GitHub user kayousterhout opened a pull request:

    https://github.com/apache/spark/pull/1762

    Remove support for waiting for executors in standalone mode.

    Current code waits until some minimum fraction of expected executors
    have registered before beginning scheduling.  The current code in
    standalone mode suffers from a race condition (SPARK-2635). This
    race condition could be fixed, but this functionality is easily
    achieved by the user (they can use the storage status to determine
    how many executors are up, as described by @pwendell in #1462)
    so adding the extra complexity to the scheduler code may not be worthwhile.
    
    This commit removes the functionality in standalone mode but not for
    YARN -- where it is more necessary and the number of expected executors
    is well-defined.
    
    This PR is a POC; if the powers-that-be determine that this is what we 
should
    do, I will file a JIRA.
    
    This should be backported into 1.1 if committed.

You can merge this pull request into a Git repository by running:

    $ git pull https://github.com/kayousterhout/spark-1 remove_executor_wait

Alternatively you can review and apply these changes as the patch at:

    https://github.com/apache/spark/pull/1762.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #1762
    
----
commit fa746ed65a8ac685edd33c79159521398d99aa69
Author: Kay Ousterhout <[email protected]>
Date:   2014-08-04T06:59:05Z

    Remove support for waiting for executors in standalone mode.
    
    Current code waits until some minimum fraction of expected executors
    have registered before beginning scheduling.  The current code in
    standalone mode suffers from a race condition (SPARK-2635). This
    race condition could be fixed, but this functionality is easily
    achieved by the user (they can use the storage status to determine
    how many executors are up, as described by @pwendell in #1462)
    so adding the extra complexity to the scheduler code is not worthwile.

----


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to