[
https://issues.apache.org/jira/browse/HDDS-17265?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Siyao Meng updated HDDS-17265:
------------------------------
Attachment: HDDS-17265.001.patch
> [Website v2] [Docs] [Administrator Guide] Troubleshooting failing or slow
> datanode disks
> ----------------------------------------------------------------------------------------
>
> Key: HDDS-17265
> URL: https://issues.apache.org/jira/browse/HDDS-17265
> Project: Apache Ozone
> Issue Type: Task
> Components: documentation
> Reporter: Siyao Meng
> Priority: Major
> Attachments: HDDS-17265.001.patch
>
>
> Add an administrator guide page for datanode disks that fail partially, turn
> slow, or hang:
> * What the volume checker and container scanners detect, and what they miss:
> bad sectors in existing data, slow disks, slow detection of hung disks.
> * Metrics, the volume health dashboard and the audit log fields to monitor.
> * Steps to find a bad disk with OS tools: findmnt, iostat, dmesg, sysfs error
> counters, smartctl, D-state threads.
> * How to remove a disk, and how to tune the disk check settings.
> The attached patch is a draft of the content in the {{hadoop-hdds/docs}}
> format of the apache/ozone repo. It is meant to be ported to the Website v2
> administrator guide in apache/ozone-site.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
