Clean up the Airflow database

Stay organized with collections Save and categorize content based on your preferences.

Cloud Composer 1 | Cloud Composer 2

This page explains how to reduce the size of the Airflow database in your environment.

As the time goes, the Airflow database of your environment stores more and more data. This data includes information and logs related to past DAG runs, tasks, and other Airflow operations.

If the Airflow database size is more than 16 GB, then you cannot perform environment upgrades. To reduce the database size, perform the database cleanup.

Run the Airflow database maintenance DAG

You can use the following maintenance DAG to prune the content of your database. This DAG removes old entries from DagRun, TaskInstance, Log, XCom, Job DB and SlaMiss tables.

Database maintenance DAG - Airflow 2

A maintenance workflow that you can deploy into Airflow to periodically clean
out the DagRun, TaskInstance, Log, XCom, Job DB and SlaMiss entries to avoid
having too much data in your Airflow MetaStore.

## Authors

The DAG is a fork of [teamclairvoyant repository.](

## Usage

1. Update the global variables (SCHEDULE_INTERVAL, DAG_OWNER_NAME,
  ALERT_EMAIL_ADDRESSES and ENABLE_DELETE) in the DAG with the desired values

2. Modify the DATABASE_OBJECTS list to add/remove objects as needed. Each
   dictionary in the list features the following parameters:
    - airflow_db_model: Model imported from airflow.models corresponding to
      a table in the airflow metadata database
    - age_check_column: Column in the model/table to use for calculating max
      date of data deletion
    - keep_last: Boolean to specify whether to preserve last run instance
        - keep_last_filters: List of filters to preserve data from deleting
          during clean-up, such as DAG runs where the external trigger is set to 0.
        - keep_last_group_by: Option to specify column by which to group the
          database entries and perform aggregate functions.

3. Create and Set the following Variables in the Airflow Web Server
  (Admin -> Variables)
    - airflow_db_cleanup__max_db_entry_age_in_days - integer - Length to retain
      the log files if not already provided in the conf. If this is set to 30,
      the job will remove those files that are 30 days old or older.

4. Put the DAG in your gcs bucket.
from datetime import datetime, timedelta
import logging
import os

import airflow
from airflow import settings
from airflow.configuration import conf
from import BaseJob
from airflow.models import DAG, DagModel, DagRun, Log, SlaMiss, \
    TaskInstance, Variable, XCom
from airflow.operators.python import PythonOperator
import dateutil.parser
from sqlalchemy import and_, func
from sqlalchemy.exc import ProgrammingError
from sqlalchemy.orm import load_only

    # airflow.utils.timezone is available from v1.10 onwards
    from airflow.utils import timezone
    now = timezone.utcnow
except ImportError:
    now = datetime.utcnow

# airflow-db-cleanup
DAG_ID = os.path.basename(__file__).replace(".pyc", "").replace(".py", "")
START_DATE = airflow.utils.dates.days_ago(1)
# How often to Run. @daily - Once a day at Midnight (UTC)
# Who is listed as the owner of this DAG in the Airflow Web Server
DAG_OWNER_NAME = "operations"
# List of email address to send email alerts to if this job fails
# Length to retain the log files if not already provided in the conf. If this
# is set to 30, the job will remove those files that arE 30 days old or older.
AIRFLOW_VERSION = os.getenv("MAJOR_VERSION", "2.2.0").split(".")
    Variable.get("airflow_db_cleanup__max_db_entry_age_in_days", 30))
# Prints the database entries which will be getting deleted; set to False
# to avoid printing large lists and slowdown process
# Whether the job should delete the db entries or not. Included if you want to
# temporarily avoid deleting the db entries.
# List of all the objects that will be deleted. Comment out the DB objects you
# want to skip.
    "airflow_db_model": BaseJob,
    "age_check_column": BaseJob.latest_heartbeat,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None
}, {
    "airflow_db_model": DagRun,
    "age_check_column": DagRun.execution_date,
    "keep_last": True,
    "keep_last_filters": [DagRun.external_trigger.is_(False)],
    "keep_last_group_by": DagRun.dag_id
}, {
    "airflow_db_model": TaskInstance,
    "age_check_column": TaskInstance.execution_date if AIRFLOW_VERSION < ['2', '2', '0'] else TaskInstance.start_date,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None
}, {
    "airflow_db_model": Log,
    "age_check_column": Log.dttm,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None
}, {
    "airflow_db_model": XCom,
    "age_check_column": XCom.execution_date,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None
}, {
    "airflow_db_model": SlaMiss,
    "age_check_column": SlaMiss.execution_date,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None
}, {
    "airflow_db_model": DagModel,
    "age_check_column": DagModel.last_scheduler_run if AIRFLOW_VERSION < ['2', '0', '2'] else DagModel.last_parsed_time,
    "keep_last": False,
    "keep_last_filters": None,
    "keep_last_group_by": None

# Check for TaskReschedule model
    from airflow.models import TaskReschedule
        "airflow_db_model": TaskReschedule,
        "age_check_column": TaskReschedule.execution_date if AIRFLOW_VERSION < ['2', '2', '0'] else TaskReschedule.start_date,
        "keep_last": False,
        "keep_last_filters": None,
        "keep_last_group_by": None

except Exception as e:

# Check for TaskFail model
    from airflow.models import TaskFail
        "airflow_db_model": TaskFail,
        "age_check_column": TaskFail.execution_date,
        "keep_last": False,
        "keep_last_filters": None,
        "keep_last_group_by": None

except Exception as e:

# Check for RenderedTaskInstanceFields model
    from airflow.models import RenderedTaskInstanceFields
        "airflow_db_model": RenderedTaskInstanceFields,
        "age_check_column": RenderedTaskInstanceFields.execution_date,
        "keep_last": False,
        "keep_last_filters": None,
        "keep_last_group_by": None

except Exception as e:

# Check for ImportError model
    from airflow.models import ImportError
        "airflow_db_model": ImportError,
        "age_check_column": ImportError.timestamp,
        "keep_last": False,
        "keep_last_filters": None,
        "keep_last_group_by": None

except Exception as e:

# Check for celery executor
airflow_executor = str(conf.get("core", "executor"))"Airflow Executor: " + str(airflow_executor))
if (airflow_executor == "CeleryExecutor"):"Including Celery Modules")
        from celery.backends.database.models import Task, TaskSet
            "airflow_db_model": Task,
            "age_check_column": Task.date_done,
            "keep_last": False,
            "keep_last_filters": None,
            "keep_last_group_by": None
        }, {
            "airflow_db_model": TaskSet,
            "age_check_column": TaskSet.date_done,
            "keep_last": False,
            "keep_last_filters": None,
            "keep_last_group_by": None

    except Exception as e:

session = settings.Session()

default_args = {
    "owner": DAG_OWNER_NAME,
    "depends_on_past": False,
    "email_on_failure": True,
    "email_on_retry": False,
    "start_date": START_DATE,
    "retries": 1,
    "retry_delay": timedelta(minutes=1)

dag = DAG(
if hasattr(dag, "doc_md"):
    dag.doc_md = __doc__
if hasattr(dag, "catchup"):
    dag.catchup = False

def print_configuration_function(**context):"Loading Configurations...")
    dag_run_conf = context.get("dag_run").conf"dag_run.conf: " + str(dag_run_conf))
    max_db_entry_age_in_days = None
    if dag_run_conf:
        max_db_entry_age_in_days = dag_run_conf.get(
            "maxDBEntryAgeInDays", None)"maxDBEntryAgeInDays from dag_run.conf: " + str(dag_run_conf))
    if (max_db_entry_age_in_days is None or max_db_entry_age_in_days < 1):
            "maxDBEntryAgeInDays conf variable isn't included or Variable " +
            "value is less than 1. Using Default '" +
            str(DEFAULT_MAX_DB_ENTRY_AGE_IN_DAYS) + "'")
        max_db_entry_age_in_days = DEFAULT_MAX_DB_ENTRY_AGE_IN_DAYS
    max_date = now() + timedelta(-max_db_entry_age_in_days)"Finished Loading Configurations")"")"Configurations:")"max_db_entry_age_in_days: " + str(max_db_entry_age_in_days))"max_date:                 " + str(max_date))"enable_delete:            " + str(ENABLE_DELETE))"session:                  " + str(session))"")"Setting max_execution_date to XCom for Downstream Processes")
    context["ti"].xcom_push(key="max_date", value=max_date.isoformat())

print_configuration = PythonOperator(

def cleanup_function(**context):

    if AIRFLOW_VERSION > ['2', '2', '5']:
        logging.error("The script is not supported for this Airflow Version. "
                      "Skipped deleting the data.")
        return"Retrieving max_execution_date from XCom")
    max_date = context["ti"].xcom_pull(
        task_ids=print_configuration.task_id, key="max_date")
    max_date = dateutil.parser.parse(max_date)  # stored as iso8601 str in xcom

    airflow_db_model = context["params"].get("airflow_db_model")
    state = context["params"].get("state")
    age_check_column = context["params"].get("age_check_column")
    keep_last = context["params"].get("keep_last")
    keep_last_filters = context["params"].get("keep_last_filters")
    keep_last_group_by = context["params"].get("keep_last_group_by")"Configurations:")"max_date:                 " + str(max_date))"enable_delete:            " + str(ENABLE_DELETE))"session:                  " + str(session))"airflow_db_model:         " + str(airflow_db_model))"state:                    " + str(state))"age_check_column:         " + str(age_check_column))"keep_last:                " + str(keep_last))"keep_last_filters:        " + str(keep_last_filters))"keep_last_group_by:       " + str(keep_last_group_by))"")"Running Cleanup Process...")

        query = session.query(airflow_db_model).options(
            load_only(age_check_column))"INITIAL QUERY : " + str(query))

        if keep_last:

            subquery = session.query(func.max(DagRun.execution_date))
            # workaround for MySQL "table specified twice" issue
            if keep_last_filters is not None:
                for entry in keep_last_filters:
                    subquery = subquery.filter(entry)

      "SUB QUERY [keep_last_filters]: " + str(subquery))

            if keep_last_group_by is not None:
                subquery = subquery.group_by(keep_last_group_by)
                    "SUB QUERY [keep_last_group_by]: " +

            subquery = subquery.from_self()

            query = query.filter(
                and_(age_check_column <= max_date))

            query = query.filter(age_check_column <= max_date,)

        if PRINT_DELETES:
            entries_to_delete = query.all()

  "Query: " + str(query))
  "Process will be Deleting the following " +
                         str(airflow_db_model.__name__) + "(s):")
            for entry in entries_to_delete:
                date = str(entry.__dict__[str(age_check_column).split(".")[1]])
      "\tEntry: " + str(entry) + ", Date: " + date)

  "Process will be Deleting "
                         + str(len(entries_to_delete)) + " "
                         + str(airflow_db_model.__name__) + "(s)")
                "You've opted to skip printing the db entries to be deleted. "
                "Set PRINT_DELETES to True to show entries!!!")

        if ENABLE_DELETE:
  "Performing Delete...")
            # using bulk delete
  "Finished Performing Delete")
            logging.warn("You've opted to skip deleting the db entries. "
                         "Set ENABLE_DELETE to True to delete entries!!!")"Finished Running Cleanup Process")

    except ProgrammingError as e:
            str(airflow_db_model) + " is not present in the metadata."

for db_object in DATABASE_OBJECTS:

    cleanup_op = PythonOperator(
        task_id="cleanup_" + str(db_object["airflow_db_model"].__name__),


Remove entries for unused DAGs

You can remove database entries for unused DAGs by removing DAGs from the Airflow web interface.

What's next