nehsyc commented on a change in pull request #14723:
URL: https://github.com/apache/beam/pull/14723#discussion_r643459194
##########
File path:
sdks/python/apache_beam/io/gcp/datastore/v1new/rampup_throttling_fn.py
##########
@@ -0,0 +1,80 @@
+import datetime
+import logging
+import time
+from typing import TypeVar
+
+from apache_beam import typehints
+from apache_beam.io.gcp.datastore.v1new import util
+from apache_beam.transforms import DoFn
+from apache_beam.utils.retry import FuzzedExponentialIntervals
+
+T = TypeVar('T')
+
+_LOG = logging.getLogger(__name__)
+
+
[email protected]_input_types(T)
[email protected]_output_types(T)
+class RampupThrottlingFn(DoFn):
+ """A ``DoFn`` that throttles ramp-up following an exponential function.
+
+ An implementation of a client-side throttler that enforces a gradual ramp-up,
+ broadly in line with Datastore best practices. See also
+ https://cloud.google.com/datastore/docs/best-practices#ramping_up_traffic.
+ """
+ def to_runner_api_parameter(self, unused_context):
+ from apache_beam.internal import pickler
+ config = {
+ 'num_workers': self._num_workers,
+ }
+ return 'beam:fn:rampup_throttling:v0', pickler.dumps(config)
+
+ _BASE_BUDGET = 500
+ _RAMP_UP_INTERVAL = datetime.timedelta(minutes=5)
+
+ def __init__(self, num_workers, *unused_args, **unused_kwargs):
+ """Initializes a ramp-up throttler transform.
+
+ Args:
+ num_workers: A hint for the expected number of workers, used to derive
+ the local rate limit.
+ """
+ super(RampupThrottlingFn, self).__init__(*unused_args, **unused_kwargs)
+ self._num_workers = num_workers
+ self._successful_ops = util.MovingSum(window_ms=1000, bucket_ms=1000)
+ self._first_instant = datetime.datetime.now()
+
+ def _calc_max_ops_budget(
+ self,
+ first_instant: datetime.datetime,
+ current_instant: datetime.datetime):
+ """Function that returns per-second budget according to best practices.
+
+ The exact function is `500 / num_shards * 1.5^max(0, (x-5)/5)`, where x is
Review comment:
nit: num_workers to align with the variable name
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
