Docker fix (#1101)

* Docker Fix, User Ingestion Fix

* Docker file optimized

* ES docker version rolledback

* Healthcheck removed - incompatible with 3.9

* Docker & Airflow Config files updated with - resolved comments

* Openmetadata managed Airflow apis support added

* Dockerfile updated

* Docker file Updated with release package

* Elasticsearch allocated memory increased

docker/local-metadata/docker-compose.yml

@@ -25,15 +25,17 @@ services:
     expose:
       - 3306
     networks:
-      app_net:
+      local_app_net:
         ipv4_address: 172.16.239.10
 
   elasticsearch:
     image: docker.elastic.co/elasticsearch/elasticsearch:7.10.2
     environment:
       - discovery.type=single-node
+      - ES_JAVA_OPTS=-Xms1024m -Xmx1024m
+
     networks:
-      app_net:
+      local_app_net:
         ipv4_address: 172.16.239.11
     expose:
       - 9200
@@ -57,7 +59,7 @@ services:
     depends_on:
       - mysql
     networks:
-      app_net:
+      local_app_net:
         ipv4_address: 172.16.239.13
     extra_hosts:
       - "localhost:172.16.239.10"
@@ -74,14 +76,14 @@ services:
     ports:
       - 8080:8080
     networks:
-      - app_net
+      - local_app_net
     extra_hosts:
       - "localhost:172.16.239.10"
       - "localhost:172.16.239.11"
       - "localhost:172.16.239.13"
 
 networks:
-  app_net:
+  local_app_net:
     ipam:
       driver: default
       config:

docker/metadata/docker-compose.yml

@@ -25,15 +25,17 @@ services:
       - 3306
     networks:
       app_net:
-        ipv4_address: 172.16.239.10
+        ipv4_address: 172.16.240.10
 
   elasticsearch:
     image: docker.elastic.co/elasticsearch/elasticsearch:7.10.2
     environment:
       - discovery.type=single-node
+      - ES_JAVA_OPTS=-Xms1024m -Xmx1024m
+
     networks:
       app_net:
-        ipv4_address: 172.16.239.11
+        ipv4_address: 172.16.240.11
     ports:
       - 9200:9200
       - 9300:9300
@@ -52,10 +54,10 @@ services:
       - mysql
     networks:
       app_net:
-        ipv4_address: 172.16.239.13
+        ipv4_address: 172.16.240.13
     extra_hosts:
-      - "localhost:172.16.239.10"
-      - "elasticsearch:172.16.239.11"
+      - "localhost:172.16.240.10"
+      - "elasticsearch:172.16.240.11"
 
   ingestion:
     image: openmetadata/ingestion:latest
@@ -68,13 +70,13 @@ services:
     networks:
       - app_net
     extra_hosts:
-      - "localhost:172.16.239.10"
-      - "localhost:172.16.239.11"
-      - "localhost:172.16.239.13"
+      - "localhost:172.16.240.10"
+      - "localhost:172.16.240.11"
+      - "localhost:172.16.240.13"
 
 networks:
   app_net:
     ipam:
       driver: default
       config:
-        - subnet: "172.16.239.0/24"
+        - subnet: "172.16.240.0/24"

ingestion/Dockerfile

@@ -1,13 +1,24 @@
 FROM python:3.9-slim
 ENV AIRFLOW_HOME=/airflow
 WORKDIR /ingestion
-
 RUN apt-get update && \
-    apt-get install -y gcc libsasl2-dev curl unixodbc-dev wget --no-install-recommends && \
+    apt-get install -y gcc libsasl2-dev curl build-essential libssl-dev libffi-dev librdkafka-dev unixodbc-dev python3.9-dev libevent-dev wget --no-install-recommends && \
     rm -rf /var/lib/apt/lists/*
-RUN pip install 'openmetadata-ingestion[sample-data,elasticsearch,mysql]' apache-airflow==2.1.4
-COPY ./ingestion /ingestion
-RUN pip install '.[sample-data,elasticsearch,mysql]'
+RUN wget https://github.com/open-metadata/openmetadata-airflow-apis/releases/download/0.1/openmetadata-airflow-apis-plugin.tar.gz
+RUN tar zxvf openmetadata-airflow-apis-plugin.tar.gz
+RUN mkdir /om-airflow
+RUN mv plugins /om-airflow
+ENV AIRFLOW_VERSION=2.2.1
+ENV CONSTRAINT_URL="https://raw.githubusercontent.com/apache/airflow/constraints-${AIRFLOW_VERSION}/constraints-3.9.txt"
+RUN pip install "apache-airflow==${AIRFLOW_VERSION}" --constraint "${CONSTRAINT_URL}"
+COPY ingestion /ingestion
+RUN pip install -e '.[all]' openmetadata-airflow-managed-apis
+RUN airflow db init
+RUN cp -r /ingestion/examples/airflow/airflow.cfg /airflow/airflow.cfg
+RUN cp -r /om-airflow/plugins /airflow/plugins
+RUN cp -r /om-airflow/plugins/dag_templates /airflow/
+RUN mkdir -p /airflow/dag_generated_configs
+RUN cp -r /om-airflow/plugins/dag_managed_operators /airflow/
 RUN chmod 755 ingestion_dependency.sh
 EXPOSE 8080
-CMD [ "./ingestion_dependency.sh" ]     
+CMD [ "./ingestion_dependency.sh" ]

ingestion/examples/airflow/airflow.cfg

@@ -419,6 +419,11 @@ airflow_service_name = local_airflow_3
 openmetadata_api_endpoint = http://localhost:8585/api
 auth_provider_type = no-auth
 
+[openmetadata_airflow_apis]
+dag_runner_template = /airflow/dag_templates/dag_runner.j2
+dag_generated_configs = /airflow/dag_generated_configs
+dag_managed_operators = /airflow/dag_managed_operators
+
 [atlas]
 sasl_enabled = False
 host =

ingestion/examples/airflow/dags/airflow_metadata_to_es.py

@@ -12,6 +12,7 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+import json
 import pathlib
 from datetime import timedelta
 
@@ -29,21 +30,45 @@ from metadata.ingestion.api.workflow import Workflow
 
 default_args = {
     "owner": "user_name",
-    "email": ["username@org.com"],
-    "email_on_failure": False,
     "retries": 3,
     "retry_delay": timedelta(minutes=2),
     "execution_timeout": timedelta(minutes=60),
 }
 
 config = """
+{
+  "source": {
+    "type": "metadata",
+    "config": {
+      "include_tables": "true",
+      "include_topics": "true",
+      "include_dashboards": "true",
+      "limit_records": 10
+    }
+  },
+  "sink": {
+    "type": "elasticsearch",
+    "config": {
+      "index_tables": "true",
+      "index_topics": "true",
+      "index_dashboards": "true",
+      "es_host": "localhost",
+      "es_port": 9200
+    }
+  },
+  "metadata_server": {
+    "type": "metadata-server",
+    "config": {
+      "api_endpoint": "http://localhost:8585/api",
+      "auth_provider_type": "no-auth"
+    }
+  }
+}
 """
 
 
 def metadata_ingestion_workflow():
-    config_file = pathlib.Path("/ingestion/pipelines/metadata_to_es.json")
-    workflow_config = load_config_file(config_file)
-
+    workflow_config = json.loads(config)
     workflow = Workflow.create(workflow_config)
     workflow.execute()
     workflow.raise_from_status()
@@ -52,7 +77,7 @@ def metadata_ingestion_workflow():
 
 
 with DAG(
-    "elasticsearch",
+    "index_metadata",
     default_args=default_args,
     description="An example DAG which runs a OpenMetadata ingestion workflow",
     start_date=days_ago(1),

ingestion/examples/airflow/dags/airflow_sample_usage.py

@@ -12,18 +12,21 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+import json
 import pathlib
 from datetime import timedelta
+
 from airflow import DAG
-import json
+
 try:
     from airflow.operators.python import PythonOperator
 except ModuleNotFoundError:
     from airflow.operators.python_operator import PythonOperator
 
+from airflow.utils.dates import days_ago
+
 from metadata.config.common import load_config_file
 from metadata.ingestion.api.workflow import Workflow
-from airflow.utils.dates import days_ago
 
 default_args = {
     "owner": "user_name",
@@ -31,7 +34,7 @@ default_args = {
     "email_on_failure": False,
     "retries": 3,
     "retry_delay": timedelta(minutes=5),
-    "execution_timeout": timedelta(minutes=60)
+    "execution_timeout": timedelta(minutes=60),
 }
 
 config = """
@@ -72,9 +75,9 @@ config = """
 }
 """
 
+
 def metadata_ingestion_workflow():
     workflow_config = json.loads(config)
-    
     workflow = Workflow.create(workflow_config)
     workflow.execute()
     workflow.raise_from_status()
@@ -94,4 +97,4 @@ with DAG(
     ingest_task = PythonOperator(
         task_id="ingest_using_recipe",
         python_callable=metadata_ingestion_workflow,
-    )
+    )

ingestion/ingestion_dependency.sh

@@ -17,10 +17,6 @@
 #
 
 while ! wget -O /dev/null -o /dev/null mysql:3306; do sleep 5; done
-export AIRFLOW_HOME=/airflow
-airflow db init
-echo "AUTH_ROLE_PUBLIC = 'Admin'" >> /airflow/webserver_config.py
-mv /ingestion/examples/airflow/airflow.cfg /airflow/airflow.cfg
 airflow users create \
     --username admin \
     --firstname Peter \
@@ -28,11 +24,5 @@ airflow users create \
     --role Admin \
     --email spiderman@superhero.org \
     --password admin
-airflow webserver --port 8080 -D & 
-(sleep 5; airflow db init)
-(sleep 5; airflow db init)
-(sleep 5; curl -u admin:admin --data '{"dag_run_id":"sample_data"}' -H "Content-type: application/json" -X POST http://localhost:8080/api/v1/dags/sample_data/dagRuns) &
-(sleep 7; curl -u admin:admin --data '{"dag_run_id":"sample_users"}' -H "Content-type: application/json" -X POST http://localhost:8080/api/v1/dags/sample_users/dagRuns) &
-(sleep 12; curl -u admin:admin --data '{"dag_run_id":"sample_usage"}' -H "Content-type: application/json" -X POST http://localhost:8080/api/v1/dags/sample_usage/dagRuns) &
-(sleep 17; curl -u admin:admin --data '{"dag_run_id":"elasticsearch"}' -H "Content-type: application/json" -X POST http://localhost:8080/api/v1/dags/elasticsearch/dagRuns) &
-airflow scheduler
+airflow db upgrade
+airflow standalone