[
https://issues.apache.org/jira/browse/IGNITE-23203?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Kirill Tkalenko reassigned IGNITE-23203:
----------------------------------------
Assignee: Kirill Tkalenko
> Write retry pages by multiple threads at checkpoint
> ---------------------------------------------------
>
> Key: IGNITE-23203
> URL: https://issues.apache.org/jira/browse/IGNITE-23203
> Project: Ignite
> Issue Type: Improvement
> Reporter: Kirill Tkalenko
> Assignee: Kirill Tkalenko
> Priority: Major
> Labels: ignite-3
>
> I found that in
> *org.apache.ignite.internal.pagememory.persistence.checkpoint.CheckpointPagesWriter*
> we write the retry pages with one thread (which filled them), which may be a
> bit inefficient.
> We can write these pages in parallel with several threads, for example, put
> them in some concurrent queue in pairs <PersistentPageMemery,
> List<FullPageId>> and each thread would write the pages in parallel.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
