[
https://issues.apache.org/jira/browse/BEAM-4783?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Kyle Winkelman updated BEAM-4783:
---------------------------------
Description:
When the spark-runner is used along with the configuration
spark.dynamicAllocation.enabled=true the SourceRDD does not detect this. It
then falls back to the value calculated in this description:
// when running on YARN/SparkDeploy it's the result of max(totalCores, 2).
// when running on Mesos it's 8.
// when running local it's the total number of cores (local = 1, local[N]
= N,
// local[*] = estimation of the machine's cores).
// ** the configuration "spark.default.parallelism" takes precedence over
all of the above **
So in most cases this default is quite small. This is an issue when using a
very large input file as it will only get split in half.
I believe that when Dynamic Allocation is enable the SourceRDD should use the
DEFAULT_BUNDLE_SIZE and possibly expose a SparkPipelineOptions that allows you
to change this DEFAULT_BUNDLE_SIZE.
was:
When the spark-runner is used along with the configuration
spark.dynamicAllocation.enabled=true the SourceRDD does not detect this. It
then falls back to the value calculated in this description: 'when running on
YARN/SparkDeploy it's the result of max(totalCores, 2)'. The totalCores is
--executor-cores multiplied with --num-executors so this ends up being 2 in the
most common case. This is an issue when using a very large input file as it
will only get split in half.
I believe that when Dynamic Allocation is enable the SourceRDD should use the
DEFAULT_BUNDLE_SIZE and possibly expose a SparkPipelineOptions that allows you
to change this DEFAULT_BUNDLE_SIZE.
> Spark SourceRDD Not Designed With Dynamic Allocation In Mind
> ------------------------------------------------------------
>
> Key: BEAM-4783
> URL: https://issues.apache.org/jira/browse/BEAM-4783
> Project: Beam
> Issue Type: Improvement
> Components: runner-spark
> Affects Versions: 2.5.0
> Reporter: Kyle Winkelman
> Assignee: Amit Sela
> Priority: Major
> Labels: newbie
>
> When the spark-runner is used along with the configuration
> spark.dynamicAllocation.enabled=true the SourceRDD does not detect this. It
> then falls back to the value calculated in this description:
> // when running on YARN/SparkDeploy it's the result of max(totalCores,
> 2).
> // when running on Mesos it's 8.
> // when running local it's the total number of cores (local = 1,
> local[N] = N,
> // local[*] = estimation of the machine's cores).
> // ** the configuration "spark.default.parallelism" takes precedence
> over all of the above **
> So in most cases this default is quite small. This is an issue when using a
> very large input file as it will only get split in half.
> I believe that when Dynamic Allocation is enable the SourceRDD should use the
> DEFAULT_BUNDLE_SIZE and possibly expose a SparkPipelineOptions that allows
> you to change this DEFAULT_BUNDLE_SIZE.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
