feat(api): label Postgres connections with application_name per component and alias (#11494)

api/CHANGELOG.md

@@ -9,6 +9,7 @@ All notable changes to the **Prowler API** are documented in this file.
 - Automatic recovery of allowlisted idempotent background tasks whose worker died during a deploy or crash: stuck scan and summary tasks are detected and re-run instead of staying pending forever, with a `reconcile_orphan_tasks` management command for on-demand recovery [(#11416)](https://github.com/prowler-cloud/prowler/pull/11416)
 - Jira integration no longer creates duplicate issues on a retried send; findings already ticketed are skipped [(#11416)](https://github.com/prowler-cloud/prowler/pull/11416)
 - DORA compliance framework support [(#11131)](https://github.com/prowler-cloud/prowler/pull/11131)
+- Label Postgres connections with `application_name="<component>:<alias>"` (component injected per process via `DJANGO_APP_COMPONENT`) so connections are attributable by component in `pg_stat_activity` [(#11494)](https://github.com/prowler-cloud/prowler/pull/11494)
 
 ### 🔄 Changed
 

api/docker-entrypoint.sh

@@ -68,6 +68,15 @@ manage_db_partitions() {
   fi
 }
 
+# Identify this process to Postgres (application_name=<component>:<alias>) so
+# connections are attributable by component in pg_stat_activity. Web tiers
+# report "api"; everything else uses the launch subcommand.
+case "$1" in
+  prod|dev) DJANGO_APP_COMPONENT="api" ;;
+  *)        DJANGO_APP_COMPONENT="$1" ;;
+esac
+export DJANGO_APP_COMPONENT
+
 case "$1" in
   dev)
     apply_migrations

api/src/backend/api/tests/test_db_connection_labels.py

@@ -0,0 +1,55 @@
+from config.django.base import label_postgres_connections
+
+
+class TestLabelPostgresConnections:
+    def test_labels_postgres_and_skips_neo4j(self, monkeypatch):
+        monkeypatch.setenv("DJANGO_APP_COMPONENT", "scan")
+        databases = {
+            "default": {"ENGINE": "psqlextra.backend"},
+            "neo4j": {"HOST": "neo4j", "PORT": "7687"},
+        }
+
+        label_postgres_connections(databases)
+
+        assert databases["default"]["OPTIONS"]["application_name"] == "scan:default"
+        assert "OPTIONS" not in databases["neo4j"]
+
+    def test_labels_plain_postgresql_backend(self, monkeypatch):
+        monkeypatch.setenv("DJANGO_APP_COMPONENT", "api")
+        databases = {"saas": {"ENGINE": "django.db.backends.postgresql"}}
+
+        label_postgres_connections(databases)
+
+        assert databases["saas"]["OPTIONS"]["application_name"] == "api:saas"
+
+    def test_defaults_component_to_api_when_unset(self, monkeypatch):
+        monkeypatch.delenv("DJANGO_APP_COMPONENT", raising=False)
+        databases = {"default": {"ENGINE": "psqlextra.backend"}}
+
+        label_postgres_connections(databases)
+
+        assert databases["default"]["OPTIONS"]["application_name"] == "api:default"
+
+    def test_preserves_existing_options(self, monkeypatch):
+        monkeypatch.setenv("DJANGO_APP_COMPONENT", "worker")
+        databases = {
+            "replica": {
+                "ENGINE": "psqlextra.backend",
+                "OPTIONS": {"sslmode": "require"},
+            }
+        }
+
+        label_postgres_connections(databases)
+
+        assert databases["replica"]["OPTIONS"] == {
+            "sslmode": "require",
+            "application_name": "worker:replica",
+        }
+
+    def test_truncates_application_name_to_63_bytes(self, monkeypatch):
+        monkeypatch.setenv("DJANGO_APP_COMPONENT", "c" * 80)
+        databases = {"default": {"ENGINE": "psqlextra.backend"}}
+
+        label_postgres_connections(databases)
+
+        assert len(databases["default"]["OPTIONS"]["application_name"]) == 63

api/src/backend/config/django/base.py

@@ -306,3 +306,20 @@ SESSION_COOKIE_SECURE = True
 ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES = env.int(
     "ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES", 2880
 )  # 48h
+
+
+def label_postgres_connections(databases):
+    """Tag each Postgres connection with ``application_name="<component>:<alias>"``
+    so connections are attributable by component in ``pg_stat_activity`` (and any
+    tooling that surfaces ``application_name``). The component (api / worker /
+    scan / ...) is injected per process by the container entrypoint via
+    ``DJANGO_APP_COMPONENT``; the alias distinguishes which pool inside the
+    process owns the connection. The neo4j entry is skipped (not a Postgres
+    backend). Postgres truncates ``application_name`` at 63 bytes.
+    """
+    component = env.str("DJANGO_APP_COMPONENT", default="api")
+    for alias, config in databases.items():
+        engine = config.get("ENGINE", "")
+        if engine.startswith("psqlextra") or "postgresql" in engine:
+            name = f"{component}:{alias}"[:63]
+            config.setdefault("OPTIONS", {})["application_name"] = name

api/src/backend/config/django/devel.py

@@ -54,6 +54,8 @@ DATABASES = {
 
 DATABASES["default"] = DATABASES["prowler_user"]
 
+label_postgres_connections(DATABASES)  # noqa: F405
+
 REST_FRAMEWORK["DEFAULT_RENDERER_CLASSES"] = tuple(  # noqa: F405
     render_class
     for render_class in REST_FRAMEWORK["DEFAULT_RENDERER_CLASSES"]  # noqa: F405

api/src/backend/config/django/production.py

@@ -58,3 +58,5 @@ DATABASES = {
 }
 
 DATABASES["default"] = DATABASES["prowler_user"]
+
+label_postgres_connections(DATABASES)  # noqa: F405