[DRILL-5609] Resources leak on parquet table when the query hangs with CANCELLATION_REQUESTED state

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Duplicate
• Affects Version/s: 1.11.0
• Component/s: Execution - Flow
• Assignee: Unassigned
• Reporter: Roman Kulyk
• Created: 26/Jun/17 09:34
• Updated: 31/Aug/17 07:35
• Resolved: 03/Jul/17 10:42

Description

I tried to run tpcds_sf100-query2 on parquet table in 10 concurrency threads on single node drillbit cluster (I use Drill with DRILL-5599 fix) and caught a resources leak. The query hanged in CANCELLATION_REQUESTED state.

Steps to reproduce:

1) Start ConcurrencyTest.java with tpcds_sf100-query2 on parquet table (in attachment);
2) Wait 3-5 seconds and make Ctrl+c to kill a client.
3) Retry step 2) several times until you get "CANCELLATION_REQUESTED" on some queries.

Queries will hang until drillbit restart. If we make "top", we can see that drillbit uses CPU.

Jstack example:

"26af36b2-7a44-5af8-e0c3-95a4f132fc7a:frag:14:1" #1268 daemon prio=10 os_prio=0 tid=0x00007f25a5afa800 nid=0x16f2 runnable [0x00007f2535a5a000]
   java.lang.Thread.State: RUNNABLE
	at java.lang.Throwable.fillInStackTrace(Native Method)
	at java.lang.Throwable.fillInStackTrace(Throwable.java:783)
	- locked <0x0000000728ca82b0> (a java.lang.InterruptedException)
	at java.lang.Throwable.<init>(Throwable.java:250)
	at java.lang.Exception.<init>(Exception.java:54)
	at java.lang.InterruptedException.<init>(InterruptedException.java:57)
	at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireInterruptibly(AbstractQueuedSynchronizer.java:1220)
	at java.util.concurrent.locks.ReentrantLock.lockInterruptibly(ReentrantLock.java:335)
	at java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:439)
	at org.apache.drill.exec.store.parquet.columnreaders.AsyncPageReader.clear(AsyncPageReader.java:301)
	at org.apache.drill.exec.store.parquet.columnreaders.ColumnReader.clear(ColumnReader.java:147)
	at org.apache.drill.exec.store.parquet.columnreaders.ReadState.close(ReadState.java:179)
	at org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader.close(ParquetRecordReader.java:318)
	at org.apache.drill.exec.physical.impl.ScanBatch.next(ScanBatch.java:209)
	at org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
	at org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
	at org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
	at org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:133)
	at org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
	at org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:105)
	at org.apache.drill.exec.physical.impl.broadcastsender.BroadcastSenderRootExec.innerNext(BroadcastSenderRootExec.java:95)
	at org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:95)
	at org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:234)
	at org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:227)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1595)
	at org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:227)
	at org.apache.drill.common.SelfCleaningRunnable.run(SelfCleaningRunnable.java:38)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:748)

I added drillbit.log and full jstack log in attachments.

Issue Links

• duplicates: DRILL-5420 all cores at 100% of all servers