql = """
+                SELECT COALESCE(appservice_id, 'native'), COALESCE(count(*), 0)
+                FROM monthly_active_users
+                LEFT JOIN users ON monthly_active_users.user_id=users.name
+                GROUP BY appservice_id;
+            """
+
+            txn.execute(sql)
+            result = txn.fetchall()
+            return dict(result)
+
+        return self.db.runInteraction("count_users_by_service", _count_users_by_service)
+
     @defer.inlineCallbacks
     def get_registered_reserved_users(self):
         """Of the reserved threepids defined in config, which are associated
@@ -292,6 +319,9 @@ class MonthlyActiveUsersStore(MonthlyActiveUsersWorkerStore):
 
         self._invalidate_cache_and_stream(txn, self.get_monthly_active_count, ())
         self._invalidate_cache_and_stream(
+            txn, self.get_monthly_active_count_by_service, ()
+        )
+        self._invalidate_cache_and_stream(
             txn, self.user_last_seen_monthly_active, (user_id,)
         )