+1 (binding)
Thanks for putting this together, Wangda.
I deployed a 7-node hadoop cluster and:
- ran various MR jobs
- ran the same jobs with a mix of opportunistic containers via centralized
scheduling
- ran the jobs with opportunistic containers and distributed scheduling
- ran some jobs with v
Thanks for starting the thread Arun, +1 from me too.
Konstantinos
On Thu, Jan 25, 2018 at 18:54 Weiwei Yang wrote:
> +1, thanks for getting to this milestone Arun.
> I’ve done some basic validations on a 4 nodes cluster, with some general
> affinity/anti-affinty/cardinality constraints, it work
+1.
Did the following:
1) set up a 6-node cluster;
2) tried some simple HDFS commands and generated some Gridmix data;
2) ran some Gridmix jobs;
3) ran (2) after enabling opportunistic containers (used a mix of
guaranteed and opportunistic containers for each job);
4) ran (3) but this time enablin
+1 from me too.
Did the following:
1) set up a 9-node cluster;
2) ran some Gridmix jobs;
3) ran (2) after enabling opportunistic containers (used a mix of
guaranteed and opportunistic containers for each job);
4) ran (3) but this time enabling distributed scheduling of opportunistic
containers.
A
