You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "zhoukang (JIRA)" <ji...@apache.org> on 2019/01/01 05:08:00 UTC

[jira] [Created] (SPARK-26514) Introduce a new conf to improve the task parallelism

zhoukang created SPARK-26514:
--------------------------------

             Summary: Introduce a new conf to improve the task parallelism
                 Key: SPARK-26514
                 URL: https://issues.apache.org/jira/browse/SPARK-26514
             Project: Spark
          Issue Type: Improvement
          Components: Spark Core
    Affects Versions: 2.4.0, 2.1.0
            Reporter: zhoukang


Currently, we have a conf below.
{code:java}
private[spark] val CPUS_PER_TASK = ConfigBuilder("spark.task.cpus").intConf.createWithDefault(1)
{code}
For some applications which are not cpu-intensive,we may want to let one cpu to run more than one task.
Like:
{code:java}
private[spark] val TASKS_PER_CPU = ConfigBuilder("spark.cpu.tasks").intConf.createWithDefault(1)
{code}
Which can improve performance for some applications and can also improve resource utilization




--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org