[jira] [Created] (IGNITE-27431) Calcite engine. Optimize scans with filter

["Aleksey Plekhanov (Jira)" <ji...@apache.org>]

Aleksey Plekhanov created IGNITE-27431:
------------------------------------------

             Summary: Calcite engine. Optimize scans with filter
                 Key: IGNITE-27431
                 URL: https://issues.apache.org/jira/browse/IGNITE-27431
             Project: Ignite
          Issue Type: Improvement
            Reporter: Aleksey Plekhanov
            Assignee: Aleksey Plekhanov


Currently we process scans in the following way:
 * Read all row columns from storage
 * Check row by filter
 * If row is accepted - transform it, and pass to the next node
 * Process next row

Usually filter checks only subset of columns, we don't need to fill all row columns, some of them filled but not used. Let's implement the following scheme:
 * Read columns required by filter from storage
 * Check row by filter
 * If row is accepted, read remaining columns, transform row, and pass to the next node
 * Process next row

 

 



--
This message was sent by Atlassian Jira
(v8.20.10#820010)