dev
environment spark.2.1.1 carbondata 1.1.1 hadoop 2.7.2 add debug information Block B-tree loading faile why CarbonUtil.calculateMetaSize Calculation results getBlockLength=0 getBlockOffset=8301549 ? Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata :getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 1 debug information scala> cc.sql("select prod_inst_id,count(*) from e_carbon.prod_inst_his1023c group by prod_inst_id having count(*)>1").show [Stage 0:=============================> (157 + 50) / 283]17/10/30 10:39:24 WARN scheduler.TaskSetManager: Lost task 252.0 in stage 0.0 (TID 201, HDD010, executor 22): org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more [Stage 0:==========================================> (223 + 50) / 283]17/10/30 10:39:26 ERROR scheduler.TaskSetManager: Task 252 in stage 0.0 failed 10 times; aborting job 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 61.0 in stage 0.0 (TID 184, HDD012, executor 7): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 71.0 in stage 0.0 (TID 212, HDD008, executor 18): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 27.0 in stage 0.0 (TID 83, HDD007, executor 8): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 94.0 in stage 0.0 (TID 250, HDD014, executor 24): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN spark.ExecutorAllocationManager: No stages are running, but numRunningTasks != 0 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 49.0 in stage 0.0 (TID 219, HDD010, executor 22): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 92.0 in stage 0.0 (TID 222, HDD008, executor 26): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 99.0 in stage 0.0 (TID 200, HDD009, executor 13): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 97.0 in stage 0.0 (TID 115, HDD010, executor 22): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 216.0 in stage 0.0 (TID 281, HDD009, executor 13): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 90.0 in stage 0.0 (TID 220, HDD008, executor 6): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 77.0 in stage 0.0 (TID 215, HDD008, executor 6): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 69.0 in stage 0.0 (TID 188, HDD012, executor 25): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 38.0 in stage 0.0 (TID 209, HDD010, executor 4): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 46.0 in stage 0.0 (TID 177, HDD012, executor 25): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 98.0 in stage 0.0 (TID 151, HDD009, executor 9): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 96.0 in stage 0.0 (TID 237, HDD011, executor 11): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 83.0 in stage 0.0 (TID 150, HDD009, executor 9): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 86.0 in stage 0.0 (TID 165, HDD011, executor 11): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 215.0 in stage 0.0 (TID 280, HDD011, executor 16): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 48.0 in stage 0.0 (TID 218, HDD010, executor 15): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 43.0 in stage 0.0 (TID 213, HDD010, executor 15): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 68.0 in stage 0.0 (TID 98, HDD011, executor 3): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 10.0 in stage 0.0 (TID 52, HDD016, executor 14): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 9.0 in stage 0.0 (TID 51, HDD016, executor 14): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 211.0 in stage 0.0 (TID 278, HDD007, executor 20): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 91.0 in stage 0.0 (TID 80, HDD014, executor 1): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 213.0 in stage 0.0 (TID 279, HDD014, executor 1): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 95.0 in stage 0.0 (TID 251, HDD007, executor 20): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 93.0 in stage 0.0 (TID 226, HDD008, executor 26): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 199.0 in stage 0.0 (TID 277, HDD023, executor 10): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 12.0 in stage 0.0 (TID 54, HDD016, executor 21): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 72.0 in stage 0.0 (TID 214, HDD008, executor 18): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 11.0 in stage 0.0 (TID 53, HDD016, executor 21): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 219.0 in stage 0.0 (TID 282, HDD014, executor 12): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 54.0 in stage 0.0 (TID 183, HDD012, executor 7): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 62.0 in stage 0.0 (TID 86, HDD011, executor 16): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 66.0 in stage 0.0 (TID 88, HDD011, executor 3): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 84.0 in stage 0.0 (TID 68, HDD014, executor 12): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 44.0 in stage 0.0 (TID 47, HDD013, executor 19): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 36.0 in stage 0.0 (TID 46, HDD013, executor 19): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 80.0 in stage 0.0 (TID 107, HDD011, executor 23): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 59.0 in stage 0.0 (TID 70, HDD023, executor 5): TaskKilled (killed intentionally) org.apache.spark.SparkException: Job aborted due to stage failure: Task 252 in stage 0.0 failed 10 times, most recent failure: Lost task 252.9 in stage 0.0 (TID 276, HDD014, executor 12): org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata :getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2386) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57) at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2788) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2385) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2392) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2128) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2127) at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2818) at org.apache.spark.sql.Dataset.head(Dataset.scala:2127) at org.apache.spark.sql.Dataset.take(Dataset.scala:2342) at org.apache.spark.sql.Dataset.showString(Dataset.scala:248) at org.apache.spark.sql.Dataset.show(Dataset.scala:638) at org.apache.spark.sql.Dataset.show(Dataset.scala:597) at org.apache.spark.sql.Dataset.show(Dataset.scala:606) ... 50 elided Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more 2. Caused by: java.io.EOFException: Cannot seek to negative offset at org.apache.hadoop.hdfs.DFSInputStream.seek(DFSInputStream.java:1527) at org.apache.hadoop.fs.FSDataInputStream.seek(FSDataInputStream.java:62) at org.apache.carbondata.core.datastore.impl.DFSFileHolderImpl.readLong(DFSFileHolderImpl.java:129) at org.apache.carbondata.core.util.CarbonUtil.calculateMetaSize(CarbonUtil.java:948) at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:94) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more yixu2001 |
dev
What time is expected to release a patch, we can test 发件人: yixu2001 发送时间: 2017-10-30 18:11 收件人: dev 主题: Block B-tree loading failed add debug information dev environment spark.2.1.1 carbondata 1.1.1 hadoop 2.7.2 add debug information Block B-tree loading faile why CarbonUtil.calculateMetaSize Calculation results getBlockLength=0 getBlockOffset=8301549 ? Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata :getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 1 debug information scala> cc.sql("select prod_inst_id,count(*) from e_carbon.prod_inst_his1023c group by prod_inst_id having count(*)>1").show [Stage 0:=============================> (157 + 50) / 283]17/10/30 10:39:24 WARN scheduler.TaskSetManager: Lost task 252.0 in stage 0.0 (TID 201, HDD010, executor 22): org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more [Stage 0:==========================================> (223 + 50) / 283]17/10/30 10:39:26 ERROR scheduler.TaskSetManager: Task 252 in stage 0.0 failed 10 times; aborting job 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 61.0 in stage 0.0 (TID 184, HDD012, executor 7): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 71.0 in stage 0.0 (TID 212, HDD008, executor 18): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 27.0 in stage 0.0 (TID 83, HDD007, executor 8): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 94.0 in stage 0.0 (TID 250, HDD014, executor 24): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN spark.ExecutorAllocationManager: No stages are running, but numRunningTasks != 0 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 49.0 in stage 0.0 (TID 219, HDD010, executor 22): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 92.0 in stage 0.0 (TID 222, HDD008, executor 26): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 99.0 in stage 0.0 (TID 200, HDD009, executor 13): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 97.0 in stage 0.0 (TID 115, HDD010, executor 22): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 216.0 in stage 0.0 (TID 281, HDD009, executor 13): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 90.0 in stage 0.0 (TID 220, HDD008, executor 6): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 77.0 in stage 0.0 (TID 215, HDD008, executor 6): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 69.0 in stage 0.0 (TID 188, HDD012, executor 25): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 38.0 in stage 0.0 (TID 209, HDD010, executor 4): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 46.0 in stage 0.0 (TID 177, HDD012, executor 25): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 98.0 in stage 0.0 (TID 151, HDD009, executor 9): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 96.0 in stage 0.0 (TID 237, HDD011, executor 11): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 83.0 in stage 0.0 (TID 150, HDD009, executor 9): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 86.0 in stage 0.0 (TID 165, HDD011, executor 11): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 215.0 in stage 0.0 (TID 280, HDD011, executor 16): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 48.0 in stage 0.0 (TID 218, HDD010, executor 15): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 43.0 in stage 0.0 (TID 213, HDD010, executor 15): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 68.0 in stage 0.0 (TID 98, HDD011, executor 3): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 10.0 in stage 0.0 (TID 52, HDD016, executor 14): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 9.0 in stage 0.0 (TID 51, HDD016, executor 14): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 211.0 in stage 0.0 (TID 278, HDD007, executor 20): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 91.0 in stage 0.0 (TID 80, HDD014, executor 1): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 213.0 in stage 0.0 (TID 279, HDD014, executor 1): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 95.0 in stage 0.0 (TID 251, HDD007, executor 20): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 93.0 in stage 0.0 (TID 226, HDD008, executor 26): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 199.0 in stage 0.0 (TID 277, HDD023, executor 10): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 12.0 in stage 0.0 (TID 54, HDD016, executor 21): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 72.0 in stage 0.0 (TID 214, HDD008, executor 18): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 11.0 in stage 0.0 (TID 53, HDD016, executor 21): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 219.0 in stage 0.0 (TID 282, HDD014, executor 12): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 54.0 in stage 0.0 (TID 183, HDD012, executor 7): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 62.0 in stage 0.0 (TID 86, HDD011, executor 16): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 66.0 in stage 0.0 (TID 88, HDD011, executor 3): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 84.0 in stage 0.0 (TID 68, HDD014, executor 12): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 44.0 in stage 0.0 (TID 47, HDD013, executor 19): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 36.0 in stage 0.0 (TID 46, HDD013, executor 19): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 80.0 in stage 0.0 (TID 107, HDD011, executor 23): TaskKilled (killed intentionally) 17/10/30 10:39:26 WARN scheduler.TaskSetManager: Lost task 59.0 in stage 0.0 (TID 70, HDD023, executor 5): TaskKilled (killed intentionally) org.apache.spark.SparkException: Job aborted due to stage failure: Task 252 in stage 0.0 failed 10 times, most recent failure: Lost task 252.9 in stage 0.0 (TID 276, HDD014, executor 12): org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata :getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2386) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57) at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2788) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2385) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2392) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2128) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2127) at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2818) at org.apache.spark.sql.Dataset.head(Dataset.scala:2127) at org.apache.spark.sql.Dataset.take(Dataset.scala:2342) at org.apache.spark.sql.Dataset.showString(Dataset.scala:248) at org.apache.spark.sql.Dataset.show(Dataset.scala:638) at org.apache.spark.sql.Dataset.show(Dataset.scala:597) at org.apache.spark.sql.Dataset.show(Dataset.scala:606) ... 50 elided Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Block B-tree loading failed at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:264) at org.apache.carbondata.core.datastore.BlockIndexStore.getAll(BlockIndexStore.java:189) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.initQuery(AbstractQueryExecutor.java:131) at org.apache.carbondata.core.scan.executor.impl.AbstractQueryExecutor.getBlockExecutionInfos(AbstractQueryExecutor.java:186) at org.apache.carbondata.core.scan.executor.impl.VectorDetailQueryExecutor.execute(VectorDetailQueryExecutor.java:36) at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.initialize(VectorizedCarbonRecordReader.java:112) at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.ExecutionException: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata=lianch:getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at java.util.concurrent.FutureTask.report(FutureTask.java:122) at java.util.concurrent.FutureTask.get(FutureTask.java:192) at org.apache.carbondata.core.datastore.BlockIndexStore.fillLoadedBlocks(BlockIndexStore.java:254) ... 21 more Caused by: org.apache.carbondata.core.datastore.exception.IndexBuilderException: Invalid carbon data file: hdfs://ns1/user/e_carbon/public/carbon.store/e_carbon/prod_inst_his1023c/Fact/Part0/Segment_1.1/part-0-172_batchno0-0-1508833127408.carbondata getBlockLength=0 getBlockOffset=8301549 requiredMetaSize=-8301549 isV1=false getVersion=ColumnarFormatV3 at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:116) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more 2. Caused by: java.io.EOFException: Cannot seek to negative offset at org.apache.hadoop.hdfs.DFSInputStream.seek(DFSInputStream.java:1527) at org.apache.hadoop.fs.FSDataInputStream.seek(FSDataInputStream.java:62) at org.apache.carbondata.core.datastore.impl.DFSFileHolderImpl.readLong(DFSFileHolderImpl.java:129) at org.apache.carbondata.core.util.CarbonUtil.calculateMetaSize(CarbonUtil.java:948) at org.apache.carbondata.core.datastore.AbstractBlockIndexStoreCache.checkAndLoadTableBlocks(AbstractBlockIndexStoreCache.java:94) at org.apache.carbondata.core.datastore.BlockIndexStore.loadBlock(BlockIndexStore.java:304) at org.apache.carbondata.core.datastore.BlockIndexStore.get(BlockIndexStore.java:109) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:294) at org.apache.carbondata.core.datastore.BlockIndexStore$BlockLoaderThread.call(BlockIndexStore.java:284) at java.util.concurrent.FutureTask.run(FutureTask.java:266) ... 3 more yixu2001 |
Free forum by Nabble | Edit this page |