[
https://issues.apache.org/jira/browse/IGNITE-20021?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Vladislav Pyatkov updated IGNITE-20021:
---------------------------------------
Description:
There are too many threads in the attached dump. The majority of them related
to stopped nodes:
{noformat}
"%irclilurt_n_1%JRaft-FSMCaller-Disruptor-_stripe_5-0" #147152 daemon prio=5
os_prio=0 cpu=0.11ms elapsed=184.09s tid=0x00007f8a95578000 nid=0xfe0d3 waiting
on condition [0x00007f85a94e4000]
java.lang.Thread.State: WAITING (parking)
at jdk.internal.misc.Unsafe.park([email protected]/Native Method)
- parking to wait for <0x000000040aee3db8> (a
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject)
at
java.util.concurrent.locks.LockSupport.park([email protected]/LockSupport.java:194)
at
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await([email protected]/AbstractQueuedSynchronizer.java:2081)
at
com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:45)
at
com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56)
at
com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:128)
at java.lang.Thread.run([email protected]/Thread.java:834)
{noformat}
was:
There are too many threads in the attached dump. The majority of them related
to stopped nodes:
{noformat}
"%irst_n_3344%JRaft-FSMCaller-Disruptor-_stripe_0-0" #112582 daemon prio=5
os_prio=0 cpu=0.14ms elapsed=0.84s tid=0x00007f19ee2f9800 nid=0x271367 waiting
on condition [0x00007f19ce8f9000]
java.lang.Thread.State: WAITING (parking)
at jdk.internal.misc.Unsafe.park([email protected]/Native Method)
- parking to wait for <0x0000000446aa6268> (a
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject)
at
java.util.concurrent.locks.LockSupport.park([email protected]/LockSupport.java:194)
at
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await([email protected]/AbstractQueuedSynchronizer.java:2081)
at com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:45)
at
com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56)
at com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:128)
at java.lang.Thread.run([email protected]/Thread.java:834)
{noformat}
This seems like the FMC Caller disruptor stops incorreectly. The most
suspicious fix that could be influential on this is IGNITE-19231.
> Too many Raft-FSMCaller-Disruptor threads
> -----------------------------------------
>
> Key: IGNITE-20021
> URL: https://issues.apache.org/jira/browse/IGNITE-20021
> Project: Ignite
> Issue Type: Improvement
> Reporter: Vladislav Pyatkov
> Priority: Major
> Labels: ignite-3
> Attachments: threads.txt
>
>
> There are too many threads in the attached dump. The majority of them related
> to stopped nodes:
> {noformat}
> "%irclilurt_n_1%JRaft-FSMCaller-Disruptor-_stripe_5-0" #147152 daemon prio=5
> os_prio=0 cpu=0.11ms elapsed=184.09s tid=0x00007f8a95578000 nid=0xfe0d3
> waiting on condition [0x00007f85a94e4000]
> java.lang.Thread.State: WAITING (parking)
> at jdk.internal.misc.Unsafe.park([email protected]/Native Method)
> - parking to wait for <0x000000040aee3db8> (a
> java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject)
> at
> java.util.concurrent.locks.LockSupport.park([email protected]/LockSupport.java:194)
> at
> java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await([email protected]/AbstractQueuedSynchronizer.java:2081)
> at
> com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:45)
> at
> com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56)
> at
> com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:128)
> at java.lang.Thread.run([email protected]/Thread.java:834)
> {noformat}
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
