GitHub user jinxing64 opened a pull request:
https://github.com/apache/spark/pull/17276
[WIP][SPARK-19937] Collect metrics of block sizes when shuffle.
## What changes were proposed in this pull request?
Metrics of blocks sizes(when shuffle) should be collected for later
analysis. This is helpful for analysis when skew situations or OOM
happens(though maxBytesInFlight is set).
This pr proposes to:
1. Store the distribution of sizes in `MapStatus` and count the block sizes
in ranges
[0, 1k), [1k, 10k), [10k, 100k), [100k, 1m), [1m, 10m), [10m, 100m), [100m,
1g), [1g, 10g), [10g, Long.MaxValue).
2. Record the inaccuracy of block sizes. Because
`HighlyCompressedMapStatus` is returned and only average size is recorded when
block sizes is over 2000.
## How was this patch tested?
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/jinxing64/spark SPARK-19937
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/17276.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 #17276
----
commit 430ec95291393f49096fc07df98c15e700f23e8c
Author: jinxing <[email protected]>
Date: 2017-03-13T13:35:51Z
[SPARK-19937] Collect metrics of block sizes when shuffle.
----
---
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]
