pankajkoti commented on code in PR #30853:
URL: https://github.com/apache/airflow/pull/30853#discussion_r1184756193
##########
airflow/providers/amazon/aws/triggers/redshift_cluster.py:
##########
@@ -137,3 +140,70 @@ async def run(self):
},
)
yield TriggerEvent({"status": "success", "message": "Cluster Created"})
+
+
+class RedshiftPauseClusterTrigger(BaseTrigger):
+ """
+ Trigger for RedshiftPauseClusterOperator.
+ The trigger will asynchronously poll the boto3 API and wait for the
+ Redshift cluster to be in the `paused` state.
+
+ :param cluster_identifier: A unique identifier for the cluster.
+ :param poll_interval: The amount of time in seconds to wait between
attempts.
+ :param max_attempts: The maximum number of attempts to be made.
+ :param aws_conn_id: The Airflow connection used for AWS credentials.
+ """
+
+ def __init__(
+ self,
+ cluster_identifier: str,
+ poll_interval: int,
+ max_attempts: int,
+ aws_conn_id: str,
+ ):
+ self.cluster_identifier = cluster_identifier
+ self.poll_interval = poll_interval
+ self.max_attempts = max_attempts
+ self.aws_conn_id = aws_conn_id
+
+ def serialize(self) -> tuple[str, dict[str, Any]]:
+ return (
+
"airflow.providers.amazon.aws.triggers.redshift_cluster.RedshiftPauseClusterTrigger",
+ {
+ "cluster_identifier": str(self.cluster_identifier),
+ "poll_interval": str(self.poll_interval),
+ "max_attempts": str(self.max_attempts),
+ "aws_conn_id": str(self.aws_conn_id),
+ },
+ )
+
+ @cached_property
+ def hook(self) -> RedshiftHook:
+ return RedshiftHook(aws_conn_id=self.aws_conn_id)
+
+ async def run(self):
+ async with self.hook.async_conn as client:
+ attempt = 0
+ while attempt < int(self.max_attempts):
+ attempt = attempt + 1
+ try:
+ waiter = self.hook.get_waiter("cluster_paused",
deferrable=True, client=client)
+ await waiter.wait(
+ ClusterIdentifier=self.cluster_identifier,
+ WaiterConfig={
+ "Delay": int(self.poll_interval),
+ "MaxAttempts": 1,
Review Comment:
I get the hack and looks like a good workaround for now, but then don't we
lose the purpose of using waiters if we're setting `MaxAttempts` to 1? With
this, will it have an additional overhead of getting the waiter for each
attempt and launching it?
##########
airflow/providers/amazon/aws/triggers/redshift_cluster.py:
##########
@@ -137,3 +140,70 @@ async def run(self):
},
)
yield TriggerEvent({"status": "success", "message": "Cluster Created"})
+
+
+class RedshiftPauseClusterTrigger(BaseTrigger):
+ """
+ Trigger for RedshiftPauseClusterOperator.
+ The trigger will asynchronously poll the boto3 API and wait for the
+ Redshift cluster to be in the `paused` state.
+
+ :param cluster_identifier: A unique identifier for the cluster.
+ :param poll_interval: The amount of time in seconds to wait between
attempts.
+ :param max_attempts: The maximum number of attempts to be made.
+ :param aws_conn_id: The Airflow connection used for AWS credentials.
+ """
+
+ def __init__(
+ self,
+ cluster_identifier: str,
+ poll_interval: int,
+ max_attempts: int,
+ aws_conn_id: str,
+ ):
+ self.cluster_identifier = cluster_identifier
+ self.poll_interval = poll_interval
+ self.max_attempts = max_attempts
+ self.aws_conn_id = aws_conn_id
+
+ def serialize(self) -> tuple[str, dict[str, Any]]:
+ return (
+
"airflow.providers.amazon.aws.triggers.redshift_cluster.RedshiftPauseClusterTrigger",
+ {
+ "cluster_identifier": str(self.cluster_identifier),
+ "poll_interval": str(self.poll_interval),
+ "max_attempts": str(self.max_attempts),
+ "aws_conn_id": str(self.aws_conn_id),
+ },
+ )
+
+ @cached_property
+ def hook(self) -> RedshiftHook:
+ return RedshiftHook(aws_conn_id=self.aws_conn_id)
+
+ async def run(self):
+ async with self.hook.async_conn as client:
+ attempt = 0
+ while attempt < int(self.max_attempts):
+ attempt = attempt + 1
+ try:
+ waiter = self.hook.get_waiter("cluster_paused",
deferrable=True, client=client)
+ await waiter.wait(
+ ClusterIdentifier=self.cluster_identifier,
+ WaiterConfig={
+ "Delay": int(self.poll_interval),
+ "MaxAttempts": 1,
+ },
+ )
+ break
+ except WaiterError as error:
+ self.log.info(
+ "Status of cluster is %s",
error.last_response["Clusters"][0]["ClusterStatus"]
+ )
+ await asyncio.sleep(int(self.poll_interval))
Review Comment:
Shouldn't we re-raise the `WaiterError` here? If the waiter reaches a
failure path, it would be good if we don't wait for all the attempts to finish.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
