Optimize connection pool

Author: MarkusSintonen

httpcore/_async/connection_pool.py

@@ -238,24 +238,27 @@ def _assign_requests_to_connections(self) -> List[AsyncConnectionInterface]:
         those connections to be handled seperately.
         """
         closing_connections = []
+        idling_connections = {c for c in self._connections if c.is_idle()}
 
         # First we handle cleaning up any connections that are closed,
         # have expired their keep-alive, or surplus idle connections.
         for connection in list(self._connections):
             if connection.is_closed():
                 # log: "removing closed connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
             elif connection.has_expired():
                 # log: "closing expired connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
                 closing_connections.append(connection)
             elif (
                 connection.is_idle()
-                and len([connection.is_idle() for connection in self._connections])
-                > self._max_keepalive_connections
+                and len(idling_connections) > self._max_keepalive_connections
             ):
                 # log: "closing idle connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
                 closing_connections.append(connection)
 
         # Assign queued requests to connections.
@@ -267,9 +270,6 @@ def _assign_requests_to_connections(self) -> List[AsyncConnectionInterface]:
                 for connection in self._connections
                 if connection.can_handle_request(origin) and connection.is_available()
             ]
-            idle_connections = [
-                connection for connection in self._connections if connection.is_idle()
-            ]
 
             # There are three cases for how we may be able to handle the request:
             #
@@ -286,15 +286,18 @@ def _assign_requests_to_connections(self) -> List[AsyncConnectionInterface]:
                 connection = self.create_connection(origin)
                 self._connections.append(connection)
                 pool_request.assign_to_connection(connection)
-            elif idle_connections:
-                # log: "closing idle connection"
-                connection = idle_connections[0]
-                self._connections.remove(connection)
-                closing_connections.append(connection)
-                # log: "creating new connection"
-                connection = self.create_connection(origin)
-                self._connections.append(connection)
-                pool_request.assign_to_connection(connection)
+            else:
+                idling_connection = next(
+                    (c for c in self._connections if c.is_idle()), None
+                )
+                if idling_connection is not None:
+                    # log: "closing idle connection"
+                    self._connections.remove(idling_connection)
+                    closing_connections.append(idling_connection)
+                    # log: "creating new connection"
+                    new_connection = self.create_connection(origin)
+                    self._connections.append(new_connection)
+                    pool_request.assign_to_connection(new_connection)
 
         return closing_connections
 

httpcore/_async/http11.py

@@ -1,5 +1,6 @@
 import enum
 import logging
+import random
 import ssl
 import time
 from types import TracebackType
@@ -56,10 +57,12 @@ def __init__(
         origin: Origin,
         stream: AsyncNetworkStream,
         keepalive_expiry: Optional[float] = None,
+        socket_poll_interval_between: Tuple[float, float] = (1, 3),
     ) -> None:
         self._origin = origin
         self._network_stream = stream
-        self._keepalive_expiry: Optional[float] = keepalive_expiry
+        self._keepalive_expiry = keepalive_expiry
+        self._socket_poll_interval_between = socket_poll_interval_between
         self._expire_at: Optional[float] = None
         self._state = HTTPConnectionState.NEW
         self._state_lock = AsyncLock()
@@ -68,6 +71,7 @@ def __init__(
             our_role=h11.CLIENT,
             max_incomplete_event_size=self.MAX_INCOMPLETE_EVENT_SIZE,
         )
+        self._prev_socket_use_time = time.monotonic()
 
     async def handle_async_request(self, request: Request) -> Response:
         if not self.can_handle_request(request.url.origin):
@@ -173,6 +177,7 @@ async def _send_event(
         bytes_to_send = self._h11_state.send(event)
         if bytes_to_send is not None:
             await self._network_stream.write(bytes_to_send, timeout=timeout)
+            self._prev_socket_use_time = time.monotonic()
 
     # Receiving the response...
 
@@ -224,6 +229,7 @@ async def _receive_event(
                 data = await self._network_stream.read(
                     self.READ_NUM_BYTES, timeout=timeout
                 )
+                self._prev_socket_use_time = time.monotonic()
 
                 # If we feed this case through h11 we'll raise an exception like:
                 #
@@ -281,16 +287,27 @@ def is_available(self) -> bool:
     def has_expired(self) -> bool:
         now = time.monotonic()
         keepalive_expired = self._expire_at is not None and now > self._expire_at
+        if keepalive_expired:
+            return True
 
         # If the HTTP connection is idle but the socket is readable, then the
         # only valid state is that the socket is about to return b"", indicating
         # a server-initiated disconnect.
-        server_disconnected = (
-            self._state == HTTPConnectionState.IDLE
-            and self._network_stream.get_extra_info("is_readable")
-        )
+        # Checking the readable status is relatively expensive so check it at a lower frequency.
+        if (now - self._prev_socket_use_time) > self._socket_poll_interval():
+            self._prev_socket_use_time = now
+            server_disconnected = (
+                self._state == HTTPConnectionState.IDLE
+                and self._network_stream.get_extra_info("is_readable")
+            )
+            return server_disconnected
+        else:
+            return False
 
-        return keepalive_expired or server_disconnected
+    def _socket_poll_interval(self) -> float:
+        # Randomize to avoid polling for all the connections at once
+        low, high = self._socket_poll_interval_between
+        return random.uniform(low, high)
 
     def is_idle(self) -> bool:
         return self._state == HTTPConnectionState.IDLE

httpcore/_sync/connection_pool.py

@@ -238,24 +238,27 @@ def _assign_requests_to_connections(self) -> List[ConnectionInterface]:
         those connections to be handled seperately.
         """
         closing_connections = []
+        idling_connections = {c for c in self._connections if c.is_idle()}
 
         # First we handle cleaning up any connections that are closed,
         # have expired their keep-alive, or surplus idle connections.
         for connection in list(self._connections):
             if connection.is_closed():
                 # log: "removing closed connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
             elif connection.has_expired():
                 # log: "closing expired connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
                 closing_connections.append(connection)
             elif (
                 connection.is_idle()
-                and len([connection.is_idle() for connection in self._connections])
-                > self._max_keepalive_connections
+                and len(idling_connections) > self._max_keepalive_connections
             ):
                 # log: "closing idle connection"
                 self._connections.remove(connection)
+                idling_connections.discard(connection)
                 closing_connections.append(connection)
 
         # Assign queued requests to connections.
@@ -267,9 +270,6 @@ def _assign_requests_to_connections(self) -> List[ConnectionInterface]:
                 for connection in self._connections
                 if connection.can_handle_request(origin) and connection.is_available()
             ]
-            idle_connections = [
-                connection for connection in self._connections if connection.is_idle()
-            ]
 
             # There are three cases for how we may be able to handle the request:
             #
@@ -286,15 +286,18 @@ def _assign_requests_to_connections(self) -> List[ConnectionInterface]:
                 connection = self.create_connection(origin)
                 self._connections.append(connection)
                 pool_request.assign_to_connection(connection)
-            elif idle_connections:
-                # log: "closing idle connection"
-                connection = idle_connections[0]
-                self._connections.remove(connection)
-                closing_connections.append(connection)
-                # log: "creating new connection"
-                connection = self.create_connection(origin)
-                self._connections.append(connection)
-                pool_request.assign_to_connection(connection)
+            else:
+                idling_connection = next(
+                    (c for c in self._connections if c.is_idle()), None
+                )
+                if idling_connection is not None:
+                    # log: "closing idle connection"
+                    self._connections.remove(idling_connection)
+                    closing_connections.append(idling_connection)
+                    # log: "creating new connection"
+                    new_connection = self.create_connection(origin)
+                    self._connections.append(new_connection)
+                    pool_request.assign_to_connection(new_connection)
 
         return closing_connections
 

httpcore/_sync/http11.py

@@ -1,5 +1,6 @@
 import enum
 import logging
+import random
 import ssl
 import time
 from types import TracebackType
@@ -56,10 +57,12 @@ def __init__(
         origin: Origin,
         stream: NetworkStream,
         keepalive_expiry: Optional[float] = None,
+        socket_poll_interval_between: Tuple[float, float] = (1, 3),
     ) -> None:
         self._origin = origin
         self._network_stream = stream
-        self._keepalive_expiry: Optional[float] = keepalive_expiry
+        self._keepalive_expiry = keepalive_expiry
+        self._socket_poll_interval_between = socket_poll_interval_between
         self._expire_at: Optional[float] = None
         self._state = HTTPConnectionState.NEW
         self._state_lock = Lock()
@@ -68,6 +71,7 @@ def __init__(
             our_role=h11.CLIENT,
             max_incomplete_event_size=self.MAX_INCOMPLETE_EVENT_SIZE,
         )
+        self._prev_socket_use_time = time.monotonic()
 
     def handle_request(self, request: Request) -> Response:
         if not self.can_handle_request(request.url.origin):
@@ -173,6 +177,7 @@ def _send_event(
         bytes_to_send = self._h11_state.send(event)
         if bytes_to_send is not None:
             self._network_stream.write(bytes_to_send, timeout=timeout)
+            self._prev_socket_use_time = time.monotonic()
 
     # Receiving the response...
 
@@ -224,6 +229,7 @@ def _receive_event(
                 data = self._network_stream.read(
                     self.READ_NUM_BYTES, timeout=timeout
                 )
+                self._prev_socket_use_time = time.monotonic()
 
                 # If we feed this case through h11 we'll raise an exception like:
                 #
@@ -281,16 +287,27 @@ def is_available(self) -> bool:
     def has_expired(self) -> bool:
         now = time.monotonic()
         keepalive_expired = self._expire_at is not None and now > self._expire_at
+        if keepalive_expired:
+            return True
 
         # If the HTTP connection is idle but the socket is readable, then the
         # only valid state is that the socket is about to return b"", indicating
         # a server-initiated disconnect.
-        server_disconnected = (
-            self._state == HTTPConnectionState.IDLE
-            and self._network_stream.get_extra_info("is_readable")
-        )
+        # Checking the readable status is relatively expensive so check it at a lower frequency.
+        if (now - self._prev_socket_use_time) > self._socket_poll_interval():
+            self._prev_socket_use_time = now
+            server_disconnected = (
+                self._state == HTTPConnectionState.IDLE
+                and self._network_stream.get_extra_info("is_readable")
+            )
+            return server_disconnected
+        else:
+            return False
 
-        return keepalive_expired or server_disconnected
+    def _socket_poll_interval(self) -> float:
+        # Randomize to avoid polling for all the connections at once
+        low, high = self._socket_poll_interval_between
+        return random.uniform(low, high)
 
     def is_idle(self) -> bool:
         return self._state == HTTPConnectionState.IDLE