[
https://issues.apache.org/jira/browse/SPARK-26941?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
liupengcheng updated SPARK-26941:
---------------------------------
Component/s: YARN
Summary: maxNumExecutorFailures should be computed with
spark.streaming.dynamicAllocation.maxExecutors in ApplicationMaster for
streaming (was: maxNumExecutorFailures should be computed with
spark.streaming.dynamicAllocation.maxExecutors in streaming )
> maxNumExecutorFailures should be computed with
> spark.streaming.dynamicAllocation.maxExecutors in ApplicationMaster for
> streaming
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-26941
> URL: https://issues.apache.org/jira/browse/SPARK-26941
> Project: Spark
> Issue Type: Bug
> Components: Spark Core, YARN
> Affects Versions: 2.1.0, 2.4.0
> Reporter: liupengcheng
> Priority: Major
>
> Currently, when enabled streaming dynamic allocation for streaming
> applications, the maxNumExecutorFailures in ApplicationMaster is still
> computed with `spark.dynamicAllocation.maxExecutors`.
> Actually, we should consider `spark.streaming.dynamicAllocation.maxExecutors`
> instead.
> Related codes:
> {code:java}
> private val maxNumExecutorFailures = {
> val effectiveNumExecutors =
> if (Utils.isStreamingDynamicAllocationEnabled(sparkConf)) {
> sparkConf.get(STREAMING_DYN_ALLOCATION_MAX_EXECUTORS)
> } else if (Utils.isDynamicAllocationEnabled(sparkConf)) {
> sparkConf.get(DYN_ALLOCATION_MAX_EXECUTORS)
> } else {
> sparkConf.get(EXECUTOR_INSTANCES).getOrElse(0)
> }
> // By default, effectiveNumExecutors is Int.MaxValue if dynamic allocation
> is enabled. We need
> // avoid the integer overflow here.
> val defaultMaxNumExecutorFailures = math.max(3,
> if (effectiveNumExecutors > Int.MaxValue / 2) Int.MaxValue else (2 *
> effectiveNumExecutors))
>
> sparkConf.get(MAX_EXECUTOR_FAILURES).getOrElse(defaultMaxNumExecutorFailures)
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
