Reduce task stalls due to a task fail & resumes on retry

2014-02-12 13:50:40,829 INFO [AsyncDispatcher event handler] org.apache.tez.dag.history.HistoryEventHandler: [HISTORY][DAG:dag_1392067467498_0279_3][Event:TASK_ATTEMPT_FINISHED]: vertexName=Reducer 3, taskAttemptId=attempt_1392067467498_0279_3_02_000102_0, startTime=1392241839503, finishTime=1392241840829, timeTaken=1326, status=FAILED, diagnostics=Error: java.lang.IllegalStateException: All inputs are expected to ask for memory
    at com.google.common.base.Preconditions.checkState(Preconditions.java:150)
    at org.apache.tez.runtime.common.resources.MemoryDistributor.makeInitialAllocations(MemoryDistributor.java:122)
    at org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.initialize(LogicalIOProcessorRuntimeTask.java:195)
    at org.apache.hadoop.mapred.YarnTezDagChild$4.run(YarnTezDagChild.java:503)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:415)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
    at org.apache.hadoop.mapred.YarnTezDagChild.main(YarnTezDagChild.java:496)
, counters=Counters: 17, org.apache.tez.common.counters.TaskCounter, MAP_OUTPUT_RECORDS=0, MAP_OUTPUT_BYTES=0, MAP_OUTPUT_MATERIALIZED_BYTES=0, COMBINE_INPUT_RECORDS=0, REDUCE_INPUT_GROUPS=0, REDUCE_SHUFFLE_BYTES=0, REDUCE_INPUT_RECORDS=0, SPILLED_RECORDS=0, SHUFFLED_MAPS=0, FAILED_SHUFFLE=0, MERGED_MAP_OUTPUTS=0, Shuffle Errors, BAD_ID=0, CONNECTION=0, IO_ERROR=0, WRONG_LENGTH=0, WRONG_MAP=0, WRONG_REDUCE=0
2014-02-12 13:50:40,829 INFO [AsyncDispatcher event handler] org.apache.tez.dag.app.dag.impl.TaskAttemptImpl: attempt_1392067467498_0279_3_02_000102_0 TaskAttempt Transitioned from RUNNING to FAIL_IN_PROGRESS due to event TA_FAILED