Reorganise request and block metrics

In order to circumvent the number of duplicate foo:count metrics increasing
without bounds, it's time for a rearrangement.

The following are all deprecated, and replaced with synapse_util_metrics_block_count:
  synapse_util_metrics_block_timer:count
  synapse_util_metrics_block_ru_utime:count
  synapse_util_metrics_block_ru_stime:count
  synapse_util_metrics_block_db_txn_count:count
  synapse_util_metrics_block_db_txn_duration:count

The following are all deprecated, and replaced with synapse_http_server_response_count:
   synapse_http_server_requests
   synapse_http_server_response_time:count
   synapse_http_server_response_ru_utime:count
   synapse_http_server_response_ru_stime:count
   synapse_http_server_response_db_txn_count:count
   synapse_http_server_response_db_txn_duration:count

The following are renamed (the old metrics are kept for now, but deprecated):

  synapse_util_metrics_block_timer:total ->
     synapse_util_metrics_block_time_seconds

  synapse_util_metrics_block_ru_utime:total ->
     synapse_util_metrics_block_ru_utime_seconds

  synapse_util_metrics_block_ru_stime:total ->
     synapse_util_metrics_block_ru_stime_seconds

  synapse_util_metrics_block_db_txn_count:total ->
     synapse_util_metrics_block_db_txn_count

  synapse_util_metrics_block_db_txn_duration:total ->
     synapse_util_metrics_block_db_txn_duration_seconds

  synapse_http_server_response_time:total ->
     synapse_http_server_response_time_seconds

  synapse_http_server_response_ru_utime:total ->
     synapse_http_server_response_ru_utime_seconds

  synapse_http_server_response_ru_stime:total ->
     synapse_http_server_response_ru_stime_seconds

   synapse_http_server_response_db_txn_count:total ->
      synapse_http_server_response_db_txn_count

   synapse_http_server_response_db_txn_duration:total
      synapse_http_server_response_db_txn_duration_seconds

2 files changed, 84 insertions, 25 deletions

diff --git a/synapse/http/server.py b/synapse/http/server.py
index 6e8f4c9c5f..269b65ca41 100644
--- a/synapse/http/server.py
+++ b/synapse/http/server.py
@@ -42,34 +42,62 @@ logger = logging.getLogger(__name__)
 
 metrics = synapse.metrics.get_metrics_for(__name__)
 
-incoming_requests_counter = metrics.register_counter(
-    "requests",
+# total number of responses served, split by method/servlet/tag
+response_count = metrics.register_counter(
+    "response_count",
     labels=["method", "servlet", "tag"],
+    alternative_names=(
+        # the following are all deprecated aliases for the same metric
+        metrics.name_prefix + x for x in (
+            "_requests",
+            "_response_time:count",
+            "_response_ru_utime:count",
+            "_response_ru_stime:count",
+            "_response_db_txn_count:count",
+            "_response_db_txn_duration:count",
+        )
+    )
 )
+
 outgoing_responses_counter = metrics.register_counter(
     "responses",
     labels=["method", "code"],
 )
 
-response_timer = metrics.register_distribution(
-    "response_time",
-    labels=["method", "servlet", "tag"]
+response_timer = metrics.register_counter(
+    "response_time_seconds",
+    labels=["method", "servlet", "tag"],
+    alternative_names=(
+        metrics.name_prefix + "_response_time:total",
+    ),
 )
 
-response_ru_utime = metrics.register_distribution(
-    "response_ru_utime", labels=["method", "servlet", "tag"]
+response_ru_utime = metrics.register_counter(
+    "response_ru_utime_seconds", labels=["method", "servlet", "tag"],
+    alternative_names=(
+        metrics.name_prefix + "_response_ru_utime:total",
+    ),
 )
 
-response_ru_stime = metrics.register_distribution(
-    "response_ru_stime", labels=["method", "servlet", "tag"]
+response_ru_stime = metrics.register_counter(
+    "response_ru_stime_seconds", labels=["method", "servlet", "tag"],
+    alternative_names=(
+        metrics.name_prefix + "_response_ru_stime:total",
+    ),
 )
 
-response_db_txn_count = metrics.register_distribution(
-    "response_db_txn_count", labels=["method", "servlet", "tag"]
+response_db_txn_count = metrics.register_counter(
+    "response_db_txn_count", labels=["method", "servlet", "tag"],
+    alternative_names=(
+        metrics.name_prefix + "_response_db_txn_count:total",
+    ),
 )
 
-response_db_txn_duration = metrics.register_distribution(
-    "response_db_txn_duration", labels=["method", "servlet", "tag"]
+response_db_txn_duration = metrics.register_counter(
+    "response_db_txn_duration_seconds", labels=["method", "servlet", "tag"],
+    alternative_names=(
+        metrics.name_prefix + "_response_db_txn_duration:total",
+    ),
 )
 
 
@@ -330,7 +358,7 @@ class RequestMetrics(object):
                 )
                 return
 
-        incoming_requests_counter.inc(request.method, self.name, tag)
+        response_count.inc(request.method, self.name, tag)
 
         response_timer.inc_by(
             clock.time_msec() - self.start, request.method,
diff --git a/synapse/util/metrics.py b/synapse/util/metrics.py
index 4ea930d3e8..8d22ff3068 100644
--- a/synapse/util/metrics.py
+++ b/synapse/util/metrics.py
@@ -27,25 +27,56 @@ logger = logging.getLogger(__name__)
 
 metrics = synapse.metrics.get_metrics_for(__name__)
 
-block_timer = metrics.register_distribution(
-    "block_timer",
-    labels=["block_name"]
+# total number of times we have hit this block
+response_count = metrics.register_counter(
+    "block_count",
+    labels=["block_name"],
+    alternative_names=(
+        # the following are all deprecated aliases for the same metric
+        metrics.name_prefix + x for x in (
+            "_block_timer:count",
+            "_block_ru_utime:count",
+            "_block_ru_stime:count",
+            "_block_db_txn_count:count",
+            "_block_db_txn_duration:count",
+        )
+    )
+)
+
+block_timer = metrics.register_counter(
+    "block_time_seconds",
+    labels=["block_name"],
+    alternative_names=(
+        metrics.name_prefix + "_block_timer:total",
+    ),
 )
 
-block_ru_utime = metrics.register_distribution(
-    "block_ru_utime", labels=["block_name"]
+block_ru_utime = metrics.register_counter(
+    "block_ru_utime_seconds", labels=["block_name"],
+    alternative_names=(
+        metrics.name_prefix + "_block_ru_utime:total",
+    ),
 )
 
-block_ru_stime = metrics.register_distribution(
-    "block_ru_stime", labels=["block_name"]
+block_ru_stime = metrics.register_counter(
+    "block_ru_stime_seconds", labels=["block_name"],
+    alternative_names=(
+        metrics.name_prefix + "_block_ru_stime:total",
+    ),
 )
 
-block_db_txn_count = metrics.register_distribution(
-    "block_db_txn_count", labels=["block_name"]
+block_db_txn_count = metrics.register_counter(
+    "block_db_txn_count", labels=["block_name"],
+    alternative_names=(
+        metrics.name_prefix + "_block_db_txn_count:total",
+    ),
 )
 
-block_db_txn_duration = metrics.register_distribution(
-    "block_db_txn_duration", labels=["block_name"]
+block_db_txn_duration = metrics.register_counter(
+    "block_db_txn_duration_seconds", labels=["block_name"],
+    alternative_names=(
+        metrics.name_prefix + "_block_db_txn_count:total",
+    ),
 )