[
https://issues.apache.org/jira/browse/HIVE-23006?focusedWorklogId=418816&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-418816
]
ASF GitHub Bot logged work on HIVE-23006:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 08/Apr/20 19:30
Start Date: 08/Apr/20 19:30
Worklog Time Spent: 10m
Work Description: jcamachor commented on pull request #952: HIVE-23006
ProbeDecode compiler support
URL: https://github.com/apache/hive/pull/952#discussion_r405762816
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/parse/TezCompiler.java
##########
@@ -1483,17 +1489,64 @@ private void
removeSemijoinsParallelToMapJoin(OptimizeTezProcContext procCtx)
}
}
- if (semijoins.size() > 0) {
- for (ReduceSinkOperator rs : semijoins.keySet()) {
- if (LOG.isDebugEnabled()) {
- LOG.debug("Semijoin optimization with parallel edge to map join.
Removing semijoin "
- + OperatorUtils.getOpNamePretty(rs) + " - " +
OperatorUtils.getOpNamePretty(semijoins.get(rs)));
+ if
(!procCtx.conf.getBoolVar(ConfVars.TEZ_DYNAMIC_SEMIJOIN_REDUCTION_FOR_MAPJOIN))
{
+ if (semijoins.size() > 0) {
Review comment:
Probably I am missing part of the mechanism to enable your optimization. It
seems you are skipping the removal of SJ, so you are adding the context AND
keeping those branches in the plan. Is the intention to keep both optimizations
in these cases? Or is it because there is some dependency between them? I
thought for MJ, the intention was to keep only your new optimization, that's
maybe where my misunderstanding is coming from.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 418816)
Time Spent: 1h 50m (was: 1h 40m)
> Compiler support for Probe MapJoin
> ----------------------------------
>
> Key: HIVE-23006
> URL: https://issues.apache.org/jira/browse/HIVE-23006
> Project: Hive
> Issue Type: Sub-task
> Reporter: Panagiotis Garefalakis
> Assignee: Panagiotis Garefalakis
> Priority: Major
> Labels: pull-request-available
> Attachments: HIVE-23006.01.patch, HIVE-23006.02.patch
>
> Time Spent: 1h 50m
> Remaining Estimate: 0h
>
> The decision of pushing down information to the Record reader (potentially
> reducing decoding time by row-level filtering) should be done at query
> compilation time.
> This patch adds an extra optimisation step with the goal of finding Table
> Scan operators that could reduce the number of rows decoded at runtime using
> extra available information.
> It currently looks for all the available MapJoin operators that could use the
> smaller HashTable on the probing side (where TS is) to filter-out rows that
> would never match.
> To do so the HashTable information is pushed down to the TS properties and
> then propagated as part of MapWork.
> If the a single TS is used by multiple operators (shared-word), this rule can
> not be applied.
> This rule can be extended to support static filter expressions like:
> _select * from sales where sold_state = 'PR';_
> This optimisation manly targets the Tez execution engine running on Llap.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
