forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Reduce run time of StorageUtils.updateRddInfo to near constant
With the existing changes in the PR, the StorageListener still needed to iterate through all the blocks within a single RDD. Although this is already much better than before, it is still slow if a single RDD has many partitions. This commit further reduces the run time of StorageUtils.updateRddInfo to near constant. It achieves this by incrementally updating the storage information of each RDD (memory, disk, tachyon sizes) incrementally, rather than all at once when the caller demands it. A preliminary benchmark shows that the event queue length never exceeds 600 even for caching 10000 partitions within a single RDD. An important TODO is to add tests for the new code, as well as for the StorageListener, the source of the storage information on the UI.
- Loading branch information
1 parent
2c3ef6a
commit e080b9e
Showing
4 changed files
with
114 additions
and
94 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters