[jira] [Created] (SPARK-21408) Default RPC dispatcher thread pool size too large for small executors

["Marcelo Vanzin (JIRA)" <ji...@apache.org>]

Marcelo Vanzin created SPARK-21408:
--------------------------------------

             Summary: Default RPC dispatcher thread pool size too large for small executors
                 Key: SPARK-21408
                 URL: https://issues.apache.org/jira/browse/SPARK-21408
             Project: Spark
          Issue Type: Improvement
          Components: Spark Core
    Affects Versions: 2.3.0
            Reporter: Marcelo Vanzin
            Priority: Minor


This is the code that sizes the RPC dispatcher thread pool:

{noformat}
  private val threadpool: ThreadPoolExecutor = {
    val numThreads = nettyEnv.conf.getInt("spark.rpc.netty.dispatcher.numThreads",
      math.max(2, Runtime.getRuntime.availableProcessors()))
    val pool = ThreadUtils.newDaemonFixedThreadPool(numThreads, "dispatcher-event-loop")
{noformat}

That is based on the number of available cores on the host, instead of the number of cores the executor was told to use. Meaning if you start an executor with a single "core" on a host with 64 CPUs, you'll get 64 threads, which is kinda overkill.

Using the allocated cores + a lower bound is probably a better approach.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

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