[
https://issues.apache.org/jira/browse/HDFS-7858?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14511949#comment-14511949
]
Chris Nauroth commented on HDFS-7858:
-------------------------------------
This is very interesting. Thanks for working on it, Arun!
bq. Yup, QJM ensures only 1 namenode can write, but fencing is still
recommended since there is still a possibility of the stale reads from the old
Active NN before going down (I am hoping this will not be too much of an issue)
I don't think the patch introduces any new problems here. If two NameNodes
think they are active, there is already a risk of reads being served by the
wrong node.
> Improve HA Namenode Failover detection on the client
> ----------------------------------------------------
>
> Key: HDFS-7858
> URL: https://issues.apache.org/jira/browse/HDFS-7858
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Arun Suresh
> Assignee: Arun Suresh
> Attachments: HDFS-7858.1.patch, HDFS-7858.2.patch, HDFS-7858.2.patch,
> HDFS-7858.3.patch
>
>
> In an HA deployment, Clients are configured with the hostnames of both the
> Active and Standby Namenodes.Clients will first try one of the NNs
> (non-deterministically) and if its a standby NN, then it will respond to the
> client to retry the request on the other Namenode.
> If the client happens to talks to the Standby first, and the standby is
> undergoing some GC / is busy, then those clients might not get a response
> soon enough to try the other NN.
> Proposed Approach to solve this :
> 1) Since Zookeeper is already used as the failover controller, the clients
> could talk to ZK and find out which is the active namenode before contacting
> it.
> 2) Long-lived DFSClients would have a ZK watch configured which fires when
> there is a failover so they do not have to query ZK everytime to find out the
> active NN
> 2) Clients can also cache the last active NN in the user's home directory
> (~/.lastNN) so that short-lived clients can try that Namenode first before
> querying ZK
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
