You are viewing a plain text version of this content. The canonical link for it is here.

Posted to user@spark.apache.org by Sung Hwan Chung <co...@cs.stanford.edu> on 2014/07/31 01:02:49 UTC

Spark fault tolerance after a executor failure.

I sometimes see that after fully caching the data, if one of the executors
fails for some reason, that portion of cache gets lost and does not get
re-cached, even though there are plenty of resources. Is this a bug or a
normal behavior (V1.0.1)?