場景：在gremlin終端中通過Hadoop-gremlin批量導入生成json，
graph = GraphFactory.open('data/zl/hadoop-load-company-modern.properties')
blvp = BulkLoaderVertexProgram.build().bulkLoader(OneTimeBulkLoader).writeGraph('data/zl/company-hbase-es.properties').create(graph)
graph.compute(SparkGraphComputer).program(blvp).submit().get()
出現了如下錯誤：
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 1 times, most recent failure: Lost task 0.0 in stage 5.0 (TID 3, localhost): java.util.NoSuchElementException
at org.apache.tinkerpop.gremlin.process.traversal.util.DefaultTraversal.next(DefaultTraversal.java:204)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoader.getVertexById(BulkLoader.java:116)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.lambda$executeInternal$4(BulkLoaderVertexProgram.java:251)
at java.util.Iterator.forEachRemaining(Unknown Source)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.executeInternal(BulkLoaderVertexProgram.java:249)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.execute(BulkLoaderVertexProgram.java:197)
at org.apache.tinkerpop.gremlin.spark.process.computer.SparkExecutor.lambda$null$5(SparkExecutor.java:118)
at org.apache.tinkerpop.gremlin.util.iterator.IteratorUtils$3.next(IteratorUtils.java:247)
at scala.collection.convert.Wrappers$JIteratorWrapper.next(Wrappers.scala:43)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:462)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:439)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:920)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:918)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:918)
at org.apache.spark.api.java.JavaRDDLike$class.foreachPartition(JavaRDDLike.scala:225)
at org.apache.spark.api.java.AbstractJavaRDDLike.foreachPartition(JavaRDDLike.scala:46)
at org.apache.tinkerpop.gremlin.spark.process.computer.SparkExecutor.executeVertexProgramIteration(SparkExecutor.java:179)
at org.apache.tinkerpop.gremlin.spark.process.computer.SparkGraphComputer.lambda$submitWithExecutor$0(SparkGraphComputer.java:279)
at java.util.concurrent.FutureTask.run(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.util.NoSuchElementException
at org.apache.tinkerpop.gremlin.process.traversal.util.DefaultTraversal.next(DefaultTraversal.java:204)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoader.getVertexById(BulkLoader.java:116)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.lambda$executeInternal$4(BulkLoaderVertexProgram.java:251)
at java.util.Iterator.forEachRemaining(Unknown Source)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.executeInternal(BulkLoaderVertexProgram.java:249)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.execute(BulkLoaderVertexProgram.java:197)
at org.apache.tinkerpop.gremlin.spark.process.computer.SparkExecutor.lambda$null$5(SparkExecutor.java:118)
at org.apache.tinkerpop.gremlin.util.iterator.IteratorUtils$3.next(IteratorUtils.java:247)
at scala.collection.convert.Wrappers$JIteratorWrapper.next(Wrappers.scala:43)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:462)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:439)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
... 3 more
問題是java.util.NoSuchElementException，但是這個問題很不明確，我想知道更具體的錯誤，比如是json文件中的那條記錄產生了這個影響等。
解決：讓其打印更詳細的信息
由上面錯誤知道在調用at org.apache.tinkerpop.gremlin.process.traversal.util.DefaultTraversal.next方法時出現了NoSuchElementException異常
經過查詢知道org.apache.tinkerpop.gremlin.process.traversal.util.DefaultTraversal是gremlin-core-x.x.x.jar包中的類。
通過修改gremlin-core-xxx模塊，在合適的方法處讓其打印更詳細的日志信息。
gremlin-core是tinkerpop項目中的一個模塊，所以git clone https://github.com/apache/tinkerpop.git 修改gremlin-core模塊，讓其打印更詳細信息。
最后將編譯好的gremlin-core-x.x.x.jar替換掉janusgraph-0.2.0-hadoop2\lib目錄中的版本
最后錯誤如下，讓其打印出了頂點id邊等信息，
16:13:27 ERROR org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram - ???????:sourceVertex=v[eefbad45-a079-4883-b936-42817618f094]edge=e[e4d13af5-ff29-4646-a06d-9ee20cfe8f8e][eefbad45-a079-4883-b936-42817618f094-class_staff_2_staff->82e1e894-3abc-41e5-ba16-7bba53a7df67]
16:13:27 ERROR org.apache.spark.executor.Executor - Managed memory leak detected; size = 5309058 bytes, TID = 3
16:13:27 ERROR org.apache.spark.executor.Executor - Exception in task 0.0 in stage 5.0 (TID 3)
java.util.NoSuchElementException
at org.apache.tinkerpop.gremlin.process.traversal.util.DefaultTraversal.next(DefaultTraversal.java:204)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoader.getVertexById(BulkLoader.java:116)
at org.apache.tinkerpop.gremlin.process.computer.bulkloading.BulkLoaderVertexProgram.lambda$executeInternal$4(BulkLoaderVertexProgram.java:255)
at java.util.Iterator.forEachRemaining(Unknown Source)
- 經查看json文件，82e1e894-3abc-41e5-ba16-7bba53a7df67頂點的json數據和前一條數據并排放了，而導入的json文件中的json數據必須是一個頂點數據的json占一行。
結論
- json文件數據格式有誤產生的，一個頂點的json數據應該占用一行，而不是并排放置。）
- 最后產生錯誤的原因很簡單，但是找錯卻比較費事，其實針對上面這個問題，在知道json格式應該是單行顯示情況下，通過上面的錯誤提示，采用小黃鴨調試法應該就能找出原因的，但是，桌子上沒有小黃鴨?。?！
