[
https://issues.apache.org/jira/browse/IMPALA-8791?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Bikramjeet Vig updated IMPALA-8791:
-----------------------------------
Description:
For insert statements executed on a dedicated coord, the fragments get schduled
only on executors but a query state object still gets started up on the coord
host with the coord_mem_limit. we end up with a situation where the mem
admitted is zero for the coord but the mem_reserved is non-zero which would
affect other admission decisions.
There is also a case where there is no coordinator fragment but the execution
fragment gets scheduled on the coord (eg. insert into <tbl> values....) for
this case, the mem admitted is per_backend_mem_limit_ but the mem limit applied
to the coord query state is coord_backend_mem_limit_ which again causes a
inconsistency.
was:For insert statements executed on a dedicated coord, the fragments get
schduled only on executors but a query state object still gets started up on
the coord host with the coord_mem_limit. we end up with a situation where the
mem admitted is zero for the coord but the mem_reserved is non-zero which would
affect other admission decisions.
> Handle the case where there is no fragment scheduled on the coordinator for a
> query
> -----------------------------------------------------------------------------------
>
> Key: IMPALA-8791
> URL: https://issues.apache.org/jira/browse/IMPALA-8791
> Project: IMPALA
> Issue Type: Bug
> Affects Versions: Product Backlog
> Reporter: Bikramjeet Vig
> Assignee: Bikramjeet Vig
> Priority: Major
>
> For insert statements executed on a dedicated coord, the fragments get
> schduled only on executors but a query state object still gets started up on
> the coord host with the coord_mem_limit. we end up with a situation where the
> mem admitted is zero for the coord but the mem_reserved is non-zero which
> would affect other admission decisions.
> There is also a case where there is no coordinator fragment but the execution
> fragment gets scheduled on the coord (eg. insert into <tbl> values....) for
> this case, the mem admitted is per_backend_mem_limit_ but the mem limit
> applied to the coord query state is coord_backend_mem_limit_ which again
> causes a inconsistency.
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
