[
https://issues.apache.org/jira/browse/AURORA-1211?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14370500#comment-14370500
]
Maxim Khutornenko commented on AURORA-1211:
-------------------------------------------
Java GC latencies may be impacted by IO bandwidth under certain conditions.
Likewise, GC activity may result in increased IO utilization. I don't have an
experimental proof but these links provide some food for thought:
https://engineering.linkedin.com/voldemort/voldemort-solid-state-drives
http://www.slideshare.net/cuonghuutran/gc-andpagescanattacksbylinux
Given it's much easier to add a minor delay than provide a definitive proof
(given a variety of JVM configurations used in practice) I'd rather take this
change to rule out their cross-influence.
> Spread snapshot creation and backup file write
> ----------------------------------------------
>
> Key: AURORA-1211
> URL: https://issues.apache.org/jira/browse/AURORA-1211
> Project: Aurora
> Issue Type: Task
> Components: Scheduler
> Reporter: Maxim Khutornenko
>
> Currently, backup files are written asynchronously and overlay with the peak
> of GC cleaning up after persisting snapshot in native log. We should
> generally avoid overlaying resource-heavy activities when possible to avoid
> troubleshooting complicated performance related issues.
> Consider delaying backup file write (e.g. for 1 minute) to clearly separate
> its impact from the snapshot GC.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
