[
https://issues.apache.org/jira/browse/DRILL-1457?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14941907#comment-14941907
]
Victoria Markman commented on DRILL-1457:
-----------------------------------------
Verified that it works for couple of simple test cases: joins, union and
negative case with order by (in addition to Jinfeng's negative cases of limit
number exceeding number of rows in the table).
Need to still check in test suite.
Verified in: 1.2.0
#Thu Oct 01 23:19:53 UTC 2015
git.commit.id.abbrev=fe2b743
> Limit operator optimization : push limit operator past exchange operator;
> disable parallel plan if no order is required.
> ------------------------------------------------------------------------------------------------------------------------
>
> Key: DRILL-1457
> URL: https://issues.apache.org/jira/browse/DRILL-1457
> Project: Apache Drill
> Issue Type: Bug
> Components: Query Planning & Optimization
> Reporter: Jinfeng Ni
> Assignee: Jinfeng Ni
> Priority: Critical
> Labels: no_verified_test
> Fix For: 1.2.0
>
> Attachments:
> 0001-DRILL-1457-Push-Limit-past-through-UnionExchange.patch
>
>
> When there is LIMIT clause in a query, we would want to push down the LIMIT
> operator as much as possible, so that the upstream operator will stop
> execution once the desired number of rows are fetched.
> Within one execution fragment, Drill applies a pull model. In many cases,
> there would be no performance impact if LIMIT operator is not pushed down,
> since LIMIT would inform the upstream operators to stop. However, in multiple
> fragments, Drill use a push model. if LIMIT is not pushed past the exchange
> operator, and the upstream fragment would continue the execution, until it
> receives a notice from downstream fragment, even if LIMIT operator has
> already got the required # of rows.
> For instance:
> explain plan for select * from
> dfs.`/Users/jni/work/tpch-data/tpch-sf10/lineitem` limit 1;
> +------------+------------+
> | 00-00 Screen
> 00-01 SelectionVectorRemover
> 00-02 Limit(fetch=[1])
> 00-03 UnionExchange
> 01-01 Scan(groupscan=[ParquetGroupScan [entries=[ReadEntryWithPath
> [path=file:/Users/jni/work/tpch-data/tpch-sf10/lineitem]],
> selectionRoot=/Users/jni/work/tpch-data/tpch-sf10/lineitem,
> columns=[SchemaPath [`*`]]]])
> The query profile shows Scan operator fetches much more records than desired:
> Minor Fragment Start End Total Time Max Records Max
> Batches
> 01-00-xx 0.507 1.059 0.552 43688 8
> 01-01-xx 0.570 1.054 0.484 27305 5
> 01-02-xx 0.617 1.038 0.421 16383 3
> 01-03-xx 0.668 1.056 0.388 10922 2
> 01-04-xx 0.740 1.055 0.315 10922 2
> 01-05-xx 0.813 1.057 0.244 5461 1
> In the above plan, there would be two choices for performance optimization:
> 1) push the LIMIT operator past through EXCHANGE operator, ideally into SCAN
> operator.
> 2) Disable the parallel plan by removing EXCHANGE operator.
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
