GitHub user Ru-Xiang reopened a pull request:
https://github.com/apache/spark/pull/16033
SPARK-18607 get a result on a percent of the tasks succeed
## What changes were proposed in this pull request?
In this patch, we modify the codes corresponding to runApproximateJob so
that we can get a result when the specified percent of tasks succeed.
In a production environment, 'long tail' is a common urgent problem. In
practice, as long as we can get a specified percent of tasks' results, we can
guarantee the final results. And this is a common requirement in the practice
of machine learning algorithms.
## How was this patch tested?
We compile the codes by dev/make-distribution.sh, and deploy it on a
cluster. and run a test codes reduce on the cluster, and we get the desired
results.
https://issues.apache.org/jira/browse/SPARK-18607
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/Ru-Xiang/spark my_change
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/16033.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 #16033
----
commit 62691543505526f25f0f962c7bbaebe6d04510f5
Author: Aplysia <[email protected]>
Date: 2016-12-04T12:24:17Z
Get a result while having a percent of the tasks succeed
----
---
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]
