Yuming Wang created SPARK-19146:
-----------------------------------
Summary: Drop more elements when stageData.taskData.size >
retainedTasks to reduce the number of times on call drop
Key: SPARK-19146
URL: https://issues.apache.org/jira/browse/SPARK-19146
Project: Spark
Issue Type: Improvement
Components: Spark Core
Affects Versions: 2.1.0
Reporter: Yuming Wang
The performance of the
[{{drop}}|https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala#L412]
function is bad.
* Modify the code:
{code:java}
if (stageData.taskData.size > retainedTasks) {
val start = System.currentTimeMillis()
stageData.taskData = stageData.taskData.drop(stageData.taskData.size -
retainedTasks)
logInfo(s"Time consuming: ${System.currentTimeMillis() - start}")
}
{code}
* Time consuming
{noformat}
17/01/10 14:04:05 INFO JobProgressListener: Time consuming: 156
17/01/10 14:04:05 INFO JobProgressListener: Time consuming: 145
17/01/10 14:04:05 INFO JobProgressListener: Time consuming: 148
17/01/10 14:04:05 INFO JobProgressListener: Time consuming: 159
{noformat}
My opinion is drop more elements when {{stageData.taskData.size >
retainedTasks}} to reduce the number of times on call {{drop}}.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
