You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-user@hadoop.apache.org by arun k <ar...@gmail.com> on 2011/11/10 11:18:11 UTC

Modifyiing Scheduler code in Mumak

Hi guys !

I have gone thru Mumak code.
I ran mumak.sh with given Job and Topology trace files .In my understanding
i see that when a job is fetched from JobStoryProducer an event is
asscoiated with it and the listener / node where it is assigned is fixed
when these events are created.
I have not understood how *mumak is simulating scheduling exactly*.Can
anyone help me in this regard ?

I am interested in coding a simple scheduler in Mumak.
1> Which files do i need to modify if i want to change the way the events
are allocated to a particular node/Taskracker ?
2> How do i compare throughput with existing schedulers ?
3> Do i need to have my own Job trace file ?

Thanks,
Arun