You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@tez.apache.org by "Rajesh Balamohan (JIRA)" <ji...@apache.org> on 2014/08/25 14:47:58 UTC

[jira] [Created] (TEZ-1494) DAG hangs waiting for ShuffleManager.getNextInput()

Rajesh Balamohan created TEZ-1494:
-------------------------------------

             Summary: DAG hangs waiting for ShuffleManager.getNextInput()
                 Key: TEZ-1494
                 URL: https://issues.apache.org/jira/browse/TEZ-1494
             Project: Apache Tez
          Issue Type: Bug
            Reporter: Rajesh Balamohan
            Assignee: Rajesh Balamohan


Attaching the DAG and the stack trace of the hung process.  

digraph rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1 {
graph [ label="rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1", fontsize=24, fontname=Helvetica];
node [fontsize=12, fontname=Helvetica];
edge [fontsize=9, fontcolor=blue, fontname=Arial];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_1" [ label = "Map_1[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_1" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_7" [ label = "Map_7[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_7" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_6_out_Reducer_6" [ label = "Reducer_6[out_Reducer_6]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_8" [ label = "Map_8[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_8" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_4_date_dim" [ label = "Map_4[date_dim]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_4_date_dim" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_4" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5" [ label = "Map_5[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_6" [ label = "[input=OrderedPartitionedKVOutput,\n output=OrderedGroupedKVInput,\n dataMovement=SCATTER_GATHER,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_8_customer_address" [ label = "Map_8[customer_address]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_8_customer_address" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_8" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2_store_sales" [ label = "Map_2[store_sales]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2_store_sales" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_1_household_demographics" [ label = "Map_1[household_demographics]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_1_household_demographics" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_1" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_9" [ label = "Map_9[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_9" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5_customer" [ label = "Map_5[customer]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5_customer" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_7_current_addr" [ label = "Map_7[current_addr]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_7_current_addr" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_7" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_6" [ label = "Reducer_6[ReduceTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_6" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_6_out_Reducer_6" [ label = "Output [outputClass=MROutput,\n initializer=]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_4" [ label = "Map_4[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_4" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" [ label = "Map_2[MapTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_2" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_3" [ label = "[input=OrderedPartitionedKVOutput,\n output=OrderedGroupedKVInput,\n dataMovement=SCATTER_GATHER,\n schedulingType=SEQUENTIAL]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_9_store" [ label = "Map_9[store]", shape = "box" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_9_store" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_9" [ label = "Input [inputClass=MRInputLegacy,\n initializer=HiveSplitGenerator]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_3" [ label = "Reducer_3[ReduceTezProcessor]" ];
"rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Reducer_3" -> "rajesh_20140825050909_6206d911_7de1_47aa_8788_dd9ffcc9ad36_1.Map_5" [ label = "[input=UnorderedKVOutput,\n output=UnorderedKVInput,\n dataMovement=BROADCAST,\n schedulingType=SEQUENTIAL]" ];
}




Thread 30071: (state = BLOCKED)
 - sun.misc.Unsafe.park(boolean, long) @bci=0 (Interpreted frame)
 - java.util.concurrent.locks.LockSupport.park(java.lang.Object) @bci=14, line=186 (Interpreted frame)
 - java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await() @bci=42, line=2043 (Interpreted frame)
 - java.util.concurrent.LinkedBlockingQueue.take() @bci=29, line=442 (Interpreted frame)
 - org.apache.tez.runtime.library.shuffle.common.impl.ShuffleManager.getNextInput() @bci=67, line=610 (Interpreted frame)
 - org.apache.tez.runtime.library.common.readers.UnorderedKVReader.moveToNextInput() @bci=26, line=176 (Interpreted frame)
 - org.apache.tez.runtime.library.common.readers.UnorderedKVReader.next() @bci=30, line=117 (Interpreted frame)



--
This message was sent by Atlassian JIRA
(v6.2#6252)