[
https://issues.apache.org/jira/browse/GIRAPH-1046?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15225297#comment-15225297
]
Hudson commented on GIRAPH-1046:
--------------------------------
FAILURE: Integrated in Giraph-trunk-Commit #1594 (See
[https://builds.apache.org/job/Giraph-trunk-Commit/1594/])
GIRAPH-1046: Add a way to synchronize full GC calls across workers
(majakabiljo:
[http://git-wip-us.apache.org/repos/asf?p=giraph.git&a=commit&h=24bed1a9bdbe3a1edd46bc3b2af83ee385e041a9])
* giraph-core/src/main/java/org/apache/giraph/bsp/BspService.java
* src/site/xdoc/options.xml
* giraph-core/src/main/java/org/apache/giraph/worker/MemoryObserver.java
* giraph-core/src/main/java/org/apache/giraph/worker/BspServiceWorker.java
> Add a way to synchronize full GC calls across workers
> -----------------------------------------------------
>
> Key: GIRAPH-1046
> URL: https://issues.apache.org/jira/browse/GIRAPH-1046
> Project: Giraph
> Issue Type: New Feature
> Reporter: Maja Kabiljo
> Assignee: Maja Kabiljo
>
> In applications which use memory more heavily, we can see full GC pauses
> happening on different workers at different times, and each of these is
> causing some delay because other workers are often waiting on something from
> the worker in GC (closing open requests, finishing superstep, etc). Having a
> way to coordinate when full GCs are called could help them have less effect
> on job performance.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
