[
https://issues.apache.org/jira/browse/IMPALA-4080?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17046000#comment-17046000
]
ASF subversion and git services commented on IMPALA-4080:
---------------------------------------------------------
Commit ad3177035103dfcb1625b32f04f22ea87456eb6c in impala's branch
refs/heads/master from Bikramjeet Vig
[ https://gitbox.apache.org/repos/asf?p=impala.git;h=ad31770 ]
IMPALA-4080 [part 2]: Invoke codegen from scan's plan node instead of
exec node
This patch moves the code responsible for invoking codegen for
hdfs scanner to the plan node.
Testing:
Successfully ran exhaustive tests.
Also verified manually that codegen code is generated and
used for each hdfs scanner.
Change-Id: I02c6183271b3731aa0d3cae2426be7269e462967
Reviewed-on: http://gerrit.cloudera.org:8080/15259
Reviewed-by: Impala Public Jenkins <[email protected]>
Tested-by: Impala Public Jenkins <[email protected]>
> Share codegen work between fragment instances
> ---------------------------------------------
>
> Key: IMPALA-4080
> URL: https://issues.apache.org/jira/browse/IMPALA-4080
> Project: IMPALA
> Issue Type: Improvement
> Components: Backend
> Affects Versions: Impala 2.8.0
> Reporter: Tim Armstrong
> Assignee: Bikramjeet Vig
> Priority: Major
> Labels: codegen, multithreading
>
> With multithreading, we should find a way to share codegen modules between
> fragment instances to avoid redundant compilation, optimisation, etc.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
