[
https://issues.apache.org/jira/browse/HADOOP-10794?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14060283#comment-14060283
]
eric baldeschwieler commented on HADOOP-10794:
----------------------------------------------
As YARN supports more services, this is going to rise in priority. I agree
with steve that it may be hard to fix it in Hadoop, but I think YARN needs to
monitor clock skew, which it can do piggybacked on its heartbeat RPC. That
would allow centralized reporting / health checks. One could argue this
belongs in Ambari, shrug. Depends on how you see the YARN and Ambari missions.
It would also seem that either YARN or ambari should be able to nanny
lightweight processes that run on each node (either continuously or
periodically). That would provide a mechanism for running various setup and
health checks, etc. That could be useful in addressing this issue.
> A hadoop cluster needs clock synchronization
> --------------------------------------------
>
> Key: HADOOP-10794
> URL: https://issues.apache.org/jira/browse/HADOOP-10794
> Project: Hadoop Common
> Issue Type: Bug
> Reporter: Zhijie Shen
>
> As a distributed system, a hadoop cluster wants the clock on all the
> participating hosts synchronized. Otherwise, some problems might happen. For
> example, in YARN-2251, due to the clock on the host for the task container
> falls behind that on the host of the AM container, the computed elapsed time
> (the diff between the timestamps produced on two hosts) becomes negative.
> In YARN-2251, we tried to mask the negative elapsed time. However, we should
> seek for a decent long term solution, such as providing mechanism to do and
> check clock synchronization.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
