Open vvksh opened 3 years ago
this blog shows benchmark comparing Ray vs Spark vs Dask for a given task; might be interesting to replicate it on rpi cluster or even azure.
look into ray cluster and play with autoscaling: https://docs.ray.io/en/master/cluster/index.html
came out of RISELab at Berkeley, supposed to be a general purpose distributed computing framework.
arxiv paper here
notes:
"""elative inflexibility of the BSP model, the high per-task overhead, and the lack of an actor abstraction led us to develop a new system"""
fault tolerance helps save money since it allows us to run on cheap resources like spot instances on AWS
extra systems discussed:
Qs:
tasks: