[
https://issues.apache.org/jira/browse/YARN-3803?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14585370#comment-14585370
]
Yuliya Feldman commented on YARN-3803:
--------------------------------------
In LocalizedResource class in state transition there are following transitions:
{code}
// From INIT (ref == 0, awaiting req)
.addTransition(ResourceState.INIT, ResourceState.DOWNLOADING,
ResourceEventType.REQUEST, new FetchResourceTransition())
// From DOWNLOADING (ref > 0, may be localizing)
.addTransition(ResourceState.DOWNLOADING, ResourceState.DOWNLOADING,
ResourceEventType.REQUEST, new DuplicateFetchResourceTransition())
{code}
So it assumes that if "from state" and "to state" is _DOWNLOADING_ and
_ResourceEventType_ is _REQUEST_ then resource is being downloaded and
transition becomes _DuplicateFetchResourceTransition_.
Problem is that "ref" is not greater then 0 here, as resources were cleaned up
during first attempt and we end up in the situation where nothing is happening
until RM kills this app.
> Application hangs after more then one localization attempt fails on the same
> NM
> -------------------------------------------------------------------------------
>
> Key: YARN-3803
> URL: https://issues.apache.org/jira/browse/YARN-3803
> Project: Hadoop YARN
> Issue Type: Bug
> Components: nodemanager
> Affects Versions: 2.7.0, 2.5.1
> Reporter: Yuliya Feldman
> Assignee: Yuliya Feldman
> Priority: Minor
>
> In the sandbox (single node) environment with LinuxContainerExecutor when
> first Application Localization attempt fails second attempt can not proceed
> and subsequently application hangs until RM kills it as non-responding.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
