pankajastro commented on code in PR #30853:
URL: https://github.com/apache/airflow/pull/30853#discussion_r1185321640
##########
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),
Review Comment:
why we are casting here to str?
##########
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))
+ if attempt >= int(self.max_attempts):
+ yield TriggerEvent(
+ {"status": "failure", "message": "Resume Cluster Failed - max
attempts reached."}
+ )
+ else:
Review Comment:
does it makes sense to check status before marking success
##########
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))
+ if attempt >= int(self.max_attempts):
+ yield TriggerEvent(
+ {"status": "failure", "message": "Resume Cluster Failed - max
attempts reached."}
Review Comment:
why resume cluster, typo?
##########
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)
Review Comment:
I think we won't be able to use waiter which Boto lib provides for example
in create cluster we are using
https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/redshift/waiter/ClusterAvailable.html
??
Here, I believe you are handling it but in general, for all triggers, we
will have to
- wait for desired state + all terminal state
- When either we reach the desired state or terminal state or are done with
all the attempts check the state and based on that mark the task fail or
success
##########
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 agree with @pankajkoti waiter having 1 attempt is a bit unnatural
--
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]
