Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/18940#discussion_r133077743
--- Diff:
common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java
---
@@ -104,15 +105,22 @@ public
GitHub user redsanket opened a pull request:
https://github.com/apache/spark/pull/18940
YSPARK-734 Change CacheLoader to limit entries based on memory footprint
Right now the spark shuffle service has a cache for index files. It is
based on a # of files cached
