[jira] [Closed] (QUICKSTEP-68) Adjust the ordering of intermediate relations' output attributes to improve copy performance.

["Jianqiao Zhu (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/QUICKSTEP-68?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jianqiao Zhu closed QUICKSTEP-68.
---------------------------------
    Resolution: Implemented

The improvement has been implemented with PR #171.

> Adjust the ordering of intermediate relations' output attributes to improve copy performance.
> ---------------------------------------------------------------------------------------------
>
>                 Key: QUICKSTEP-68
>                 URL: https://issues.apache.org/jira/browse/QUICKSTEP-68
>             Project: Apache Quickstep
>          Issue Type: Improvement
>          Components: Query Optimizer
>            Reporter: Jianqiao Zhu
>            Assignee: Jianqiao Zhu
>            Priority: Minor
>
> Currently, all the intermediate relations (i.e. temporary relations created during query execution) have SPLIT_ROW_STORE layout. One existing optimization that improves copy performance for SPLIT_ROW_STORE layout is that, if two (or more) attributes are consecutive in both the source relation and the destination relation, then we can memory-copy the attributes' byte stream with just one std::memcpy call.
> This PR is a complementary improvement that it adjusts the ordering of the attributes in the physical plan to maximize the opportunity of copying consecutive attributes -- i.e. to minimize the number of std::memcpy calls.
> This PR uses a simple greedy algorithm to reorder the attributes, which works well with SSB/TPCH workloads. The algorithm may be further improved later.
> The feature can be turned on/off (default is on) with the -reorder_columns flag.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)