[
https://issues.apache.org/jira/browse/IMPALA-9919?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17159146#comment-17159146
]
Vagelis Nomikos commented on IMPALA-9919:
-----------------------------------------
>From what i can see the impala after starting the query execution and after a
>couple of minutes, it starts cancelling the streams with the other nodes.Then,
>it freezes for a period of time (maybe it is waiting something) and when it
>starts executing the queries again it finishes the execution.
It is the same behaviour in all nodes. Is this a normal behaviour? We check our
queries profiles and all the queries spent a huge amount of time waiting for
putting new batches to the queue. *RowBatchQueuePutWaitTime* metric. We checked
our nodes for the CPU consumption and we didn't observe any problem. Also, the
disk IO waiting time seems not to be a problem. Is this a problem with the
threads of hdfsscannode and iomgr? Do you want me to send you any other
profile/log?
> Bad Impala Performance after a period of time
> ---------------------------------------------
>
> Key: IMPALA-9919
> URL: https://issues.apache.org/jira/browse/IMPALA-9919
> Project: IMPALA
> Issue Type: Bug
> Components: Backend
> Affects Versions: Impala 2.10.0
> Environment: OS: CentOS 6.9
> Reporter: Vagelis Nomikos
> Priority: Major
> Labels: performance
> Attachments: profiles.zip
>
>
> Our cluster is consisting of about 60 Impala nodes. After a period of time
> and after executing some "heavy" queries the performance of the cluster
> becomes bad and the Impala is not responding after a period of time. We
> observed that day after day the Impala Resident memory and the running
> threads of the machine keep growing even if we do not run queries. Everytime
> we perform an Impala restart everything seems to work fine for a period of
> time.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
