[
https://issues.apache.org/jira/browse/HDDS-11217?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ethan Rose updated HDDS-11217:
------------------------------
Description: In HDDS-10376, the API to read a container's merkle tree was
implemented without zero-copy. This should be ok for phase 1 where
reconciliation is only triggered manually. However, we should avoid the extra
copy of the file's data before reconciliation is automated and calls to the API
increase in frequency. (was: In HDDS-10144, the API to read a container's
merkle tree was implemented without zero-copy. This should be ok for phase 1
where reconciliation is only triggered manually. However, we should avoid the
extra copy of the file's data before reconciliation is automated and calls to
the API increase in frequency.)
> Use zero-copy for readMerkleTree API
> ------------------------------------
>
> Key: HDDS-11217
> URL: https://issues.apache.org/jira/browse/HDDS-11217
> Project: Apache Ozone
> Issue Type: Sub-task
> Reporter: Ethan Rose
> Priority: Major
>
> In HDDS-10376, the API to read a container's merkle tree was implemented
> without zero-copy. This should be ok for phase 1 where reconciliation is only
> triggered manually. However, we should avoid the extra copy of the file's
> data before reconciliation is automated and calls to the API increase in
> frequency.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
