Merge branch 'develop' of github.com:matrix-org/synapse into t3chguy/default_inviter_display_name_3pid

1 files changed, 113 insertions, 36 deletions

diff --git a/synapse/http/site.py b/synapse/http/site.py
index 4b09d7ee66..5fd30a4c2c 100644
--- a/synapse/http/site.py
+++ b/synapse/http/site.py
@@ -12,27 +12,50 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from synapse.util.logcontext import LoggingContext
-from twisted.web.server import Site, Request
-
 import contextlib
 import logging
-import re
 import time
 
-ACCESS_TOKEN_RE = re.compile(r'(\?.*access(_|%5[Ff])token=)[^&]*(.*)$')
+from twisted.web.server import Request, Site
+
+from synapse.http import redact_uri
+from synapse.http.request_metrics import RequestMetrics
+from synapse.util.logcontext import ContextResourceUsage, LoggingContext
+
+logger = logging.getLogger(__name__)
+
+_next_request_seq = 0
 
 
 class SynapseRequest(Request):
-    def __init__(self, site, *args, **kw):
-        Request.__init__(self, *args, **kw)
+    """Class which encapsulates an HTTP request to synapse.
+
+    All of the requests processed in synapse are of this type.
+
+    It extends twisted's twisted.web.server.Request, and adds:
+     * Unique request ID
+     * Redaction of access_token query-params in __repr__
+     * Logging at start and end
+     * Metrics to record CPU, wallclock and DB time by endpoint.
+
+    It provides a method `processing` which should be called by the Resource
+    which is handling the request, and returns a context manager.
+
+    """
+    def __init__(self, site, channel, *args, **kw):
+        Request.__init__(self, channel, *args, **kw)
         self.site = site
+        self._channel = channel
         self.authenticated_entity = None
         self.start_time = 0
 
+        global _next_request_seq
+        self.request_seq = _next_request_seq
+        _next_request_seq += 1
+
     def __repr__(self):
         # We overwrite this so that we don't log ``access_token``
-        return '<%s at 0x%x method=%s uri=%s clientproto=%s site=%s>' % (
+        return '<%s at 0x%x method=%r uri=%r clientproto=%r site=%r>' % (
             self.__class__.__name__,
             id(self),
             self.method,
@@ -41,16 +64,27 @@ class SynapseRequest(Request):
             self.site.site_tag,
         )
 
+    def get_request_id(self):
+        return "%s-%i" % (self.method, self.request_seq)
+
     def get_redacted_uri(self):
-        return ACCESS_TOKEN_RE.sub(
-            r'\1<redacted>\3',
-            self.uri
-        )
+        return redact_uri(self.uri)
 
     def get_user_agent(self):
-        return self.requestHeaders.getRawHeaders("User-Agent", [None])[-1]
+        return self.requestHeaders.getRawHeaders(b"User-Agent", [None])[-1]
+
+    def render(self, resrc):
+        # override the Server header which is set by twisted
+        self.setHeader("Server", self.site.server_version_string)
+        return Request.render(self, resrc)
+
+    def _started_processing(self, servlet_name):
+        self.start_time = time.time()
+        self.request_metrics = RequestMetrics()
+        self.request_metrics.start(
+            self.start_time, name=servlet_name, method=self.method,
+        )
 
-    def started_processing(self):
         self.site.access_logger.info(
             "%s - %s - Received request: %s %s",
             self.getClientIP(),
@@ -58,44 +92,85 @@ class SynapseRequest(Request):
             self.method,
             self.get_redacted_uri()
         )
-        self.start_time = int(time.time() * 1000)
-
-    def finished_processing(self):
 
+    def _finished_processing(self):
         try:
             context = LoggingContext.current_context()
-            ru_utime, ru_stime = context.get_resource_usage()
-            db_txn_count = context.db_txn_count
-            db_txn_duration = context.db_txn_duration
-        except:
-            ru_utime, ru_stime = (0, 0)
-            db_txn_count, db_txn_duration = (0, 0)
+            usage = context.get_resource_usage()
+        except Exception:
+            usage = ContextResourceUsage()
+
+        end_time = time.time()
+
+        # need to decode as it could be raw utf-8 bytes
+        # from a IDN servname in an auth header
+        authenticated_entity = self.authenticated_entity
+        if authenticated_entity is not None:
+            authenticated_entity = authenticated_entity.decode("utf-8", "replace")
+
+        # ...or could be raw utf-8 bytes in the User-Agent header.
+        # N.B. if you don't do this, the logger explodes cryptically
+        # with maximum recursion trying to log errors about
+        # the charset problem.
+        # c.f. https://github.com/matrix-org/synapse/issues/3471
+        user_agent = self.get_user_agent()
+        if user_agent is not None:
+            user_agent = user_agent.decode("utf-8", "replace")
 
         self.site.access_logger.info(
             "%s - %s - {%s}"
-            " Processed request: %dms (%dms, %dms) (%dms/%d)"
-            " %sB %s \"%s %s %s\" \"%s\"",
+            " Processed request: %.3fsec (%.3fsec, %.3fsec) (%.3fsec/%.3fsec/%d)"
+            " %sB %s \"%s %s %s\" \"%s\" [%d dbevts]",
             self.getClientIP(),
             self.site.site_tag,
-            self.authenticated_entity,
-            int(time.time() * 1000) - self.start_time,
-            int(ru_utime * 1000),
-            int(ru_stime * 1000),
-            int(db_txn_duration * 1000),
-            int(db_txn_count),
+            authenticated_entity,
+            end_time - self.start_time,
+            usage.ru_utime,
+            usage.ru_stime,
+            usage.db_sched_duration_sec,
+            usage.db_txn_duration_sec,
+            int(usage.db_txn_count),
             self.sentLength,
             self.code,
             self.method,
             self.get_redacted_uri(),
             self.clientproto,
-            self.get_user_agent(),
+            user_agent,
+            usage.evt_db_fetch_count,
         )
 
+        try:
+            self.request_metrics.stop(end_time, self)
+        except Exception as e:
+            logger.warn("Failed to stop metrics: %r", e)
+
     @contextlib.contextmanager
-    def processing(self):
-        self.started_processing()
+    def processing(self, servlet_name):
+        """Record the fact that we are processing this request.
+
+        Returns a context manager; the correct way to use this is:
+
+        @defer.inlineCallbacks
+        def handle_request(request):
+            with request.processing("FooServlet"):
+                yield really_handle_the_request()
+
+        This will log the request's arrival. Once the context manager is
+        closed, the completion of the request will be logged, and the various
+        metrics will be updated.
+
+        Args:
+            servlet_name (str): the name of the servlet which will be
+                processing this request. This is used in the metrics.
+
+                It is possible to update this afterwards by updating
+                self.request_metrics.servlet_name.
+        """
+        # TODO: we should probably just move this into render() and finish(),
+        # to save having to call a separate method.
+        self._started_processing(servlet_name)
         yield
-        self.finished_processing()
+        self._finished_processing()
 
 
 class XForwardedForRequest(SynapseRequest):
@@ -133,7 +208,8 @@ class SynapseSite(Site):
     Subclass of a twisted http Site that does access logging with python's
     standard logging
     """
-    def __init__(self, logger_name, site_tag, config, resource, *args, **kwargs):
+    def __init__(self, logger_name, site_tag, config, resource,
+                 server_version_string, *args, **kwargs):
         Site.__init__(self, resource, *args, **kwargs)
 
         self.site_tag = site_tag
@@ -141,6 +217,7 @@ class SynapseSite(Site):
         proxied = config.get("x_forwarded", False)
         self.requestFactory = SynapseRequestFactory(self, proxied)
         self.access_logger = logging.getLogger(logger_name)
+        self.server_version_string = server_version_string
 
     def log(self, request):
         pass