You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@ignite.apache.org by "Sergey Chugunov (Jira)" <ji...@apache.org> on 2022/11/16 14:11:00 UTC

[jira] [Updated] (IGNITE-18169) IoomFailureHandlerTest.testIoomErrorPdsHandling fails on 64 core machines

     [ https://issues.apache.org/jira/browse/IGNITE-18169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Sergey Chugunov updated IGNITE-18169:
-------------------------------------
    Ignite Flags:   (was: Docs Required,Release Notes Required)

> IoomFailureHandlerTest.testIoomErrorPdsHandling fails on 64 core machines
> -------------------------------------------------------------------------
>
>                 Key: IGNITE-18169
>                 URL: https://issues.apache.org/jira/browse/IGNITE-18169
>             Project: Ignite
>          Issue Type: Bug
>    Affects Versions: 2.14
>            Reporter: Semyon Danilov
>            Assignee: Semyon Danilov
>            Priority: Major
>             Fix For: 2.15
>
>          Time Spent: 10m
>  Remaining Estimate: 0h
>
> It seems like minimal fragment size of the data region is 1 megabyte. The quantity of fragments is equal to concurrency level + 1 (checkpoint buffer). So in case if we set up region size to 10 megabytes and we have 64 cores, then by default we will have concurrency level 64 and instead of 10 megabytes region size + 10 megabytes checkpoint buffer size we will have 64 megabytes region size.



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