Github user omuravskiy commented on a diff in the pull request: https://github.com/apache/spark/pull/16006#discussion_r91035292 --- Diff: external/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka010/DirectKafkaInputDStream.scala --- @@ -67,6 +67,10 @@ private[spark] class DirectKafkaInputDStream[K, V]( ekp } + val backpressureInitialRate: Long = + _ssc.sparkContext.conf.getLong("spark.streaming.backpressure.initialRate", + 1 + _ssc.sparkContext.conf.getLong("spark.streaming.kafka.maxRatePerPartition", 1000L) / 10) + --- End diff -- It is to supply just a 10% of the maximum rate at the start of execution, while workers are still warming up. At least on my system this starting rate works nicely, gradually increasing the rate without building a backlog of stages.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org