HOWTO configure multiple queues and instance types in AWS ParallelCluster
In today’s show, we talk about AWS ParallelCluster 2.9 and its new features built on Slurm’s power management module. This lets you build clusters with multiple queues and instances types within those queues. This allows the cluster to scale nodes that fit a given workload, making scaling decisions much more job-driven, and means each queue can be quite specifically optimized for a code .
We’ll show a real live cluster upgrade happening, doing in 10 minutes what it generally takes 18 months to pull off if you still live with on-premises facilities.
Rex Chen is one of our amazing Software Engineers who works every day on AWS ParallelCluster and he’s joined by Angel Pizarro, our Principal Developer Advocate for HPC & Batch who has personal experience building those clusters and upgrading them, and knows better now.
Here’s the blog we mentioned in the show:
If you have ideas for technical topics you’d like to see us cover in a future show, let us know by finding us on Twitter (@TechHpc) and DM’ing us with your idea.