hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Suresh Srinivas (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-3705) Add the possibility to mark a node as 'low priority' for read in the DFSClient
Date Fri, 07 Sep 2012 18:31:08 GMT

    [ https://issues.apache.org/jira/browse/HDFS-3705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13450862#comment-13450862

Suresh Srinivas commented on HDFS-3705:

Thanks for helping with testing HDFS-3703. Your help is much appreciated.

I may not have understood parts of your previous comment. 

bq. If I take HBase & HDFS as they are today, it's more a less a yes: Most of the time,
people configure HBase with a timeout of 45s. So if HDFS does 30s, it has the right state
when HBase starts the recovery. So done and HDFS-3705 is useless. However, even today, I've
seen people claiming a configuration with a 10 seconds timeout.
I understood the first part. As long as HDFS has marked nodes stale before HBase starts recovery,
change from HDFS-3703 is sufficient. I did not understand the second part related to 10 seconds.
Are you saying, people may want more aggressive recovery time for HBase than say 30s that
HDFS may be configured with?

My takeaway from your comments is, even though HDFS supports this functionality, HBase might
need even more aggressive timeout. This timeout may not be suitable for other applications
using HDFS. Hence having client side capability that HBase can use is still needed. Is that

> Add the possibility to mark a node as 'low priority' for read in the DFSClient
> ------------------------------------------------------------------------------
>                 Key: HDFS-3705
>                 URL: https://issues.apache.org/jira/browse/HDFS-3705
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: hdfs client
>    Affects Versions: 1.0.3, 2.0.0-alpha, 3.0.0
>            Reporter: nkeywal
>             Fix For: 3.0.0
>         Attachments: hdfs-3705.sample.patch, HDFS-3705.v1.patch
> This has been partly discussed in HBASE-6435.
> The DFSClient includes a 'bad nodes' management for reads and writes. Sometimes, the
client application already know that some deads are dead or likely to be dead.
> An example is the 'HBase Write-Ahead-Log': when HBase reads this file, it knows that
the HBase regionserver died, and it's very likely that the box died so the datanode on the
same box is dead as well. This is actually critical, because:
> - it's the hbase recovery that reads these log files
> - if we read them it means that we lost a box, so we have 1 dead replica out the the
> - for all files read, we have 33% of chance to go to the dead datanode
> - as the box just died, we're very likely to get a timeout exception so we're delaying
the hbase recovery by 1 minute. For HBase, it means that the data is not available during
this minute.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

View raw message