Experimental testing setup for Unix sockets with Complement.

Enable testing Unix sockets by passing UNIX_SOCKETS=1 (yes, it's plural) to the command line when running Complement, or export to the environment ahead of time.

I apologize for the liberties I took with Opinions for this implementation.
1. The main process gets two sockets, one for public(client and federation) traffic, and one for private(replication) traffic. These were placed at /run/mainpublic.sock and /run/mainprivate.sock, respectively.
2. Additionally, for workers, the sockets were placed at /run/worker.{port_number}. I would have preferred to name them according to worker_name, but that would have taken a much deeper restructure of the configure_workers_and_start.py than I was prepared to make. This approach still allows them to be sequentially numbered just as the ports are now.
3. Redis and Postgres also get the Unix socket treatment while here.

docker/conf-workers/nginx.conf.j2

@@ -35,7 +35,11 @@ server {
 
     # Send all other traffic to the main process
     location ~* ^(\\/_matrix|\\/_synapse) {
+{% if using_unix_sockets %}
+        proxy_pass http://unix:/run/mainpublic.sock;
+{% else %}
         proxy_pass http://localhost:8080;
+{% endif %}
         proxy_set_header X-Forwarded-For $remote_addr;
         proxy_set_header X-Forwarded-Proto $scheme;
         proxy_set_header Host $host;

docker/conf-workers/shared.yaml.j2

@@ -6,6 +6,9 @@
 {% if enable_redis %}
 redis:
     enabled: true
+    {% if using_unix_sockets %}
+    path: /tmp/redis.sock
+    {% endif %}
 {% endif %}
 
 {% if appservice_registrations is not none %}

docker/conf-workers/supervisord.conf.j2

@@ -19,7 +19,11 @@ username=www-data
 autorestart=true
 
 [program:redis]
+{% if using_unix_sockets %}
+command=/usr/local/bin/prefix-log /usr/local/bin/redis-server --unixsocket /tmp/redis.sock
+{% else %}
 command=/usr/local/bin/prefix-log /usr/local/bin/redis-server
+{% endif %}
 priority=1
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0

docker/conf-workers/worker.yaml.j2

@@ -8,7 +8,11 @@ worker_name: "{{ name }}"
 
 worker_listeners:
   - type: http
+{% if using_unix_sockets %}
+    path: "/run/worker.{{ port }}"
+{% else %}
     port: {{ port }}
+{% endif %}
 {% if listener_resources %}
     resources:
       - names:

docker/conf/homeserver.yaml

@@ -36,12 +36,17 @@ listeners:
 
   # Allow configuring in case we want to reverse proxy 8008
   # using another process in the same container
+{% if SYNAPSE_USE_UNIX_SOCKET %}
+  # Unix sockets don't care about TLS or IP addresses or ports
+  - path: '/run/mainpublic.sock'
+    type: http
+{% else %}
   - port: {{ SYNAPSE_HTTP_PORT or 8008 }}
     tls: false
     bind_addresses: ['::']
     type: http
     x_forwarded: false
-
+{% endif %}
     resources:
       - names: [client]
         compress: true
@@ -57,8 +62,11 @@ database:
     user: "{{ POSTGRES_USER or "synapse" }}"
     password: "{{ POSTGRES_PASSWORD }}"
     database: "{{ POSTGRES_DB or "synapse" }}"
+{% if not SYNAPSE_USE_UNIX_SOCKET %}
+{# Fun fact: if left with no host or port, Synapse looks for the default Unix socket instead. #}
     host: "{{ POSTGRES_HOST or "db" }}"
     port: "{{ POSTGRES_PORT or "5432" }}"
+{% endif %}
     cp_min: 5
     cp_max: 10
 {% else %}

docker/configure_workers_and_start.py

@@ -74,6 +74,9 @@
 MAIN_PROCESS_INSTANCE_NAME = "main"
 MAIN_PROCESS_LOCALHOST_ADDRESS = "127.0.0.1"
 MAIN_PROCESS_REPLICATION_PORT = 9093
+# Obviously, these would only be used with the UNIX socket option
+MAIN_PROCESS_UNIX_SOCKET_PUBLIC_PATH = "/run/mainpublic.sock"
+MAIN_PROCESS_UNIX_SOCKET_PRIVATE_PATH = "/run/mainprivate.sock"
 
 # A simple name used as a placeholder in the WORKERS_CONFIG below. This will be replaced
 # during processing with the name of the worker.
@@ -408,11 +411,15 @@ def add_worker_roles_to_shared_config(
         )
 
         # Map of stream writer instance names to host/ports combos
-        instance_map[worker_name] = {
-            "host": "localhost",
-            "port": worker_port,
-        }
-
+        if os.environ.get("SYNAPSE_USE_UNIX_SOCKET", False):
+            instance_map[worker_name] = {
+                "path": f"/run/worker.{worker_port}",
+            }
+        else:
+            instance_map[worker_name] = {
+                "host": "localhost",
+                "port": worker_port,
+            }
     # Update the list of stream writers. It's convenient that the name of the worker
     # type is the same as the stream to write. Iterate over the whole list in case there
     # is more than one.
@@ -424,10 +431,15 @@ def add_worker_roles_to_shared_config(
 
             # Map of stream writer instance names to host/ports combos
             # For now, all stream writers need http replication ports
-            instance_map[worker_name] = {
-                "host": "localhost",
-                "port": worker_port,
-            }
+            if os.environ.get("SYNAPSE_USE_UNIX_SOCKET", False):
+                instance_map[worker_name] = {
+                    "path": f"/run/worker.{worker_port}",
+                }
+            else:
+                instance_map[worker_name] = {
+                    "host": "localhost",
+                    "port": worker_port,
+                }
 
 
 def merge_worker_template_configs(
@@ -719,17 +731,29 @@ def generate_worker_files(
     # Note that yaml cares about indentation, so care should be taken to insert lines
     # into files at the correct indentation below.
 
+    # Convenience helper for if using unix sockets instead of host:port
+    using_unix_sockets = environ.get("SYNAPSE_USE_UNIX_SOCKET", False)
     # First read the original config file and extract the listeners block. Then we'll
     # add another listener for replication. Later we'll write out the result to the
     # shared config file.
-    listeners = [
-        {
-            "port": MAIN_PROCESS_REPLICATION_PORT,
-            "bind_address": MAIN_PROCESS_LOCALHOST_ADDRESS,
-            "type": "http",
-            "resources": [{"names": ["replication"]}],
-        }
-    ]
+    listeners: List[Any]
+    if using_unix_sockets:
+        listeners = [
+            {
+                "path": MAIN_PROCESS_UNIX_SOCKET_PRIVATE_PATH,
+                "type": "http",
+                "resources": [{"names": ["replication"]}],
+            }
+        ]
+    else:
+        listeners = [
+            {
+                "port": MAIN_PROCESS_REPLICATION_PORT,
+                "bind_address": MAIN_PROCESS_LOCALHOST_ADDRESS,
+                "type": "http",
+                "resources": [{"names": ["replication"]}],
+            }
+        ]
     with open(config_path) as file_stream:
         original_config = yaml.safe_load(file_stream)
         original_listeners = original_config.get("listeners")
@@ -770,7 +794,15 @@ def generate_worker_files(
 
     # A list of internal endpoints to healthcheck, starting with the main process
     # which exists even if no workers do.
-    healthcheck_urls = ["http://localhost:8080/health"]
+    # This list ends up being part of the command line to curl, which added unix socket
+    # support in version 7.40. The scheme and hostname are ignored, the path is not.
+    if using_unix_sockets:
+        healthcheck_urls = [
+            f"--unix-socket {MAIN_PROCESS_UNIX_SOCKET_PUBLIC_PATH} "
+            "http://localhost/health"
+        ]
+    else:
+        healthcheck_urls = ["http://localhost:8080/health"]
 
     # Get the set of all worker types that we have configured
     all_worker_types_in_use = set(chain(*requested_worker_types.values()))
@@ -807,8 +839,12 @@ def generate_worker_files(
         # given worker_type needs to stay assigned and not be replaced.
         worker_config["shared_extra_conf"].update(shared_config)
         shared_config = worker_config["shared_extra_conf"]
-
-        healthcheck_urls.append("http://localhost:%d/health" % (worker_port,))
+        if using_unix_sockets:
+            healthcheck_urls.append(
+                f"--unix-socket /run/worker.{worker_port} http://localhost/health"
+            )
+        else:
+            healthcheck_urls.append("http://localhost:%d/health" % (worker_port,))
 
         # Update the shared config with sharding-related options if necessary
         add_worker_roles_to_shared_config(
@@ -827,6 +863,7 @@ def generate_worker_files(
             "/conf/workers/{name}.yaml".format(name=worker_name),
             **worker_config,
             worker_log_config_filepath=log_config_filepath,
+            using_unix_sockets=using_unix_sockets,
         )
 
         # Save this worker's port number to the correct nginx upstreams
@@ -847,8 +884,13 @@ def generate_worker_files(
     nginx_upstream_config = ""
     for upstream_worker_base_name, upstream_worker_ports in nginx_upstreams.items():
         body = ""
-        for port in upstream_worker_ports:
-            body += f"    server localhost:{port};\n"
+        if using_unix_sockets:
+            for port in upstream_worker_ports:
+                body += f"    server unix:/run/worker.{port};\n"
+
+        else:
+            for port in upstream_worker_ports:
+                body += f"    server localhost:{port};\n"
 
         # Add to the list of configured upstreams
         nginx_upstream_config += NGINX_UPSTREAM_CONFIG_BLOCK.format(
@@ -878,10 +920,15 @@ def generate_worker_files(
     # If there are workers, add the main process to the instance_map too.
     if workers_in_use:
         instance_map = shared_config.setdefault("instance_map", {})
-        instance_map[MAIN_PROCESS_INSTANCE_NAME] = {
-            "host": MAIN_PROCESS_LOCALHOST_ADDRESS,
-            "port": MAIN_PROCESS_REPLICATION_PORT,
-        }
+        if using_unix_sockets:
+            instance_map[MAIN_PROCESS_INSTANCE_NAME] = {
+                "path": MAIN_PROCESS_UNIX_SOCKET_PRIVATE_PATH,
+            }
+        else:
+            instance_map[MAIN_PROCESS_INSTANCE_NAME] = {
+                "host": MAIN_PROCESS_LOCALHOST_ADDRESS,
+                "port": MAIN_PROCESS_REPLICATION_PORT,
+            }
 
     # Shared homeserver config
     convert(
@@ -891,6 +938,7 @@ def generate_worker_files(
         appservice_registrations=appservice_registrations,
         enable_redis=workers_in_use,
         workers_in_use=workers_in_use,
+        using_unix_sockets=using_unix_sockets,
     )
 
     # Nginx config
@@ -901,6 +949,7 @@ def generate_worker_files(
         upstream_directives=nginx_upstream_config,
         tls_cert_path=os.environ.get("SYNAPSE_TLS_CERT"),
         tls_key_path=os.environ.get("SYNAPSE_TLS_KEY"),
+        using_unix_sockets=using_unix_sockets,
     )
 
     # Supervisord config
@@ -910,6 +959,7 @@ def generate_worker_files(
         "/etc/supervisor/supervisord.conf",
         main_config_path=config_path,
         enable_redis=workers_in_use,
+        using_unix_sockets=using_unix_sockets,
     )
 
     convert(

scripts-dev/complement.sh

@@ -257,6 +257,10 @@ if [[ -n "$ASYNCIO_REACTOR" ]]; then
   export PASS_SYNAPSE_COMPLEMENT_USE_ASYNCIO_REACTOR=true
 fi
 
+if [[ -n "$UNIX_SOCKETS" ]]; then
+  # Enable full on Unix socket mode for Synapse, Redis and Postgresql
+  export PASS_SYNAPSE_USE_UNIX_SOCKET=1
+fi
 
 if [[ -n "$SYNAPSE_TEST_LOG_LEVEL" ]]; then
   # Set the log level to what is desired