Add experimental configuration option to allow disabling legacy Prometheus metric names. (#13540)

Co-authored-by: David Robertson <davidr@element.io>

3 files changed, 46 insertions, 5 deletions

diff --git a/synapse/app/_base.py b/synapse/app/_base.py

index 923891ae0d..4742435d3b 100644
--- a/synapse/app/_base.py
+++ b/synapse/app/_base.py
@@ -266,15 +266,48 @@ def register_start(
     reactor.callWhenRunning(lambda: defer.ensureDeferred(wrapper()))
 
 
-def listen_metrics(bind_addresses: Iterable[str], port: int) -> None:
+def listen_metrics(
+    bind_addresses: Iterable[str], port: int, enable_legacy_metric_names: bool
+) -> None:
     """
     Start Prometheus metrics server.
     """
-    from synapse.metrics import RegistryProxy, start_http_server
+    from prometheus_client import start_http_server as start_http_server_prometheus
+
+    from synapse.metrics import (
+        RegistryProxy,
+        start_http_server as start_http_server_legacy,
+    )
 
     for host in bind_addresses:
         logger.info("Starting metrics listener on %s:%d", host, port)
-        start_http_server(port, addr=host, registry=RegistryProxy)
+        if enable_legacy_metric_names:
+            start_http_server_legacy(port, addr=host, registry=RegistryProxy)
+        else:
+            _set_prometheus_client_use_created_metrics(False)
+            start_http_server_prometheus(port, addr=host, registry=RegistryProxy)
+
+
+def _set_prometheus_client_use_created_metrics(new_value: bool) -> None:
+    """
+    Sets whether prometheus_client should expose `_created`-suffixed metrics for
+    all gauges, histograms and summaries.
+    There is no programmatic way to disable this without poking at internals;
+    the proper way is to use an environment variable which prometheus_client
+    loads at import time.
+
+    The motivation for disabling these `_created` metrics is that they're
+    a waste of space as they're not useful but they take up space in Prometheus.
+    """
+
+    import prometheus_client.metrics
+
+    if hasattr(prometheus_client.metrics, "_use_created"):
+        prometheus_client.metrics._use_created = new_value
+    else:
+        logger.error(
+            "Can't disable `_created` metrics in prometheus_client (brittle hack broken?)"
+        )
 
 
 def listen_manhole(
diff --git a/synapse/app/generic_worker.py b/synapse/app/generic_worker.py

index 30e21d9707..5e3825fca6 100644
--- a/synapse/app/generic_worker.py
+++ b/synapse/app/generic_worker.py
@@ -412,7 +412,11 @@ class GenericWorkerServer(HomeServer):
                         "enable_metrics is not True!"
                     )
                 else:
-                    _base.listen_metrics(listener.bind_addresses, listener.port)
+                    _base.listen_metrics(
+                        listener.bind_addresses,
+                        listener.port,
+                        enable_legacy_metric_names=self.config.metrics.enable_legacy_metrics,
+                    )
             else:
                 logger.warning("Unsupported listener type: %s", listener.type)
 
diff --git a/synapse/app/homeserver.py b/synapse/app/homeserver.py

index 68993d91a9..e57a926032 100644
--- a/synapse/app/homeserver.py
+++ b/synapse/app/homeserver.py
@@ -307,7 +307,11 @@ class SynapseHomeServer(HomeServer):
                         "enable_metrics is not True!"
                     )
                 else:
-                    _base.listen_metrics(listener.bind_addresses, listener.port)
+                    _base.listen_metrics(
+                        listener.bind_addresses,
+                        listener.port,
+                        enable_legacy_metric_names=self.config.metrics.enable_legacy_metrics,
+                    )
             else:
                 # this shouldn't happen, as the listener type should have been checked
                 # during parsing