[
https://issues.apache.org/jira/browse/IMPALA-8316?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16794129#comment-16794129
]
Todd Lipcon commented on IMPALA-8316:
-------------------------------------
(to be specific, the regexp_extract(l_shipinstruct, '.*E', 0) bit is the slow
expression in this example, not the LIKE)
> Update re2 to avoid lock contention
> -----------------------------------
>
> Key: IMPALA-8316
> URL: https://issues.apache.org/jira/browse/IMPALA-8316
> Project: IMPALA
> Issue Type: Improvement
> Components: Backend
> Reporter: Todd Lipcon
> Priority: Major
> Labels: perf
>
> I ran the following test query and found that it spent a lot of time in lock
> contention within the re2 library:
> ```select sum(l_linenumber) from item_20x where
> regexp_extract(l_shipinstruct, '.*E', 0) like '%E' ;```
> I think this lock contention would happen on any regex that involves
> backtracking. This was fixed in the re2 library upstream in
> https://github.com/google/re2/commit/eb00dfdd82015be22086cacc6bf830f72a10e2bc#diff-a60a8d25ed15adf68b94c85775fd3cf7
> We should consider upgrading re2 to the latest release, or if not that, at
> least cherry-picking this perf fix.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
