You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ignite.apache.org by "Vladimir Ozerov (JIRA)" <ji...@apache.org> on 2017/11/10 09:19:01 UTC

[jira] [Resolved] (IGNITE-4957) First join query execution in client mode takes too long when there are many caches on remote nodes

     [ https://issues.apache.org/jira/browse/IGNITE-4957?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Vladimir Ozerov resolved IGNITE-4957.
-------------------------------------
    Resolution: Duplicate

> First join query execution in client mode takes too long when there are many caches on remote nodes
> ---------------------------------------------------------------------------------------------------
>
>                 Key: IGNITE-4957
>                 URL: https://issues.apache.org/jira/browse/IGNITE-4957
>             Project: Ignite
>          Issue Type: Task
>          Components: sql
>    Affects Versions: 1.9
>            Reporter: Alexandr Fedotov
>              Labels: performance
>         Attachments: first_run_from_client.png
>
>
> When there are many caches deployed on server nodes and a query containing joins is executed on a client for the first time then it takes much time to complete compared to the following executions.
> If caches aren't enabled locally then the first query tries to load all the missing caches by calling
> {{org.apache.ignite.internal.processors.cache.GridCacheProcessor#createMissingCaches}}
> {{createMissingCaches}} internally sends a request per each registered but not enabled cache.
> Performance could be improved by performing a batch request.
> VisualVM results for the first join query run are below
> !first_run_from_client.png!



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