[jira] [Commented] (KUDU-1913) Tablet server runs out of threads when creating lots of tablets

["Adar Dembo (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/KUDU-1913?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16137731#comment-16137731 ] 

Adar Dembo commented on KUDU-1913:
----------------------------------

Commit 21b0f3d5e255760535e281efe5879fe657df1f1c (consensus: use periodic timers for failure detection) just landed and will be part of 1.5, which means a tserver's steady state thread utilization should no longer scale linearly with the number of hosted replicas.

I think that about wraps up this JIRA, though we should try a real workload on a cluster to see whether thread usage climbs too high during non-steady states (i.e. heavy writes, failovers, etc.).

> Tablet server runs out of threads when creating lots of tablets
> ---------------------------------------------------------------
>
>                 Key: KUDU-1913
>                 URL: https://issues.apache.org/jira/browse/KUDU-1913
>             Project: Kudu
>          Issue Type: Sub-task
>          Components: consensus, log
>            Reporter: Juan Yu
>            Assignee: Adar Dembo
>              Labels: data-scalability
>
> When adding lots of range partitions, all tablet server crashed with the following error:
> F0308 14:51:04.109369 12952 raft_consensus.cc:1985] Check failed: _s.ok() Bad status: Runtime error: Could not create thread: Resource temporarily unavailable (error 11)
> Tablet server should handle error/failure more gracefully instead of crashing.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)