Github user tillrohrmann commented on the issue: https://github.com/apache/flink/pull/6103 With [FLINK-5129](https://issues.apache.org/jira/browse/FLINK-5129) which is part of Flink 1.3.0, we allow the `BlobCache` to retrieve the blobs from the HA storage location. In your case this seems to be HDFS. The idea was that this should alleviate the I/O pressure from the `JobManager` because not all blobs are served by a single node. Thus, this should rather improve the situation with this issue.
---