[
https://issues.apache.org/jira/browse/MAPREDUCE-961?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Scott Chen updated MAPREDUCE-961:
---------------------------------
Attachment: MAPREDUCE-961-v2.patch
After deploying on our cluster, I have fixed several minor things. Here's the
new patch.
It seems this works well on our cluster. I will run more real-world tests on it.
I haven't integrated this in JT and TT. I will do that once I have time.
One more thought: we use PS and use grep to find job_id pattern and ppid =
tasktracker pid.
This method has a benefit that it dose not depend on TT to find relevant
processes.
With this approach, we are able to find some "orphan" jobs (TT does not track
them but they are running) on our cluster.
> ResourceAwareLoadManager to dynamically decide new tasks based on current
> CPU/memory load on TaskTracker(s)
> -----------------------------------------------------------------------------------------------------------
>
> Key: MAPREDUCE-961
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-961
> Project: Hadoop Map/Reduce
> Issue Type: New Feature
> Components: contrib/fair-share
> Reporter: dhruba borthakur
> Assignee: dhruba borthakur
> Attachments: HIVE-961.patch, MAPREDUCE-961-v2.patch
>
>
> Design and develop a ResouceAwareLoadManager for the FairShare scheduler that
> dynamically decides how many maps/reduces to run on a particular machine
> based on the CPU/Memory/diskIO/network usage in that machine. The amount of
> resources currently used on each task tracker is being fed into the
> ResourceAwareLoadManager in real-time via an entity that is external to
> Hadoop.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
