def block_until_done(client, bq_job):
def _is_done(job_id):
return client.get_job(job_id).state in ["PENDING", "RUNNING"]
@retry(wait=wait_fixed(10), stop=stop_after_delay(1800), reraise=True)
def _wait_until_done(job_id):
return _is_done(job_id)
job_id = bq_job.job_id
_wait_until_done(job_id=job_id)
if not _is_done(job_id):
client.cancel_job(job_id)
raise BigQueryJobCancelled(job_id=job_id)
if bq_job.exception():
raise bq_job.exception()
def block_until_done(
client: Client,
bq_job: Union[bigquery.job.query.QueryJob, bigquery.job.load.LoadJob],
timeout: int = 1800,
retry_cadence: float = 1,
):
"""
Waits for bq_job to finish running, up to a maximum amount of time specified by the timeout parameter (defaulting to 30 minutes).
Args:
client: A bigquery.client.Client to monitor the bq_job.
bq_job: The bigquery.job.QueryJob that blocks until done runnning.
timeout: An optional number of seconds for setting the time limit of the job.
retry_cadence: An optional number of seconds for setting how long the job should checked for completion.
Raises:
BigQueryJobStillRunning exception if the function has blocked longer than 30 minutes.
BigQueryJobCancelled exception to signify when that the job has been cancelled (i.e. from timeout or KeyboardInterrupt).
"""
# For test environments, retry more aggressively
if flags_helper.is_test():
retry_cadence = 0.1
def _wait_until_done(bq_job):
if client.get_job(bq_job).state in ["PENDING", "RUNNING"]:
raise BigQueryJobStillRunning(job_id=bq_job.job_id)
try:
retryer = Retrying(
wait=wait_fixed(retry_cadence),
stop=stop_after_delay(timeout),
retry=retry_if_exception_type(BigQueryJobStillRunning),
reraise=True,
)
retryer(_wait_until_done, bq_job)
finally:
if client.get_job(bq_job).state in ["PENDING", "RUNNING"]:
client.cancel_job(bq_job)
raise BigQueryJobCancelled(job_id=bq_job.job_id)
if bq_job.exception():
raise bq_job.exception()