[
https://issues.apache.org/jira/browse/IGNITE-24124?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Roman Puchkovskiy updated IGNITE-24124:
---------------------------------------
Description: Replicas belonging to partitions are stopped in table-io pool,
and in that same pool we are blockingly waiting for replica futures to be
completed. This is the classic pool starvation pattern, probably this is why
hangs on stop occur sometimes when a lot of tables need to be stopped.
> Pool starvation in TableManager#beforeNodeStop()
> ------------------------------------------------
>
> Key: IGNITE-24124
> URL: https://issues.apache.org/jira/browse/IGNITE-24124
> Project: Ignite
> Issue Type: Bug
> Reporter: Roman Puchkovskiy
> Assignee: Roman Puchkovskiy
> Priority: Major
> Labels: ignite-3
> Time Spent: 10m
> Remaining Estimate: 0h
>
> Replicas belonging to partitions are stopped in table-io pool, and in that
> same pool we are blockingly waiting for replica futures to be completed. This
> is the classic pool starvation pattern, probably this is why hangs on stop
> occur sometimes when a lot of tables need to be stopped.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
