659 Add Postgres and Redis to health endpoint (#690)

* adds db and redis to health endpoint, untested

* updates typing, suppresses sqlalchemy and alembic logs for healthchecks

* adds to makefile, updates docs and tests

* format

* adds check for cache enabled, update tests

* format

* standardize health endpoint structure

CHANGELOG.md

@@ -40,6 +40,7 @@ The types of changes are:
 * Datastore Connection Landing Page [#674](https://github.com/ethyca/fidesops/pull/674)
 * Added the ability to delete a datastore from the frontend [#683] https://github.com/ethyca/fidesops/pull/683
 * Added the ability to disable/enable a datastore from the frontend [#693] https://github.com/ethyca/fidesops/pull/693
+* Adds Postgres and Redis health checks to health endpoint [#690](https://github.com/ethyca/fidesops/pull/690)
 
 ### Changed
 

docker-compose.yml

@@ -64,10 +64,6 @@ services:
       dockerfile: Dockerfile
     command: celery -A fidesops.tasks beat -l info --logfile=/var/log/celery.log
     depends_on:
-      fidesops:
-        condition: service_healthy
-      db:
-        condition: service_started
       redis:
         condition: service_started
     restart: always

docs/fidesops/docs/deployment.md

@@ -143,6 +143,6 @@ Note that there's no need for a persistent volume mount for the web server, it's
 
 ### Test the Web Server
 
-To test that your server is running, visit `http://{server_url}/health` in your browser (e.g. http://0.0.0.0:8080/health) and you should see `{ "healthy": true }`.
+To test that your server is running, visit `http://{server_url}/health` in your browser (e.g. http://0.0.0.0:8080/health) and you should see `{"webserver": "healthy", "database": "healthy", "cache": "healthy"}`.
 
 You now have a functional `fidesops` server running! Now you can use the API to set up your OAuth clients, connect to databases, configure policies, execute privacy requests, etc. To learn more, head to the [How-To Guides](guides/oauth.md) for details.

docs/fidesops/docs/getting_started.md

@@ -16,7 +16,7 @@ Ensure nothing is running on ports `8080`, `5432`, or `6379` prior to these step
 
 2. Run `docker compose up` from the root of the Fidesops project directory. The provided `docker-compose.yml` will create the necessary databases and spin up the server.
 
-3. Visit `http://0.0.0.0:8080/health` in your browser. A response of `{ "healthy": true }` indicates a successful deployment.
+3. Visit `http://0.0.0.0:8080/health` in your browser. A response of `{"webserver": "healthy", "database": "healthy", "cache": "healthy"}` indicates a successful deployment.
 
 ## Build From Your Project
 
@@ -86,7 +86,7 @@ Ensure nothing is running on ports `8080`, `5432`, or `6379` prior to these step
    
 2. Ensure Docker is running, and run `docker compose up` from the project's root directory. This will pull the latest Fidesops Docker image, create the sample databases, and start the server.
 
-3. Visit `http://0.0.0.0:8080/health` in your browser. A response of `{ "healthy": true }` indicates a successful deployment.
+3. Visit `http://0.0.0.0:8080/health` in your browser. A response of `{"webserver": "healthy", "database": "healthy", "cache": "healthy"}` indicates a successful deployment.
 
 ## Next Steps
 You now have a working test installation of Fidesops! From here, use the available [How-To Guides](guides/oauth.md) to view examples of authenticating, connecting to databases, configuring policies, and more. 

src/fidesops/api/v1/endpoints/health_endpoints.py

@@ -1,14 +1,62 @@
-from typing import Dict
+import logging
+from typing import Dict, Optional, Union
 
+from alembic import migration, script
 from fastapi import APIRouter
+from redis.exceptions import ResponseError
+from sqlalchemy import create_engine
 
 from fidesops.api.v1.urn_registry import HEALTH
+from fidesops.common_exceptions import RedisConnectionError
+from fidesops.core.config import config
+from fidesops.db.database import get_alembic_config
+from fidesops.util.cache import get_cache
 
 router = APIRouter(tags=["Public"])
 
+logger = logging.getLogger(__name__)
+# stops polluting logs with sqlalchemy / alembic info-level logs
+logging.getLogger("sqlalchemy.engine").setLevel(logging.ERROR)
+logging.getLogger("alembic").setLevel(logging.WARNING)
 
-@router.get(HEALTH, response_model=Dict[str, bool])
-def health_check() -> Dict[str, bool]:
+
+@router.get(HEALTH, response_model=Dict[str, Union[bool, str]])
+def health_check() -> Dict[str, Union[bool, str]]:
     return {
-        "healthy": True,
+        "webserver": "healthy",
+        "database": get_db_health(config.database.SQLALCHEMY_DATABASE_URI),
+        "cache": get_cache_health(),
     }
+
+
+def get_db_health(database_url: Optional[str]) -> str:
+    """Checks if the db is reachable and up to date in alembic migrations"""
+    if not database_url or not config.database.ENABLED:
+        return "no db configured"
+    try:
+        engine = create_engine(database_url)
+        alembic_config = get_alembic_config(database_url)
+        alembic_script_directory = script.ScriptDirectory.from_config(alembic_config)
+        with engine.begin() as conn:
+            context = migration.MigrationContext.configure(conn)
+            if (
+                context.get_current_revision()
+                != alembic_script_directory.get_current_head()
+            ):
+                return "needs migration"
+        return "healthy"
+    except Exception as error:  # pylint: disable=broad-except
+        logger.error(f"Unable to reach the database: {error}")
+        return "unhealthy"
+
+
+def get_cache_health() -> str:
+    """Checks if the cache is reachable"""
+    if not config.redis.ENABLED:
+        return "no cache configured"
+    try:
+        get_cache()
+        return "healthy"
+    except (RedisConnectionError, ResponseError) as e:
+        logger.error(f"Unable to reach cache: {e}")
+        return "unhealthy"

tests/api/v1/endpoints/test_health_endpoints.py

@@ -5,4 +5,8 @@
 
 def test_health(api_client: TestClient) -> None:
     response = api_client.get(HEALTH)
-    assert response.json() == {"healthy": True}
+    assert response.json() == {
+        "webserver": "healthy",
+        "database": "healthy",
+        "cache": "healthy",
+    }

tests/api/v1/test_exception_handlers.py

@@ -38,7 +38,11 @@ def test_db_disabled(self, api_client: TestClient, generate_auth_header):
         assert expected_response == response_body
 
         # health endpoint should still work
-        expected_response = {"healthy": True}
+        expected_response = {
+            "webserver": "healthy",
+            "database": "no db configured",
+            "cache": "healthy",
+        }
         response = api_client.get(HEALTH)
         response_body = json.loads(response.text)
         assert 200 == response.status_code
@@ -66,7 +70,11 @@ def test_redis_disabled(self, api_client: TestClient, generate_auth_header):
         assert expected_response == response_body
 
         # health endpoint should still work
-        expected_response = {"healthy": True}
+        expected_response = {
+            "webserver": "healthy",
+            "database": "healthy",
+            "cache": "no cache configured",
+        }
         response = api_client.get(HEALTH)
         response_body = json.loads(response.text)
         assert 200 == response.status_code