[
https://issues.apache.org/jira/browse/HDFS-12521?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16196785#comment-16196785
]
Lokesh Jain commented on HDFS-12521:
------------------------------------
There are two issues which need to be solved through this jira :-
# ContainerStateManager should preload all the containers when booting up after
restart.
# MetadataStoreBuilder should use caching provided by LevelDb and RocksDb for
faster db operations. LevelDb and RocksDb are internally configured to use a
default cache of size 8 MB if a cache object is not provided. We need to pass a
cache object of the required capacity as an option.
> Ozone: SCM should read all Container info into memory when booting up
> ---------------------------------------------------------------------
>
> Key: HDFS-12521
> URL: https://issues.apache.org/jira/browse/HDFS-12521
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: ozone
> Reporter: Anu Engineer
> Assignee: Lokesh Jain
> Labels: performance
>
> When SCM boots up it should read all containers into memory. This is a
> performance optimization that allows delays on SCM side. This JIRA tracks
> that issue.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
