Fix databricks timeout issue (#10613)

* Fix databricks timeout issue

* Change based on comments

* Change timeOut word to connectionTimeout

ingestion/src/metadata/examples/workflows/databricks.yaml

@@ -7,6 +7,7 @@ source:
       databaseSchema: default
       token: <databricks token>
       hostPort: localhost:443
+      connectionTimeout: 120
       connectionArguments:
         http_path: <http path of databricks cluster>
   sourceConfig:

ingestion/src/metadata/ingestion/connections/test_connections.py

@@ -92,15 +92,7 @@ def test_connection_steps(steps: List[TestConnectionStep]) -> TestConnectionResu
     return test_connection_result
 
 
-@timeout(seconds=120)
-def test_connection_db_common(connection: Engine, steps=None) -> TestConnectionResult:
-    """
-    Default implementation is the engine to test.
-
-    Test that we can connect to the source using the given engine
-    :param connection: Engine to test
-    :return: None or raise an exception if we cannot connect
-    """
+def test_connection_engine(connection: Engine, steps=None) -> TestConnectionResult:
     try:
         with connection.connect() as conn:
             conn.execute(ConnTestFn())
@@ -116,3 +108,16 @@ def test_connection_db_common(connection: Engine, steps=None) -> TestConnectionR
         raise SourceConnectionException(msg) from exc
 
     return None
+
+
+def test_connection_db_common(
+    connection: Engine, steps=None, timeout_seconds: int = 120
+) -> TestConnectionResult:
+    """
+    Default implementation is the engine to test.
+
+    Test that we can connect to the source using the given engine
+    :param connection: Engine to test
+    :return: None or raise an exception if we cannot connect
+    """
+    return timeout(timeout_seconds)(test_connection_engine)(connection, steps)

ingestion/src/metadata/ingestion/source/database/databricks/connection.py

@@ -53,12 +53,13 @@ def get_connection(connection: DatabricksConnection) -> Engine:
     )
 
 
-def test_connection(engine: Engine, _) -> TestConnectionResult:
+def test_connection(engine: Engine, service_connection) -> TestConnectionResult:
     """
     Test connection
     """
 
     def custom_executor(engine, statement):
+
         cursor = engine.execute(statement)
         return [item[0] for item in list(cursor.all())]
 
@@ -91,4 +92,5 @@ def test_connection(engine: Engine, _) -> TestConnectionResult:
         ),
     ]
 
-    return test_connection_db_common(engine, steps)
+    timeout_seconds = service_connection.connectionTimeout
+    return test_connection_db_common(engine, steps, timeout_seconds)

openmetadata-docs/content/connectors/database/databricks/airflow.md

@@ -76,6 +76,7 @@ source:
       token: <databricks token>
       hostPort: <databricks connection host & port>
       httpPath: <http path of databricks cluster>
+      connectionTimeout: 120
   sourceConfig:
     config:
       type: DatabaseMetadata
@@ -120,6 +121,7 @@ workflowConfig:
 - **hostPort**: Enter the fully qualified hostname and port number for your Databricks deployment in the Host and Port field.
 - **token**: Generated Token to connect to Databricks.
 - **httpPath**: Databricks compute resources URL.
+- **connectionTimeout**: The maximum amount of time (in seconds) to wait for a successful connection to the data source. If the connection attempt takes longer than this timeout period, an error will be returned.
 - **catalog**: Catalog of the data source(Example: hive_metastore). This is optional parameter, if you would like to restrict the metadata reading to a single catalog. When left blank, OpenMetadata Ingestion attempts to scan all the catalog.
 - **databaseSchema**: DatabaseSchema of the data source. This is optional parameter, if you would like to restrict the metadata reading to a single databaseSchema. When left blank, OpenMetadata Ingestion attempts to scan all the databaseSchema.
 - **Connection Options (Optional)**: Enter the details for any additional connection options that can be sent to Databricks during the connection. These details must be added as Key-Value pairs.

openmetadata-docs/content/connectors/database/databricks/cli.md

@@ -76,6 +76,7 @@ source:
       token: <databricks token>
       hostPort: <databricks connection host & port>
       httpPath: <http path of databricks cluster>
+      connectionTimeout: 120
   sourceConfig:
     config:
       type: DatabaseMetadata
@@ -120,6 +121,7 @@ workflowConfig:
 - **hostPort**: Enter the fully qualified hostname and port number for your Databricks deployment in the Host and Port field.
 - **token**: Generated Token to connect to Databricks.
 - **httpPath**: Databricks compute resources URL.
+- **connectionTimeout**: The maximum amount of time (in seconds) to wait for a successful connection to the data source. If the connection attempt takes longer than this timeout period, an error will be returned.
 - **catalog**: Catalog of the data source(Example: hive_metastore). This is optional parameter, if you would like to restrict the metadata reading to a single catalog. When left blank, OpenMetadata Ingestion attempts to scan all the catalog.
 - **databaseSchema**: DatabaseSchema of the data source. This is optional parameter, if you would like to restrict the metadata reading to a single databaseSchema. When left blank, OpenMetadata Ingestion attempts to scan all the databaseSchema.
 - **Connection Options (Optional)**: Enter the details for any additional connection options that can be sent to Databricks during the connection. These details must be added as Key-Value pairs.

openmetadata-docs/content/connectors/database/databricks/index.md

@@ -150,6 +150,7 @@ the changes.
 - **Host and Port**: Enter the fully qualified hostname and port number for your Databricks deployment in the Host and Port field.
 - **Token**: Generated Token to connect to Databricks.
 - **HTTP Path**: Databricks compute resources URL.
+- **connectionTimeout**: The maximum amount of time (in seconds) to wait for a successful connection to the data source. If the connection attempt takes longer than this timeout period, an error will be returned.
 - **Catalog**: Catalog of the data source(Example: hive_metastore). This is optional parameter, if you would like to restrict the metadata reading to a single catalog. When left blank, OpenMetadata Ingestion attempts to scan all the catalog.
 - **DatabaseSchema**: databaseSchema of the data source. This is optional parameter, if you would like to restrict the metadata reading to a single databaseSchema. When left blank, OpenMetadata Ingestion attempts to scan all the databaseSchema.
 - **Connection Options (Optional)**: Enter the details for any additional connection options that can be sent to Databricks during the connection. These details must be added as Key-Value pairs.

openmetadata-spec/src/main/resources/json/schema/entity/services/connections/database/databricksConnection.json

@@ -58,6 +58,12 @@
       "description": "databaseSchema of the data source. This is optional parameter, if you would like to restrict the metadata reading to a single databaseSchema. When left blank, OpenMetadata Ingestion attempts to scan all the databaseSchema.",
       "type": "string"
     },
+    "connectionTimeout": {
+      "title": "Connection Timeout",
+      "description": "The maximum amount of time (in seconds) to wait for a successful connection to the data source. If the connection attempt takes longer than this timeout period, an error will be returned.",
+      "type": "integer",
+      "default": 120
+    },
     "connectionOptions": {
       "title": "Connection Options",
       "$ref": "../connectionBasicType.json#/definitions/connectionOptions"