Shuffle Errors on heavy load (causing task retries)

org.apache.tez.runtime.library.common.shuffle.impl.Shuffle: ShuffleRunner failed with error
org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$ShuffleError: error in shuffle in fetcher [initialmap] #13
at org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$RunShuffleCallable.call(Shuffle.java:336)
at org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$RunShuffleCallable.call(Shuffle.java:318)
at java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:334)
at java.util.concurrent.FutureTask.run(FutureTask.java:166)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:722)
Caused by: java.lang.NullPointerException
at org.apache.hadoop.io.WritableUtils.readVLong(WritableUtils.java:308)
at org.apache.hadoop.io.WritableUtils.readVInt(WritableUtils.java:329)
at org.apache.hadoop.io.WritableUtils.readStringSafely(WritableUtils.java:475)
at org.apache.tez.runtime.library.common.shuffle.impl.ShuffleHeader.readFields(ShuffleHeader.java:82)
at org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.copyMapOutput(Fetcher.java:350)
at org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.copyFromHost(Fetcher.java:294)
at org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.run(Fetcher.java:160)