[jira] [Resolved] (IMPALA-4236) Codegen CopyRows() for select nodes

["Bikramjeet Vig (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/IMPALA-4236?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Bikramjeet Vig resolved IMPALA-4236.
------------------------------------
       Resolution: Fixed
    Fix Version/s: Impala 2.11.0

https://github.com/apache/incubator-impala/commit/ca55b5926ecfaf764f3f46add4391588e18b90f0

IMPALA-4236: Codegen CopyRows() for select nodes
Testing:
Added test case to verify that CopyRows in select node is successfully
codegened.
Improved test coverage for select node with limit.

Performance:
Queries used (num_nodes set to 1):
500 Predicates: select * from (select * from tpch_parquet.lineitem
limit 6001215) t1 where l_partkey > 10 and l_extendedprice > 10000 and
l_linenumber > 1 and l_comment >'foo0' .... and l_comment >'foo500'
order by l_orderkey limit 10;

1 Predicate: select * from (select * from tpch_parquet.lineitem
limit 6001215) t1 where l_partkey > 10 order by l_orderkey limit 10;

{noformat}
+--------------+-----------------------------------------------------+
|              |      500 Predicates      |       1 Predicate        |
|              +------------+-------------+------------+-------------+
|              |   After    |   Before    |   After    |   Before    |
+--------------+------------+-------------+------------+-------------+
| Select Node  | 12s385ms   | 1m1s        | 234ms      | 797ms       |
| Codegen time | 2s619ms    | 1s962ms     | 200ms      | 181ms       |
+--------------+------------+-------------+------------+-------------+
{noformat}

Change-Id: Ie0d496d004418468e16b6f564f90f45ebbf87c1e
Reviewed-on: http://gerrit.cloudera.org:8080/8196
Reviewed-by: Bikramjeet Vig <bi...@cloudera.com>
Tested-by: Impala Public Jenkins

> Codegen CopyRows() for select nodes
> -----------------------------------
>
>                 Key: IMPALA-4236
>                 URL: https://issues.apache.org/jira/browse/IMPALA-4236
>             Project: IMPALA
>          Issue Type: Improvement
>          Components: Backend
>    Affects Versions: Impala 2.8.0
>            Reporter: Michael Ho
>            Assignee: Bikramjeet Vig
>            Priority: Minor
>              Labels: codegen, ramp-up
>             Fix For: Impala 2.11.0
>
>
> We should codegen CopyRows(() in Select node. We can already codegen EvalConjuncts() and inline it into a codegen'd version of CopyRows. One can look at how scanners codegen their conjuncts as examples.
> {noformat}
> bool SelectNode::CopyRows(RowBatch* output_batch) {
>   ExprContext** conjunct_ctxs = &conjunct_ctxs_[0];
>   int num_conjunct_ctxs = conjunct_ctxs_.size();
>   while (child_row_idx_ < child_row_batch_->num_rows()) {
>     // Add a new row to output_batch
>     int dst_row_idx = output_batch->AddRow();
>     TupleRow* dst_row = output_batch->GetRow(dst_row_idx);
>     TupleRow* src_row = child_row_batch_->GetRow(child_row_idx_);
>     // Make sure to increment row idx before returning.
>     ++child_row_idx_;
>     if (EvalConjuncts(conjunct_ctxs, num_conjunct_ctxs, src_row)) { <<----
>       output_batch->CopyRow(src_row, dst_row);
>       output_batch->CommitLastRow();
>       ++num_rows_returned_;
>       COUNTER_SET(rows_returned_counter_, num_rows_returned_);
>       if (ReachedLimit() || output_batch->AtCapacity()) return true;
>     }
>   }
>   return output_batch->AtCapacity();
> }
> {noformat}



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)