hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Walter Su (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-7896) HDFS Slow disk detection
Date Tue, 20 Oct 2015 02:04:27 GMT

    [ https://issues.apache.org/jira/browse/HDFS-7896?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14964385#comment-14964385
] 

Walter Su commented on HDFS-7896:
---------------------------------

Slow disk is different with failed disk. A slow disk still can be read. It is slow maybe because
of bad sectors or lifespan or other issues. It tend to fail, but not fail immediately.
Bad sectors usually means damage of the physical body. To avoid more data damage, this disk
should be read-only, and warn user. So it can be replaced quickly.
Apart from [~arpitagarwal] said, another way to detect slow disk is to get the disk {{SMART}}
information by script.

> HDFS Slow disk detection
> ------------------------
>
>                 Key: HDFS-7896
>                 URL: https://issues.apache.org/jira/browse/HDFS-7896
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: datanode
>            Reporter: Arpit Agarwal
>
> HDFS should detect slow disks. To start with we can flag this information via the NameNode
web UI. Alternatively DNs can avoid using slow disks for writes.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message