[
https://issues.apache.org/jira/browse/FLINK-1442?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14293258#comment-14293258
]
ASF GitHub Bot commented on FLINK-1442:
---------------------------------------
Github user mxm commented on the pull request:
https://github.com/apache/flink/pull/344#issuecomment-71616952
@StephanEwen Yes, that was on purpose. The previous two data structures
(`HashMap` and `Queue`) are now replaced by the `LinkedHashMap` which serves
the same functionality. It might not be obvious but the `LinkedHashMap`
preserves the order of the inserted items. From
`scala.collection.mutable.LinkedHashMap`:
> This class implements mutable maps using a hashtable.
> The iterator and all traversal methods of this class visit elements in
the order they were inserted.
That's why `graphs.iterator.next()` always returns the least recently
inserted item.
> Archived Execution Graph consumes too much memory
> -------------------------------------------------
>
> Key: FLINK-1442
> URL: https://issues.apache.org/jira/browse/FLINK-1442
> Project: Flink
> Issue Type: Bug
> Components: JobManager
> Affects Versions: 0.9
> Reporter: Stephan Ewen
> Assignee: Max Michels
>
> The JobManager archives the execution graphs, for analysis of jobs. The
> graphs may consume a lot of memory.
> Especially the execution edges in all2all connection patterns are extremely
> many and add up in memory consumption.
> The execution edges connect all parallel tasks. So for a all2all pattern
> between n and m tasks, there are n*m edges. For parallelism of multiple 100
> tasks, this can easily reach 100k objects and more, each with a set of
> metadata.
> I propose the following to solve that:
> 1. Clear all execution edges from the graph (majority of the memory
> consumers) when it is given to the archiver.
> 2. Have the map/list of the archived graphs behind a soft reference, to it
> will be removed under memory pressure before the JVM crashes. That may remove
> graphs from the history early, but is much preferable to the JVM crashing, in
> which case the graph is lost as well...
> 3. Long term: The graph should be archived somewhere else. Somthing like the
> History server used by Hadoop and Hive would be a good idea.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
