[
https://issues.apache.org/jira/browse/IGNITE-27431?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18047985#comment-18047985
]
Ignite TC Bot commented on IGNITE-27431:
----------------------------------------
{panel:title=Branch: [pull/12600/head] Base: [master] : No blockers
found!|borderStyle=dashed|borderColor=#ccc|titleBGColor=#D6F7C1}{panel}
{panel:title=Branch: [pull/12600/head] Base: [master] : No new tests
found!|borderStyle=dashed|borderColor=#ccc|titleBGColor=#F7D6C1}{panel}
[TeamCity *--> Run :: All*
Results|https://ci2.ignite.apache.org/viewLog.html?buildId=8772225&buildTypeId=IgniteTests24Java8_RunAll]
> 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
> Priority: Major
> Labels: calcite, ise
> Time Spent: 40m
> Remaining Estimate: 0h
>
> 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)
