[jira] [Commented] (IGNITE-6080) SQL: Batch DML updates on per-node basis

["ASF GitHub Bot (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/IGNITE-6080?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16128762#comment-16128762 ] 

ASF GitHub Bot commented on IGNITE-6080:
----------------------------------------

GitHub user devozerov opened a pull request:

    https://github.com/apache/ignite/pull/2454

    IGNITE-6080

    

You can merge this pull request into a Git repository by running:

    $ git pull https://github.com/gridgain/apache-ignite ignite-6080

Alternatively you can review and apply these changes as the patch at:

    https://github.com/apache/ignite/pull/2454.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #2454
    
----
commit b562886d8e73a08667115c69b0bf78bd397452d0
Author: devozerov <vo...@gridgain.com>
Date:   2017-08-16T12:22:41Z

    Minors.

----


> SQL: Batch DML updates on per-node basis
> ----------------------------------------
>
>                 Key: IGNITE-6080
>                 URL: https://issues.apache.org/jira/browse/IGNITE-6080
>             Project: Ignite
>          Issue Type: Task
>    Affects Versions: 2.1
>            Reporter: Vladimir Ozerov
>            Assignee: Vladimir Ozerov
>              Labels: performance
>             Fix For: 2.2
>
>
> Currently DML updates are batched and then applied using {{IgniteCache.invokeAll}}. See {{org.apache.ignite.internal.processors.query.h2.DmlStatementsProcessor#processPage}}. This is not efficient, because typical update will hit a lot of data nodes.
> Instead, we should create separate batches for every primary node. This way we can significantly improve update performance.



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