GitHub user dreamworks007 opened a pull request:
https://github.com/apache/spark/pull/15616
[SPARK-16827][Shuffle] add disk spill bytes to UnsafeExternalSorter
## What changes were proposed in this pull request?
disk spill bytes metrics was disabled due to apache/spark#15347. This PR
adds that metrics.
## How was this patch tested?
Integration test with the following query:
val hc = new org.apache.spark.sql.hive.PlasmaHiveContext(sc).xyz_namespace
hc.sql("SET spark.sql.shuffle.partitions=800")
val sqlString = """
SELECT a.target_id AS userid
FROM table_a a
JOIN table_b b
ONa.ds = '2016-07-15'
AND b.ds = '2016-07-15'
AND a.source_id = b.id"""
hc.sql(sqlString).count()
in 1.6, in stage 2 , it does not have spill bytes metrics reporting, and in
2.0 (with my change) , in stage 2, it has the spill bytes metrics reported
Spark 1.6 -
Spark 2.0 -
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/dreamworks007/spark oss_spill_metrics
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/15616.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 #15616
commit cbf933d0b20bfbd9840506270885caa14bbb5bce
Author: dreamworks007
Date: 2016-10-24T21:09:17Z
first commit - oss add spill metrics for UnsafeExternalSorter
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
