Merge pull request #3090 from matrix-org/erikj/processed_event_lag

Add metrics for event processing lag

2 files changed, 65 insertions, 2 deletions

diff --git a/synapse/metrics/__init__.py b/synapse/metrics/__init__.py
index 2ed82b04a5..e3b831db67 100644
--- a/synapse/metrics/__init__.py
+++ b/synapse/metrics/__init__.py
@@ -23,7 +23,7 @@ from twisted.internet import reactor
 
 from .metric import (
     CounterMetric, CallbackMetric, DistributionMetric, CacheMetric,
-    MemoryUsageMetric,
+    MemoryUsageMetric, GaugeMetric,
 )
 from .process_collector import register_process_collector
 
@@ -65,6 +65,13 @@ class Metrics(object):
         """
         return self._register(CounterMetric, *args, **kwargs)
 
+    def register_gauge(self, *args, **kwargs):
+        """
+        Returns:
+            GaugeMetric
+        """
+        return self._register(GaugeMetric, *args, **kwargs)
+
     def register_callback(self, *args, **kwargs):
         """
         Returns:
@@ -144,6 +151,32 @@ reactor_metrics = get_metrics_for("python.twisted.reactor")
 tick_time = reactor_metrics.register_distribution("tick_time")
 pending_calls_metric = reactor_metrics.register_distribution("pending_calls")
 
+synapse_metrics = get_metrics_for("synapse")
+
+# Used to track where various components have processed in the event stream,
+# e.g. federation sending, appservice sending, etc.
+event_processing_positions = synapse_metrics.register_gauge(
+    "event_processing_positions", labels=["name"],
+)
+
+# Used to track the current max events stream position
+event_persisted_position = synapse_metrics.register_gauge(
+    "event_persisted_position",
+)
+
+# Used to track the received_ts of the last event processed by various
+# components
+event_processing_last_ts = synapse_metrics.register_gauge(
+    "event_processing_last_ts", labels=["name"],
+)
+
+# Used to track the lag processing events. This is the time difference
+# between the last processed event's received_ts and the time it was
+# finished being processed.
+event_processing_lag = synapse_metrics.register_gauge(
+    "event_processing_lag", labels=["name"],
+)
+
 
 def runUntilCurrentTimer(func):
 
diff --git a/synapse/metrics/metric.py b/synapse/metrics/metric.py
index ff5aa8c0e1..89bd47c3f7 100644
--- a/synapse/metrics/metric.py
+++ b/synapse/metrics/metric.py
@@ -115,7 +115,7 @@ class CounterMetric(BaseMetric):
         # dict[list[str]]: value for each set of label values. the keys are the
         # label values, in the same order as the labels in self.labels.
         #
-        # (if the metric is a scalar, the (single) key is the empty list).
+        # (if the metric is a scalar, the (single) key is the empty tuple).
         self.counts = {}
 
         # Scalar metrics are never empty
@@ -145,6 +145,36 @@ class CounterMetric(BaseMetric):
         )
 
 
+class GaugeMetric(BaseMetric):
+    """A metric that can go up or down
+    """
+
+    def __init__(self, *args, **kwargs):
+        super(GaugeMetric, self).__init__(*args, **kwargs)
+
+        # dict[list[str]]: value for each set of label values. the keys are the
+        # label values, in the same order as the labels in self.labels.
+        #
+        # (if the metric is a scalar, the (single) key is the empty tuple).
+        self.guages = {}
+
+    def set(self, v, *values):
+        if len(values) != self.dimension():
+            raise ValueError(
+                "Expected as many values to inc() as labels (%d)" % (self.dimension())
+            )
+
+        # TODO: should assert that the tag values are all strings
+
+        self.guages[values] = v
+
+    def render(self):
+        return flatten(
+            self._render_for_labels(k, self.guages[k])
+            for k in sorted(self.guages.keys())
+        )
+
+
 class CallbackMetric(BaseMetric):
     """A metric that returns the numeric value returned by a callback whenever
     it is rendered. Typically this is used to implement gauges that yield the