[
https://issues.apache.org/jira/browse/ASTERIXDB-3548?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ian Maxon updated ASTERIXDB-3548:
---------------------------------
Labels: triaged (was: )
> Avoiding Column Assembly when possible
> --------------------------------------
>
> Key: ASTERIXDB-3548
> URL: https://issues.apache.org/jira/browse/ASTERIXDB-3548
> Project: Apache AsterixDB
> Issue Type: Bug
> Components: COMP - Compiler, STO - Storage
> Affects Versions: 0.9.10
> Reporter: Ritik Raj
> Assignee: Ritik Raj
> Priority: Major
> Labels: triaged
> Fix For: 0.9.10
>
>
> One of the main bottlenecks in Columnar is assembling the columns back into
> objects. Such assembly mostly isn't useful for the user, but it is an easy
> way to process data without tankering with the query execution engine. The
> compiler can be more intelligent to replace all field access/array access
> functions with simple variables that points to a already flattened data
> (disk-stored columns). Doing so would save us from paying the unnecessary
> cost of assembling columns just to be re-disassembled by the field
> access/array access functions later in the upper operators.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
