[ https://issues.apache.org/jira/browse/SPARK-10898?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15091478#comment-15091478 ]
Praveen Devarao commented on SPARK-10898: ----------------------------------------- Hi [~mark.goodall] Is this still a valid issue, reproducible on SPARK 1.6? If yes, could you provide more info on your configuration and steps to repro. I would like to take a shot at this and help resolve. Thanks Praveen > Setting spark.streaming.concurrentJobs causes blocks to be deleted before read > ------------------------------------------------------------------------------ > > Key: SPARK-10898 > URL: https://issues.apache.org/jira/browse/SPARK-10898 > Project: Spark > Issue Type: Bug > Components: Streaming > Affects Versions: 1.4.1 > Environment: CentOS 6.6 > Reporter: Mark Goodall > > The scheduler deletes the block literally just before it is used first time. > The input is set to mem and disk ser. > 15/10/01 15:10:04 INFO scheduler.InputInfoTracker: remove old batch metadata: > 1443708599000 ms 1443708602000 ms 1443708601000 ms 1443708600000 ms > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708601800 on discos8.localdomain:45076 in memory (size: 8.7 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708602000 on discos8.localdomain:45076 in memory (size: 8.7 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708602200 on discos8.localdomain:45076 in memory (size: 7.3 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708602400 on discos8.localdomain:45076 in memory (size: 5.7 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708602600 on discos8.localdomain:45076 in memory (size: 2.6 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708599800 on discos8.localdomain:45076 in memory (size: 5.8 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708600000 on discos8.localdomain:45076 in memory (size: 6.4 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708600200 on discos8.localdomain:45076 in memory (size: 7.0 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708600400 on discos8.localdomain:45076 in memory (size: 6.9 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708600600 on discos8.localdomain:45076 in memory (size: 3.8 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708600800 on discos8.localdomain:45076 in memory (size: 4.2 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708601000 on discos8.localdomain:45076 in memory (size: 4.7 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708601200 on discos8.localdomain:45076 in memory (size: 5.4 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708601400 on discos8.localdomain:45076 in memory (size: 5.5 MB, > free: 3.0 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708601600 on discos8.localdomain:45076 in memory (size: 8.9 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708598800 on discos8.localdomain:45076 in memory (size: 8.1 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708599000 on discos8.localdomain:45076 in memory (size: 7.8 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708599200 on discos8.localdomain:45076 in memory (size: 5.9 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708599400 on discos8.localdomain:45076 in memory (size: 6.0 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Removed > input-0-1443708599600 on discos8.localdomain:45076 in memory (size: 6.6 MB, > free: 3.1 GB) > 15/10/01 15:10:04 INFO storage.BlockManagerInfo: Added input-0-1443708604600 > in memory on discos8.localdomain:45076 (size: 8.7 MB, free: 3.1 GB) > 15/10/01 15:10:04 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 6.0 > (TID 84, discos1.localdomain): java.lang.Exception: Could not compute split, > block input-0-1443708599800 not found > at org.apache.spark.rdd.BlockRDD.compute(BlockRDD.scala:51) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) > at org.apache.spark.scheduler.Task.run(Task.scala:70) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > at java.lang.Thread.run(Thread.java:745) -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org