You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ignite.apache.org by "Pavel Tupitsyn (JIRA)" <ji...@apache.org> on 2017/08/29 13:27:00 UTC

[jira] [Reopened] (IGNITE-6033) Add sorted and multithreaded modes in checkpoint algorithm

     [ https://issues.apache.org/jira/browse/IGNITE-6033?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Pavel Tupitsyn reopened IGNITE-6033:
------------------------------------
      Assignee: Ivan Rakov  (was: Alexey Goncharuk)

.NET configuration is not updated, please make sure to add new properties there.

> Add sorted and multithreaded modes in checkpoint algorithm
> ----------------------------------------------------------
>
>                 Key: IGNITE-6033
>                 URL: https://issues.apache.org/jira/browse/IGNITE-6033
>             Project: Ignite
>          Issue Type: Improvement
>          Components: persistence
>    Affects Versions: 2.1
>            Reporter: Ivan Rakov
>            Assignee: Ivan Rakov
>             Fix For: 2.3
>
>
> Sequential writes to SSD are faster than random. When we write checkpoint, we iterate through hash table, which is actually random order. We should add an option to write pages sorted by page index. It should be configured in PersistentStoreConfiguration.
> Also, we already have PersistentStoreConfiguration#checkpointingThreads option, but we don't use it - we create thread pool, but submit only one task to it. This should be fixed as well.



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